Dissertations / Theses on the topic 'HEART DISEASE PREDICTION'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 49 dissertations / theses for your research on the topic 'HEART DISEASE PREDICTION.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Bolton, Jennifer Lynn. "Candidate genotypes in prediction of coronary heart disease." Thesis, University of Edinburgh, 2011. http://hdl.handle.net/1842/15877.
Full textNet, J. B. van der. "Towards genetic prediction of coronary heart disease in familial hypercholesterolemia." [S.l.] : Rotterdam : [The Author] ; Erasmus University [Host], 2009. http://hdl.handle.net/1765/14566.
Full textVan, Zyl Johet Engela. "Accuracy of risk prediction tools for acute coronary syndrome : a systematic review." Thesis, Stellenbosch : Stellenbosch University, 2015. http://hdl.handle.net/10019.1/97069.
Full textENGLISH ABSTRACT: Background: Coronary artery disease is a form of cardiovascular disease (CVD) which manifests itself in three ways: angina pectoris, acute coronary syndrome and cardiac death. Thirty-three people die daily of a myocardial infarction (cardiac death) and 7.5 million deaths annually are caused by CVD (51% from strokes and 45% from coronary artery disease) worldwide. Globally, the CVD death rate is a mere 4% compared to South Africa which has a 42% death rate. It is predicted that by the year 2030 there will be 25 million deaths annually from CVD, mainly in the form of strokes and heart disease. The WHO compared the death rates of high-income countries to those of low- and middle-income countries, like South Africa, and the results show that CVD deaths are declining in high-income countries but rapidly increasing in low- and middle-income countries. Although there are several risk prediction tools in use worldwide, to predict ischemic risk, South Africa does not use any of these tools. Current practice in South Africa to diagnose acute coronary syndrome is the use of a physical examination, ECG changes and positive serum cardiac maker levels. Internationally the same practice is used to diagnose acute coronary syndrome but risk assessment tools are used additionally to this practise because of limitations of the ECG and serum cardiac markers when it comes to NSTE-ACS. Objective: The aim of this study was to systematically appraise evidence on the accuracy of acute coronary syndrome risk prediction tools in adults. Methods: An extensive literature search of studies published in English was undertaken. Electronic databases searched were Cochrane Library, MEDLINE, Embase and CINAHL. Other sources were also searched, and cross-sectional studies, cohort studies and randomised controlled trials were reviewed. All articles were screened for methodological quality by two reviewers independently with the QUADAS-2 tool which is a standardised instrument. Data was extracted using an adapted Cochrane data extraction tool. Data was entered in Review Manager 5.2 software for analysis. Sensitivity and specificity was calculated for each risk score and an SROC curve was created. This curve was used to evaluate and compare the prediction accuracy of each test. Results: A total of five studies met the inclusion criteria of this review. Two HEART studies and three GRACE studies were included. In all, 9 092 patients participated in the selected studies. Estimates of sensitivity for the HEART risks score (two studies, 3268 participants) were 0,51 (95% CI 0,46 to 0,56) and 0,68 (95% CI 0,60 to 0,75); specificity for the HEART risks score was 0,90 (95% CI 0,88 to 0,91) and 0,92 (95% CI 0,90 to 0,94). Estimates of sensitivity for the GRACE risk score (three studies, 5824 participants) were 0,03 (95% CI0,01 to 0,05); 0,20 (95% CI 0,14 to 0,29) and 0,79 (95% CI 0,58 to 0,93). The specificity was 1,00 (95% CI 0,99 to 1,00); 0,97 (95% CI 0,95 to 0,98) and 0,78 (95% CI 0,73 to 0,82). On the SROC curve analysis, there was a trend for the GRACE risk score to perform better than the HEART risk score in predicting acute coronary syndrome in adults. Conclusion: Both risk scores showed that they had value in accurately predicting the presence of acute coronary syndrome in adults. The GRACE showed a positive trend towards better prediction ability than the HEART risk score.
AFRIKAANSE OPSOMMING: Agtergrond: Koronêre bloedvatsiekte is ‘n vorm van kardiovaskulêre siekte. Koronêre hartsiekte manifesteer in drie maniere: angina pectoris, akute koronêre sindroom en hartdood. Drie-en-dertig mense sterf daagliks aan ‘n miokardiale infarksie (hartdood). Daar is 7,5 miljoen sterftes jaarliks as gevolg van kardiovaskulêre siektes (51% deur beroertes en 45% as gevolg van koronêre hartsiektes) wêreldwyd. Globaal is die sterfte syfer as gevolg van koronêre vaskulêre siekte net 4% in vergelyking met Suid Afrika, wat ‘n 42% sterfte syfer het. Dit word voorspel dat teen die jaar 2030 daar 25 miljoen sterfgevalle jaarliks sal wees, meestal toegeskryf aan kardiovaskulêre siektes. Die hoof oorsaak van sterfgevalle sal toegeskryf word aan beroertes en hart siektes. Die WHO het die sterf gevalle van hoeinkoms lande vergelyk met die van lae- en middel-inkoms lande, soos Suid Afrika, en die resultate het bewys dat sterf gevalle as gevolg van kardiovaskulêre siekte is besig om te daal in hoe-inkoms lande maar dit is besig om skerp te styg in lae- en middel-inkoms lande. Daar is verskeie risiko-voorspelling instrumente wat wêreldwyd gebruik word om isgemiese risiko te voorspel, maar Suid Afrika gebruik geen van die risiko-voorspelling instrumente nie. Huidiglik word akute koronêre sindroom gediagnoseer met die gebruik van n fisiese ondersoek, EKG verandering en positiewe serum kardiale merkers. Internationaal word die selfde gebruik maar risiko-voorspelling instrumente word aditioneel by gebruik omdat daar limitasies is met EKG en serum kardiale merkers as dit by NSTE-ACS kom. Doelwit: Die doel van hierdie sisematiese literatuuroorsig was om stelselmatig die bewyse te evalueer oor die akkuraatheid van akute koronêre sindroom risiko-voorspelling instrumente vir volwassenes. Metodes: 'n Uitgebreide literatuursoektog van studies wat in Engels gepubliseer is was onderneem. Cochrane biblioteek, MEDLINE, Embase en CINAHL databases was deursoek. Ander bronne is ook deursoek. Die tiepe studies ingesluit was deurnsee-studies, kohortstudies en verewekansigde gekontroleerde studies. Alle artikels is onafhanklik vir die metodologiese kwaliteit gekeur deur twee beoordeelaars met die gebruik van die QUADAS-2 instrument, ‘n gestandaardiseerde instrument. ‘n Aangepaste Cochrane data instrument is gebruik om data te onttrek. Data is opgeneem in Review Manager 5.2 sagteware vir ontleding. Sensitiwiteit en spesifisiteit is bereken vir elke risiko instrument en ‘n SROC kurwe is geskep. Die SROC kurwe is gebruik om die akkuraatheid van voorspelling van elke instrument te evalueer en te toets. Resultate: Twee HEART studies en drie GRACE studies is ingesluit. In total was daar 9 092 patiente wat deelgeneeem het in die gekose studies. Skattings van sensitiwiteit vir die HEART risiko instrument (twee studies, 3268 deelnemers) was 0,51 (95% CI 0,47 to 0,56) en 0,68 (95% CI 0,60 to 0,75) spesifisiteit vir die HEART risiko instrument was 0,89 (95% CI 0,88 to 0,91) en 0,92 (95% CI 0,90 to 0,94). Skattings van sensitiwiteit vir die GRACE risiko instrument (drie studies, 5824 deelnemers) was 0,28 (95% CI 0,13 to 0,53); 0,20 (95% CI 0,14 to 0,29) en 0,79 (95% CI 0,58 to 0,93). Die spesifisiteit vir die GRACE risiko instrument was 0,97 (95% CI 0,95 to 0,99); 0,97 (95% CI 0,95 to 0,98) en 0,78 (95% CI 0,73 to 0,82). Met die SROC kurwe ontleding was daar ‘n tendens vir die GRACE risiko instrument om beter te vaar as die HEART risiko instrument in die voorspelling van akute koronêre sindroom in volwassenes. Gevolgtrekking: Altwee risiko instrumente toon aan dat albei instrumente van waarde is. Albei het die vermoë om die teenwoordigheid van akute koronêre sindroom in volwassenes te voorspel. Die GRACE toon ‘n positiewe tendens teenoor beter voorspelling vermoë as die HEART risiko instrument.
Savatteri, Giuseppe. "Enviromental factors influencing heart diseases." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textLi, Jianeng. "Research on a Heart Disease Prediction Model Based on the Stacking Principle." Thesis, Högskolan Dalarna, Informatik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:du-34591.
Full textRice, Thomas H. "Prediction of oxygen consumption during exercise testing in apparently healthy subjects and coronary artery disease patients." Thesis, Virginia Polytechnic Institute and State University, 1986. http://hdl.handle.net/10919/91143.
Full textM.S.
Vedin, Ola. "Prevalence and Prognostic Impact of Periodontal Disease and Conventional Risk Factors in Patients with Stable Coronary Heart Disease." Doctoral thesis, Uppsala universitet, Institutionen för medicinska vetenskaper, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-260564.
Full textAtsalakis, Mihalis. "Prediction of initial involvement of first grade Greek school children in an out-of-school, organized, community physical activity programme : an application of the theory of planned behaviour." Thesis, University of Hull, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.262408.
Full textZuo, Heng. "3D Multi-Physics MRI-Based Human Right Ventricle Models for Patients with repaired Tetralogy of Fallot: Cardiac Mechanical Analysis and Surgical Outcome Prediction." Digital WPI, 2017. https://digitalcommons.wpi.edu/etd-dissertations/478.
Full textЗадойоний, Віктор Андрійович, and Viktor Zadoionyi. "Комп’ютерна система прогнозування ризиків появи серцевих захворювань." Bachelor's thesis, Тернопільський національний технічний університет імені Івана Пулюя, 2021. http://elartu.tntu.edu.ua/handle/lib/35577.
Full textThe computer system for predicting the risk of heart disease has been designed in the bachelor's thesis. It consists of two main components: a subsystem for collecting data on human vital signs and an intelligent module for predicting the risk of heart disease. The human vital signs collection subsystem is implemented using mobile sensors attached to the human body, a single-chip Raspberry PI mini-computer, as a central node that acts as a controller for data transmission and cloud storage - to store and analyze the collected information. The following sensors attached to the human body: a heart rate monitor, a body temperature sensor and a blood pressure monitor. In addition, sensors for analyzing air parameters: temperature, humidity, the presence of harmful substances and light intensity were using to take into account the parameters of the environment in which a person is. The intelligent module for predicting the risk of heart disease is implemented using the Python programming language and the use of open machine learning libraries. The simulation used and investigated the characteristics of six models of binary classification, as a result of which it was found that the most effective model is based on random forests (Random Forest), which provides forecasting accuracy of 97.5%.
ПЕРЕЛІК ОСНОВНИХ УМОВНИХ ПОЗНАЧЕНЬ, СИМВОЛІВ І СКОРОЧЕНЬ 7 ВСТУП 8 РОЗДІЛ 1 АНАЛІЗ ВИМОГ ТА ОСОБЛИВОСТЕЙ ПРОЕКТУВАННЯ КОМП’ЮТЕРНИХ СИСТЕМ МЕДИЧНОГО ПРИЗНАЧЕННЯ 9 1.1 Аналіз технічного завдання на проектування комп’ютерної системи прогнозування ризиків появи серцевих захворювань 9 1.2 Обґрунтування доцільності та особливості проектування комп’ютерної системи 17 РОЗДІЛ 2 МОДЕЛЬ ТА СТРУКТУРА КОМП’ЮТЕРНОЇ СИСТЕМИ ПРОГНОЗУВАННЯ РИЗИКІВ ПОЯВИ СЕРЦЕВИХ ЗАХВОРЮВАНЬ 22 2.1 Моделі та архітектури комп’ютерних систем у сфері охорони здоров’я 22 2.2 Фактори впливу навколишнього середовища на стан організму людини та комп’ютерна система автоматизованого їх аналізу 25 2.3 Різновиди та розвиток IoT у медичній галузі 29 2.4 Проектування архітектури комп’ютерної системи прогнозування ризиків появи серцевих захворювань 34 РОЗДІЛ 3 ПРОГРАМНА МОДЕЛЬ ІНТЕЛЕКТУАЛЬНОГО МОДУЛЯ ПРОГНОЗУВАННЯ РИЗИКІВ ВИНИКНЕННЯ СЕРЦЕВИХ ЗАХВОРЮВАНЬ 42 3.1 Аналіз відкритих джерел даних для побудови моделі прогнозування щодо виникнення серцевих захворювань 42 3.2 Препроцесинг даних 44 3.3 Виявлення залежностей між ознаками вхідного набору даних 51 3.4 Виявлення значимих ознак набору даних 56 3.5 Реалізація моделей прогнозування розвитку серцевих захворювань 59 РОЗДІЛ 4 БЕЗПЕКА ЖИТТЄДІЯЛЬНОСТІ, ОСНОВИ ОХОРОНИ ПРАЦІ 67 ВИСНОВКИ 68 СПИСОК ВИКОРИСТАНИХ ДЖЕРЕЛ 69 Додаток A. Технічне завдання
VERONESI, GIOVANNI. "Develoment, validation and clinical utility of a long-term cardiovascular disease risk prediction model in the italian population." Doctoral thesis, Università degli Studi di Milano-Bicocca, 2014. http://hdl.handle.net/10281/50251.
Full textEggers, Kai. "Cardiac Troponins in Patients with Suspected or Confirmed Acute Coronary Syndrome : New Applications for Biomarkers in Coronary Artery Disease." Doctoral thesis, Uppsala : Acta Universitatis Upsaliensis : Univ.-bibl. [distributör], 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-7945.
Full textNicholson, Amanda Claire. "Psychological distress as a predictor of coronary heart disease." Thesis, University College London (University of London), 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.406151.
Full textDzudie, Tamdja Anastase Innocent. "Predicting pulmonary hypertension and outcomes in patients with left heart disease." Doctoral thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/16533.
Full textPulmonary hypertension (PH) is defined as a rise in the pressure in the pulmonary arteries resulting from a variety of diseases including chronic infectious diseases, lung diseases and left heart diseases (LHD). It is a global health problem and accounts for a substantial portion of cardiovascular disease. PH due to LHD (PH-LHD) is credited to be the most common form of PH worldwide and is associated with adverse outcomes. Considering the suggestions of high prevalence and potential adverse outcomes of PH in sub-Saharan Africa (SSA), the investigation of the etiologies, clinical profile, correlates, and outcomes of PH-LHD in this region is a medical priority. Methods: Through a systematic review, we assessed existing evidence on the predictors of PH-LHD outcomes. Then, through two prospective multinational cohort registries, we investigated 1) the spectrum of PH in SSA; 2) the clinical profile and 6 months outcome of PH-LHD; 3) the role of electrocardiogram for diagnosing PH and 4) its prognostic role in heart failure (HF). PH was diagnosed by echocardiography in the context of clinical suspicion. Results: In high income countries, PH-LHD is almost invariably associated with increased mortality risk, but the effects on hospitalization are yet to be fully characterized. All groups of PH are found in SSA with LHD being the major cause. PH-LHD affects young people and is predominantly due to HF and rheumatic valvular heart disease. In these patients, left atrium size and tricuspid annular plan excursion are predictors of pulmonary pressures, and PH-LHD predicts short term hospitalization but not mortality. A normal electrocardiogram is very rare in patients with PH, but electrocardiogram criteria of right ventricular strain are rather rare and non-specific. Similarly, electrocardiogram abnormalities are frequent among Africans with HF, some have prognostic value for mortality risk. Conclusion: PH-LHD is the most common form of PH in SSA, with affected patients presenting with advanced disease, and it is associated with adverse outcomes. ECG abnormalities are prevalent in both PH and HF, but few of these abnormalities have prognostic value for mortality risk. Evaluating the efficacy and safety of low-cost and available drugs in reducing HF hospitalizations in PH-LHD is a key future priority. Improving early diagnosis of PH should also be encouraged.
Straczek, Céline. "Epidémiologie des cardiopathies ischémiques du sujet âgé non institutionnalisé-Etude des Trois Cités." Phd thesis, Université Paris Sud - Paris XI, 2011. http://tel.archives-ouvertes.fr/tel-00670145.
Full textLluís, Ganella Carla 1984. "Genetic factors associated with coronary heart disease and analysis of their predictive capacity." Doctoral thesis, Universitat Pompeu Fabra, 2012. http://hdl.handle.net/10803/84185.
Full textL’expansió principal pel que fa al descobriment de variants genètiques associades amb malalties complexes s’ha dut a terme durant la última dècada. Aquesta expansió ha estat acompanyada, i d’alguna forma motivada, pel desig d’usar aquesta informació per millorar la capacitat de predicció d’aquelles malalties on hi és present un cert component familiar però en les que no es coneixien les variants que conferien un major risc de patir la malaltia, entre elles la cardiopatia isquèmica (CI). La present tesis doctoral està estructurada en dues línies d’investigació que avaluen el possible rol d’un gen candidat en la susceptibilitat de la CI i també avalua la millora en la capacitat de predicció d’un esdeveniment coronari de les eines usades habitualment en la pràctica clínica mitjançant la inclusió d’informació genètica. Més concretament, la primera línea d’investigació es centra en la contribució de la variació genètica en un dels gens més estudiats en relació amb CI: el gen que codifica pel receptor d’estrogens alfa (ESR1). En aquesta línea hem proveït un sòlid meta-anàlisis entre la variant més àmpliament estudiada d’aquest gen i risc coronari i també hem explorat el paper de la majoria de les variants comunes descrites en aquest gen i risc de CI. Mitjançant cap dels anàlisis hem trobat evidència d’associació entre les variants genètiques en aquest gen i el risc de CI. No obstant això, i encara que podem acceptar que les variants genètiques comunes d’aquest gen no estan associades amb esdeveniments coronaris, no podem descartar que altres tipus de variació en aquest gen (com per exemple variació epigenètica) pugui estar modificant la susceptibilitat a patir un esdeveniment coronari, ni tampoc que altres elements de la mateixa cadena de senyalització estiguin associats amb la malaltia. En la segona línea d’investigació, hem explorat el possible paper de les variants genètiques, obtingudes mitjançant estudis d’associació global del genoma (GWAS), en la millora de la capacitat de predicció a 10 anys dels esdeveniments coronaris, mitjançant la seva addició en les funcions de risc cardiovascular clàssiques. Hem seguit les recomanacions proposades per la American Heart Association per l’avaluació en la pràctica clínica de nous biomarcadors, i hem demostrat que, tot i que la magnitud de l’associació d’aquestes variants és modesta, hi ha una tendència cap a la millora de la capacitat de predicció de les funcions de risc.
Whitmarsh, Anya. "An investigation of illness perceptions, mood and coping in predicting attendance at cardiac rehabilitation." Thesis, University of East Anglia, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.327201.
Full textSuleiman, David. "Measurement and prediction of phase equilibrium properties at infinite dilution : alkanes in natural gases and organic solvents in aqueous solutions." Diss., Georgia Institute of Technology, 1994. http://hdl.handle.net/1853/10270.
Full textIvanchuk, P. R. "Changes of heart rate turbulence as a predictor of risk in patients with coronary and non-coronary heart diseases and ventricultural extrasystols." Thesis, БДМУ, 2021. http://dspace.bsmu.edu.ua:8080/xmlui/handle/123456789/18548.
Full textNowak, Christoph. "Insulin Resistance : Causes, biomarkers and consequences." Doctoral thesis, Uppsala universitet, Molekylär epidemiologi, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-316891.
Full textCotto, Jennifer. "Associated and Predictive Factors of Physical Activity Engagement, Support and Cardiac Concern in a Sample of Youth with Congenital Heart Disease and their Caregivers." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1562787586432624.
Full textNaqvi, Habib. "Coronary heart disease : Lay representations of genetics, genetic testing and the decision to pursue predictive genetic testing amongst South Asians." Thesis, University of the West of England, Bristol, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.522563.
Full textTrick, Leanne Victoria. "The role of perseverative negative thinking in predicting depression, anxiety and quality of life in people with coronary heart disease." Thesis, University of Exeter, 2017. http://hdl.handle.net/10871/29314.
Full textRibera, Casellas Irene. "Estudi dels factors prenatals predictius d'anomalies del neurodesenvolupament en cardiopaties congènites." Doctoral thesis, Universitat Autònoma de Barcelona, 2021. http://hdl.handle.net/10803/672005.
Full textINTRODUCCIÓN El pronóstico vital de los pacientes con cardiopatía congénita (CC) ha mejorado significativamente en los últimos años, lo que ha centrado a los profesionales su morbilidad asociada. Los estudios de neuroimagen han demostrado que los niños con CC tienen una mayor incidencia de lesiones cerebrales y retraso de maduración que podrían originarse durante la vida intrauterina. Por otro lado, se sabe que hasta el 50% de los niños con cardiopatía congénita presentarán déficits a lo largo la infancia en alguna de las áreas del neurodesarrollo. Hay evidencia que relaciona el orígen de la afectación materna y fetal en la preeclampsia con una alteración de la invasión trofoblástica y una posterior hipoxia del tejido placentario. En ese contexto, aumentan los factores antiangiogénicos como el sFlt y disminuyen factores proangiogénicos como el PlGF. Otros estudios relacionan la enfermedad cardíaca congénita con complicaciones típicas del embarazo en un ambiente de insuficiencia placentaria. Como ejemplo, se sabe que los fetos con CC tienen incidencia aumentada de bajo peso al nacer, corregido por sexo y semanas de gestación, comparados con los niños sanos. OBJETIVOS El objetivo de esta tesis doctoral es establecer la presencia de alteraciones neurológicas prenatales utilizando técnicas de diagnóstico por imagen y determinar la implicación de la función placentaria en el desarrollo neurológico de los niños con CC. MÉTODOS Se trata de un estudio prospectivo multicéntrico. Los datos obtenidos se compararon entre niños sanos y afectados por CC así como entre grupos de enfermedades cardíacas. Para la clasificación en subgrupos se decidió dividir según los seis diagnósticos más frecuentes del tipo moderado-severo: Transposición de Grandes Vasos (TGV), Tetralogía Fallot, Hipoplasia de Cavidades Izquierdas (HCE), Defecto Septales (DS), Obstrucción Aórtica (OA) y un último grupo con cardiopatías diversas (Otras). Los casos también se separaron de acuerdo con una clasificación funcional utilizada previamente en estudios de nuestro grupo: cardiopatías valvulares, conotruncales y obstrucción del tracto de salida izquierdo. En el grupo caso 179 madres embarazadas de fetos con CC moderada o grave. Al mismo tiempo se reclutaron 138 gestantes portadores de fetos sanos. RESULTADOS Se registró un aumento significativo de las complicaciones del embarazo de origen placentario en el grupo caso en comparación con los controles. Los resultados del estudio de las medidas cefálicas y cerebrales entre las cardiopatías y los controles a través de la RMN fueron congruentes con la literatura mostrando que el tamaño cefálico de los nacidos con CC es menor que el de los niños sanos en el conjunto de CC. El grupo de HCE tenía las biometrías más pequeñas. En sangre materna, se encontraron niveles más bajos de PlGF en el grupo de CC. Entre ellos, los afectados por Fallot tuvieron el nivel más bajo. El valor del ratio de factores angiogénicos sFlt-1/PlGF fue significativamente mayor que en los casos en que en los controles y el grupo Fallot de nuevo tenía el ratio más elevado. En el estudio de correlaciones, el valor de sFlt-1 y la relación sFlt-1/PlGF en la sangre materna fueron inversamente proporcionales al peso al nacer y al perímetro cefálico. Los resultados de nuestro estudio muestran que el desarrollo neuroconductual de los niños con CC evaluado a los dos años de vida mediante la escala Bayley-III es similar al promedio de la población. No hay diferencias entre los grupos de enfermedades cardíacas. CONCLUSIONES Existen diferencias en las pruebas de diagnóstico por imágen prenatales en CC comparadas con fetos sanos, así como en el embarazo con CC hay un aumento de los factores antiangiogénicos en sangre materna y una disminución de la proangiogenicos. En nuestra cohorte, no podemos relacionar estos cambios.
INTRODUCTION Survival prognosis of patients affected by congenital heart disease (CHD) has significantly improved these last years and has turned focus on associated morbidity. Neuroimaging studies have shown children with CHD have an increased incidence of brain injury and maturing delay that could have its origin during prenatal life. On the other hand, it is known that up to 50% of children with congenital heart disease will present some type of neurological deficit throughout childhood. Evidence suggests an alteration of trophoblastic invasion and subsequent placental tissue hypoxia as the origin of maternal and fetal symptoms in preeclampsia. In this environenent, an increase of antiangiogenic factors such as sFlt and decrease proangiogenic factors such as PlGF is often found. Other studies have related CHD pregnancy to complications typical of pregnancy in an environment of placental failure. It is known that fetuses with CHD have a low incidence at birth corrected by gender and weeks of gestation higher than healthy fetuses. OBJECTIVES The aims of this PhD studies are to establish the presence of prenatal neurological alterations using imaging techniques and to assess the implication of placental function in neurological development in children with different types of CHD. METHODS This is a multicenter prospective study. The data obtained were compared between healthy children and CHD fetuses, as well as among groups of cardiac malformations. We decided to classify the types of heart disease according to the six most frequent diagnoses of the moderate-severe type: Transposition of Great Vessels (TGV), Tetralogy of Fallot, Hypoplastic Left Heart Syndrome (HLHS), Septal Defects (SD), Aortic Obstruction (AO) and a group with other heart diseases (Others). Cases were also separated according to a functional classification previously used in studies of our group: valvular heart disease, conotruncal malformations and left exit ventricular outflow track obstruction (LVOTO). Case group consisted in 179 pregnant women carrying fetuses with a moderate or severe CHD. 138 patients pregnant with a healthy fetus were recruited for control group. RESULTS A significant increase in placenta-related pregnancy complications was recorded in patients with CHD compared to controls. Cephalic and cerebral measures between heart disease and controls through MRI were consistent with previous literature: cephalic size of those born with CHD is lower than that of healthy children. HLHS group had the smallest biometrics once compared with others. In maternal blood, lower PlGF levels were found in the CHD group. Among them, those affected by Fallot had the lowest level. The ratio of angiogenic factors sFlt-1/PlGF was significantly higher in case group compared to controls and this time again, Fallot group had the highest ratio. Levels of sFlt-1 and sFlt-1/PlGF ratio in maternal blood were inversely proportional to the weight at birth and the cephalic perimeter. The results of our study show that the neuroconductive development in children with CHD rated at two years of life using Bayley-III test is no different to the average population. We also did not find any differences between CHD groups. CONCLUSIONS There are differences in prenatal imaging tests in CHD compared to controls as well as in an increase of antiangiogenic factors in maternal blood and a decrease in proangiogenics factors can be found in CHD pregnancies. In our study, we could not relate these changes to a worse neuro development at two years of age.
Universitat Autònoma de Barcelona. Programa de Doctorat en Pediatria, Obstetrícia i Ginecologia
Brindle, Christopher T. "Incidence and Predictor Variables of Pressure Injuries in Patients Undergoing Ventricular Assist Device and Total Artificial Heart Surgeries: An Eight-Year Retrospective Review." VCU Scholars Compass, 2019. https://scholarscompass.vcu.edu/etd/6038.
Full textSouza, Helen Paredes de. "Condições de vida e mortalidade por doenças cardiovasculares na área de influência do Complexo Petroquímico do Estado do Rio de Janeiro - COMPERJ." Universidade do Estado do Rio de Janeiro, 2014. http://www.bdtd.uerj.br/tde_busca/arquivo.php?codArquivo=8574.
Full textArantes, Rodolfo Leite. "Comparação entre a estratificação clínica e a cintilografia de perfusão miocárdica como preditores de eventos cardiovasculares em candidatos a transplante renal." Universidade de São Paulo, 2009. http://www.teses.usp.br/teses/disponiveis/5/5131/tde-07122009-170552/.
Full textCardiovascular (CV) disease is a common condition in chronic kidney disease (CKD) patients and is the leading cause of fatal events during and after renal transplantation. The best strategy for CV evaluation and coronary risk stratification in renal transplant candidates remains controversial. Moreover, there is no consensus regarding the best strategy for detection of coronary artery disease (CAD). We still do not know if all patients should be evaluated by noninvasive testing or if this approach should be restricted to individuals with clinical evidence of CAD, as in the general population. The objective of this study was to compare CV risk stratification based on nonivasive testing for CAD with two clinical stratification methods as advanced by The American Society of Transplantation (AST) and by The European Renal Association (ERA), respectively. The AST divides patients in high risk (age50 years and/or diabetes and/or CV disease) and low risk (all others).The ERA divides : high risk (CV disease), intermediate risk (age 50 years and/or diabetes), and low risk (as above). We studied 386 CKD patients treated by hemodyalisis, to CV evaluation before being admitted to the renal transplant waiting list. All patients were stratified for the risk of future major cardiovascular events (MACE) using the clinical algorithms and also by myocardial scintigraphy (SPECT-MIBI) with dipyridamol and followedup until death, transplant or MACE. Clinical algorithms (RR:1,8 [IC95% 1,3 2,6-P<0,0001] and SPECT-MIBI(RR:1,5 [IC95% 1,2-1,9-P=0,002] identified patients at increased risk of events. The combined use of clinical stratification followed by SPECT showed that the only patients that would benefit from SPECT risk stratification were those belonging the AST-high risk (RR1,4 [IC95%1,1-1,8-P=0,002] and ERA-intermediate risk groups (RR:1,7 [IC95% 1,2-2,3-P=0,003]. In all other groups :ERA-high-risk (RR:1,1[IC95% 0,8-1,5- P=0,41] and ERA and AST-low-risk (P=0,50) SPECT did not add to the probability of events defined by clinical stratification alone. We conclude that SPECT should not be applied to all renal transplant candidates but should be restricted to those considered at a category of risk as defined by clinical algorithms. These results delineate a more rational approach to risk stratification in renal transplant candidates with a better utilization of economical resources.
Brito, Ema C. "Gene x lifestyle interactions in type 2 diabetes mellitus and related traits." Doctoral thesis, Umeå : Umeå University, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-30523.
Full textAboal, Viñas Jaime. "Creació i validació d'un model de predicció per al càlcul del temps d'angioplàstia primària en pacients amb infart agut de miocardi que són traslladats a un hospital amb disponibilitat d'hemodinàmica." Doctoral thesis, Universitat de Girona, 2020. http://hdl.handle.net/10803/669976.
Full textIntroducció: És difícil aconseguir temps òptims d´angioplàstia primària (AP) en un percentatge de pacients amb IAMEST procedents del medi extra-hospitalari o d'hospitals sense programa d'AP. Disposar d'una eina de predicció del temps d'AP desde el diagnòstic podria ser útil. El nostre objectiu va ser crear un model de predicció del temps d'ECG diagnòstic-pas de guia i realitzar una validació d'aquest model. Mètode Estudi de cohorts prospectiu de pacients ingressats a la unitat de cures crítiques cardiològiques (2007-2018) amb IAMEST, tractats amb AP i que van requerir ser traslladats a un centre amb disponibilitat d'hemodinàmica. Es va realitzar un anàlisi per identificar les variables predictores de demora de l'ECG diagnòstic- pas de guia, es va crear un model de predicció d'aquest temps i una validació interna del model. Resultats Es van incloure un total de 1.049 pacients en l'estudi. Les variables incloses en el model de predicció van ser la insuficiència cardíaca greu a l'ingrés (Killip ≥3) (OR 1,100 IC 95% (1,048-1,155) p = 0,0001), la cirurgia cardíaca prèvia de bypass (OR 1,241 IC 95% (1,119-1,377) p <0,001), la mort sobtada extrahospitalària (OR 1,150 IC 95% (1,078-1,228) p <0,001), la localització lateral de l'IAM (OR 1,065 IC 95% (1,030-1,102) p = 0, 0002), el primer contacte amb hospital sense disponibilitat d'hemodinàmica (OR 1,225 IC 95% (1,174-1,279) p <0,001), centre d'atenció primària (OR 1,183 IC 95% (1,131-1,238) p <0,001), domicili ( OR 1,077 IC 95% (1,026-1,131) p = 0,003) i finalment la distància al centre amb hemodinàmica; <40 Km (OR 1,034 IC 95% (1,026-1,043) p <0,001) i> 40 km (OR 1.079 IC 95% (1,066-1,092) p <0,001). La validació interna va mostrar un R quadrat de 0,355 i una correlació de 0,6. L'àrea sota la corba per a temps superiors a 120 minuts va ser de 0,785. Conclusions Identificades les variables predictores del temps ECG diagnòstic-pas de guia es va crear un model de predicció, amb una validació interna satisfactòria, que pot ser útil en la presa de decisions clíniques en el IAMEST
LIOU, SIOU-WEI, and 劉修維. "PCA Feature Extraction and Supervised Machine Learning for VSD Heart Disease Prediction." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/c4w786.
Full text國立高雄應用科技大學
電子工程系
106
Ventricular septal defect (VSD) is the most common congenital heart disease in newborns. It has become an important topic for researchers and doctors to study through early detection and diagnosis for the treatment. In this thesis, 140 clinical reports of cardiac ultrasound are collected and adopted from the hospital. Through professional interpretation, the doctors filtered and selected 29 valid samples related to VSD with the VSD disease presented by the heart sound signal. The VSD feature is generated and compared the characteristics of the VSD signal with a normal physiological signal and using a supervised learning algorithm for classification and prediction. Firstly, the processing of the heart sound signal extracts and divides the periodic signal through the standardized R-R interval. Secondly, the process uses the Fast Fourier Transform (FFT) to obtain the frequency domain of the heart sound signal. Finally, the heart sound signal is performed the cross-correlation quality verification procedure. The automatically diagnosed the disease for this thesis can provide and assist doctors reducing the time and accuracy of congenital heart disease diagnosis. The related algorithms for this thesis are compared with Support Vector Machine (SVM), Bayes (NB), Decision Tree (DT) and k-Nearest Neighbor (kNN), etc. The resulted data are shown SVM, it can be to provide a good weapon to diagnose heart disease accuracy 96.43% and F1 score 0.964, respectively.
Huang, Li-Chi, and 黃李琪. "Prediction of heart failure risk by using c-reactive protein in individuals with chronic obstructive pulmonary disease." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/67110723363991175801.
Full text國立臺北護理健康大學
運動保健研究所
102
The purpose of the study was to understand the prevalence of heart failure and related factors of heart failure among patients with chronic obstructive pulmonary disease. Based on retrospective review of the medical records for patients who diagnosed chronic obstructive pulmonary disease were enrolled in this study. There were 258 patients of COPD as the sample of this study (mean age 75.96±11.18 years old) and divided into heart failure group (n=128) and the health group (n=130). First, the blood levels of CRP and other risk factors (gender, age and smoking) were analyzed. Second, the subjects were divided by age into 4 groups including the below 65 y/o, 66-75 y/o, 76-85 y/o and above 85 y/o to compare the difference with the other risk factors. The results showed that:(1) It was found that CRP, smoking, and age is the top three risk factors for heart failure. (2) The 76-85 y/o of heart failure group had risk factors were significantly different than other age groups. (3) CRP, smoking, age, and gender were found to be predictors for heart failure. This study suggested patient of COPD should quit smoke to reduce the morbidity of heart failure.
O'Loughlin, Aiden J. "Coronary artery motion analysis for the prediction of clinical coronary artery events." Thesis, 2014. http://hdl.handle.net/1959.7/uws:37264.
Full textLiu, Chia Hao, and 劉家豪. "Prediction of peak oxygen consumption in patient with cardiac disease using 3 minutes' step test combine with heart rate variability." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/3d88k7.
Full textSmall, Neil A., C. Gardiner, S. Barnes, M. Gott, S. Payne, D. Seamark, and D. Halpin. "Using a prediction of death in the next 12 months as a prompt for referral to palliative care acts to the detriment of patients with heart failure and chronic obstructive pulmonary disease." 2017. http://hdl.handle.net/10454/13642.
Full textDear Editor In undertaking studies of palliative care in heart failure and chronic obstructive pulmonary disease (COPD) in the UK, we identified procedural, conceptual and ethical challenges that may arise from one feature of The End of Life Care Strategy for England.1 The strategy presents the question, ‘Would I be surprised if the person in front of me was to die in the next six months or one year?’ as a prompt to initiate discussion of endof-life care needs and preferences (paragraph 3.23). We believe this question is inappropriate in heart failure and COPD and its use will inhibit the initiation of a palliative care approach with these patients.
Gentile, Christina. "Individual differences in the prediction of metabolic dysfunction from physiological responses to stress : a target for intervention?" Thèse, 2017. http://hdl.handle.net/1866/20773.
Full textFeldner-Busztin, Adrienne. "Predicting the psychological and physiological prognosis of cardiac rehabilitation patients." Thesis, 1995. http://hdl.handle.net/10539/23011.
Full textThe large percentage of deaths attributed to recurrent Coronary Heart Disease (CHD) has generated a search for behavioural and psychological factors which mitigate the consequences of CHD. An aim of the present thesis is to extend this search by identifying factors which predict prognosis fer recovery from CHD. Two key factors seen to influence prognosis are aerobic exercise and Type A behaviour. Extant research into the role of exercise has been hindered by methodological weaknesses. As a consequence, the precise means by which exercise influences CHD patients' psychological and physiological strain remains unclear. Similarly, the Type A literature has been flawed by the inaccurate conceptualisation and measurement of Type A behaviour as a global, and 110t a multidimensional, construct. Research which has examined the multidimensional nature of Type A behaviour has been restricted to low risk samples. Thus, a further aim. of the present research is to examine ; prognostic role of exercise and Type A components within the context of cardiac rehabilitation. In achieving this aim, three studies are conducted. [Abbreviated Abstract. Open document to view full version]
MT2017
Macrodimitris, Sophia D. "Predicting motivational readiness to change lifestyle practices in individuals at risk for heart disease /." 2005. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:NR11594.
Full textTypescript. Includes bibliographical references (leaves 202-245). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&res_dat=xri:pqdiss&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&rft_dat=xri:pqdiss:NR11594
Ferreira, Dos Santos Claudia Marisa Goncalves. "The use of echocardiography in predicting left ventricle thrombus in patients with idiopathic dilated cardiomyopathy at Chris Hani Baragwanath Hospital." Thesis, 2013. http://hdl.handle.net/10321/814.
Full textCardiomyopathies and their resultant heart failure (HF) remain a major cause of cardiovascular morbidity and mortality (Wood and Picard, 2004). Idiopathic dilated cardiomyopathy (IDCMO) is a primary myocardial disease of unknown cause, characterized by left ventricular (LV) or biventricular dilatation and impaired myocardial contractility. Dilated cardiomyopathy (DCMO), along with rheumatic heart disease and hypertension (HPT), is one of the leading causes of HF in Africa. In fact, in an epidemiology study of 884 patients in Soweto, IDCMO was the second major cause of HF. Thirty five percent of patients in the study, with HF, had IDCMO (Sliwa, Damasceno, Mayosi, 2005). Methodology: Patients referred to the cardiomyopathy (CMO) clinic at Chris Hani Baragwanath hospital, situated in the echocardiographic lab, were recruited, provided they satisfied the exclusion and inclusion criteria and were enrolled after obtaining voluntary informed consent. From May 2009 to September 2010, 70 patients with IDCMO were recruited for this trial. Patients with DCMO were identified by means of echocardiographic criteria which included a left ventricular ejection fraction (LVEF) of less than 45% and an end diastolic dimension (EDD) of greater than of 52 mm (2D in long parasternal axis). Results: In the present study the prevalence of left ventricular (LV) thrombus in patients with IDCMO was 18.6%. When using Univariate logistic regression, the only independent predictors of LV thrombus formation was LVEF and age. However, when multivariate logistic regression analysis was applied to the data, the only predictor with a significant association was age. The reason for this is not clear. It is postulated that perhaps younger patients have differences in the pathophysiology of their disease such as a greater smoldering inflammatory component which may therefore predispose them to thrombus formation. For example the presence of IL-6 may be important in the formation of LV clot in cases of LV dysfunction (Sosin, Bhatia, Davis, Lip, 2003). The association between LVEF and LV thrombus was borderline significant. Conclusion: The prevalence of LV thrombus formation in this cohort of patients with IDCMO was 18.6%. Echocardiographic parameters alone cannot predict which patients are more likely to develop thrombus formation.
National Research Foundation
Zheng, Nan-Cheng, and 鄭南成. "Is uric acid an independent predictor of mortality in coronary heart disease patients?─ Hualien Coronary Heart Study." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/87945371720464053917.
Full text慈濟大學
醫學研究所
93
During the past 30 years, there has been a shift in the spectrum of leading causes of deaths from infectious disease to chronic disease, which resulted from the economic, culture and life style changes in Taiwan. Many of the chronic diseases are closely related to atherosclerosis. Cardiac death, most of that related to coronary atherosclerosis, was still the third of the ten leading causes of death in Taiwan in 2003. Therefore, atherosclerotic prevention is important in public health. Reviewed literatures revealed that the role of uric acid in coronary artery disease (CAD) was unclear. Framingham study reported that uric acid was not a significant factor to concern the formation and prognosis of CAD. British and Japanese teams also supported these results between 1997 and 2001. National Health and Nutrition Examination Survey (NHANES) study, however, found the uric acid significantly correlated with CAD in women, but not in men. Moreover, Germany and Italian teams had sequentially concluded that there was a significant correlation in men. They also started to study these relations in a specific age and race. In Taiwan, the cohort study for CAD has been conducted in 4 townships: Jin-Shan, San-Zhi, Zhu-Dong and Pu-Zi. They focused on the primary prevention using lipid profile, obesity, insulin level, diabetes mellitus and family history as the risk factors. Moreover, the follow-up years were shorter than those of overseas studies. As we know, a longitudinal study on CAD patients was not found in Taiwan yet. In this study, we used survival analysis to predict if uric acid as a factor to affect the survival time of CAD patients. We reviewed the clinical data of 1308 CAD patients, who were followed up by “Coronary artery disease, A secondary prevention program”, in Tzu-Chi medical center between January 1997 and December 2003. The clinical characters, medical records, blood chemistry data and dead time were collected. Kaplan-Meier survival curve analysis was used to analyze the relations between survival time and different level of uric acid. The relative risk (RR) of uric acid on cardiac death and total were evaluated by Cox regression analysis. We also discussed if uric acid is an independent predictor of mortality for CAD patients. A total of 254 patients were excluded. The data of 1054 patients (80.6%) were analyzed. There were 195 patients died (127 cardiac deaths) during the follow-up with annular cardiac death rate of 3.80%. A positive relation between cardiac death rate and uric acid level was found in this study. This result suggests that uric acid level correlate with the survival time of CAD patients significantly. Multivariate Cox regression analysis revealed that the relative risk of cardiac death rise 9% with an increase 1mg/dl of uric acid (RR 1.09, 95%CI 1.01 to 1.18, p<0.05). When the level of uric acid was classified into four quartiles, it appeared that patients in the fourth quartile had a higher cardiac death rate than those in the first quartile with a RR of 2.05 (95%CI 1.18 to 3.57, p<0.05). The influence of uric acid on the prediction of cardiac death was not affected by sex and age, although annular cardiac death was different between male and female (2.91 vs 6.85%). Univariate Cox regression analysis revealed that uric acid significantly affected the cardiac death rate in low risk groups, except for hypertension and diabetes mellitus. Moreover, uric acid may increase platelet agglutination, stimulate vascular smooth muscle cell proliferation and induce inflammation, resulted in hypertension and renal disease. These effects may influence the incidence and prognosis of CAD. Thus, the results of this study support uric acid is an independent predictor of mortality on CAD patients and suggest that uric acid should be considered as one of controllable factors for CAD.
LIN, YU-HSIEN, and 林育嫺. "Applying Genetic Algorithms in Feature Selection to Construct Data Mining Predictive Model for Heart Disease." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/99039719355741640884.
Full text國立雲林科技大學
工業工程與管理系
104
Chronic diseases have the highest mortality rate in the world, in which the main cause of death is heart disease. The number of patients died of heart disease increases year by year, and here is a trend of younger age prevalence. Electrocardiogram (ECG) is often used to determine whether a patient has heart disease or myocardial infarction. It is the most commonly used diagnostic technique for the diagnosis of heart disease. However some patients can’t use the device in static state. Therefore, the exercise ECG is the best way to detect heart disease. Exercise ECG is the amount of oxygen consumed per minute of the body during exercise. It uses the maximum oxygen uptake (VO2 max) to interpret the situation of heart and lung function, but not every patient is suitable for the use of exercise test to detect heart disease. We need a method that can accurately determine the risk of heart disease without exercise. The purpose of this study is to establish a prediction model to pre-examine patients suffering from heart disease. The National Health and Nutrition Examination Survey was adopted in this study. From 2003 to 2004, a total of 2638 was used as the participants. Through the genetic algorithm combining with Naïve Bayes Classifier and Logistic Regression, we established a model to predict the maximum oxygen uptaking in patients to determine whether a patient is likely to have a heart disease. According Genetic Algorithm combine with data mining, the impact factors of affecting heart disease were age, heart rate, standing height, weight, waist circumference, BMI and blood urea nitrogen. The results of this study can advance the possibility of heart disease in patients and provide patients with risk factors for disease to prevent and reduce the risk of disease.
Dai, Wuyang. "Detection and prediction problems with applications in personalized health care." Thesis, 2015. https://hdl.handle.net/2144/15651.
Full textFernandes, Maria Inês Resende da Lomba. "Data Mining Application for Healthcare Sector: Predictive Analysis of Heart Attacks." Master's thesis, 2021. http://hdl.handle.net/10362/127475.
Full textCardiovascular diseases are the main cause of the number of deaths in the world, being the heart disease the most killing one affecting more than 75% of individuals living in countries of low and middle earnings. Considering all the consequences, firstly for the individual’s health, but also for the health system and the cost of healthcare (for instance, treatments and medication), specifically for cardiovascular diseases treatment, it has become extremely important the provision of quality services by making use of preventive medicine, whose focus is identifying the disease risk, and then, applying the right action in case of early signs. Therefore, by resorting to DM (Data Mining) and its techniques, there is the ability to uncover patterns and relationships amongst the objects in healthcare data, giving the potential to use it more efficiently, and to produce business intelligence and extract knowledge that will be crucial for future answers about possible diseases and treatments on patients. Nowadays, the concept of DM is already applied in medical information systems for clinical purposes such as diagnosis and treatments, that by making use of predictive models can diagnose some group of diseases, in this case, heart attacks. The focus of this project consists on applying machine learning techniques to develop a predictive model based on a real dataset, in order to detect through the analysis of patient’s data whether a person can have a heart attack or not. At the end, the best model is found by comparing the different algorithms used and assessing its results, and then, selecting the one with the best measures. The correct identification of early cardiovascular problems signs through the analysis of patient data can lead to the possible prevention of heart attacks, to the consequent reduction of complications and secondary effects that the disease may bring, and most importantly, to the decrease on the number of deaths in the future. Making use of Data Mining and analytics in healthcare will allow the analysis of high volumes of data, the development of new predictive models, and the understanding of the factors and variables that have the most influence and contribution for this disease, which people should pay attention. Hence, this practical approach is an example of how predictive analytics can have an important impact in the healthcare sector: through the collection of patient’s data, models learn from it so that in the future they can predict new unknown cases of heart attacks with better accuracies. In this way, it contributes to the creation of new models, to the tracking of patient’s health data, to the improvement of medical decisions, to efficient and faster responses, and to the wellbeing of the population that can be improved if diseases like this can be predicted and avoided. To conclude, this project aims to present and show how Data Mining techniques are applied in healthcare and medicine, and how they contribute for the better knowledge of cardiovascular diseases and for the support of important decisions that will influence the patient’s quality of life.
Chiang, Yueh Tao, and 姜月桃. "The Predictive Model of Transiently Lost to Follow-Up Among Patients with Congenital Heart Disease in Taiwan." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/01227227350619942384.
Full textNaidoo, Nivashni. "The predictive value of pro brain natriuretic peptide (ProBNP) levels to determine the presence and severity of coronary artery disease in patients with a positive or inconclusive exercise stress test." Thesis, 2010. http://hdl.handle.net/10321/619.
Full textCardiovascular disease (CVD) is one of the major causes of premature deaths worldwide. In South Africa, approximately 195 people die from cardiovascular diseases each day. The earlier coronary artery disease (CAD) is detected, the better the prognosis. NT- pro- brain natriuretic peptide (NT-proBNP) is a cardiac neurohormone that is secreted in the cardiac ventricles in response to excessive stretching of heart muscle cells. Brain natriuretic peptide (BNP) is currently being used as a marker of left ventricular dysfunction but limitations are evident in patients with sepsis, volume overload, stroke and acute mitral regurgitation. OBJECTIVES: The main objective of this study was to identify a possible value of NT- proBNP level which indicates CAD. It also aimed to compare NT- proBNP levels with the number of diseased vessels; to assess the association between proBNP levels and patients’ age and gender; to determine the percentage of false positive proBNP levels; to determine the probability of false positive exercise stress testing and to correlate NT- proBNP levels with LVEDP. METHODS: Sixty patients were recruited from the Cardiology Department at St Anne’s hospital to participate in this trial. They were divided into two groups; Group A, the control group, consisted of thirty patients with a positive EST and Group B, the experimental group, consisted of thirty patients with an inconclusive EST. After the EST, all patients from both groups were required to have a NT- proBNP blood test, a left and right coronary angiogram and a left ventriculogram. iii RESULTS: Results of the study showed that post EST NT- proBNP levels, in both groups, increased in the presence of CAD (p<0.001). For the positive EST group, the area under the ROC curve was 0.975 which was highly statistically significantly different from the null hypothesis value of 0.5 (p<0.001) and a cut- off value of 120 pg/ml was identified with the highest sensitivity (95.7%) and specificity (100%). For patients in the inconclusive EST group, the area under the ROC curve was 0.912 which was highly statistically significantly different from the null hypothesis value of 0.5 (p<0.001) and a cut-off value of 85 pg/ml was identified with the highest sensitivity (87.5%) and specificity (86.4%). There was a statistically significant difference between the median NT- proBNP values of males and females in the group of patients with positive EST (p=0.048). The values were higher in males. However, there was no significant difference between the genders in the group with an inconclusive EST. A strong and significant correlation (p<0.001) between left ventricular end diastolic pressures (LVEDP) and number of disease vessels was demonstrated. The probability of a false positive result for EST was 24.1%. and the probability of a false negative result was 25.8%. CONCLUSION: Results of the study showed that post EST NT- proBNP levels, in both groups, increased in the presence of CAD and could accurately predict the presence of CAD. Cut- off values of 120 pg/ml for the positive EST group and 85 pg/ml for the inconclusive EST group were identified with the highest sensitivity and specificity. In the positive EST group, a trend of increasing NT-proBNP with age was and NT-proBNP values were higher in males. The positive EST was relatively accurate at predicting CAD; however, 75.9% of patients with an inconclusive EST did not have CAD.Exercise stress testing in this regard, is therefore relatively inaccurate at predicting CAD in patients with inconclusive ESTs, and the need for an additional tool, such as NT-proBNP measurements post inconclusive EST is warranted in the determination of the presence of CAD.
XIAO, MIN-FENG, and 蕭閔峯. "Revised inverse problem algorithm-based prediction of coronary artery stenosis readings from the clinical data of patients with coronary heart diseases." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/fmm532.
Full text中臺科技大學
醫學影像暨放射科學系暨研究所
105
Coronary artery stenosis readings were predicted in this study on the basis of clinical data for patients with coronary heart diseases using the inverse problem algorithm. Five factors, including age, BSA (body surface area), MAP (mean artery pressure), sugar AC (ante cibum), and LDL-C (low-density Lipoprotein-Cholesterol) were incorporated into a nonlinear first-order regression fit analysis to develop a prediction equation with sixteen terms derived via a revised inverse problem algorithm implemented through the STATISTICA 7.0 default regression fit. The clinical data acquired from ninety-three coronary heart disease patients were first normalized to the same domain range of [-1 to +1], and then processed by the above algorithm to find the compromised solution of predicted coronary artery stenosis reading. The actual reading was obtained by weighting the stenosis of three major cardiac artery branches, namely, the left anterior descending artery (LAD) (wi 0.3), left circumflex artery (LCA) (wi 0.3), and right coronary artery (RCA) (wi 0.4). The derived regression fit possessed the final loss function value Φ=3.589 and correlation coefficient r2 =0.892 with variance of 79.55%. Accordingly, forty-five patients with similar syndromes were analyzed to verify the prediction, which exhibited a high coincidence. The LDL-C factor was dominant for the prediction of the largest coefficient in the derived equation, whereas the age factor exhibited a minor contribution to the regression fit. The attempts to reduce the number of influence factors to 4, 3 or 2 for the model simplification yielded the results, whose low linearity and high loss function values reflected their inappropriate setting.
Huang, Hui-Chun, and 黃惠君. "Analysis of T- wave Morphology for Predicting of Long-term Prognosis in Coronary Heart Disease Patients with Implantable Cardioverter Defibrillator." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/77540986498667905658.
Full text國立臺灣大學
臨床醫學研究所
98
Background The most common underlying reason for patients to die suddenly from cardiac arrest is coronary heart disease (CHD). Although a large number of risk factors for Sudden Cardiac Death have been identified, translating these findings into a comprehensive risk stratification strategy is challenging. T wave morphology descriptors on standard twelve-lead electrocardiogram (ECG) have shown to predict arrhythmic events in patients with previous myocardial infarction or congestive heart failure. However, these descriptors have not been considered to determine the risk stratification in CHD patients with Implantable Cardioverter Defibrillator (ICD). This study was conducted to examine T wave morphology descriptors prognostic importance in CHD patients with ICD, comparison CHD patients without ICD. Methods 41 CHD patients with ICD were compared with 55 CHD patients without ICD and 55 healthy patients using a case-control design. T wave morphology descriptors including (lead dispersion, T wave morphology dispersion, percentage of the loop area, percentage of the outer area, and the total cosine between QRS and T wave [TCRT] were studied in these patients Results A total of 41 CHD with ICD patients with a mean age of 65 ± 10 years were enrolled and followed-up for 3.1 ± 2.1 years. In the ICD group, the occurrence rate of HTN and DM were 73% and 50%. The mean left ventricular ejection fraction (LVEF) was 47% ± 14%. The total mortality rate in ICD group was 21.9%, shock within 1 year rate was 27% and shock rate was 32%. QRS duration and T wave morphology descriptors like TCRT, TMD were statistically significantly different in CHD patients and CHD patients with ICD patients.(P<0.001,<0.001 and <0.001 respectively). A stepwise backward Cox regression analysis showed that first shock rate was significantly associated with TMD(P = 0.05). On the basis of PL<0.64, PO>0.298 and TMD>74.1 as cutoff points, a significant difference in long-term survival were observed from a Kaplan-Meier survival curve (P < 0.022, P<0.032 and P<0.038 respectively). The Cox regression analysis showed that total mortality was significantly associated with LVEF (p=0.037), No. of diseased vessel(p=0.028) ,HTN(p=0.024), DM(p=0.033), Creatine (p=0.019), QRS duration (p=0.027), PO(p=0.032) and PL(p=0.032) (Table 5) and first shock was significantly associated with b-blocker use(p=0.046), sex(p=0.047), hypertension (p=0.027)and TMD (P = 0.031). Conclusion In conclusion, TCRT ,TMD and QRS duration may provide further risk stratification for CHD patients, and TMD,PO and PL may impact on the long term survival of CHD patients with ICD. Moreover, TMD may be a good predictor for shock rate in CHD patients with ICD.
Alves, Rita Dias Cabrita. "Fully non-invasive pressure drop measurements and post treatment prediction in congenital heart diseases via cardiac magnetic resonance and computer flow dynamics." Master's thesis, 2017. http://hdl.handle.net/10451/31815.
Full textDe acordo com os dados de 2017 da Organização Mundial da Saúde, as doenças cardiovasculares são a principal causa de morte a nível mundial. Se estes tipos de doenças não forem diagnosticadas e tratadas atempadamente, podem levar a insuficiências cardíacas ou outras complicações irreversíveis. As duas doenças cardiovasculares congénitas estudadas neste trabalho são a coarctação aórtica (CoA), caracterizada por uma estenose, habitualmente, na zona do arco da artéria aorta, e a doença da válvula aórtica (AvD), uma malformação ao nível da válvula aórtica. Estas doenças são responsáveis por cerca de 50,000 intervenções por ano. Deste modo, a melhoria métodos de diagnóstico e de intervenção adequados e eficientes é uma prioridade e pode levar ao decréscimo no número das intervenções, bem como reduzir a morbilidade e a mortalidade. A área de imagiologia médica de diagnóstico tem tido uma evolução significativa ao longo dos anos e é de extrema importância nas tentativas de substituição de métodos de diagnóstico invasivos. As imagens médicas são adquiridas e posteriormente processadas e analisadas, com recurso a programas adequados. Atualmente, é possível obter os valores de gradientes de pressão relativa a partir de Ecocardiografia Doppler e Ressonância Magnética. Contudo, os gradientes de pressão medidos no cateterismo cardíaco, o método gold standard para o diagnóstico de CoA e AvD, são gradientes de pressão absoluta. Nesta dissertação desenvolveu-se um método de diagnóstico de CoA e AvD, a partir dos mapas de pressão relativa no estreitamento da aorta e na válvula aórtica, respectivamente. O método matemático desenvolvido tem por base as equações de Poisson, resolvida com a condição de fronteira de Neumann utilizando os métodos de elementos finitos, e a de Navier Stokes para a conservação do momento. O método desenvolvido também tem em conta a informação proveniente da função de Windkessel da artéria aorta, uma artéria distensível. Esta função dá-nos o comportamento da propagação do pulso de pressão com uma velocidade de pulso de propagação. Deste modo, é observado um desfasamento temporal entre as curvas de fluxo da pressão e da velocidade, entre as duas regiões de interesse escolhidas. Deste modo, o método, denominado de Time-shift Corrected Pressure Maps (TCPM, sigla em inglês), permite obter os mapas de pressão absoluta, isto é, mapas de pressão que têm em conta o intervalo de tempo entre os picos de pressão na aorta descendente e ascendente, no caso do primeiro estudo, e antes e depois da válvula aórtica, no caso do segundo estudo. Os pacientes de ambos os estudos tinham indicação clínica para cateterismo cardíaco e foram submetidos a ressonância magnética cardiovascular de contraste de fase em tempo real (4D PC MRI, em inglês), para recolher as imagens ao nível da aorta e da válvula aórtica e os respectivos campos de velocidade da corrente sanguínea. O primeiro estudo tem como objetivo a aplicação do método TCPM a 27 pacientes de CoA (n=16 masculinos, n=11 femininos, faixa etária de 4 a 52 anos, idade média de 20±15 anos). Após aquisição das imagens, estas foram processadas usando programas específicos. Em primeiro lugar foi necessário segmentar a aorta, seguiu-se a seleção das regiões de interesse e, finalmente, a obtenção dos campos de velocidade e dos mapas de pressão relativa entre as duas regiões de interesse selecionadas. Após aplicação do método TCPM, foram aplicados testes estatísticos (correlação, teste t e Bland-Altman) para comparar os valores obtidos a partir de TCPM com os valores obtidos no cateterismo cardíaco. Após processamento das imagens dos 27 pacientes, 6 pacientes foram retirados do estudo. N=3 pacientes foram retirados porque a percentagem de fluxo que passa pelo estreitamento é insuficiente para calcular o gradiente de pressão a partir de TCPM e N=3 pacientes foram retirados porque a aorta não estava inserida por completo no FOV. As medições obtidas a partir de TPCM e cateterismo cardíaco têm uma correlação linear significante (R²=0,90; p<0,001). A partir dos gráficos Bland-Altman é possível verificar uma boa concordância entre as medições de ambos os métodos, com bias de -2,69 mmHg e os limites de concordância de ±4,74 mmHg. O teste de equivalência mostrou uma relação significante entre os métodos (p=0,007). O segundo estudo tem como objetivo a aplicação do método TPCM e o método da Área de Gorlin a 4 pacientes de AvD (n=4 masculinos, faixa etária 17 a 36 anos, idade média 27±7 anos). O método da Área de Gorlin permite obter o gradiente de pressão absoluta a partir da área geométrica da válvula e do fluxo total que passa nessa área. Após a aquisição das imagens, foi feito o processamento das mesmas. Numa primeira fase, as imagens foram segmentadas na região da válvula aórtica. Depois, as imagens segmentadas foram analisadas em dois programas distintos. O primeiro foi utilizado de forma a obter os campos de velocidade e os mapas de pressão relativa entre dois pontos antes e depois da válvula aórtica. O segundo permitiu definir a região da válvula como região de interesse e exportar os valores de velocidade, área, pressão relativa e fluxo absoluto nessa região. Os resultados mostram uma correlação linear significativa entre os valores de cateterismo cardíaco e de TCPM (R²=0,99; p<0,001). Os gráficos de Bland-Altman mostram uma boa concordância entre os valores de TCPM (24,75±22,50 mmHg) e de cateterismo (20,88±19,51 mmHg), com um bias de -3,87 mmHg e limites de concordância de ±3,64 mmHg. Os resultados também sugeriram uma ligeira subestimação dos valores do cateterismo cardíaco a partir do método da Área de Gorlin (14,47±13,00 mmHg), com um bias de 6,41 mmHg e limites de concordância de ±7,15 mmHg. Este estudo foi feito com uma amostra diminuta de 4 pacientes, o que não é suficiente para retirar conclusões com significância. Contudo, foi uma primeira abordagem positiva, que mostra a potencialidade que este método pode vir a apresentar. O método TCPM proposto neste projeto permite a medição não invasiva de gradientes de pressão absoluta a partir de mapas de pressão relativa em pacientes de CoA e AvD. Vários aspectos têm que ser tidos em conta de forma a garantir a eficácia deste método. Por exemplo, as regiões de interesse escolhidas têm que se cuidadosamente selecionadas de forma a serem perpendicular à direção do fluxo naquele local. Só desta maneira é possível obter o fluxo, os campos de velocidade e as pressões relativas corretas. Também, se o raio da estenose for menor que 2 voxéis, a relação sinal-ruído aumenta substancialmente, e a resolução especial da aquisição é insuficiente. Contudo, a aplicação do método TPCM a casos de grande estreitamento não é necessária visto que estes casos já são tipicamente identificados em imagens anatómicas de ressonância magnética e que o paciente segue automaticamente para intervenção quando a área do estreitamente representa cerca de 50% do valor de área típico da aorta. O método não invasivo TCPM apresenta uma boa concordância com o cateterismo cardíaco em termos da medição dos gradientes de pressão em CoA e AvD. Os bias e os limites de concordância entre cateterismo e TCPM foram substancialmente mais pequenos que os bias e os limites de concordância entre cateterismo e ecocardiografia Doppler e entre o cateterismo e o método da Área de Gorlin. Com os resultados apresentados já é possível ver o potencial desta técnica no processo de diagnóstico e decisão de intervenção em casos de CoA e AvD. Contudo, estudos com populações maiores será extremamente benéfico para validar clinicamente este método.
This dissertation aims to validate MRI-based time-shift corrected pressure mapping (TCPM) against cardiac catheterization in CoA and AvD patients. Also, in AvD patients, catheterization will be compared against Gorlin Area method. This project is divided in two independent studies: the first one for CoA patients and the second one for AvD patients, all with clinical indication for cardiac catheterization. In both CoA and AvD, clinical guidelines recommend treatment in the presence of a relevant pressure gradient. While reliable non-invasive measurement approaches would be crucial, the accuracy of currently available methods has been limited. In both studies, 4D PC-MRI was performed to compute relative pressure maps via Pressure-Poisson equation. To consider the patient-specific peak pressure time-shift from the ascending to the descending aorta and before and after the aortic valve, relative pressure gradient maps were corrected by the inertial term. Comparison between TCPM and invasive peak-to-peak measurements was performed using correlation, Bland-Altman plots and mean-equivalence t-test. In the first study, with a cohort of 21 patients with CoA, TCPM and catheter measurements showed significant linear correlation (R²=0.90; p<0.001). Bland-Altman plots demonstrated good agreement between TCPM and catheter derived pressure gradients with mean differences of -2.69 mmHg and 95% limits of agreement between -6.38 and 1.00 mmHg between methods. The mean-equivalence test was significant (p=0.007). In the second study, with a cohort of 4 patients with AvD, the catheterization measurements were compared against TPCM measurements. The results showed significant linear correlation (R²=0.99; p<0.001). Bland Altman plots showed a good agreement between TCPM (24.75±22.50 mmHg) and catheter derived peak-to-peak pressure gradients (20.88±19.51 mmHg), and suggested slight underestimation of the pressure gradients by the Gorlin Area method (14.47±13.00 mmHg). Non-invasive TCPM showed equivalence to pressure gradients from invasive heart catheterization in patients with CoA and AvD. However, in the AvD study, they were obtained for a very small cohort of patients and do not have sufficient statistical significance to validate the method for AvD patients.
Baker, Maria Kathryn. "Assessing the psychosocial risk factors for coronary artery disease: an investigation of predictive validity for the psychosocial inventory for cardiovascular illness." 2009. http://hdl.handle.net/2152/7516.
Full texttext
Lu, Weixun. "Multi-risk modeling for improved agriculture decision-support: predicting crop yield variability and gaps due to climate variability, extreme events, and disease." Thesis, 2020. http://hdl.handle.net/1828/12130.
Full textGraduate
2021-08-19