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

Shauna M. Overgaard, Kevin J. Peterson, Chung Ii Wi, Bhavani Singh Agnikula Kshatriya, Joshua W. Ohde, Tracey Brereton, Lu Zheng, Lauren Rost, Janet Zink, Amin Nikakhtar, Tara Pereira, Sunghwan Sohn, Lynnea Myers, Young J. Juhn

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
Pages (from-to)25-35
Number of pages11
JournalAMIA ... Annual Symposium proceedings. AMIA Symposium
Volume2022
StatePublished - 2022

ASJC Scopus subject areas

  • Medicine(all)

Fingerprint

Dive into the research topics of 'A Technical Performance Study and Proposed Systematic and Comprehensive Evaluation of an ML-based CDS Solution for Pediatric Asthma'. Together they form a unique fingerprint.

Cite this