Literatura académica sobre el tema "Predictive HCI models"

Purpose – The purpose of this paper is to proposes a forward search algorithm for detecting and identifying natural structures arising in human-computer interaction (HCI) and human physiological response (HPR) data. Design/methodology/approach – The paper portrays aspects that are essential to modelling and precision in detection. The methods involves developed algorithm for detecting outliers in data to recognise natural patterns in incessant data such as HCI-HPR data. The detected categorical data are simultaneously labelled based on the data reliance on parametric rules to predictive models used in classification algorithms. Data were also simulated based on multivariate normal distribution method and used to compare and validate the original data. Findings – Results shows that the forward search method provides robust features that are capable of repelling over-fitting in physiological and eye movement data. Research limitations/implications – One of the limitations of the robust forward search algorithm is that when the number of digits for residuals value is more than the expected size for stack flow, it normally yields an error caution; to counter this, the data sets are normally standardized by taking the logarithmic function of the model before running the algorithm. Practical implications – The authors conducted some of the experiments at individual residence which may affect environmental constraints. Originality/value – The novel approach to this method is the detection of outliers for data sets based on the Mahalanobis distances on HCI and HPR. And can also involve a large size of data with p possible parameters. The improvement made to the algorithm is application of more graphical display and rendering of the residual plot.

371 Background: To validate the independent predictive value of Ki-67 in patients with high-grade upper tract urothelial carcinoma (UTUC). Methods: 475 patients from the international UTUC collaboration who underwent extirpative surgery for high-grade UTUC were included in this study. Immunohistochemical staining for Ki-67 was performed on tissue microarray (TMA) formed from this patient cohort. Ki-67 expression was assessed in a semi-quantitative fashion and considered overexpressed at a cut-off of 20%. Multivariate analyses (MVA) were performed to assess independent predictors of oncological outcomes and Harrell’s C indices (HCI) were calculated for predictive models. Results: Median age of the cohort was 69.7 years and 55.2% of patients were male. Ki-67 was overexpressed in 25.9% of patients. Ki-67 overexpression was significantly associated with ureteral tumor location, higher pT-stage, lymphovascular invasion, sessile tumor architecture, tumor necrosis, concomitant carcinoma in situ (CIS), and regional lymph node metastases. In Kaplan-Meier analyses, overexpressed Ki-67 was associated with worse recurrence-free (RFS) (HR 12.6, p<0.001) and cancer-specific survival (CSS) (HR 15.8, p<0.001). In MVA, Ki-67 was an independent predictor of RFS (HR 1.6, 95% CI 1.07-2.30, p=0.021) and CSS (HR 1.9, 95% CI 1.29-2.90, p=0.001). Ki-67 improved HCI from 0.66 to 0.70 (p<0.0001) for both RFS and CSS in our preoperative model, and from 0.81 to 0.82 (p=0.0018) for RFS and 0.81 to 0.83 (p=0.005) for CSS in our post-operative model. Conclusions: Ki-67 was validated as an independent prognostic predictor of RFS and CSS in patients treated with extirpative surgery for high-grade UTUC in a large, multi-institutional cohort.

Training data for user behavior models that predict subjective dimensions of visual perception are often too scarce for deep learning methods to be applicable. With the typical datasets in HCI limited to thousands or even hundreds of records, feature-based approaches are still widely used in visual analysis of graphical user interfaces (UIs). In our paper, we benchmarked the predictive accuracy of the two types of neural network (NN) models, and explored the effects of the number of features, and the dataset volume. To this end, we used two datasets that comprised over 4000 webpage screenshots, assessed by 233 subjects per the subjective dimensions of Complexity, Aesthetics and Orderliness. With the experimental data, we constructed and trained 1908 models. The feature-based NNs demonstrated 16.2%-better mean squared error (MSE) than the convolutional NNs (a modified GoogLeNet architecture); however, the CNNs’ accuracy improved with the larger dataset volume, whereas the ANNs’ did not: therefore, provided that the effect of more data on the models’ error improvement is linear, the CNNs should become superior at dataset sizes over 3000 UIs. Unexpectedly, adding more features to the NN models caused the MSE to somehow increase by 1.23%: although the difference was not significant, this confirmed the importance of careful feature engineering.

This study aimed to evaluate the predictive performance of pre-existing well-validated hepatocellular carcinoma (HCC) prediction models, established in patients with HBV-related cirrhosis who started potent antiviral therapy (AVT). We retrospectively reviewed the cases of 1339 treatment-naïve patients with HBV-related cirrhosis who started AVT (median period, 56.8 months). The scores of the pre-existing HCC risk prediction models were calculated at the time of AVT initiation. HCC developed in 211 patients (15.1%), and the cumulative probability of HCC development at 5 years was 14.6%. Multivariate Cox regression analysis revealed that older age (adjusted hazard ratio [aHR], 1.023), lower platelet count (aHR, 0.997), lower serum albumin level (aHR, 0.578), and greater LS value (aHR, 1.012) were associated with HCC development. Harrell’s c-indices of the PAGE-B, modified PAGE-B, modified REACH-B, CAMD, aMAP, HCC-RESCUE, AASL-HCC, Toronto HCC Risk Index, PLAN-B, APA-B, CAGE-B, and SAGE-B models were suboptimal in patients with HBV-related cirrhosis, ranging from 0.565 to 0.667. Nevertheless, almost all patients were well stratified into low-, intermediate-, or high-risk groups according to each model (all log-rank p < 0.05), except for HCC-RESCUE (p = 0.080). Since all low-risk patients had cirrhosis at baseline, they had unneglectable cumulative incidence of HCC development (5-year incidence, 4.9–7.5%). Pre-existing risk prediction models for patients with chronic hepatitis B showed suboptimal predictive performances for the assessment of HCC development in patients with HBV-related cirrhosis.