EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

Clinical utility of large language models in metastatic prostate cancer: A multicenter expert validation for decision support

Yinsong Chen, Kangwen He, Weinuo Qu, Luping Ma, Xing Su, Xinqi Liu, Zhen Kang, Feng Li, Junrong Yan, Zhibo Wang, Jing Li, Zhen Li

European Journal of Cancer · 2026-05 · 238 · 116667

DOI: 10.1016/j.ejca.2026.116667 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift European Journal of Cancer, 2026-05. Verfasst von Yinsong Chen und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Large Language Models, Decision Support Systems, Clinical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Huazhong University of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Initial systemic treatment planning for metastatic prostate cancer (mPCa) requires rapid synthesis of heterogeneous clinical and biomarker information. Large language models (LLMs) could assist clinicians, but their safety and acceptability in this high-stakes setting remain uncertain. METHODS: We conducted a multicenter retrospective evaluation of 238 consecutive mPCa cases from three tertiary centers (2018-2025). Five contemporary LLMs were tested via publicly available web interfaces under a locked, zero-shot prompting protocol to generate a clinical summary, a first-line systemic treatment recommendation, and a rationale. Outputs underwent two-stage assessment: (1) multidisciplinary team (MDT) binary safety adjudication using a one-strike gate with a prespecified taxonomy of critical errors; unsafe outputs were assigned a Likert score of 1 for all domains; (2) three senior medical oncologists independently rated safety-passed outputs on 5-point Likert scales for summary accuracy, guideline-concordant and patient-tailored recommendations, and rationale quality. Paired ordinal outcomes were analyzed with Friedman tests and Holm-adjusted post hoc comparisons, and binary safety outcomes with Cochran's Q and McNemar tests. RESULTS: Safety rates ranged from 79.0% to 84.9%. Among safety-passed outputs, mean utility scores (5-point Likert) were in the low-to-mid 4 range. Between-model differences were most apparent for summarization, whereas treatment recommendations and rationales showed modest separation after multiplicity adjustment. Failures clustered in hard cases with incomplete documentation and were dominated by missingness-related extraction errors, disease-state/pathway errors, guideline logic deviations, and safety-check omissions. CONCLUSIONS: Current LLMs can support mPCa care as drafting assistants, but ∼15%-21% of outputs breached safety thresholds under a strict gate, precluding unsupervised use at initial treatment-planning encounters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsLarge Language ModelsDecision Support Systems, ClinicalHumansMaleRetrospective StudiesNeoplasm MetastasisClinical Decision-MakingAged

Stichwörter der Autor:innen

clinical decision supportexpert validationguideline concordancelarge language modelsmetastatic prostate cancerreal-world evaluationsafety gating

Autor:innen und Institutionen

  • Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • Department of Urologic Oncology, First Affiliated Hospital, School of Medicine, Shihezi University, Shihezi, Xinjiang, China.
  • Department of Oncology, The Friendship Hospital of Ili Kazak Autonomous Prefecture, Ili Kazak Autonomous Prefecture, Xinjiang, China.
  • Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China.
  • Department of Radiology, Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang, Hubei, China.
  • Department of Radiology, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Third Hospital of Shanxi Medical University, Tongji Shanxi Hospital, Taiyuan, Shanxi, China.

Förderung

  • Huazhong University of Science and Technology

Zitieren

APA

Chen, Y., He, K., Qu, W., Ma, L., Su, X., Liu, X., Kang, Z., Li, F., Yan, J., Wang, Z., Li, J., & Li, Z. (2026). Clinical utility of large language models in metastatic prostate cancer: A multicenter expert validation for decision support. European Journal of Cancer, 238, 116667. https://doi.org/10.1016/j.ejca.2026.116667

Vancouver

Chen Y, He K, Qu W, Ma L, Su X, Liu X, et al. Clinical utility of large language models in metastatic prostate cancer: A multicenter expert validation for decision support. European Journal of Cancer. 2026;238:116667. doi:10.1016/j.ejca.2026.116667

BibTeX
@article{Chen2026,
  author = {Chen, Yinsong and He, Kangwen and Qu, Weinuo and Ma, Luping and Su, Xing and Liu, Xinqi and Kang, Zhen and Li, Feng and Yan, Junrong and Wang, Zhibo and Li, Jing and Li, Zhen},
  title = {Clinical utility of large language models in metastatic prostate cancer: A multicenter expert validation for decision support},
  journal = {European Journal of Cancer},
  year = {2026},
  volume = {238},
  pages = {116667},
  doi = {10.1016/j.ejca.2026.116667}
}
Kostenlos starten →