ConfidentCare: A Clinical Decision Support System for Personalized Breast Cancer Screening

Abstract

Breast cancer screening policies attempt to achieve timely diagnosis by the regular screening of apparently healthy women. Various clinical decisions are needed to manage the screening process; those include: selecting the screening tests for a woman to take, interpreting the test outcomes, and deciding whether or not a woman should be referred to a diagnostic test. Such decisions are currently guided by clinical practice guidelines (CPGs), which represent a "one-size-fits-all" approach that are designed to work well on average for a population, without guaranteeing that it will work well uniformly over that population. Since the risks and benefits of screening are functions of each patients features, personalized screening policies that are tailored to the features of individuals are needed in order to ensure that the right tests are recommended to the right woman. In order to address this issue, we present ConfidentCare: a computer-aided clinical decision support system that learns a personalized screening policy from the electronic health record (EHR) data. ConfidentCare operates by recognizing clusters of "similar" patients, and learning the "best" screening policy to adopt for each cluster. A cluster of patients is a set of patients with similar features (e.g. age, breast density, family history, etc.), and the screening policy is a set of guidelines on what actions to recommend for a woman given her features and screening test scores. ConfidentCare utilizes an iterative algorithm that applies K-means clustering to the women's feature space, followed by learning an active classifier (decision tree) for every cluster. The algorithm ensures that the policy adopted for every cluster of patients satisfies a predefined accuracy requirement with a high level of confidence. We show that our algorithm outperforms the current CPGs in terms of cost-efficiency and false positive rates.

Using Sequential Decision Making to Improve Lung Cancer Screening Performance

“…We did not account for this imbalance during training other than performing a stratified five-fold cross-validation to obtain an unbiased estimate of the model. Similarly, other temporal studies have used a k-fold cross validation to assess model performance [32]- [36]. This data imbalance over time occurred as a result of simplifying our lung POMDP model to consider only cases reporting a single pulmonary nodule over the course of the trial.…”

A Survey on Nature-Inspired Medical Image Analysis: A Step Further in Biomedical Data Integration

“…The principal contribution of research in computer science to biomedical data integration concerns the proper fusion of diverse and heterogeneous datasets [18,19]-i.e., medical imaging modalities (possibly validating radiomics-based biomarkers against histopathology [20]), Electronic Health Record (EHR) engines [21], high-throughput technologies (i.e., multi-omics studies [22]), and real-time monitoring (exploiting m-health applications)-to provide a comprehensive clinical knowledge for precision medicine [9]. Fig.…”

A novel decision support system for the interpretation of remote sensing big data

“…Authors consider non-professional applications using images acquired with a conventional (consumer-type) digital camera. Alaa et al in [25] developed a clinical DSS that learns a personalized screening policy from electronic health record data. The presented system groups patients' features into clusters and provides screening policies for every cluster of patients.…”