Thomas F Heston

Scopus Publications

Fragility of Assumptions: Letter to the Editor
Thomas F. Heston
Orthopaedic Journal of Sports Medicine, 2026
Adjusting fragility metrics for unequal trial randomizations
Thomas F. Heston
Autoimmunity Reviews, 2025
Letter to the Editor: The Relative Risk Index: A Complementary Metric for Assessing Statistical Fragility in Orthopaedic Surgery Research
Thomas F. Heston
Journal of the American Academy of Orthopaedic Surgeons, 2025
Editorial: Large Language Models for medical applications
Ariel Soares Teles, Alaa Abd-alrazaq, Thomas F. Heston, Rafat Damseh, Lívia Ruback
Frontiers in Medicine, 2025
Prompt Engineering in Healthcare
Rajvardhan Patil, Thomas F. Heston, Vijay Bhuse
Electronics Switzerland, 2024
The rapid advancements in artificial intelligence, particularly generative AI and large language models, have unlocked new possibilities for revolutionizing healthcare delivery. However, harnessing the full potential of these technologies requires effective prompt engineering—designing and optimizing input prompts to guide AI systems toward generating clinically relevant and accurate outputs. Despite the importance of prompt engineering, medical education has yet to fully incorporate comprehensive training on this critical skill, leading to a knowledge gap among medical clinicians. This article addresses this educational gap by providing an overview of generative AI prompt engineering, its potential applications in primary care medicine, and best practices for its effective implementation. The role of well-crafted prompts in eliciting accurate, relevant, and valuable responses from AI models is discussed, emphasizing the need for prompts grounded in medical knowledge and aligned with evidence-based guidelines. The article explores various applications of prompt engineering in primary care, including enhancing patient–provider communication, streamlining clinical documentation, supporting medical education, and facilitating personalized care and shared decision-making. Incorporating domain-specific knowledge, engaging in iterative refinement and validation of prompts, and addressing ethical considerations and potential biases are highlighted. Embracing prompt engineering as a core competency in medical education will be crucial for successfully adopting and implementing AI technologies in primary care, ultimately leading to improved patient outcomes and enhanced healthcare delivery.
Redefining Significance: Robustness and Percent Fragility Indices in Biomedical Research
Thomas F. Heston
Stats, 2024
The p-value has long been the standard for statistical significance in scientific research, but this binary approach often fails to consider the nuances of statistical power and the potential for large sample sizes to show statistical significance despite trivial treatment effects. Including a statistical fragility assessment can help overcome these limitations. One common fragility metric is the fragility index, which assesses statistical fragility by incrementally altering the outcome data in the intervention group until the statistical significance flips. The robustness index takes a different approach by maintaining the integrity of the underlying data distribution while examining changes in the p-value as the sample size changes. The percent fragility index is another useful alternative that is more precise than the fragility index and is more uniformly applied to both the intervention and control groups. Incorporating these fragility metrics into routine statistical procedures could address the reproducibility crisis and increase research efficacy. Using these fragility indices can be seen as a step toward a more mature phase of statistical reasoning, where significance is a multi-faceted and contextually informed judgment.
ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain
Thomas F. Heston, Lawrence M. Lewis
Plos One, 2024
Background ChatGPT-4 is a large language model with promising healthcare applications. However, its ability to analyze complex clinical data and provide consistent results is poorly known. Compared to validated tools, this study evaluated ChatGPT-4’s risk stratification of simulated patients with acute nontraumatic chest pain. Methods Three datasets of simulated case studies were created: one based on the TIMI score variables, another on HEART score variables, and a third comprising 44 randomized variables related to non-traumatic chest pain presentations. ChatGPT-4 independently scored each dataset five times. Its risk scores were compared to calculated TIMI and HEART scores. A model trained on 44 clinical variables was evaluated for consistency. Results ChatGPT-4 showed a high correlation with TIMI and HEART scores (r = 0.898 and 0.928, respectively), but the distribution of individual risk assessments was broad. ChatGPT-4 gave a different risk 45–48% of the time for a fixed TIMI or HEART score. On the 44-variable model, a majority of the five ChatGPT-4 models agreed on a diagnosis category only 56% of the time, and risk scores were poorly correlated (r = 0.605). Conclusion While ChatGPT-4 correlates closely with established risk stratification tools regarding mean scores, its inconsistency when presented with identical patient data on separate occasions raises concerns about its reliability. The findings suggest that while large language models like ChatGPT-4 hold promise for healthcare applications, further refinement and customization are necessary, particularly in the clinical risk assessment of atraumatic chest pain patients.
Statistical Fragility in Surveys
Thomas F. Heston
Academic Medicine, 2024
Prompt Engineering in Medical Education
Thomas Heston, Charya Khun
International Medical Education, 2023
Artificial intelligence-powered generative language models (GLMs), such as ChatGPT, Perplexity AI, and Google Bard, have the potential to provide personalized learning, unlimited practice opportunities, and interactive engagement 24/7, with immediate feedback. However, to fully utilize GLMs, properly formulated instructions are essential. Prompt engineering is a systematic approach to effectively communicating with GLMs to achieve the desired results. Well-crafted prompts yield good responses from the GLM, while poorly constructed prompts will lead to unsatisfactory responses. Besides the challenges of prompt engineering, significant concerns are associated with using GLMs in medical education, including ensuring accuracy, mitigating bias, maintaining privacy, and avoiding excessive reliance on technology. Future directions involve developing more sophisticated prompt engineering techniques, integrating GLMs with other technologies, creating personalized learning pathways, and researching the effectiveness of GLMs in medical education.
Distributed Research Networks
Thomas F. Heston, Alexandra Dullea
Integrated Science, 2023
Concordance of chest x-ray with chest CT by body mass index
Thomas F. Heston, John Y. Jiang
Peerj, 2023
Moral injury and the four pillars of bioethics
Thomas F Heston, Joshuel A Pahang
F1000research, 2023
Should the Medical Humanities Be Vital to Curricula?
Thomas F. Heston
Academic Medicine, 2020
Comment on "effect of Montmorency tart cherry juice on cognitive performance in older adults: A randomized controlled trial" by S. C. Chai, J. Jerusik, K. Davis, R. S. Wright and Z. Zhang,: Food Funct., 2019, 10, 4423-4431
Thomas F. Heston
Food and Function, 2020
Moral Injury or Burnout?
Thomas F. Heston, Joshuel A. Pahang
Southern Medical Journal, 2019
Canagliflozin lowers blood sugar, but does it also lower cardiovascular risk? Maybe not
Thomas F. Heston, Anndres H. Olson, Nicholas R. Randall
Annals of Translational Medicine, 2017
Standardized predictive values
Thomas F. Heston
Journal of Magnetic Resonance Imaging, 2014
Commentary on "effect of patients' awareness of CVD risk factors on health-related behaviors"
Thomas F. Heston
Southern Medical Journal, 2013
Letter by Heston Regarding article, "comparative effectiveness of exercise electrocardiography with or without myocardial perfusion single photon emission computed tomography in women with suspected coronary artery disease: Results from the what is the optimal method for ischemia evaluation in women (WOMEN) trial"
Thomas F. Heston
Circulation, 2012
Commentary
Thomas F. Heston
Southern Medical Journal, 2011
Standardizing predictive values in diagnostic imaging research
Thomas F. Heston
Journal of Magnetic Resonance Imaging, 2011
Positive adenosine stress ECG in patients with a normal myocardial perfusion scan
Thomas F. Heston
Journal of Nuclear Cardiology, 2010
SNM Practice guideline for breast scintigraphy with breast-specific γ-cameras 1.0
S. J. Goldsmith, W. Parsons, M. J. Guiberteau, L. H. Stern, L. Lanzkowsky, et al.
Journal of Nuclear Medicine Technology, 2010
Molecular imaging in thyroid cancer
T.F. Heston, R.L. Wahl
Cancer Imaging, 2010
Editorial: Hypovitaminosis D in hypertension
Thomas F. Heston
Southern Medical Journal, 2010

RECENT SCHOLAR PUBLICATIONS

Blockchain Audit Trails Resolve the Electronic Health Record Traceability Problem Created by Generative AI
TF Heston
Internet Medical Journal 1 (1), e20337356-e20337356 , 2026
2026
Specification Perturbation Measures Fragility, Not Robustness: Preserving the p–fr–nb Distinction
TF Heston
Internet Medical Journal 1 (1), e20149369-e20149369 , 2026
2026
Statistical Fragility of Saline Nasal Irrigation for Rhinosinusitis Is Incomplete Without Robustness Assessment
TF Heston
Internet Medical Journal 1 (1), e20074314-e20074314 , 2026
2026
Nonattainability of the Fragility Index
TF Heston
Cureus 18 (5) , 2026
2026
Reverse Fragility in Cochrane Meta-Analyses with P Values 0.05 to 0.20 Requires a Robustness Dimension
TF Heston
Internet Medical Journal 1 (1), e19741629-e19741629 , 2026
2026
Reverse Continuous Fragility Index Misleads in Biceps Tenotomy Versus Tenodesis Trials: The Case for a Continuous Fragility Score and Quotient
TF Heston
Internet Medical Journal 1 (1), e19720537-e19720537 , 2026
2026
Guideline evidence audits require robustness beyond the fragility index
TF Heston
Internet Medical Journal 1 (1) , 2026
2026
AI and the Soul of Medicine
TF Heston
Internet Medical Journal 1 (1), e1954401-e1954401 , 2026
2026
Accountable clinical AI requires more than accuracy
TF Heston
Internet Medical Journal 1 (1), e19519377-e19519377 , 2026
2026
Citations: 1
Beyond fragility: what the fragility index cannot measure
TF Heston
Internet Medical Journal 1 (1), e19465222-e19465222 , 2026
2026
Bidirectional fragility is a step forward but not far enough: the case for a global fragility index
TF Heston
Internet Medical Journal 1 (1), e19464166-e19464166 , 2026
2026
Citations: 2
The Continuous Fragility Quotient as a Model-Free Assessment for Continuous Outcomes
TF Heston
Internet Medical Journal 1 (1), e19445024-e19445024 , 2026
2026
Mathematical incompleteness of the fragility index
TF Heston
2026
Citations: 1
Fragility of Assumptions
TF Heston
Orthopaedic Journal of Sports Medicine 14 (2), 23259671251409150 , 2026
2026
Moving Beyond Sorry: The Acknowledge-Repair-Prevent (ARP) Framework for Colleague Apologies in Medicine
TF Heston
Cureus 18 (1) , 2026
2026
THE HERMENEUTICS OF PROMPT ENGINEERING: INTERPRETATION, MEANING-MAKING, AND DECISION QUALITY IN LARGE LANGUAGE MODEL INTERACTIONS
M White, L Giray, G Marvin, N Knoth, J White, TF Heston
2026
Neutrality Boundary Robustness for Meta-Analyses
TF Heston
2026
Fragility Metrics Toolkit
TF Heston
Zenodo , 2026
2026
Citations: 2
Evidence-Based Frameworks for Generative Artificial Intelligence
TF Heston
Int J Blockchain Technol Appl 4, 34-38 , 2026
2026
Citations: 1
Significance, Fragility, and Robustness in Clinical Trials: Stratifying Statistical Evidence
TF Heston
Cureus 17 (12) , 2025
2025
Citations: 7

MOST CITED SCHOLAR PUBLICATIONS

Prompt Engineering in Medical Education
TF Heston, C Khun
International Medical Education 2 (3), 198-205 , 2023
2023
Citations: 337
Barriers to Development of Telemedicine in Developing Countries
S Bali, TF Heston (ed)
Telehealth, 29-42 , 2019
2019
Citations: 157
Safety of large language models in addressing depression
TF Heston
Cureus 15 (12), e50729 , 2023
2023
Citations: 117
A case study in blockchain health care innovation
TF Heston
International Journal of Current Research 9 (11), 60587-60588 , 2017
2017
Citations: 113
SNM practice guideline for breast scintigraphy with breast-specific γ-cameras 1.0
SJ Goldsmith, W Parsons, MJ Guiberteau, LH Stern, L Lanzkowsky, ...
Journal of Nuclear Medicine Technology 38 (4), 219-224 , 2010
2010
Citations: 108
Gender bias in the evaluation and management of acute nontraumatic chest pain
TF Heston, LM Lewis
Family Practice Research Journal 12 (4), 383-389 , 1992
1992
Citations: 108
Prompt engineering in healthcare
R Patil, TF Heston, V Bhuse
Electronics 13 (15), 2961 , 2024
2024
Citations: 94
Standardizing predictive values in diagnostic imaging research
TF Heston
Journal of Magnetic Resonance Imaging 33 (2), 505-505 , 2011
2011
Citations: 65
PET scanning
M Kapoor, TF Heston, A Kasi
StatPearls [Internet] , 2025
2025
Citations: 61
Quantifying transient ischemic dilation using gated SPECT
TF Heston, DM Sigg
Journal of Nuclear Medicine 46 (12), 1990-1996 , 2005
2005
Citations: 58
Molecular imaging in thyroid cancer
TF Heston, RL Wahl
Cancer Imaging 10 (1), 1 , 2010
2010
Citations: 52
Predictive power of statistical significance
TF Heston, JM King
World journal of methodology 7 (4), 112 , 2017
2017
Citations: 39
Cardiac risk stratification in renal transplantation using a form of artificial intelligence
TF Heston, DJ Norman, JM Barry, WM Bennett, RA Wilson
The American journal of cardiology 79 (4), 415-417 , 1997
1997
Citations: 37
Moral injury and the four pillars of bioethics
TF Heston, JA Pahang
F1000 Research 8 , 2019
2019
Citations: 35
Statistical Significance Versus Clinical Relevance: A Head-to-Head Comparison of the Fragility Index and Relative Risk Index
TF Heston
Cureus 15 (10), e47741 , 2023
2023
Citations: 34
Nuclear medicine in oral and maxillofacial diagnosis: a review for the practicing dental professional
DA Baur, TF Heston, JI Helman
The journal of contemporary dental practice 5 (1), 94-104 , 2006
2006
Citations: 33
Subchondral architecture in bones of the canine shoulder.
PA Simkin, TF Heston, DJ Downey, RS Benedict, HS Choi
Journal of anatomy 175, 213-227 , 1991
1991
Citations: 33
Prompt engineering for students of medicine and their teachers
TF Heston
arXiv preprint arXiv:2308.11628 , 2023
2023
Citations: 32
The cost of living index as a primary driver of homelessness in the United States: a cross-state analysis
TF Heston
Cureus 15 (10) , 2023
2023
Citations: 29
The robustness index: going beyond statistical significance by quantifying fragility
TF Heston
Cureus 15 (8), e44397 , 2023
2023
Citations: 26

Thomas F Heston

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS