ChatGPT as a Tool for Biostatisticians: A Tutorial on Applications, Opportunities, and Limitations

Statistics in Medicine, vol. 44, pp. e70263

Abstract

Modern large language models (LLMs) have reshaped the workflows of people across countless fields-and biostatistics is no exception. These models offer novel support in drafting study plans, generating software code, or writing reports. However, reliance on LLMs carries the risk of inaccuracies due to potential hallucinations that may produce fabricated "facts", leading to erroneous statistical statements and conclusions. Such errors could compromise the high precision and transparency fundamental to our field. This tutorial aims to illustrate the impact of LLM-based applications on various contemporary biostatistical tasks. We will explore both the risks and opportunities presented by this new era of artificial intelligence. Our ultimate conclusion emphasizes that advanced applications should only be used in combination with sufficient background knowledge. Over time, consistently verifying LLM outputs may lead to an appropriately calibrated trust in these tools among users.

Authors 11

1. Dennis Dobler corresponding Aachen Department of Mathematics

   RWTH Aachen University

   Affiliation as printed

   Department of Mathematics RWTH Aachen University Aachen Germany

2. Harald Binder

   University of Freiburg · University Medical Center Freiburg

   Affiliation as printed

   Institute of Medical Biometry and Statistics Faculty of Medicine and Medical Center ‐ University of Freiburg Freiburg im Breisgau Germany

3. Anne‐Laure Boulesteix

   Munich Center for Machine Learning · Institut für Medizinische Informationsverarbeitung, Biometrie und Epidemiologie · Ludwig-Maximilians-Universität München

   Affiliation as printed

   Institute for Medical Information Processing, Biometry, and Epidemiology LMU Munich Munich Germany

   Munich Center for Machine Learning Munich Germany

4. Jan-Bernd Igelmann

   TU Dortmund University

   Affiliation as printed

   Department of Statistics TU Dortmund University Dortmund Germany

5. David Köhler

   University Hospital Bonn · Institut für Medizinische Biometrie, Informatik und Epidemiologie

   Affiliation as printed

   Institute for Medical Biometry, Informatics and Epidemiology University Hospital Bonn Bonn Germany

6. Ulrich Mansmann

   Institut für Medizinische Informationsverarbeitung, Biometrie und Epidemiologie · Ludwig-Maximilians-Universität München

   Affiliation as printed

   Institute for Medical Information Processing, Biometry, and Epidemiology LMU Munich Munich Germany

7. Markus Pauly

   TU Dortmund University

   Affiliation as printed

   Department of Statistics TU Dortmund University Dortmund Germany

   Research Center Trustworthy Data Science and Security University Alliance Ruhr Dortmund Germany

8. André Scherag

   Jena University Hospital · Friedrich Schiller University Jena

   Affiliation as printed

   Institute of Medical Statistics, Computer and Data Sciences Jena University Hospital ‐ Friedrich Schiller University Jena Germany

9. Matthias C. Schmid

   University Hospital Bonn · Institut für Medizinische Biometrie, Informatik und Epidemiologie

   Affiliation as printed

   Institute for Medical Biometry, Informatics and Epidemiology University Hospital Bonn Bonn Germany

10. Amani Al Tawil

    Institut für Medizinische Informationsverarbeitung, Biometrie und Epidemiologie · Ludwig-Maximilians-Universität München

    Affiliation as printed

    Institute for Medical Information Processing, Biometry, and Epidemiology LMU Munich Munich Germany

11. Susanne Weber

    University of Freiburg · University Medical Center Freiburg

    Affiliation as printed

    Institute of Medical Biometry and Statistics Faculty of Medicine and Medical Center ‐ University of Freiburg Freiburg im Breisgau Germany