Leo Anthony Celi

Research interests

Publications

• The TRIPOD-LLM reporting guideline for studies using large language models

  Nature Medicine · 2025 · 10.1038/s41591-024-03425-5

• The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence

  Nature Medicine · 2025 · https://doi.org/10.1038/s41591-025-03953-8

• The TRIPOD-LLM reporting guideline for studies using large language models

  Nature Medicine · 2025 · 10.1038/s41591-024-03425-5

• PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods

  BMJ · 2025 · https://doi.org/10.1136/bmj-2024-082505

• Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

  Circulation · 2024 · 10.1161/cir.0000000000001201

• TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods

  BMJ · 2024 · https://doi.org/10.1136/bmj-2023-078378

• Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

  Circulation · 2024 · 10.1161/cir.0000000000001201

• ChatGPT passing USMLE shines a spotlight on the flaws of medical education

  PLOS Digital Health · 2023 · 10.1371/journal.pdig.0000205

• MIMIC-IV, a freely accessible electronic health record dataset

  Scientific Data · 2023 · https://doi.org/10.1038/s41597-022-01899-x

• Ethics of large language models in medicine and medical research

  The Lancet Digital Health · 2023 · 10.1016/s2589-7500(23)00083-3

• The promise of digital healthcare technologies

  Frontiers in Public Health · 2023 · https://doi.org/10.3389/fpubh.2023.1196596

• Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study

  The Lancet Digital Health · 2023 · https://doi.org/10.1016/s2589-7500(23)00225-x

• AI pitfalls and what not to do: mitigating bias in AI

  British Journal of Radiology · 2023 · 10.1259/bjr.20230023

• Digital literacy as a new determinant of health: A scoping review

  PLOS Digital Health · 2023 · 10.1371/journal.pdig.0000279

• AI pitfalls and what not to do: mitigating bias in AI

  British Journal of Radiology · 2023 · 10.1259/bjr.20230023

• Digital literacy as a new determinant of health: A scoping review

  PLOS Digital Health · 2023 · 10.1371/journal.pdig.0000279

• Ethics of large language models in medicine and medical research

  The Lancet Digital Health · 2023 · 10.1016/s2589-7500(23)00083-3

• ChatGPT passing USMLE shines a spotlight on the flaws of medical education

  PLOS Digital Health · 2023 · 10.1371/journal.pdig.0000205

• Sources of bias in artificial intelligence that perpetuate healthcare disparities—A global review

  PLOS Digital Health · 2022 · 10.1371/journal.pdig.0000022

• Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare

  npj Digital Medicine · 2022 · 10.1038/s41746-022-00611-y

• AI recognition of patient race in medical imaging: a modelling study

  The Lancet Digital Health · 2022 · 10.1016/s2589-7500(22)00063-2

• Sources of bias in artificial intelligence that perpetuate healthcare disparities—A global review

  PLOS Digital Health · 2022 · 10.1371/journal.pdig.0000022

• Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare

  npj Digital Medicine · 2022 · 10.1038/s41746-022-00611-y

• AI recognition of patient race in medical imaging: a modelling study

  The Lancet Digital Health · 2022 · 10.1016/s2589-7500(22)00063-2

• Analysis of Discrepancies Between Pulse Oximetry and Arterial Oxygen Saturation Measurements by Race and Ethnicity and Association With Organ Dysfunction and Mortality

  JAMA Network Open · 2021 · 10.1001/jamanetworkopen.2021.31674

• Analysis of Discrepancies Between Pulse Oximetry and Arterial Oxygen Saturation Measurements by Race and Ethnicity and Association With Organ Dysfunction and Mortality

  JAMA Network Open · 2021 · 10.1001/jamanetworkopen.2021.31674

• What do medical students actually need to know about artificial intelligence?

  npj Digital Medicine · 2020 · https://doi.org/10.1038/s41746-020-0294-7

• The myth of generalisability in clinical research and machine learning in health care

  The Lancet Digital Health · 2020 · 10.1016/s2589-7500(20)30186-2

• The myth of generalisability in clinical research and machine learning in health care

  The Lancet Digital Health · 2020 · 10.1016/s2589-7500(20)30186-2

• The “inconvenient truth” about AI in healthcare

  npj Digital Medicine · 2019 · 10.1038/s41746-019-0155-4

• The “inconvenient truth” about AI in healthcare

  npj Digital Medicine · 2019 · 10.1038/s41746-019-0155-4

• Guidelines for reinforcement learning in healthcare

  Nature Medicine · 2018 · 10.1038/s41591-018-0310-5

• The eICU Collaborative Research Database, a freely available multi-center database for critical care research

  Scientific Data · 2018 · https://doi.org/10.1038/sdata.2018.178

• Mechanical power of ventilation is associated with mortality in critically ill patients: an analysis of patients in two observational cohorts

  Intensive Care Medicine · 2018 · https://doi.org/10.1007/s00134-018-5375-6

• Guidelines for reinforcement learning in healthcare

  Nature Medicine · 2018 · 10.1038/s41591-018-0310-5

• The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care

  Nature Medicine · 2018 · https://doi.org/10.1038/s41591-018-0213-5

• The MIMIC Code Repository: enabling reproducibility in critical care research

  Journal of the American Medical Informatics Association · 2017 · 10.1093/jamia/ocx084

• The MIMIC Code Repository: enabling reproducibility in critical care research

  Journal of the American Medical Informatics Association · 2017 · 10.1093/jamia/ocx084

• MIMIC-III, a freely accessible critical care database

  Scientific Data · 2016 · 10.1038/sdata.2016.35

• MIMIC-III, a freely accessible critical care database

  Scientific Data · 2016 · 10.1038/sdata.2016.35

• ICU admission characteristics and mortality rates among elderly and very elderly patients

  Intensive Care Medicine · 2012 · 10.1007/s00134-012-2629-6

• ICU admission characteristics and mortality rates among elderly and very elderly patients

  Intensive Care Medicine · 2012 · 10.1007/s00134-012-2629-6

• Early intervention with erythropoietin does not affect the outcome of acute kidney injury (the EARLYARF trial)

  Kidney International · 2010 · 10.1038/ki.2010.25

• Early intervention with erythropoietin does not affect the outcome of acute kidney injury (the EARLYARF trial)

  Kidney International · 2010 · 10.1038/ki.2010.25

Current projects

No projects listed.