paper-with-me

홈 › Papers

On the Limits of Selective AI Prediction: A Case Study in Clinical Decision Making

2025-08-11 · Sarah Jabbour, David Fouhey, Nikola Banovic, Stephanie D. Shepard, Ella Kazerooni, Michael W. Sjoding, Jenna Wiens arxiv

AI has the potential to augment human decision making. However, even high-performing models can produce inaccurate predictions when deployed. These inaccuracies, combined with automation bias, where humans overrely on AI predictions, can result in worse decisions. Selective prediction, in which potentially unreliable model predictions are hidden from users, has been proposed as a solution. This approach assumes that when AI abstains and informs the user so, humans make decisions as they would without AI involvement. To test this assumption, we study the effects of selective prediction on human decisions in a clinical context. We conducted a user study of 259 clinicians tasked with diagnosing and treating hospitalized patients. We compared their baseline performance without any AI involvement to their AI-assisted accuracy with and without selective prediction. Our findings indicate that selective prediction mitigates the negative effects of inaccurate AI in terms of decision accuracy. Compared to no AI assistance, clinician accuracy declined when shown inaccurate AI predictions (66% [95% CI: 56%-75%] vs. 56% [95% CI: 46%-66%]), but recovered under selective prediction (64% [95% CI: 54%-73%]). However, while selective prediction nearly maintains overall accuracy, our results suggest that it alters patterns of mistakes: when informed the AI abstains, clinicians underdiagnose (18% increase in missed diagnoses) and undertreat (35% increase in missed treatments) compared to no AI input at all. Our findings underscore the importance of empirically validating assumptions about how humans engage with AI within human-AI systems.

📄 PDF Abstract BibTeX arXiv:2508.07617

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Multi-pathology Chest X-ray Classification with Rejection Mechanisms

2025-09-12 · Yehudit Aperstein, Amit Tzahar, Alon Gottlib, Tal Verber 외 arxiv

Overconfidence in deep learning models poses a significant risk in high-stakes medical imaging tasks, particularly in multi-label classification of chest X-rays, where multiple co-occurring pathologies must be detected s…

Multi-Label Classification

An Empirical Analysis of Calibration and Selective Prediction in Multimodal Clinical Condition Classification

2026-03-03 · L. Julián Lechuga López, Farah E. Shamout, Tim G. J. Rudner arxiv

As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decision-making tasks. One proposed safeguard is selective prediction, where mo…

When BERT Fails -- The Limits of EHR Classification

2022-07-26 · Augusto Garcia-Agundez, Carsten Eickhoff

Transformers are powerful text representation learners, useful for all kinds of clinical decision support tasks. Although they outperform baselines on readmission prediction, they are not infallible. Here, we look into o…

ClassificationReadmission Prediction

Modeling methodology for the accurate and prompt prediction of symptomatic events in chronic diseases

2024-02-15 · Josué Pagán, José L. Risco-Martín, José M. Moya, José L. Ayala

Prediction of symptomatic crises in chronic diseases allows to take decisions before the symptoms occur, such as the intake of drugs to avoid the symptoms or the activation of medical alarms. The prediction horizon is in…

Model SelectionPrediction

SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification

2020-03-11 · CVPR 2020 6 · Sam Maksoud, Kun Zhao, Peter Hobson, Anthony Jennings 외

The difficulty of processing gigapixel whole slide images (WSIs) in clinical microscopy has been a long-standing barrier to implementing computer aided diagnostic systems. Since modern computing resources are unable to p…

DiagnosticGeneral Classificationimage-classificationImage Classification+1