Literatura académica sobre el tema ""Early Obesity Prediction""

Statistical models have been developed for the prediction or diagnosis of a wide range of outcomes. However, to our knowledge, only 7 published studies have reported models to specifically predict overweight and/or obesity in early childhood. These models were developed using known risk factors and vary greatly in terms of their discrimination and predictive capacities. There are currently no established guidelines on what constitutes an acceptable level of risk (i.e., risk threshold) for childhood obesity prediction models, but these should be set following consideration of the consequences of false-positive and false-negative predictions, as well as any relevant clinical guidelines. To date, no studies have examined the impact of using early childhood obesity prediction models as intervention tools. While these are potentially valuable to inform targeted interventions, the heterogeneity of the existing models and the lack of consensus on adequate thresholds limit their usefulness in practice.

AbstractObesity is highly prevalent in children under the age of 5 years, although its identification in infants under 2 years remains difficult. Several clinical prediction models have been developed for obesity risk in early childhood, using a number of different predictors. The predictive capacity (sensitivity and specificity) of these models varies greatly, and there is no agreed risk threshold for the prediction of early childhood obesity. Of the existing models, only two have been practically utilized, but neither have been particularly successful. This commentary suggests how future research may successfully utilize existing early childhood obesity prediction models for intervention. We also consider the need for such models, and how targeted obesity intervention may be more effective than population-based intervention.

Summary Objectives: This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Methods: Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Results: Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. Conclusions: This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two. Citation: Dugan TM, Mukhopadhyay S, Carroll AE, Downs SM. Machine learning techniques for prediction of early childhood obesity. Appl Clin Inform 2015; 6: 506–520http://dx.doi.org/10.4338/ACI-2015-03-RA-0036

Obesity is one of the most important problems in modern health care. The high prevalence of this pathology also affects women of reproductive age, which leads to an increase in the prevalence of obesity in pregnant women. Purpose of the work ‒ analysis of the effect of adipokine indicators on predicting the development of placental insufficiency in obese women. Materials and methods. 225 women were examined who were subdivided by such a parameter as obesity into 4 groups: 3 main and 1 control. The control group consisted of 55 pregnant women with an initially normal BMI value (18.5‒24.9 kg/m2). Group 1st included 109 pregnant women with grade I obesity (BMI 31.88 1.4 kg/m2), group 2nd ‒ 34 pregnant women with grade II obesity (BMI 36.6 1.1 kg/m2), group 3rd ‒ 31 pregnant women with grade III obesity (BMI 42.2 1.9 kg/m2). We studied the data of the anamnesis of pregnant women (somatic and obstetric-gynecological), indicators of adiponectin and omentin, peculiarities of the course of pregnancy and childbirth (data of cardiotocography (CTG), ultrasound markers of disturbances in the formation and functioning of the fetoplacental complex), indicators of labor activity, parameters of newborns (mass-growth, state on the Apgar scale, ponderal index, fetal-placental ratio) and the course of the postpartum period. When conducting statistical analysis in the case of comparing two dependent (paired) samples of parameters, the paired Students t-test was used. The results were considered statistically significant if the р was less than 0.05. With this indicator, the value of the probability of difference between the compared categories was more than 95%. Results. The possibility of predicting the development of placental insufficiency depending on the concentrations of omentin and adiponectin was confirmed. The development of placental insufficiency is most likely with omentin values in the range of 177.6‒191.2 g/ml and adiponectin in the range of 16.0‒22.5 g/ml. Conclusion. Determination of adipokine levels at 8‒9 weeks gestation may be practically significant in predicting the development of placental insufficiency in obese women.

Protein patterns were collected, the presence or absence of which allows a fairly good prediction of the patient's weight. Such proteomic patterns with high predictive power should facilitate the transformation of potential biomarker candidates for clinical use for the early stratification of obesity therapy.

Previous studies demonstrate the feasibility of predicting obesity using various machine learning techniques; however, these studies do not address the limitations of these methods in real-life settings where available data for children may vary. We investigated the medical history required for machine learning models to accurately predict body mass index (BMI) during early childhood. Within a longitudinal dataset of children ages 0–4 years, we developed predictive models based on long short-term memory (LSTM), a recurrent neural network architecture, using history EHR data from 2 to 8 clinical encounters to estimate child BMI. We developed separate, sex-stratified models using 80% of the data for training and 20% for external validation. We evaluated model performance using K-fold cross-validation, mean average error (MAE), and Pearson’s correlation coefficient (R2). Two history encounters and a 4-month prediction yielded a high prediction error and low correlation between predicted and actual BMI (MAE of 1.60 for girls and 1.49 for boys). Model performance improved with additional history encounters; improvement was not significant beyond five history encounters. The combined model outperformed the sex-stratified models, with a MAE = 0.98 (SD 0.03) and R2 = 0.72. Our models show that five history encounters are sufficient to predict BMI prior to age 4 for both boys and girls. Moreover, starting from an initial dataset with more than 269 exposure variables, we were able to identify a limited set of 24 variables that can facilitate BMI prediction in early childhood. Nine of these final variables are collected once, and the remaining 15 need to be updated during each visit.

Women with obesity receive intensified antenatal care due to their increased risk of pregnancy complications, even though not all of these women develop complications. We developed a model based on maternal characteristics for prediction of healthy pregnancy outcomes in women with obesity or who are overweight. We assessed whether early-pregnancy metabolites improved prediction. In a population-based cohort study among a subsample of 1180 Dutch pregnant women with obesity or who are overweight, we developed a prediction model using 32 maternal socio-demographic, lifestyle, physical and pregnancy-related characteristics. We determined early-pregnancy amino acids, nonesterifed fatty acids, phospholipids and carnitines in blood serum using liquid chromatography-tandem mass spectrometry. A healthy pregnancy outcome was the absence of fetal death, gestational hypertension, preeclampsia, gestational diabetes, caesarian section, preterm birth, large-for-gestational-age at birth, macrosomia, postpartum weight retention and offspring overweight/obesity at 5 years. Maternal age, relationship status, parity, early-pregnancy body mass index, mid-pregnancy gestational weight gain, systolic blood pressure and estimated fetal weight were selected into the model using backward selection (area under the receiver operating characteristic curve: 0.65 (95% confidence interval 0.61 to 0.68)). Early-pregnancy metabolites did not improve model performance. Thus, in women with obesity or who are overweight, maternal characteristics can moderately predict a healthy pregnancy outcome. Maternal early-pregnancy metabolites have no incremental value in the prediction of a healthy pregnancy outcome.

Childhood obesity is a major public health challenge. Early prediction and identification of the children at an elevated risk of developing childhood obesity may help in engaging earlier and more effective interventions to prevent and manage obesity. Most existing predictive tools for childhood obesity primarily rely on traditional regression-type methods using only a few hand-picked features and without exploiting longitudinal patterns of children’s data. Deep learning methods allow the use of high-dimensional longitudinal datasets. In this article, we present a deep learning model designed for predicting future obesity patterns from generally available items on children’s medical history. To do this, we use a large unaugmented electronic health records dataset from a large pediatric health system in the United States. We adopt a general LSTM network architecture and train our proposed model using both static and dynamic EHR data. To add interpretability, we have additionally included an attention layer to calculate the attention scores for the timestamps and rank features of each timestamp. Our model is used to predict obesity for ages between 3 and 20 years using the data from 1 to 3 years in advance. We compare the performance of our LSTM model with a series of existing studies in the literature and show it outperforms their performance in most age ranges.

Currently, safeguarding the community is vital in terms of finding solution to health related problems which can be achieved through medical research using the advent of technology. Obesity has become worldwide health concern as it is becoming a threat to the future. It is the most common health problems all over the world. Thousands of diseases as well as risks and death are associated to it. An early prediction of a disease will help both doctors and patients to act and minimize if not total eradication of the root cause or work on preventing the disease symptom from further deterioration. Going through patient’s medical history is one of the methods of identifying a disease which most time consuming as processing manually and it comes with an error-prone analyses and expense. Therefore, there is need to scientifically develop a predicting model of the occurrence of the disease or its existence using an automated technique as it is becoming a need of the day. In this research work, we used machine learning techniques on a public clinical available dataset to predict obesity status using different machine learning algorithms. Five machine learning algorithms were applied. Gboost Classifier, Random Forest Classifier, Decision Tree Classifier, K-Nearest Neighbor and Support Vector Machine and the model has shown promising results with as Gboost classifier achieves the highest accuracy of 99.05% as compared to other classifiers. Meanwhile, the K-Nearest Neighbor gave the relatively strong accuracy of 95.74%.

L’obesità infantile dovrebbe essere prevenuta il prima possibile durante la vita del bambino. Stabilire il rischio alla nascita di sviluppare obesità infantile potrebbe essere il primo passo verso una prevenzione focalizzata tempestiva. Durante il mio dottorato di ricerca, mi sono prefissa di costruire strumenti clinici utili a predire il rischio del neonato di sviluppare obesità infantile. A questo scopo, ho analizzato una coorte prospettica, la “Northern finland Birth Cohort 1986” (NFBC1986) (N=4032) (http://kelo.oulu.fi/NFBC) per stabilire il valore predittivo per obesità e/o sovrappeso infantile e dell’adolescenza, di tradizionali fattori di rischio innati, come il BMI dei genitori, il peso alla nascita, l’aumento di peso materno in gravidanza, indicatori comportamentali e sociali, così come di uno score genetico di rischio derivato da 39 polimorfismi notoriamente associati al BMI e/o all’obesità. Ho anche analizzato, come gruppo di validazione, un campione retrospettivo di 1503 bambini di 4-12 anni provenienti dal Veneto, precedentemente utilizzato in uno studio di prevalenza dell’obesità infantile in Nord Italia, allo scopo di determinare se i risultati derivanti dalla NFBC1986 possono essere applicati ad una coorte europea contemporanea all’NFBC1986, con uguale prevalenza di obesità infantile (4%) ma differente background culturale. Infine, ho analizzato un campione prospettico di 1032 bambini (7 anni) del Massachusetts (US) partecipanti al “Project Viva” (http://www.dacp.org/viva/index.html) come ulteriore campione di validazione, allo scopo di determinare se i risultati derivanti dall’NFBC1986 siano applicabili ad una coorte statunitense molto recente, con maggiore prevalenza di obesità (8%) e background culturale molto differente. Nella NFBC1986, ho riscontrato un’accuratezza discriminativa da discreta a buona dei fattori di rischio tradizionali per la predizione dell’obesità infantile, dell’obesità in adolescenza e dell’obesità infantile persistente in adolescenza (0.75 < AUROCs < 0.85, p < 0.001). Lo score genetico di per se ha mostrato scarsa accuratezza per la predizione di tutti gli outcomes considerati (0.55 < AUROCs < 0.60, p < 0.001) e, combinato con i predittori tradizionali, ha prodotto piccolissimi o nulli miglioramenti della discriminazione (integrated discrimination improvements [IDIs] < 1%). La versione dell’equazione NFBC1986 per l’obesità infantile senza tabagismo in gravidanza e numero di componenti familiari (non disponibili nel databse del Veneto) ha mostrato un’AUROC = 0.70[0.63-0.77] quando applicata alla coorte veneta, contro un’AUROC = 0.73[0.69-0.77] nell’NFBC1986, con calibrazione accettabile (p per il test di Hosmer Lemeshow > 0.05). L’equazione NFBC1986 per l’obesità infantile ha mostrato un’AUROC accettabile = 0.73[0.67-0.80] quando applicata ai bambini del Project Viva. Tuttavia la calibrazione nella coorte del Project Viva si è mostrata non completamente soddisfacente (p per il test di Hosmer Lemeshow = 0.02). Lo studio proposto fornisce la prima evidenza che variabili alla nascita disponibili di routine possono essere combinate in scorse di rischio maneggevoli ed economici per la predizione dell’obesità infantile. Una stima accurata del rischio di sviluppare obesità infantile potrebbe avere importanti implicazioni da un punto di vista di salute pubblica, essendo la base per futuri sforzi verso la delineazione di strategie di prevenzione precoci focalizzate sulle famiglie dei neonati a rischio, basate dunque sull’approccio del rischio aumentato e non sull’ approccio di vasta scala. I modelli descritti sfruttano variabili usualmente facili da recuperare retrospettivamente e fortemente e consistentemente associate all’obesità in numerosi paesi. Di conseguenza, è probabile che la riproduzione/implementazione o adattamento dei modelli stessi in popolazioni differenti sia rapidamente possibile. Questo studio inoltre confuta l’ipotesi che i polimorfismi attualmente noti potrebbero contribuire efficacemente alla predizione dell'obesità infantile.
Childhood obesity should be ideally prevented as early as possible during the child life. Assessing the inborn risk of obesity development would be the first step towards timely focused prevention. During my doctoral fellowship, I aimed at building clinical tools to predict the newborn risk for obesity development. To this purpose, I analyzed a unique prospective Northern Finland Birth Cohort 1986 (N=4032) (http://kelo.oulu.fi/NFBC) to assess the predictive value for child and adolescent obesity phenotypes of inborn traditional risk factors, like parental BMI, birth weight, maternal gestational weight, behaviour and social indicators, as well as of a genetic score issued from 39 BMI/obesity-associated polymorphisms. I also analysed a retrospective sample of 1,503 children aged 4-12 from Veneto, Italy, previously used in a survey assessing prevalence and risk factors of childhood obesity in the North of Italy, as a validation sample, in order to explore whether results issued from the NFBC1986 could be applied to a European paediatric cohort contemporary to the NFBC1986, with similar obesity prevalence (4%) but different cultural background. Finally, I analysed a prospective sample of 1032 children (7 years) from Massachusetts (United States) participating in the Project Viva (http://www.dacp.org/viva/index.html) as additional validation sample, in order to explore whether results issued from the NFBC1986 would remain valid when applied to a very recent U.S. child cohort, with higher obesity prevalence (8%) and very different cultural background. In the NFBC1986, I found a fair to good cumulative discrimination accuracy of traditional risk factors for the prediction of child obesity, adolescent obesity, and child obesity persistent into adolescence (0.75 < AUROCs < 0.85, p<0.001). The genetic score alone showed poor accuracy (0.55 < AUROCs < 0.60, p<0.001) for the prediction of obesity outcomes and, combined with clinical predictors, it only produced integrated discrimination improvements (IDI) < 1%. The version of the NFBC1986 equation for childhood obesity lacking gestational smoking and number of household members (not available in the Veneto dataset) had an AUROC = 0.70[0.63-0.77] (p < 0.001) when applied to the Veneto cohort versus an AUROC = 0.73[0.69 – 0.77] in the NFBC1986, with acceptable calibration accuracy (p for Hosmer-Lemeshow test > 0.05). The NFBC1986 equation for childhood obesity had an acceptable AUROC = 0.73[0.67-0.80] (p < 0.001) when applied to the project Viva children. However calibration in the Project Viva sample was not satisfactory (p for Hosmer-Lemeshow test = 0.02). The study I present here provides the first evidence that routinely available inborn variables may be combined into handy and cheap scores to estimate the newborn risk for obesity. An accurate estimation of the inborn risk to develop obesity may have important public health implications, being the basis for further efforts towards potential precocious prevention based on the “high risk approach”, i.e. focused on families of high risk newborns. The models I describe exploit variables usually easy to record retrospectively and strongly and consistently associated with obesity in several countries. Therefore, it is likely that reproduction/implementation or adaptation elsewhere can be successfully performed in a short time. This study also rules out the hypothesis that currently known polymorphisms may provide any useful contribution to accuracy of child obesity prediction.

Gestational Diabetes Mellitus (GDM) happens to be a very frequent and major complication of pregnancy because of higher morbidity and mortality, both for the mother and the baby. After delivery, GDM carries the risk of higher maternal morbidity due to post pregnancy obesity, development of diabetes mellitus, obesity and also cardiovascular diseases in significant number in both the mother and child for future. As per current guidelines, GDM is diagnosed at the end of the second trimester by elevated blood glucose values when, foetal damages by metabolic and epigenetic changes had already started. As a result, treatments cannot be started before the late second or third trimester, when the process of high risk of foetal morbidity and mortality has been set in. If by any method we can predict development of GDM at earliest part of first trimester or even more overjealously, we can predict, before pregnancy, then and then only we can avoid many disasters induced by GDM. With this idea many biomarkers, both clinical and laboratory based like clinical, metabolic, inflammatory and genetic markers etc., related with early pregnancy metabolic alterations have been studied for their potential to help in the prediction of later pregnancy glucose intolerance. Though promises are seen with some biomarker-enhanced risk prediction models for GDM, but lack of external validation and translation into day-to-day clinical applications, cost effectiveness, with which they may be utilized in routine prenatal care has limited their clinical use. But future is very promising and incorporating the biomarkers which precede the onset of hyperglycaemia into a risk prediction model for GDM and may help us for earlier risk assessment, screening, and diagnosis of GDM and also prevention of its both the immediate and remote complications. This review highlights the current knowledge of the understanding of the candidacy and practical utility of these biomarkers for GDM with recommendations for further research.

Cardiovascular disease is the one of the most leading causes of death. Based on symptoms and risk factors the diagnosis of heart can be done. Predicting the cardiovascular disease in the early stage can save the human being. There is no complete cure which reduces the risk of CVD. Deep learning technique has been used to predict the CVD in a prior stage. Based on the symptoms and risk factors, the CVD has been classified into four types such as No heart disease and no symptoms, Structural Heart Disease without symptoms, Structural Heart Disease with Symptoms and the risk factor for Heart failure are “High blood pressure, high cholesterol, genetic, diabetes, obesity is the major risk factors” to identify the cardiovascular disease and current technique is used to control the risks. To manage all the risk factors Electrocardiography (ECG) method is used to manipulate based on particular situation.

OBJECTIVES The prevalence of childhood obesity is significantly higher among racial and/or ethnic minority children in the United States. It is unclear to what extent well-established obesity risk factors in infancy and preschool explain these disparities. Our objective was to decompose racial and/or ethnic disparities in children’s weight status according to contributing socioeconomic and behavioral risk factors. METHODS We used nationally representative data from ~10 700 children in the Early Childhood Longitudinal Study Birth Cohort who were followed from age 9 months through kindergarten entry. We assessed the contribution of socioeconomic factors and maternal, infancy, and early childhood obesity risk factors to racial and/or ethnic disparities in children’s BMI z scores by using Blinder-Oaxaca decomposition analyses. RESULTS The prevalence of risk factors varied significantly by race and/or ethnicity. African American children had the highest prevalence of risk factors, whereas Asian children had the lowest prevalence. The major contributor to the BMI z score gap was the rate of infant weight gain during the first 9 months of life, which was a strong predictor of BMI z score at kindergarten entry. The rate of infant weight gain accounted for between 14.9% and 70.5% of explained disparities between white children and their racial and/or ethnic minority peers. Gaps in socioeconomic status were another important contributor that explained disparities, especially those between white and Hispanic children. Early childhood risk factors, such as fruit and vegetable consumption and television viewing, played less important roles in explaining racial and/or ethnic differences in children’s BMI z scores. CONCLUSIONS Differences in rapid infant weight gain contribute substantially to racial and/or ethnic disparities in obesity during early childhood. Interventions implemented early in life to target this risk factor could help curb widening racial and/or ethnic disparities in early childhood obesity.

This chapter covers colorectal cancer, and includes information on epidemiology, risk factors (chronic inflammation/inflammatory bowel disease, radiation, diet and lifestyle, post cholecystectomy, diabetes, obesity and insulin resistance, cigarette smoking, alcohol, ureterocolic anastamosis, and genetic risk factors, screening, and chemoprevention (aspirin, and NSAIDS), the molecular biology and pathology of colorectal cancer, colorectal carcinoma (location, pathologic prognostic markers, and predictive markers), surgical management (colonic cancer and inflammatory bowel disease, hereditary non-polyposis colonic cancer or HNPCC, presenting as an emergency, treatment of polyp or early cancers, liver and lung metastasis, peritoneal disease, results of surgery and treatment for colon cancer, medical management of early stage disease, adjuvant chemotherapy for stage III disease (T1-4, N1-2M0), adjuvant therapy of patients with resected stage II colon cancer, radiotherapy, multidisciplinary care and special groups, the role of allied teams, and surveillance and follow-up.

This chapter covers colorectal cancer, and includes information on epidemiology, risk factors (chronic inflammation/inflammatory bowel disease, radiation, diet and lifestyle, post cholecystectomy, diabetes, obesity and insulin resistance, cigarette smoking, alcohol, ureterocolic anastamosis, and genetic risk factors, screening, and chemoprevention (aspirin, and NSAIDS), the molecular biology and pathology of colorectal cancer, colorectal carcinoma (location, pathologic prognostic markers, and predictive markers), surgical management (colonic cancer and inflammatory bowel disease, hereditary non-polyposis colonic cancer or HNPCC, presenting as an emergency, treatment of polyp or early cancers, liver and lung metastasis, peritoneal disease, results of surgery and treatment for colon cancer, medical management of early stage disease, adjuvant chemotherapy for stage III disease (T1-4, N1-2M0), adjuvant therapy of patients with resected stage II colon cancer, radiotherapy, multidisciplinary care and special groups, the role of allied teams, and surveillance and follow-up.

Obesity has been associated with the development of important degenerative diseases such as hypertension, metabolic syndrome, diabetes mellitus (DM), cardiovascular disease (CVD), cancer, among others. And is also described that the disease severity of infections illnesses such as coronavirus, influenza, parainfluenza, and rhinovirus in increased. Besides, in 2009 was recognized as a risk factor during the pandemic of influenza H1N1 Currently there are several studies which suggest that some adipocytokines as leptin, resistin, plasminogen activator inhibitor-1 (PAI-1), adiponectin, visfatina among others have mediators affects in cardiovascular system. Some authors had shown plasmatic levels of leptin seem to be one of the best biological markers of obesity, and hyperleptinemia is closely related with several metabolic risk factors on insulin resistance in DM Some studies reveals that visfatin have mimetic affects with insulin in muscle stimulation and in glucose transport in adipocyte, also inhibit glucose production in liver. The objective of this work was to describe the association between leptin and visfatina in the development of obesity in a young population to identify the possible risk factor or as a protective factor of this adipocytokines with obesity. Methodology. Cross-sectional study. The present study was carried out in the facilities of the Centro Universitario de Ciencias Exactas e Ingenierías of the Universidad de Guadalajara. We recruit 171 young students (57.6 % female, 42.4% male) with the following characteristics: age between 18- 25 years old, fasting of 8 to 10 hours to take the blood sample. The results shows that BMI is higher in male and triglycerides also. On the other hand, leptin levels and total cholesterol are higher in women. The group with hyperleptinemia has higher values of BMI, total cholesterol, triglycerides, LDL and visfatina comparing with the group with normal leptin levels. We observed that hyperleptinemia is a risk factor for the development of obesity with OR 5.86 (p=0.01), in the other hand, visfatina acts as a protector factor with OR 0.2901 (0.02). Conclusion. Therapeutic intervention in early stages previous the beginning of the metabolic complications could have a favorable cost-benefit. However, the incorporation of markers such as the size of the particle of LDL, insulin resistance index, adipocytokines pro inflammatory as leptin and visfatin could improve the current predictive capacity.

Obesity is becoming a major problem all over the world, and it is severely affecting the United Arab Emirates (UAE). This inspired us to create a mathematical model that allows predicting the weight, as a function of time, based on two factors: diet and exercise. An early model dealing with diet only was used as a starting point, and then the exercise component was added based on an experiment we have performed where a group of students, wearing pedometers, have walked on a treadmill for thirty minutes in an average temperature between 20 to 25 degrees Celsius, with fixed speed. Data was collected and used to calculate the relation between weight and the energy burned, then Mathematica® was used to find how many days a person needs in order to reach his ideal weight calculated based on the Body Mass Index (BMI). Finally, we analyze the model, show that it is realistic with identified limitations, and we present future perspectives.

Introduction: Advancements and increase in access to healthcare have increased the life expectancy in India from 32 years in 1947 to almost 70 years currently. Due to robust vaccination and basic health programs, most of the communicable diseases are kept under control. The disease burden is now skewed towards non-communicable diseases. It is an established fact that body mass index (BMI) is a reliable predictor of cardiovascular disease (CVD) later in life. Early prediction can decrease the disease load and enable early preventative measures. A more novel approach of connecting it with blood groups would yield profound results in predictability and subsequent management. This study was done to see correlation between BMI and known blood groups in order to predict the potential incidence of CVDs in medical students. Material and Method - A cross-sectional descriptive study was conducted in Bhaskar Medical College from September 2022 - November 2022. The sample population included 150- 1st year medical students chosen by Randomized sampling method. BMI was calculated based as weight in kilograms divided by the square of the height in meters (kg/m2). Discussion - Many studies conducted on the association of Blood groups with BMI yielded mixed and inconclusive results. On analysis of the data obtained from this study, O- positive blood group showed the highest inclination towards obesity i.e. 30 of the total participants. A-positive and B- positive blood groups were shown to have a lesser association with obesity i.e. 11 participants of the 150. These results were in accordance with a study done among female students by Shireen Javad et.al, nding blood group O to be the most prone to obesity.8 Incompatible to our results, a study conducted by Samuel Smith Isaac Okai et.al. found no signicant association between blood groups and BMI.10 Another study conducted by Christina Ravillo et.al. found that blood group O had the highest and blood group AB with lowest prevalence of obesity9. These ndings were similar to the results obtained in our study. To study the correlation of BMI with ABO blood group and Cardiovascula AIMS and OBJECTIVES Aim: - r risk among medical students. 1. Calculate and segregate the participants according to BM Objectives: - I using the standard formula provided by the WHO. 1. Determine Blood group using antisera 2. Evaluation of Lipid prole in obese individuals