Governing Decisions of Probability Cutoffs in Clinical AI Deployment: A Case Study of Asthma Exacerbation Prediction
Zheng, L.; Agnikula Kshatriya, B. S.; Ohde, J.; Rost, L.; Malik, M.; Peterson, K.; Brereton, T.; Loufek, B.; Pereira, T.; Gai, C.; Park, M.; Hartz, M.; Fladager-Muth, J.; Wi, C.-I.; Tao, C. J.; Garovic, V.; Juhn, Y. J.; Overgaard, S. M.
Show abstract
Models that estimate the probability of an adverse clinical outcome require an operational cutoff to translate continuous estimated probabilities into discrete labels that can trigger clinical action. Although statistical methods identify optimal cut-offs, threshold selection ultimately reflects value judgments regarding harm tolerance, resource allocation, and workflow feasibility. We describe a governance-informed approach to selecting a deployment threshold for an asthma exacerbation (AE) prediction model integrated into clinical workflows. Using prevalence-adjusted performance metrics and real-world provider capacity modeling, we evaluated multiple candidate thresholds and quantified downstream workload and missed-event trade-offs. We demonstrate that statistically optimal thresholds may produce operationally infeasible alert volumes or unacceptable miss rates. We propose a structured threshold governance framework integrating statistical performance, clinical utility, stakeholder input, and human oversight safeguards. This case illustrates how threshold decisions should be treated as organizational governance processes rather than purely technical optimizations.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development and preliminary testing of Health Equity Across the AI Lifecycle (HEAAL): A framework for healthcare delivery organizations to mitigate the risk of AI solutions worsening health inequities 91%
- Predictability and Stability Testing to Assess Clinical Decision Instrument Performance for Children After Blunt Torso Trauma 90%
- External validation of a paediatric SMART triage model for use in resource limited facilities 90%
Similar papers in this journal
- Development and Validation of Phenotype Classifiers across Multiple Sites in the Observational Health Sciences and Informatics (OHDSI) Network 90%
- Measuring Quality-of-Care in Treatment of Children with Attention-Deficit/Hyperactivity Disorder: A Novel Application of Natural Language Processing 90%
- Empowering Personalized Pharmacogenomics with Generative AI Solutions 90%
Similar papers in this journal
- Mind the gap: Mapping Variation between National and Local Clinical Practice Guidelines for Acute Paediatric Asthma from the United Kingdom and the Netherlands 93%
- Identifying clinical skill gaps of healthcare workers using a digital clinical decision support algorithm during outpatient pediatric consultations in primary health centers in Rwanda 92%
- Essential Indicators of Quality in Primary Care Settings: An Evidence-Based, Structured, Expert Approach 91%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.