Calibrated Reliance on Large Language Models for Personalized Surgical Care: A Critical Narrative Review of Confidence, Clinical Reasoning and Decision Support
6 affiliations
- 1Department of General and Thoracic Surgery, SS. Annunziata University Hospital, 66100 Chieti, Italy
- 2Villa Serena Foundation for Research, 65013 Città Sant’Angelo, Italy
- 3Epidemiological Operations Affair, SS. Annunziata University Hospital, 66100 Chieti, Italy
- 4Department of Surgical Oncology, Basavatarakam Indo American Cancer Hospital and Research Institute, Hyderabad 500034, Telangana, India
- 5Department of General, Visceral and Thoracic Surgery, Sana Clinic Hof, 95028 Hof, Germany
- 6Department of Medicine, Academy of Applied Medical and Social Sciences-AMiSNS (Akademia Medycznych I Spolecznych Nauk Stosowanych), AMiSNS, 82-300 Elbląg, Poland
Abstract
Large language models can synthesize clinical records, identify phenotypic features and support patient-specific decisions, but fluent explanations may obscure uncertainty. Surgical practice provides a demanding setting in which to examine this problem because decisions combine heterogeneous evidence, procedural risk and individual preferences. This critical narrative review connects surgical self-assessment research with studies of clinician–LLM interaction, clinical summarization, uncertainty estimation and perioperative implementation. Targeted searches of PubMed records through Europe PMC were supplemented by retrieval of methodological and foundational sources. Selection was purposive, with attention to contradictory findings and the distinction between simulated performance and clinical benefit. Randomized studies using general clinical vignettes and simulated tasks show that LLM assistance does not uniformly improve physician reasoning; their applicability to surgical decisions remains indirect. Direct clinical studies extend from preoperative documentation and triage to shared decision-making and postoperative support, with mixed findings and limited evidence of sustained patient benefit. We distinguish clinician self-appraisal, LLM uncertainty, prognostic calibration, appropriate reliance and patient-specific decision quality, each requiring distinct evaluation criteria. For personalized surgical care, generated interpretations should preserve the provenance, timing and limitations of the underlying patient data and predictive models. We propose a workflow for examining discrepancies between clinician judgment and LLM output, together with an evaluation agenda centered on harmful decision changes, verification burden and patient-relevant outcomes. This framework requires prospective validation.
Related
- HistoMRIFuseNet: retrospective confidence-calibrated decision fusion of independent histopathology and DCE-MRI classifiers
- HybridSwingNet for explainable swing trading using multi-encoder deep learning and confidence-calibrated signal execution
- Personalized Management of Hydrosalpinx Before IVF: A Narrative Review of Reproductive Outcomes and Treatment Timing
- Personalized Revision Arthroplasty After Failed Medial Unicompartmental Knee Arthroplasty: A Contemporary Narrative Review
- Beyond the Implant: Towards a Predictive, Preventive, Personalized and Participatory Approach to Patient-Centered Implant Dentistry—A Narrative Review
BibTeX
@article{barone2026calibrated,
title = {{Calibrated Reliance on Large Language Models for Personalized Surgical Care: A Critical Narrative Review of Confidence, Clinical Reasoning and Decision Support}},
author = {Mirko Barone and Federico Selvaggi and Valeria Pasquale and Syed Nusrath and Yogesh Vashist and Luigi Marano},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15207802},
url = {https://www.mdpi.com/2077-0383/15/20/7802},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Calibrated Reliance on Large Language Models for Personalized Surgical Care: A Critical Narrative Review of Confidence, Clinical Reasoning and Decision Support
AU - Mirko Barone
AU - Federico Selvaggi
AU - Valeria Pasquale
AU - Syed Nusrath
AU - Yogesh Vashist
AU - Luigi Marano
PY - 2026
DA - 2026/10/01
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15207802
UR - https://www.mdpi.com/2077-0383/15/20/7802
AB - Large language models can synthesize clinical records, identify phenotypic features and support patient-specific decisions, but fluent explanations may obscure uncertainty. Surgical practice provides a demanding setting in which to examine this problem because decisions combine heterogeneous evidence, procedural risk and individual preferences. This critical narrative review connects surgical self-assessment research with studies of clinician–LLM interaction, clinical summarization, uncertainty estimation and perioperative implementation. Targeted searches of PubMed records through Europe PMC were supplemented by retrieval of methodological and foundational sources. Selection was purposive, with attention to contradictory findings and the distinction between simulated performance and clinical benefit. Randomized studies using general clinical vignettes and simulated tasks show that LLM assistance does not uniformly improve physician reasoning; their applicability to surgical decisions remains indirect. Direct clinical studies extend from preoperative documentation and triage to shared decision-making and postoperative support, with mixed findings and limited evidence of sustained patient benefit. We distinguish clinician self-appraisal, LLM uncertainty, prognostic calibration, appropriate reliance and patient-specific decision quality, each requiring distinct evaluation criteria. For personalized surgical care, generated interpretations should preserve the provenance, timing and limitations of the underlying patient data and predictive models. We propose a workflow for examining discrepancies between clinician judgment and LLM output, together with an evaluation agenda centered on harmful decision changes, verification burden and patient-relevant outcomes. This framework requires prospective validation.
SN - 2077-0383
ER -