The objective of this study was to build and assess the performance of survival prediction models using the gender-specific informative risk factors for patients with left ventricular systolic dysfunction. A lasso approach was used to decide the informative predictors for building semi-parametric proportional hazards Cox model. Separate models were built for all patients [N = 299], male patients [N_male = 194 (64.88%)], and female patients [N_female = 105 (35.12%)], to observe the risk factors associated with the individual’s risk of death. The likelihood- ratio test was used to test the goodness of fit of the selected model, and the C-index was used to assess the predictive performance of the selected model(s) with respect to the overall model with all observed risk factors. The survival prediction model for females is notably different from that for males. For males, smoking, diabetes, and anaemia, whereas for females, ejection fraction, sodium, and platelets count are non-informative with zero regression coefficients. The goodness of fit of the selected models with respect to the general model with all observed risk factors is tested using the likelihood-ratio test. The results are in favor of the selected models with p-values 0.51,0.61, and 0.70 for all patients, male patients, and female patients, respectively. The same values of C-index for the full model and the selected models for overall data, for males, and for females (0.72, 0.73, and 0.77 for overall data, male data, and female data, respectively) indicate that the selected models are as good as the corresponding overall models regarding their predictive performance. There is a substantial difference in the survival prediction models for heart failure (HF) of male and female patients in this study. More studies are needed in Pakistan for confirming this striking male-female difference regarding the potential risk factors to predict survival with heart failure.

High dimensional data like gene expression and RNA-sequences often contain missing values. The subsequent analysis and results based on these incomplete data can suffer strongly from the presence of these missing values. Several approaches to imputation of missing values in gene expression data have been developed but the task is difficult due to the high dimensionality (number of genes) of the data. Here an imputation procedure is proposed that uses weighted nearest neighbors. Instead of using nearest neighbors defined by a distance that includes all genes the distance is computed for genes that are apt to contribute to the accuracy of imputed values. The method aims at avoiding the curse of dimensionality, which typically occurs if local methods as nearest neighbors are applied in high dimensional settings. The proposed weighted nearest neighbors algorithm is compared to existing missing value imputation techniques like mean imputation, KNNimpute and the recently proposed imputation by random forests. We use RNA-sequence and microarray data from studies on human cancer to compare the performance of the methods. The results from simulations as well as real studies show that the weighted distance procedure can successfully handle missing values for high dimensional data structures where the number of predictors is larger than the number of samples. The method typically outperforms the considered competitors.

Breast cancer is one of the most commonly diagnosed female disorders globally. Numerous studies have been conducted to predict survival markers, although the majority of these analyses were conducted using simple statistical techniques. In lieu of that, this research employed machine learning approaches to develop models for identifying and visualizing relevant prognostic indications of breast cancer survival rates. A comprehensive hospital-based breast cancer dataset was collected from the National Cancer Institute’s SEER Program’s November 2017 update, which offers population-based cancer statistics. The dataset included female patients diagnosed between 2006 and 2010 with infiltrating duct and lobular carcinoma breast cancer (SEER primary cites recode NOS histology codes 8522/3). The dataset included nine predictor factors and one predictor variable that were linked to the patients’ survival status (alive or dead). To identify important prognostic markers associated with breast cancer survival rates, prediction models were constructed using -nearest neighbor (K-NN), decision tree (DT), gradient boosting (GB), random forest (RF), AdaBoost, logistic regression (LR), voting classifier, and support vector machine (SVM). All methods yielded close results in terms of model accuracy and calibration measures, with the lowest achieved from logistic regression ( ) and the greatest acquired from the random forest ( ). Notably, the multiple machine learning algorithms utilized in this research achieved high accuracy, suggesting that these approaches might be used as alternative prognostic tools in breast cancer survival studies, especially in the Asian area.

Immunization is a precautionary measure that helps to stop diseases before their occurrence. Vaccine-preventable diseases are a primary cause of death among children under the age of five in many developing nations. The purpose of this study is to investigate the immunization status and associated demographic characteristics among children aged 1223 months in Punjab, Pakistan. The study used the data from the Multiple Indicator Cluster Survey (MICS) for Punjab, Pakistan. Data were collected from caregivers using interviewer-administered questionnaires. To summarize the data, descriptive statistics are computed, and logistic regression is used to identify the significant factors that are responsible for complete immunization among the children in Punjab. Odds ratios, 95 CI, and Chi-square statistics were computed to identify the factors associated with no or partial immunization. The prevalence of complete immunization coverage was 89.1. Women in the rich wealth quantile had the highest odds of completing the immunization for their children (AOR=2.314; 95 CI: 1.6423.261) compared to those who are poor. Those in rural areas were more likely to fully vaccinate their children (AOR=1.54; 95 CI: 1.2321.925) compared to those in urban areas. Those in the highest level of the educational group (AOR=2.639; 95 CI: 1.8003.87) are more likely to complete vaccination for their children compared to those with no formal education. However, female children are less likely to complete immunization compared to male children (AOR=0.813; 95 CI: 0.6870.963). The immunization status of children shows a significant association with maternal education, wealth status, and area of residence.