Malaria is the world’s most prevalent vector-borne disease. Accurate prediction of malaria outbreaks may lead to public health interventions that mitigate disease morbidity and mortality.
Background: Mosaic somatic alterations are present in all multi-cellular organisms, but the physiological effects of low-level mosaicism are largely unknown. Most mosaic alterations remain undetectable with current analytical approaches, although the presence of such alterations is increasingly implicated as causative for disease. Results: Here, we present the Parent-of-Origin-based Detection (POD) method for chromosomal abnormality detection in trio-based SNP microarray data. Our software implementation, triPOD, was benchmarked using a simulated dataset, outperformed comparable software for sensitivity of abnormality detection, and displayed substantial improvement in the detection of low-level mosaicism while maintaining comparable specificity. Examples of low-level mosaic abnormalities from a large autism dataset demonstrate the benefits of the increased sensitivity provided by triPOD. The triPOD analyses showed robustness across multiple types of Illumina microarray chips. Two large, clinically-relevant datasets were characterized and compared. Conclusions: Our method and software provide a significant advancement in the ability to detect low-level mosaic abnormalities, thereby opening new avenues for research into the implications of mosaicism in pathogenic and non-pathogenic processes.
This paper introduces a novel approach to explainable artificial intelligence (XAI) that enhances interpretability by combining local insights from Shapley additive explanations (SHAP)—a widely adopted XAI tool—with global explanations expressed as fuzzy association rules. By employing fuzzy association rules, our method enables AI systems to generate explanations that closely resemble human reasoning, delivering intuitive and comprehensible insights into system behavior. We present the FuzRED methodology and evaluate its performance on models trained across three diverse datasets: two classification tasks (spam identification and phishing link detection), and one reinforcement learning task involving robot navigation. Compared to the Anchors method FuzRED offers at least one order of magnitude faster execution time (minutes vs. hours) while producing easily interpretable rules that enhance human understanding of AI decision making.
19 October 2016 in BMC Medical Informatics and Decision Making
Prediction of influenza weeks in advance can be a useful tool in the management of cases and in the early recognition of pandemic influenza seasons. This study explores the prediction of influenza-like-illness incidence using both epidemiological and climate data. It uses Lorenz’s well-known Method of Analogues, but with two novel improvements. Firstly, it determines internal parameters using the implicit near-neighbor distances in the data, and secondly, it employs climate data (mean dew point) to screen analogue near-neighbors and capture the hidden dynamics of disease spread. These improvements result in the ability to forecast, four weeks in advance, the total number of cases and the incidence at the peak with increased accuracy. In most locations the total number of cases per year and the incidence at the peak are forecast with less than 15 % root-mean-square (RMS) Error, and in some locations with less than 10 % RMS Error. The use of additional variables that contribute to the dynamics of influenza spread can greatly improve prediction accuracy.