A Technical Performance Study and Proposed Systematic and Comprehensive Evaluation of an ML-based CDS Solution for Pediatric Asthma.

Achieving optimal care for pediatric asthma patients depends on giving clinicians efficient access to pertinent patient information. Unfortunately, adherence to guidelines or best practices has shown to be challenging, as relevant information is often scattered throughout the patient record in both structured data and unstructured clinical notes. Furthermore, in the absence of supporting tools, the onus of consolidating this information generally falls upon the clinician. In this study, we propose a machine learning-based clinical decision support (CDS) system focused on pediatric asthma care to alleviate some of this burden. This framework aims to incorporate a machine learning model capable of predicting asthma exacerbation risk into the clinical workflow, emphasizing contextual data, supporting information, and model transparency and explainability. We show that this asthma exacerbation model is capable of predicting exacerbation with an 0.8 AUC-ROC. This model, paired with a comprehensive informatics-based process centered on clinical usability, emphasizes our focus on meeting the needs of the clinical practice with machine learning technology.

HOUSES Index as an Innovative Socioeconomic Measure Predicts Graft Failure Among Kidney Transplant Recipients.

BACKGROUND: Despite extensive evaluation processes to determine candidacy for kidney transplantation, variability in graft failure exists. The role of patient socioeconomic status (SES) in transplantation outcomes is poorly understood because of limitations of conventional SES measures. METHODS: This population-based retrospective cohort study assessed whether a validated objective and individual-level housing-based SES index (HOUSES) would serve as a predictive tool for graft failure in patients (n = 181) who received a kidney transplant in Olmsted County, MN (January 1, 1998 to December 8, 2016). Associations were assessed between HOUSES (quartiles: Q1 [lowest] to Q4 [highest]) and graft failure until last follow-up date (December 31, 2016) using Cox proportional hazards. The mean age (SD) was 46.1 (17.2) years, 109 (60.2%) were male, 113 (62.4%) received a living kidney donor transplant, and 40 (22.1%) had a graft failure event. RESULTS: Compared with Q1, patients with higher HOUSES (Q2-Q4) had significantly lower graft failure rates (adjusted hazard ratio, 0.47; 95% confidence interval, 0.24-0.92; P < 0.029), controlling for age, sex, race, previous kidney transplantation, and donor type. CONCLUSIONS: Although criteria for kidney transplant recipients are selective, patients with higher HOUSES had lower graft failure rates. Thus, HOUSES may enable transplantation programs to identify a target group for improving kidney transplantation outcomes.