Michael Dulin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Michael Dulin has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Andrew Gunter
Department of Pediatrics, Carolinas HealthCare System, Charlotte, NC, United States
2 shared publications - Andrew McWilliams
Center for Outcomes Research and Evaluation, Atrium Health, Charlotte, NC, United States
2 shared publications - Cheryl Courtlandt
Cheryl Courtlandt, MD, is Professor of Pediatrics, Interim Division Director of General Academic Pediatrics, and Co-Director of Center for Advancing Pediatric Excellence, Atrium Health, Wake Forest School of Medicine, Charlotte, North Carolina, USA
2 shared publications - Elizabeth Burton
Community Care Partners of Greater Mecklenburg, Carolinas HealthCare System, Charlotte, NC, United States
2 shared publications - Hazel Tapp
Atrium Health
2 shared publications - Kelly Reeves
Department of Family Medicine, Atrium Health Wake Forest Baptist, Charlotte, North Carolina, United States of America
2 shared publications
Latest Publications
- Open Access
- 15 July 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Using Artificial Intelligence to Structure Treatment Decisions in a Rare Hereditary Cancer: A Viewpoint on MET-Driven Hereditary Papillary Renal Carcinoma (Preprint)
UNSTRUCTURED Hereditary papillary renal carcinoma (HPRC) is an extremely rare autosomal dominant cancer syndrome that predisposes carriers to bilateral and multifocal papillary renal cell carcinoma later in life. Expert opinion recommends ongoing cross-sectional renal surveillance and nephron-sparing surgery when a renal lesion reaches 3 cm [1–3]. However, the rarity of this condition makes evidence supporting management very limited and derived from small observational hereditary renal-cancer cohorts with limited numbers of HPRC members. A 59-year-old male physician who was diagnosed with HPRC 10 years ago requests assistance in prevention and management of his disease. After his initial diagnosis, he enrolled in the NIH/NCI hereditary renal cancer protocol where he has undergone serial MRI surveillance studies [4]. These studies have uncovered a right lower-pole lesion that has enlarged slowly from 0.4 cm in 2016 to 0.7 cm in 2025. The patient’s current management is MRI surveillance every 2 years with anticipation of nephron-sparing surgery for lesions reaching 3 cm. The patient is seeking rational, low-risk options to delay cancer development and improve his prognosis. At age 59, he is on the steepest portion of his variant-associated age-risk curve, which contributes a clinically meaningful anxiety burden. Given the rarity of HPRC and the absence of prevention evidence, can AI-assisted evidence synthesis use the biology of MET-driven tumor neogenesis to identify plausible, theoretical low-risk adjunctive strategies to mitigate this patient’s cancer risk? The strongest current strategy remains surveillance and timely nephron-sparing surgery at the 3 cm threshold. Lifestyle measures have favorable general-health evidence and are likely to improve surgical resilience. Several medications intersect with MET-adjacent signaling nodes while also carrying independent indications relevant to this patient: dyslipidemia, obstructive sleep apnea, insulin resistance/metabolic risk, Crohn's disease, and healthspan. Newer GLP-1 literature in IBD is observational but generally reassuring, and prospective tirzepatide trials in Crohn's disease are now underway. Rapamycin has the most direct mechanistic fit but the highest personalized risk and monitoring burden. Several candidate agents carry independent clinical indications or healthspan rationales that materially change their risk–benefit balance for this patient and, in several cases, make adopting them considerably easier than the thin HPRC-specific evidence alone would suggest. This case illustrates how AI can organize a rare-cancer decision problem by integrating germline risk, family history, serial imaging, comorbidities, medications, tumor biology, and graded evidence. AI tools were highly effective in synthesizing the literature, developing an evidence-based model for tumor development, and providing guidance for managing a complex rare disease and integrating treatment options with multiple chronic conditions.
- 15 July 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUsing Artificial Intelligence to Structure Treatment Decisions in a Rare Hereditary Cancer: A Viewpoint on MET-Driven Hereditary Papillary Renal Carcinoma (Preprint)
UNSTRUCTURED Hereditary papillary renal carcinoma (HPRC) is an extremely rare autosomal dominant cancer syndrome that predisposes carriers to bilateral and multifocal papillary renal cell carcinoma later in life. Expert opinion recommends ongoing cross-sectional renal surveillance and nephron-sparing surgery when a renal lesion reaches 3 cm [1–3]. However, the rarity of this condition makes evidence supporting management very limited and derived from small observational hereditary renal-cancer cohorts with limited numbers of HPRC members. A 59-year-old male physician who was diagnosed with HPRC 10 years ago requests assistance in prevention and management of his disease. After his initial diagnosis, he enrolled in the NIH/NCI hereditary renal cancer protocol where he has undergone serial MRI surveillance studies [4]. These studies have uncovered a right lower-pole lesion that has enlarged slowly from 0.4 cm in 2016 to 0.7 cm in 2025. The patient’s current management is MRI surveillance every 2 years with anticipation of nephron-sparing surgery for lesions reaching 3 cm. The patient is seeking rational, low-risk options to delay cancer development and improve his prognosis. At age 59, he is on the steepest portion of his variant-associated age-risk curve, which contributes a clinically meaningful anxiety burden. Given the rarity of HPRC and the absence of prevention evidence, can AI-assisted evidence synthesis use the biology of MET-driven tumor neogenesis to identify plausible, theoretical low-risk adjunctive strategies to mitigate this patient’s cancer risk? The strongest current strategy remains surveillance and timely nephron-sparing surgery at the 3 cm threshold. Lifestyle measures have favorable general-health evidence and are likely to improve surgical resilience. Several medications intersect with MET-adjacent signaling nodes while also carrying independent indications relevant to this patient: dyslipidemia, obstructive sleep apnea, insulin resistance/metabolic risk, Crohn's disease, and healthspan. Newer GLP-1 literature in IBD is observational but generally reassuring, and prospective tirzepatide trials in Crohn's disease are now underway. Rapamycin has the most direct mechanistic fit but the highest personalized risk and monitoring burden. Several candidate agents carry independent clinical indications or healthspan rationales that materially change their risk–benefit balance for this patient and, in several cases, make adopting them considerably easier than the thin HPRC-specific evidence alone would suggest. This case illustrates how AI can organize a rare-cancer decision problem by integrating germline risk, family history, serial imaging, comorbidities, medications, tumor biology, and graded evidence. AI tools were highly effective in synthesizing the literature, developing an evidence-based model for tumor development, and providing guidance for managing a complex rare disease and integrating treatment options with multiple chronic conditions.
- 1 January 2026
- Published by Human Kinetics in Journal for the Measurement of Physical Behaviour
- Vol. 9 (1)
Real-Time Versus Video-Recorded Step Count Validation Among Young Adults
Background : Consumer Technology Association guidelines recommend two independent researchers review video recordings of treadmill bouts to verify accuracy of the number of steps taken. Performing multiple post hoc validation checks requires significant resources for personnel time and costs, but it is unknown if the burden is necessary. The purpose of this study was to evaluate accuracy and efficiency of step counts assessed during direct observation compared with multiple reviews of video recordings. Methods : Participants ages 18–20 years ( n = 72) completed up to twelve 5-min, zero-incline treadmill bouts, speeds ranging 0.2–2.7 m/s (0.5–6.0 mph). Directly observed steps were counted and hand-tallied in real-time. A sex-age stratified random sample of 30 participants’ bouts were selected for analysis. Two independent researchers recounted steps from video recordings, producing three independent counts. Intraclass correlation coefficient determined interrater reliability. Mean average percent deviation computed deviation magnitude among the three counts. Correlation tests determined the relationship between absolute count differences and average counts for each pairwise comparison. Results : Interrater reliability was excellent with intraclass correlation coefficients ≥ .995 ( p < .001) across all speeds. Average mean average percent deviation was 0.29% with bout-specific deviations ranging from 0.10% to 0.54%, indicating < 1% difference among the three counts for all bouts. Conclusions : A single real-time step count represents a sufficient and efficient approach to measure steps taken in a controlled treadmill setting, while video recounts serve as back-up to allay potential data loss concerns and/or for random selection verification. These data-driven findings are useful for optimizing personnel time and reducing costs associated with collecting quality data in large-scale treadmill-based step-counting studies.
- 1 January 2026
- Published by Human Kinetics in Journal for the Measurement of Physical Behaviour
- Vol. 9 (1)
Real-Time Versus Video-Recorded Step Count Validation Among Young Adults
Background : Consumer Technology Association guidelines recommend two independent researchers review video recordings of treadmill bouts to verify accuracy of the number of steps taken. Performing multiple post hoc validation checks requires significant resources for personnel time and costs, but it is unknown if the burden is necessary. The purpose of this study was to evaluate accuracy and efficiency of step counts assessed during direct observation compared with multiple reviews of video recordings. Methods : Participants ages 18–20 years ( n = 72) completed up to twelve 5-min, zero-incline treadmill bouts, speeds ranging 0.2–2.7 m/s (0.5–6.0 mph). Directly observed steps were counted and hand-tallied in real-time. A sex-age stratified random sample of 30 participants’ bouts were selected for analysis. Two independent researchers recounted steps from video recordings, producing three independent counts. Intraclass correlation coefficient determined interrater reliability. Mean average percent deviation computed deviation magnitude among the three counts. Correlation tests determined the relationship between absolute count differences and average counts for each pairwise comparison. Results : Interrater reliability was excellent with intraclass correlation coefficients ≥ .995 ( p < .001) across all speeds. Average mean average percent deviation was 0.29% with bout-specific deviations ranging from 0.10% to 0.54%, indicating < 1% difference among the three counts for all bouts. Conclusions : A single real-time step count represents a sufficient and efficient approach to measure steps taken in a controlled treadmill setting, while video recounts serve as back-up to allay potential data loss concerns and/or for random selection verification. These data-driven findings are useful for optimizing personnel time and reducing costs associated with collecting quality data in large-scale treadmill-based step-counting studies.
- Open Access
- 12 August 2025
- Published by Taylor & Francis in Journal of Health Equity
- Vol. 2 (1)
A scoping review of risk and protective factors associated with cesarean birth among Black women in the United States
- 12 August 2025
- Published by Taylor & Francis in Journal of Health Equity
- Vol. 2 (1)
Open AccessA scoping review of risk and protective factors associated with cesarean birth among Black women in the United States
- Open Access
- 22 March 2018
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 6 (3) , e68
Patient and Family Engagement in the Design of a Mobile Health Solution for Pediatric Asthma: Development and Feasibility Study
Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.
- 22 March 2018
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 6 (3) , e68
Open AccessPatient and Family Engagement in the Design of a Mobile Health Solution for Pediatric Asthma: Development and Feasibility Study
Mobile and tablet apps, ubiquitous and pervasive computing, wearable computing and domotics for health.
- Open Access
- 26 August 2017
- Published by JMIR Publications Inc. in JMIR Preprints
Patient and Family Engagement in the Design of a Mobile Health Solution for Pediatric Asthma: Development and Feasibility Study
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Asthma is a highly prevalent, chronic disease with significant morbidity, cost, and disparities in health outcomes. While adherence to asthma treatment guidelines can improve symptoms and decrease exacerbations, most patients receive care that is not guideline-based. New approaches that incorporate shared decision-making (SDM) and health information technology (IT) are needed to positively impact asthma management. Despite the promise of health IT to improve efficiency and outcomes in health care, new IT solutions frequently suffer from a lack of widespread adoption and do not achieve desired results, as a consequence of not involving end-users in design. Objective: To describe a case study of a pediatric asthma SDM health IT solution’s development and demonstrate a methodology for engaging actual patients and families in IT development. Perspectives are shared from the vantage point of the research team and a parent of a child with asthma, who participated on the development team. Methods: We adapted user-centric design principles to engage actual users across three main development phases: project initiation, ideation, and usability testing. To facilitate the necessary level of user engagement, our approach included: (1) a Development Workgroup consisting of patients, caregivers, and providers who met regularly with the research team; and (2) “real-world users” consisting of patients, caregivers, and providers recruited from a variety of care locations, including safety-net clinics. Results: Using this methodology, we successful partnered with asthma patients and families to create an interactive, digital solution called Carolinas Asthma Coach. Carolinas Asthma Coach incorporates SDM principles to elicit patient information, including goals and preferences, and provides health-literate, tailored education with specific guideline-based recommendations for patients and their providers. Of the patients, caregivers, and providers surveyed, 100% (n=60) said they would recommend Carolinas Asthma Coach to a friend or colleague. Qualitative feedback from users provided support for the usability and engaging nature of the app. Conclusions: This project demonstrates the feasibility and benefits of deploying user-centric design methods that engage real patients and caregivers throughout the health IT design process.
- 26 August 2017
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPatient and Family Engagement in the Design of a Mobile Health Solution for Pediatric Asthma: Development and Feasibility Study
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Asthma is a highly prevalent, chronic disease with significant morbidity, cost, and disparities in health outcomes. While adherence to asthma treatment guidelines can improve symptoms and decrease exacerbations, most patients receive care that is not guideline-based. New approaches that incorporate shared decision-making (SDM) and health information technology (IT) are needed to positively impact asthma management. Despite the promise of health IT to improve efficiency and outcomes in health care, new IT solutions frequently suffer from a lack of widespread adoption and do not achieve desired results, as a consequence of not involving end-users in design. Objective: To describe a case study of a pediatric asthma SDM health IT solution’s development and demonstrate a methodology for engaging actual patients and families in IT development. Perspectives are shared from the vantage point of the research team and a parent of a child with asthma, who participated on the development team. Methods: We adapted user-centric design principles to engage actual users across three main development phases: project initiation, ideation, and usability testing. To facilitate the necessary level of user engagement, our approach included: (1) a Development Workgroup consisting of patients, caregivers, and providers who met regularly with the research team; and (2) “real-world users” consisting of patients, caregivers, and providers recruited from a variety of care locations, including safety-net clinics. Results: Using this methodology, we successful partnered with asthma patients and families to create an interactive, digital solution called Carolinas Asthma Coach. Carolinas Asthma Coach incorporates SDM principles to elicit patient information, including goals and preferences, and provides health-literate, tailored education with specific guideline-based recommendations for patients and their providers. Of the patients, caregivers, and providers surveyed, 100% (n=60) said they would recommend Carolinas Asthma Coach to a friend or colleague. Qualitative feedback from users provided support for the usability and engaging nature of the app. Conclusions: This project demonstrates the feasibility and benefits of deploying user-centric design methods that engage real patients and caregivers throughout the health IT design process.