eXplainable Artificial Intelligence (XAI) aims to provide intelligible explanations to users. XAI algorithms such as SHAP, LIME and Scoped Rules compute feature importance for machine learning predictions. Although XAI has attracted much research attention, applying XAI techniques in healthcare to inform clinical decision making is challenging. In this paper, we provide a comparison of explanations given by XAI methods as a tertiary extension in analysing complex Electronic Health Records (EHRs). With a large-scale EHR dataset, we compare features of EHRs in terms of their prediction importance estimated by XAI models. Our experimental results show that the studied XAI methods circumstantially generate different top features; their aberrations in shared feature importance merit further exploration from domain-experts to evaluate human trust towards XAI.

The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed.

No abstract

Background Polypharmacy presents a serious and significant public health challenge as average lifespans increase. The objective of this study was to identify patterns of polypharmacy before dementia diagnosis, their prevalence, and possible complications.Methods We used electronic health records in the Welsh general practitioners' database from 1990 to 2015, via the Secure Anonymised Information Linkage Databank. Cohort selection, based on a previously validated phenotype, was done with the use of Read Codes to identify any dementia diagnosis within the dataset. No age restriction was applied, but complete data for each patient was required. Analysis was stratified by sex and age, but not dementia type. Medications were identified by Read Codes, and split into four 5-year sub-periods. Factor analysis was used for patients taking at least three medicines in each period.