EUVIMEDEUVIMED entdecken
Crossref

The interaction of structured data using openEHR and large Language models for clinical decision support in prostate cancer

Philippe Kaiser, Shan Yang, Michael Bach, Christian Breit, Kirsten Mertz, Bram Stieltjes, Jan Ebbing, Christian Wetterauer, Maurice Henkel

World Journal of Urology · 13.01.2025 · 43 (1)

DOI: 10.1007/s00345-024-05423-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift World Journal of Urology, online erschienen am 13.01.2025. Verfasst von Philippe Kaiser und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, Basel, 4031, Switzerland. Philippejulien.kaiser@usb.ch. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Decision Support Systems, Clinical, Clinical Decision-Making. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 23 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Multidisciplinary teams (MDTs) are essential for cancer care but are resource-intensive. Decision-making processes within MDTs, while critical, contribute to increased healthcare costs due to the need for specialist time and coordination. The recent emergence of large language models (LLMs) offers the potential to improve the efficiency and accuracy of clinical decision-making processes, potentially reducing costs associated with traditional MDT models. METHODS: We conducted a retrospective study of 171 consecutively treated patients with newly diagnosed prostate cancer. Relevant structured clinical data and the European Association of Urology (EAU) pocket guidelines were provided to two LLMs (chatGPT-4, Claude-3-Opus). LLM treatment recommendations were compared to actual treatment recommendations of the MDT meeting (MDM). RESULTS: Both LLMs demonstrated an overall adherence of 93% with the MDT treatment recommendations. Discrepancies between LLM and MDT recommendations were observed in 15 cases (9%), primarily due to lack of clinical information that could be provided to the LLMs. In 5 cases (3%), the LLM recommendations were not in line with EAU guidelines despite having access to all relevant information. CONCLUSIONS: Our findings provide evidence that LLMs can provide accurate treatment recommendations for newly diagnosed prostate cancer patients. LLMs have the potential to streamline MDT workflows, enabling specialists to focus on complex cases and patient-centered discussions. In this study, we explored the potential of artificial intelligence models called large language models (LLMs) to assist in treatment decision-making for prostate cancer patients. We found that LLMs, when provided with patient information and clinical guidelines, can recommend treatments that closely match those made by a team of cancer specialists, suggesting that LLMs could help streamline the decision-making process and potentially reduce healthcare costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsDecision Support Systems, ClinicalClinical Decision-MakingHumansMaleRetrospective StudiesAgedMiddle AgedLarge Language Models

Stichwörter der Autor:innen

Artificial intelligenceDecision supportLarge language modelsProstate cancerTreatment recommendationsopenEHR

Autor:innen und Institutionen

  • Institute of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, Basel, 4031, Switzerland. Philippejulien.kaiser@usb.ch.
  • Institute of Radiology and Nuclear Medicine, University Hospital Basel, Petersgraben 4, Basel, 4031, Switzerland.
  • Institute of Medical Genetics and Pathology, Pathology, University Hospital Basel, Schönbeinstrasse 40, Basel, 4031, Switzerland.
  • Institute of Pathology, Cantonal Hospital Liestal, Mühlemattstrasse 11, Liestal, 4410, Switzerland.
  • Research & Analysis Services, University Hospital Basel, Steinengraben 36, Basel, 4051, Switzerland.
  • Clinic for Urology, University Hospital Basel, Spitalstrasse 21, Basel, 4031, Switzerland.

Zitieren

APA

Kaiser, P., Yang, S., Bach, M., Breit, C., Mertz, K., Stieltjes, B., Ebbing, J., Wetterauer, C., & Henkel, M. (2025). The interaction of structured data using openEHR and large Language models for clinical decision support in prostate cancer. World Journal of Urology, 43(1). https://doi.org/10.1007/s00345-024-05423-1

Vancouver

Kaiser P, Yang S, Bach M, Breit C, Mertz K, Stieltjes B, et al. The interaction of structured data using openEHR and large Language models for clinical decision support in prostate cancer. World Journal of Urology. 2025;43(1). doi:10.1007/s00345-024-05423-1

BibTeX
@article{Kaiser2025,
  author = {Kaiser, Philippe and Yang, Shan and Bach, Michael and Breit, Christian and Mertz, Kirsten and Stieltjes, Bram and Ebbing, Jan and Wetterauer, Christian and Henkel, Maurice},
  title = {The interaction of structured data using openEHR and large Language models for clinical decision support in prostate cancer},
  journal = {World Journal of Urology},
  year = {2025},
  volume = {43},
  number = {1},
  doi = {10.1007/s00345-024-05423-1}
}
Kostenlos starten →