Het doel van dit onderzoek is te onderzoeken onder welke omstandigheden en onder welke condities relatief moderne modelleringstechnieken zoals support vector machines, neural networks en random forests voordelen zouden kunnen hebben in medisch-wetenschappelijk onderzoek en in de medische praktijk in vergelijking met meer traditionele modelleringstechnieken, zoals lineaire regressie, logistische regressie en Cox regressie.
MULTIFILE
Routine immunization (RI) of children is the most effective and timely public health intervention for decreasing child mortality rates around the globe. Pakistan being a low-and-middle-income-country (LMIC) has one of the highest child mortality rates in the world occurring mainly due to vaccine-preventable diseases (VPDs). For improving RI coverage, a critical need is to establish potential RI defaulters at an early stage, so that appropriate interventions can be targeted towards such population who are identified to be at risk of missing on their scheduled vaccine uptakes. In this paper, a machine learning (ML) based predictive model has been proposed to predict defaulting and non-defaulting children on upcoming immunization visits and examine the effect of its underlying contributing factors. The predictive model uses data obtained from Paigham-e-Sehat study having immunization records of 3,113 children. The design of predictive model is based on obtaining optimal results across accuracy, specificity, and sensitivity, to ensure model outcomes remain practically relevant to the problem addressed. Further optimization of predictive model is obtained through selection of significant features and removing data bias. Nine machine learning algorithms were applied for prediction of defaulting children for the next immunization visit. The results showed that the random forest model achieves the optimal accuracy of 81.9% with 83.6% sensitivity and 80.3% specificity. The main determinants of vaccination coverage were found to be vaccine coverage at birth, parental education, and socio-economic conditions of the defaulting group. This information can assist relevant policy makers to take proactive and effective measures for developing evidence based targeted and timely interventions for defaulting children.
MULTIFILE
INTRODUCTION: Innovations in head and neck cancer (HNC) treatment are often subject to economic evaluation prior to their reimbursement and subsequent access for patients. Mapping functions facilitate economic evaluation of new treatments when the required utility data is absent, but quality of life data is available. The objective of this study is to develop a mapping function translating the EORTC QLQ-C30 to EQ-5D-derived utilities for HNC through regression modeling, and to explore the added value of disease-specific EORTC QLQ-H&N35 scales to the model.METHODS: Data was obtained on patients with primary HNC treated with curative intent derived from two hospitals. Model development was conducted in two phases: 1. Predictor selection based on theory- and data-driven methods, resulting in three sets of potential predictors from the quality of life questionnaires; 2. Selection of the best out of four methods: ordinary-least squares, mixed-effects linear, Cox and beta regression, using the first set of predictors from EORTC QLQ-C30 scales with most correspondence to EQ-5D dimensions. Using a stepwise approach, we assessed added values of predictors in the other two sets. Model fit was assessed using Akaike and Bayesian Information Criterion (AIC and BIC) and model performance was evaluated by MAE, RMSE and limits of agreement (LOA).RESULTS: The beta regression model showed best model fit, with global health status, physical-, role- and emotional functioning and pain scales as predictors. Adding HNC-specific scales did not improve the model. Model performance was reasonable; R2 = 0.39, MAE = 0.0949, RMSE = 0.1209, 95% LOA of -0.243 to 0.231 (bias -0.01), with an error correlation of 0.32. The estimated shrinkage factor was 0.90.CONCLUSIONS: Selected scales from the EORTC QLQ-C30 can be used to estimate utilities for HNC using beta regression. Including EORTC QLQ-H&N35 scales does not improve the mapping function. The mapping model may serve as a tool to enable cost-effectiveness analyses of innovative HNC treatments, for example for reimbursement issues. Further research should assess the robustness and generalizability of the function by validating the model in an external cohort of HNC patients.
DOCUMENT
