Privacy-preserving large language models for structured medical information retrieval
npj Digital Medicine, vol. 7, pp. 257
Abstract
Most clinical information is encoded as free text, not accessible for quantitative analysis. This study presents an open-source pipeline using the local large language model (LLM) "Llama 2" to extract quantitative information from clinical text and evaluates its performance in identifying features of decompensated liver cirrhosis. The LLM identified five key clinical features in a zero- and one-shot manner from 500 patient medical histories in the MIMIC IV dataset. We compared LLMs of three sizes and various prompt engineering approaches, with predictions compared against ground truth from three blinded medical experts. Our pipeline achieved high accuracy, detecting liver cirrhosis with 100% sensitivity and 96% specificity. High sensitivities and specificities were also yielded for detecting ascites (95%, 95%), confusion (76%, 94%), abdominal pain (84%, 97%), and shortness of breath (87%, 97%) using the 70 billion parameter model, which outperformed smaller versions. Our study successfully demonstrates the capability of locally deployed LLMs to extract clinical information from free text with low hardware requirements.
Authors 12
-
Heidelberg University · University Hospital Carl Gustav Carus · Medizinische Fakultät Mannheim · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
Heidelberg University · University Hospital Heidelberg · National Center for Tumor Diseases · University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
Affiliation as printed
Department of Surgery I, University Hospital Würzburg, Würzburg, Germany
-
University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
-
German Cancer Research Center · University Hospital Bonn
Affiliation as printed
German Cancer Research Center, Division of Radiology, Heidelberg, Germany
University Hospital Bonn, Clinic for Neuroradiology, Bonn, Germany
-
TU Dortmund University · Essen University Hospital · Stiftung Universitätsmedizin Essen
Affiliation as printed
Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen (WTZ), 45122, Essen, Germany
Institut für KI in der Medizin (IKIM), Universitätsmedizin Essen, Girardetstr. 2, 45131, Essen, Germany
TU Dortmund University, Department of Physics, Otto-Hahn-Straße 4, 44227, Dortmund, Germany
-
German Cancer Research Center · Heidelberg University · European Molecular Biology Laboratory · University Medical Centre Mannheim · Medizinische Fakultät Mannheim
Affiliation as printed
DKFZ Hector Cancer Institute at the University Medical Center, Mannheim, Germany
Department of Medicine II, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
Molecular Medicine Partnership Unit, EMBL, Heidelberg, Germany
-
Affiliation as printed
Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany
-
Jakob Nikolas Kather corresponding
Heidelberg University · University Hospital Heidelberg · National Center for Tumor Diseases · University Hospital Carl Gustav Carus · Else Kröner Fresenius Center for Digital Health · Technische Universität Dresden
Affiliation as printed
Department of Medical Oncology, National Center for Tumor Diseases (NCT), Heidelberg University Hospital, Heidelberg, Germany. jakob_nikolas.kather@tu-dresden.de
Department of Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, 01307, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de
Else Kroener Fresenius Center for Digital Health, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany. jakob_nikolas.kather@tu-dresden.de
Cited by 136 stored of 138
No patents citing this paper on Lens.org (checked 2026-10-06).