OpenAlex · Aktualisierung stündlich · Letzte Aktualisierung: 19.05.2026, 17:55

Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.

Five essential features for adoption of clinical risk prediction tools: Insights from the VOCAL-Penn score

2025·0 Zitationen·Hepatology CommunicationsOpen Access
Volltext beim Verlag öffnen

0

Zitationen

3

Autoren

2025

Jahr

Abstract

BACKGROUND: Although medical risk prediction tools are widely developed, few achieve sustained clinical adoption. In cirrhosis patients, surgical risk calculators have achieved broad utilization. We sought to identify key design and implementation factors that influence provider uptake of such tools, using the VOCAL-Penn score (VPS) as a case example. METHODS: We conducted a qualitative study of 22 diverse clinicians who care for patients with cirrhosis. Semi-structured interviews were guided by the Consolidated Framework for Implementation Research to explore factors influencing the adoption of risk prediction tools. Interviews were transcribed and analyzed using a combined grounded theory and deductive approach. Emergent themes were synthesized into a conceptual framework. RESULTS: Five recurrent themes emerged as central: efficiency, accessibility, transparency, accuracy, and generalizability. Clinicians emphasized the need for tools that are intuitive, require minimal inputs, and integrate seamlessly into existing workflows. Ensuring input variables were clinically meaningful and readily available was cited as critical to encouraging use. Transparency in model development was essential to building trust. Participants stressed the importance of comparative performance data relative to existing clinical standards, as well as published external validations, to support the tool's credibility. Finally, generalizability was key to equitable application across diverse patient populations. CONCLUSIONS: Using the VPS as a grounding example, our findings identify 5 domains-efficiency, accessibility, transparency, accuracy, and generalizability-that inform the development and dissemination of future tools. By aligning tool design with real-world clinical needs, this framework may support broader adoption and more equitable implementation of medical risk prediction tools.

Ähnliche Arbeiten

Autoren

Institutionen

Themen

Machine Learning in HealthcareArtificial Intelligence in Healthcare and EducationElectronic Health Records Systems
Volltext beim Verlag öffnen