Riley Scherr

Riley Scherr

Auto-generated profile, based on publicly available information

Riley Scherr

School of Medicine, University of California Irvine, Irvine, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2023 in JMIR Medical Education
Verified
Journal Article
Open access
RSRiley Scherr
Riley Scherr
FHFaris F Halaseh
Faris F Halaseh
ASAidin Spina
Aidin Spina
SASaman Andalib
Saman Andalib
RRRonald Rivera
Ronald Rivera
Background: The transition to clinical clerkships can be difficult for medical students, as it requires the synthesis and application of preclinical information into diagnostic and therapeutic decisions. ChatGPT—a generative language model with many medical applications due to its creativity, memory, and accuracy—can help students in this transition. Objective: This paper models ChatGPT 3.5’s ability to perform interactive clinical simulations and shows this tool’s benefit to medical education. Methods: Simulation starting prompts were refined using ChatGPT 3.5 in Google Chrome. Starting prompts were selected based on assessment format, stepwise progression of simulation events and questions, free-response question type, responsiveness to user inputs, postscenario feedback, and medical accuracy of the feedback. The chosen scenarios were advanced cardiac life support and medical intensive care (for sepsis and pneumonia). Results: Two starting prompts were chosen. Prompt 1 was developed through 3 test simulations and used successfully in 2 simulations. Prompt 2 was developed through 10 additional test simulations and used successfully in 1 simulation. Conclusions: ChatGPT is capable of creating simulations for early clinical education. These simulations let students practice novel parts of the clinical curriculum, such as forming independent diagnostic and therapeutic impressions over an entire patient encounter. Furthermore, the simulations can adapt to user inputs in a way that replicates real life more accurately than premade question bank clinical vignettes. Finally, ChatGPT can create potentially unlimited free simulations with specific feedback, which increases access for medical students with lower socioeconomic status and underresourced medical schools. However, no tool is perfect, and ChatGPT is no exception; there are concerns about simulation accuracy and replicability that need to be addressed to further optimize ChatGPT’s performance as an educational resource.

27 February 2025 in JMIR Formative Research
Verified
Journal Article
Open access
RSRiley Scherr
Riley Scherr
ASAidin Spina
Aidin Spina
ADAllen Dao
Allen Dao
SASaman Andalib
Saman Andalib
FHFaris F Halaseh
Faris F Halaseh
RRRonald Rivera
Ronald Rivera
Background: Case studies have shown ChatGPT can run clinical simulations at the medical student level. However, no data have assessed ChatGPT’s reliability in meeting desired simulation criteria such as medical accuracy, simulation formatting, and robust feedback mechanisms. Objective: This study aims to quantify ChatGPT’s ability to consistently follow formatting instructions and create simulations for preclinical medical student learners according to principles of medical simulation and multimedia educational technology. Methods: Using ChatGPT-4 and a prevalidated starting prompt, the authors ran 360 separate simulations of an acute asthma exacerbation. A total of 180 simulations were given correct answers and 180 simulations were given incorrect answers. ChatGPT was evaluated for its ability to adhere to basic simulation parameters (stepwise progression, free response, interactivity), advanced simulation parameters (autonomous conclusion, delayed feedback, comprehensive feedback), and medical accuracy (vignette, treatment updates, feedback). Significance was determined with χ² analyses using 95% CIs for odds ratios. Results: In total, 100% (n=360) of simulations met basic simulation parameters and were medically accurate. For advanced parameters, 55% (200/360) of all simulations delayed feedback, while the Correct arm (157/180, 87%) delayed feedback was significantly more than the Incorrect arm (43/180, 24%; P<.001). A total of 79% (285/360) of simulations concluded autonomously, and there was no difference between the Correct and Incorrect arms in autonomous conclusion (146/180, 81% and 139/180, 77%; P=.36). Overall, 78% (282/360) of simulations gave comprehensive feedback, and there was no difference between the Correct and Incorrect arms in comprehensive feedback (137/180, 76% and 145/180, 81%; P=.31). ChatGPT-4 was not significantly more likely to conclude simulations autonomously (P=.34) and provide comprehensive feedback (P=.27) when feedback was delayed compared to when feedback was not delayed. Conclusions: These simulations have the potential to be a reliable educational tool for simple simulations and can be evaluated by a novel 9-part metric. Per this metric, ChatGPT simulations performed perfectly on medical accuracy and basic simulation parameters. It performed well on comprehensive feedback and autonomous conclusion. Delayed feedback depended on the accuracy of user inputs. A simulation meeting one advanced parameter was not more likely to meet all advanced parameters. Further work must be done to ensure consistent performance across a broader range of simulation scenarios.

20 March 2024 in Journal of Vascular and Interventional Radiology
Verified
Journal Article
Closed access
JBJoseph A. Breuer
Joseph A. Breuer
KAKhwaja Hamzah Ahmed
Khwaja Hamzah Ahmed
RSRiley Scherr
Riley Scherr
CSCaitlyn Sing
Caitlyn Sing
MDMichelle Dai
Michelle Dai
NANadine Abi-Jaoudeh
Nadine Abi-Jaoudeh

27 February 2025 in Journal of Racial and Ethnic Health Disparities
Verified
Journal Article
Open access
PDF file
RSRiley Scherr
Riley Scherr
JCJacqueline J. Chow
Jacqueline J. Chow
CSCaitlyn Sing
Caitlyn Sing
KKKatharine A. Kirby
Katharine A. Kirby
JBJoseph A. Breuer
Joseph A. Breuer
NANadine Abi-Jaoudeh
Nadine Abi-Jaoudeh
Background and Aims: To identify demographic predictors, with a focus on race and socioeconomic status, for advanced treatment modality, mortality, and increased length of stay (LOS) in upper gastrointestinal (GI) hemorrhage treatment. Methods: Hospitalizations with acute upper GI hemorrhage from 2016 to 2021 were identified in the Healthcare Cost and Utilization Project’s National Inpatient Sample. Cases were divided into interventional radiology (IR) and non-IR (endoscopic) treatments. Statistical analyses calculated significant odds ratios via 95% confidence intervals. The primary outcome of interest was mortality rate. The secondary outcome of interest was the mean LOS. Confounding factors affecting mortality were also examined. Results: There was no significant difference in likelihood of an IR procedure or mortality between White patients and both Non-Hispanic (NH) Black and Hispanic patients. NH Black patients had significantly longer LOS in days compared to White patients (12.61 vs 9.57) that persisted when matching for age and sex (13.78 vs 9.92), socioeconomic status (12.94 vs 10.07), chronic comorbidities (11.33 vs 8.88), blood transfusions (14.46 vs 10.21), and vasopressor use (14.43 vs 10.29) ( p < 0.001). These LOS differences were not seen under matching conditions post-COVID-19. Conclusion: This study presents racial disparities in LOS following acute upper GI hemorrhage, but no differences in advanced treatment utilization or mortality. Confounders were responsible for LOS differences in non-IR treatment, but NH Black patients had persistently longer LOS than White patients after IR treatment.

14 June 2023 in JMIR Preprints
Verified
Preprint
Open access
RSRiley Scherr
Riley Scherr
FHFaris F Halaseh
Faris F Halaseh
ASAidin Spina
Aidin Spina
SASaman Andalib
Saman Andalib
RRRonald Rivera
Ronald Rivera
BACKGROUND The transition to clinical clerkships can be difficult for medical students, as it requires the synthesis and application of preclinical information into diagnostic and therapeutic decisions. ChatGPT—a generative language model with many medical applications due to its creativity, memory, and accuracy—can help students in this transition. OBJECTIVE This paper models ChatGPT 3.5’s ability to perform interactive clinical simulations and shows this tool’s benefit to medical education. METHODS Simulation starting prompts were refined using ChatGPT 3.5 in Google Chrome. Starting prompts were selected based on assessment format, stepwise progression of simulation events and questions, free-response question type, responsiveness to user inputs, postscenario feedback, and medical accuracy of the feedback. The chosen scenarios were advanced cardiac life support and medical intensive care (for sepsis and pneumonia). RESULTS Two starting prompts were chosen. Prompt 1 was developed through 3 test simulations and used successfully in 2 simulations. Prompt 2 was developed through 10 additional test simulations and used successfully in 1 simulation. CONCLUSIONS ChatGPT is capable of creating simulations for early clinical education. These simulations let students practice novel parts of the clinical curriculum, such as forming independent diagnostic and therapeutic impressions over an entire patient encounter. Furthermore, the simulations can adapt to user inputs in a way that replicates real life more accurately than premade question bank clinical vignettes. Finally, ChatGPT can create potentially unlimited free simulations with specific feedback, which increases access for medical students with lower socioeconomic status and underresourced medical schools. However, no tool is perfect, and ChatGPT is no exception; there are concerns about simulation accuracy and replicability that need to be addressed to further optimize ChatGPT’s performance as an educational resource.

14 September 2024 in JMIR Preprints
Verified
Preprint
Open access
RSRiley Scherr
Riley Scherr
ASAidin Spina
Aidin Spina
ADAllen Dao
Allen Dao
SASaman Andalib
Saman Andalib
FHFaris F Halaseh
Faris F Halaseh
RRRonald J Rivera
Ronald J Rivera
BACKGROUND Case studies have shown ChatGPT can run clinical simulations at the medical student level. However, no data have assessed ChatGPT’s reliability in meeting desired simulation criteria such as medical accuracy, simulation formatting, and robust feedback mechanisms. OBJECTIVE To quantify ChatGPT’s ability to consistently follow formatting instructions and create simulations for preclinical medical student learners according to principles of medical simulation and multimedia educational technology. METHODS Using ChatGPT-4 and a pre-validated starting prompt, the authors ran 360 separate simulations of an acute asthma exacerbation. 180 simulations were given correct answers and 180 were given incorrect answers. ChatGPT was evaluated for its ability to adhere to basic simulation parameters (stepwise progression, free response, interactivity), advanced simulation parameters (autonomous conclusion, delayed feedback, comprehensive feedback), and medical accuracy (vignette, treatment updates, feedback). Significance was determined with chi-squared analyses using 95% confidence intervals for odds ratios. RESULTS 100% of simulations met basic simulation parameters and were medically accurate. For advanced parameters, 55% of all simulations delayed feedback, while the Correct arm (87%) delayed feedback significantly more than the Incorrect arm (24%) (p<0.001). 79% of simulations concluded autonomously, and there was no difference between the Correct and Incorrect arms in autonomous conclusion (81%, 77%; p=0.364). 78% of simulations gave comprehensive feedback, and there was no difference between the Correct and Incorrect arms in comprehensive feedback (76%, 81%; p=0.306). ChatGPT-4 was significantly more likely to conclude simulations autonomously (p<0.001) and provide comprehensive feedback (p<0.001) when feedback was delayed compared to when feedback was not delayed. CONCLUSIONS ChatGPT simulations performed perfectly on medical accuracy and basic simulation parameters. It performed well on comprehensive feedback and autonomous conclusion. Delayed feedback depended on the accuracy of user inputs. A simulation meeting one advanced parameter was more likely to meet all advanced parameters. These simulations have the potential to be a reliable educational tool for simple simulations and can be evaluated by a novel nine-part metric. Further work must be done to ensure consistent performance across a broader range of simulation scenarios.