EUVIMEDEUVIMED entdecken
Open Access

Challenges in the Postmarket Surveillance of Clinical Prediction Models

Sardar Ansari iD, Brittany Baur iD, Karandeep Singh iD, Andrew J Admon iD

NEJM AI · 24.04.2025 · 2 (5)

DOI: 10.1056/aip2401116 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NEJM AI, erschienen am 24.04.2025. Verfasst von Sardar Ansari und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, University of Michigan, Ann Arbor, MI. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 7 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive artificial intelligence (AI) models enhance clinical workflows with applications such as prognostication and decision support, yet suffer from postdeployment performance challenges due to dataset shifts. Regulatory guidelines emphasize the need for continuous monitoring, but actionable strategies are lacking. A significant issue is postdeployment assessment of predictive AI models due to confounding medical interventions where effective interventions modify outcomes, introducing bias into performance assessment. This can falsely suggest model decay, leading to unwarranted updates or decommissioning, harming clinical outcomes. Proposed solutions include withholding model outputs, monitoring outcomes as surrogates, or including clinician interventions in models, each with ethical or practical limitations. The lack of effective solutions for this problem can lead to an abundance of models that cannot be later evaluated, tuned, or withdrawn if they become ineffective, leading to patient harm. Advanced causal modeling to assess counterfactual outcomes may offer a reliable validation method. Until effective methods for postdeployment monitoring of predictive models are developed and validated, decisions on model updates should consider the causal pathways and be evidence based, ensuring the sustained utility of AI models in dynamic clinical environments.

Autor:innen und Institutionen

  • Department of Emergency Medicine, University of Michigan, Ann Arbor, MI.
  • Department of Medicine, University of California San Diego, San Diego, CA.
  • Department of Internal Medicine, University of Michigan, Ann Arbor, MI.
  • Department of Epidemiology, University of Michigan, Ann Arbor, MI.
  • VA Center for Clinical Management Research, VA Ann Arbor Healthcare System, Ann Arbor, MI.

ORCID-Profile: Sardar Ansari, Brittany Baur, Karandeep Singh, Andrew J Admon

Förderung

  • NHLBI NIH HHS

Zitieren

APA

Ansari, S., Baur, B., Singh, K., & Admon, A. J. (2025). Challenges in the Postmarket Surveillance of Clinical Prediction Models. NEJM AI, 2(5). https://doi.org/10.1056/aip2401116

Vancouver

Ansari S, Baur B, Singh K, Admon AJ. Challenges in the Postmarket Surveillance of Clinical Prediction Models. NEJM AI. 2025;2(5). doi:10.1056/aip2401116

BibTeX
@article{Ansari2025,
  author = {Ansari, Sardar and Baur, Brittany and Singh, Karandeep and Admon, Andrew J},
  title = {Challenges in the Postmarket Surveillance of Clinical Prediction Models},
  journal = {NEJM AI},
  year = {2025},
  volume = {2},
  number = {5},
  doi = {10.1056/aip2401116}
}
Kostenlos starten →