John J. Schmitz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
John J. Schmitz has a total of 83 co-authors. Here are the top co-authors by number of shared publications:
- Anil Nicholas Kurup
Department of Radiology, Mayo Clinic, Rochester, USA
4 shared publications - Jennifer S. McDonald
Department of Radiology, Mayo Clinic, Rochester, Minnesota
4 shared publications - Brian T. Welch
Department of Radiology, Mayo Clinic, Rochester, USA
3 shared publications Robert J. McDonald
Department of Radiology, Mayo Clinic, Rochester, MN
3 shared publications- Ahmad Parvinian
Department of Radiology, Mayo Clinic, Rochester, USA
2 shared publications - Alex Chan
Department of Radiology, Mayo Clinic, Rochester, USA
2 shared publications
Latest Publications
- 12 September 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-8
Feasibility and safety of percutaneous cryoablation for treatment of peritoneal metastases
- 12 September 2026
- Published by Springer Nature in Abdominal Radiology
- p. 1-8
Feasibility and safety of percutaneous cryoablation for treatment of peritoneal metastases
- Open Access
- 23 October 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e77061
Human-Machine Agreement in Medical Ethics: Patient Autonomy Case-Based Evaluation of Large Language Models
Background: Medical ethics provides a moral framework for the practice of clinical medicine. Four principles, that is, beneficence, nonmaleficence, patient autonomy, and justice, form the cornerstones of medical ethics as it is practiced today. Of these 4 principles, patient autonomy holds a pivotal position and often takes precedence in ethical dilemmas that result from conflicts among the 4 principles. Its importance serves as a constant reminder to the clinician that the “needs of the patient come first.” With their remarkable ability to process natural language, large language models (LLMs) have recently pervaded nearly every aspect of human life, including medicine and medical ethics. Reliance on tools such as LLMs, however, poses fundamental questions in medical ethics, where human-like reasoning, emotional intelligence, and an understanding of local context and values are of utmost importance. Objective: While emphasizing the central role of the human factor, we undertake a bold venture to establish some confidence in LLMs, as it pertains to medical ethics by not only evaluating the status quo of foundational LLMs but also exploring ways to improve the LLMs by using patient autonomy–based hypothetical cases. Although literature today is certainly lacking in such ventures, we also believe projects such as ours must be frequently revisited in the field of LLMs, which is evolving at a pace that is both rapid and unprecedented. Methods: We evaluated 3 foundational LLMs (ChatGPT, LLaMA, and Gemini) on hypothetical cases in patient autonomy. We used Cohen κ to compare LLM responses to the consensus from a physician panel. McNemar test was used during the improvement phase and to report the final significance of improved agreement of each LLM with physician consensus. P values less than .05 were considered significant. An agreement with κ<0 was designated as poor, 0-0.2 as slight, 0.2-0.4 as fair, 0.41-0.6 as moderate, 0.61-0.8 as substantial, and 0.81-1 as almost perfect. Results: There was slight to fair agreement between the foundational LLMs and the physician consensus. With iterative improvement techniques, this agreement evolved to be substantial or higher (Cohen κ of 0.73-0.82). The degree of improvement was statistically significant (P=.006 for ChatGPT, P<.001 for Gemini, and P<.001 for LLaMA). Conclusions: Although LLMs hold great potential for use in medicine, there needs to be an abundance of caution in using foundational LLMs in domains such as medical ethics. With adequate human oversight in testing and utilizing established techniques, LLM responses can be better aligned to human responses, even in the domain of medical ethics.
- 23 October 2025
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 13, e77061
Open AccessHuman-Machine Agreement in Medical Ethics: Patient Autonomy Case-Based Evaluation of Large Language Models
Background: Medical ethics provides a moral framework for the practice of clinical medicine. Four principles, that is, beneficence, nonmaleficence, patient autonomy, and justice, form the cornerstones of medical ethics as it is practiced today. Of these 4 principles, patient autonomy holds a pivotal position and often takes precedence in ethical dilemmas that result from conflicts among the 4 principles. Its importance serves as a constant reminder to the clinician that the “needs of the patient come first.” With their remarkable ability to process natural language, large language models (LLMs) have recently pervaded nearly every aspect of human life, including medicine and medical ethics. Reliance on tools such as LLMs, however, poses fundamental questions in medical ethics, where human-like reasoning, emotional intelligence, and an understanding of local context and values are of utmost importance. Objective: While emphasizing the central role of the human factor, we undertake a bold venture to establish some confidence in LLMs, as it pertains to medical ethics by not only evaluating the status quo of foundational LLMs but also exploring ways to improve the LLMs by using patient autonomy–based hypothetical cases. Although literature today is certainly lacking in such ventures, we also believe projects such as ours must be frequently revisited in the field of LLMs, which is evolving at a pace that is both rapid and unprecedented. Methods: We evaluated 3 foundational LLMs (ChatGPT, LLaMA, and Gemini) on hypothetical cases in patient autonomy. We used Cohen κ to compare LLM responses to the consensus from a physician panel. McNemar test was used during the improvement phase and to report the final significance of improved agreement of each LLM with physician consensus. P values less than .05 were considered significant. An agreement with κ<0 was designated as poor, 0-0.2 as slight, 0.2-0.4 as fair, 0.41-0.6 as moderate, 0.61-0.8 as substantial, and 0.81-1 as almost perfect. Results: There was slight to fair agreement between the foundational LLMs and the physician consensus. With iterative improvement techniques, this agreement evolved to be substantial or higher (Cohen κ of 0.73-0.82). The degree of improvement was statistically significant (P=.006 for ChatGPT, P<.001 for Gemini, and P<.001 for LLaMA). Conclusions: Although LLMs hold great potential for use in medicine, there needs to be an abundance of caution in using foundational LLMs in domains such as medical ethics. With adequate human oversight in testing and utilizing established techniques, LLM responses can be better aligned to human responses, even in the domain of medical ethics.
- Open Access
- 6 May 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Human-Machine Agreement in Medical Ethics: Patient Autonomy Case-Based Evaluation of Large Language Models (Preprint)
BACKGROUND Medical ethics provides a moral framework for the practice of clinical medicine. Four principles, that is, beneficence, nonmaleficence, patient autonomy, and justice, form the cornerstones of medical ethics as it is practiced today. Of these 4 principles, patient autonomy holds a pivotal position and often takes precedence in ethical dilemmas that result from conflicts among the 4 principles. Its importance serves as a constant reminder to the clinician that the “needs of the patient come first.” With their remarkable ability to process natural language, large language models (LLMs) have recently pervaded nearly every aspect of human life, including medicine and medical ethics. Reliance on tools such as LLMs, however, poses fundamental questions in medical ethics, where human-like reasoning, emotional intelligence, and an understanding of local context and values are of utmost importance. OBJECTIVE While emphasizing the central role of the human factor, we undertake a bold venture to establish some confidence in LLMs, as it pertains to medical ethics by not only evaluating the status quo of foundational LLMs but also exploring ways to improve the LLMs by using patient autonomy–based hypothetical cases. Although literature today is certainly lacking in such ventures, we also believe projects such as ours must be frequently revisited in the field of LLMs, which is evolving at a pace that is both rapid and unprecedented. METHODS We evaluated 3 foundational LLMs (ChatGPT, LLaMA, and Gemini) on hypothetical cases in patient autonomy. We used Cohen κ to compare LLM responses to the consensus from a physician panel. McNemar test was used during the improvement phase and to report the final significance of improved agreement of each LLM with physician consensus. P values less than .05 were considered significant. An agreement with κ<0 was designated as poor, 0-0.2 as slight, 0.2-0.4 as fair, 0.41-0.6 as moderate, 0.61-0.8 as substantial, and 0.81-1 as almost perfect. RESULTS There was slight to fair agreement between the foundational LLMs and the physician consensus. With iterative improvement techniques, this agreement evolved to be substantial or higher (Cohen κ of 0.73-0.82). The degree of improvement was statistically significant (P=.006 for ChatGPT, P<.001 for Gemini, and P<.001 for LLaMA). CONCLUSIONS Although LLMs hold great potential for use in medicine, there needs to be an abundance of caution in using foundational LLMs in domains such as medical ethics. With adequate human oversight in testing and utilizing established techniques, LLM responses can be better aligned to human responses, even in the domain of medical ethics.
- 6 May 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessHuman-Machine Agreement in Medical Ethics: Patient Autonomy Case-Based Evaluation of Large Language Models (Preprint)
BACKGROUND Medical ethics provides a moral framework for the practice of clinical medicine. Four principles, that is, beneficence, nonmaleficence, patient autonomy, and justice, form the cornerstones of medical ethics as it is practiced today. Of these 4 principles, patient autonomy holds a pivotal position and often takes precedence in ethical dilemmas that result from conflicts among the 4 principles. Its importance serves as a constant reminder to the clinician that the “needs of the patient come first.” With their remarkable ability to process natural language, large language models (LLMs) have recently pervaded nearly every aspect of human life, including medicine and medical ethics. Reliance on tools such as LLMs, however, poses fundamental questions in medical ethics, where human-like reasoning, emotional intelligence, and an understanding of local context and values are of utmost importance. OBJECTIVE While emphasizing the central role of the human factor, we undertake a bold venture to establish some confidence in LLMs, as it pertains to medical ethics by not only evaluating the status quo of foundational LLMs but also exploring ways to improve the LLMs by using patient autonomy–based hypothetical cases. Although literature today is certainly lacking in such ventures, we also believe projects such as ours must be frequently revisited in the field of LLMs, which is evolving at a pace that is both rapid and unprecedented. METHODS We evaluated 3 foundational LLMs (ChatGPT, LLaMA, and Gemini) on hypothetical cases in patient autonomy. We used Cohen κ to compare LLM responses to the consensus from a physician panel. McNemar test was used during the improvement phase and to report the final significance of improved agreement of each LLM with physician consensus. P values less than .05 were considered significant. An agreement with κ<0 was designated as poor, 0-0.2 as slight, 0.2-0.4 as fair, 0.41-0.6 as moderate, 0.61-0.8 as substantial, and 0.81-1 as almost perfect. RESULTS There was slight to fair agreement between the foundational LLMs and the physician consensus. With iterative improvement techniques, this agreement evolved to be substantial or higher (Cohen κ of 0.73-0.82). The degree of improvement was statistically significant (P=.006 for ChatGPT, P<.001 for Gemini, and P<.001 for LLaMA). CONCLUSIONS Although LLMs hold great potential for use in medicine, there needs to be an abundance of caution in using foundational LLMs in domains such as medical ethics. With adequate human oversight in testing and utilizing established techniques, LLM responses can be better aligned to human responses, even in the domain of medical ethics.
- 2 April 2025
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 36 (7) , 1224-1226
Percutaneous Ultrasound-Guided Thrombin Injection for Radial Artery Pseudoaneurysms
- 2 April 2025
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 36 (7) , 1224-1226
Percutaneous Ultrasound-Guided Thrombin Injection for Radial Artery Pseudoaneurysms
- 2 August 2024
- Published by Elsevier in Mayo Clinic Proceedings
- Vol. 99 (11) , 1702-1709
Exploring Radiofrequency Ablation for T1 Papillary Thyroid Cancer in the United States: Mayo Clinic Experience
- 2 August 2024
- Published by Elsevier in Mayo Clinic Proceedings
- Vol. 99 (11) , 1702-1709
Exploring Radiofrequency Ablation for T1 Papillary Thyroid Cancer in the United States: Mayo Clinic Experience
- 1 December 2023
- Published by Elsevier in Mayo Clinic Proceedings
- Vol. 98 (12) , 1820-1830
Acute Adverse Events After Iodinated Contrast Agent Administration of 359,977 Injections: A Single-Center Retrospective Study
- 1 December 2023
- Published by Elsevier in Mayo Clinic Proceedings
- Vol. 98 (12) , 1820-1830
Acute Adverse Events After Iodinated Contrast Agent Administration of 359,977 Injections: A Single-Center Retrospective Study
- Open Access
- 21 October 2023
- Published by Elsevier in Radiology Case Reports
- Vol. 19 (1) , 58-61
Airway compromise following contrast extravasation from an external jugular intravenous line
- 21 October 2023
- Published by Elsevier in Radiology Case Reports
- Vol. 19 (1) , 58-61
Open AccessAirway compromise following contrast extravasation from an external jugular intravenous line
- 25 April 2023
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 34 (8) , 1303-1310
Percutaneous Cryoablation of Plasmacytomas: Oncologic Effectiveness and Adverse Events
- 25 April 2023
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 34 (8) , 1303-1310
Percutaneous Cryoablation of Plasmacytomas: Oncologic Effectiveness and Adverse Events
- 1 October 2022
- Published by Radiological Society of North America (RSNA) in RadioGraphics
- Vol. 42 (6) , 1812-1828
Radiofrequency Ablation of Benign and Malignant Thyroid Nodules
Radiofrequency ablation of thyroid nodules is a safe and minimally invasive technique that is efficacious in the treatment of benign thyroid nodules, including toxic nodules. Thyroid nodule treatment has significantly evolved over recent years with attempts to individualize treatment on the basis of the cause of the nodule and patient performance status. The risks and c...
- 1 October 2022
- Published by Radiological Society of North America (RSNA) in RadioGraphics
- Vol. 42 (6) , 1812-1828
Radiofrequency Ablation of Benign and Malignant Thyroid Nodules
Radiofrequency ablation of thyroid nodules is a safe and minimally invasive technique that is efficacious in the treatment of benign thyroid nodules, including toxic nodules. Thyroid nodule treatment has significantly evolved over recent years with attempts to individualize treatment on the basis of the cause of the nodule and patient performance status. The risks and c...