About

Samuel I. Berchuck is an Assistant Professor in the Department of Biostatistics & Bioinformatics within the Division of Translational Biomedical Informatics at Duke University. He is also affiliated with Duke AI Health and is a member of the Duke Cancer Institute. His research and academic work focus on biostatistics and bioinformatics, particularly in the context of translational biomedical informatics. Prior to his current position, he was an NIH K99/R00 Postdoctoral Fellow, during which he developed a program to assess and treat distress in glaucoma patients using an automated electronic health record (EHR)-derived artificial intelligence algorithm. This fellowship was funded by the National Eye Institute. Dr. Berchuck earned his Ph.D. in Biostatistics from the University of North Carolina-Chapel Hill. Following his doctoral studies, he joined Duke University as a Postdoctoral Associate in the Department of Statistical Science, where he was a Forge Scholar and a member of the Visual Performance Lab at the Duke Eye Center.

Research topics

• Computer Science
• Medicine
• Artificial Intelligence
• Ophthalmology
• Internal medicine
• Optometry
• Biomedical engineering
• Gerontology
• Environmental health
• Demography

Selected publications

• Artificial Intelligence in Triaging Patient Questions: An Evaluation of a Large Language Model for Distal Radius Fractures

  Journal of the American Academy of Orthopaedic Surgeons · 2025-08-27

  article

  INTRODUCTION: Large language models (LLMs) are promising tools for clinical decision support but require thorough validation to ensure safety and reliability. This study assessed a knowledge and intelligence messaging interface (KIMI; RevelAi Health), an LLM enhanced with retrieval-augmented generation configured with American Academy of Orthopaedic Surgeons guidelines for distal radius fracture management and a persistent system-prompt layer. The goal was to evaluate KIMI's efficacy in acuity triaging and generating appropriate patient-facing responses for distal radius fracture management. METHODS: We analyzed KIMI-generated responses to 100 simulated patient queries. Four clinical experts independently assessed responses for guideline concordance, safety, clarity, and acuity. Probabilities for adequate scoring in all domains were modeled. Bayesian mixed-effects logistic regression and ordered logistic regression models were used for binary and ordinal scoring outcomes, respectively, to account for repeated measures and within-reviewer correlations. RESULTS: Reviewer evaluations of KIMI responses demonstrated high performance across safety and quality domains. Posterior average probability of responses being rated as safe was 94.2% (95% credible interval [CI]: 91.2 to 96.9), as concordant was 88.7% (95% CI: 85.0 to 92.0), and as clear was 93.7% (95% CI: 90.5 to 96.5). Posterior average probability of exact agreement between reviewer-assigned and LLM-assigned acuity levels was 62.9% (95% CI: 58.0 to 67.7). Surgical queries were associated with slightly higher safety ratings (95.4% versus 91.3%) and acuity agreement (63.9% versus 60.6%) than nonsurgical queries. Query category markedly influenced acuity agreement. LLM-assigned acuity was markedly associated with reviewer-assigned acuity across all models even when adjusting for both query type and category (odds ratio = 2.66; 95% CI: 1.81 to 3.83). DISCUSSION: KIMI generated responses that were generally safe, clinically concordant, and clearly communicated. These findings support the feasibility of deploying enhanced LLMs for asynchronous patient engagement in low-to-moderate risk care coordination settings.

  PublisherDOI

• Patient Attitudes toward Distress Screening and Referral in Glaucoma Care

  Ophthalmology Glaucoma · 2025-09-23

  articleOpen accessSenior authorCorresponding

  A mixed-methods study of 300 glaucoma patients found strong support for screening and referral for psychological distress. Greater interest among those with elevated distress or higher intraocular pressure highlights an opportunity to integrate psychosocial support into glaucoma care.

  PublisherDOI

• Validation of Existing Comorbidity Models and Development of a New Transplant-Specific Index

  American Journal of Transplantation · 2025-08-01

  article
  PublisherDOI

• Discovering Spatial Patterns of Readmission Risk Using a Bayesian Competing Risks Model with Spatially Varying Coefficients

  ArXiv.org · 2025-11-25

  preprintOpen accessSenior author

  Time-to-event models are commonly used to study associations between risk factors and disease outcomes in the setting of electronic health records (EHR). In recent years, focus has intensified on social determinants of health, highlighting the need for methods that account for patients' locations. We propose a Bayesian approach for introducing point-referenced spatial effects into a competing risks proportional hazards model. Our method leverages Gaussian process (GP) priors for spatially varying intercept and slope. To improve computational efficiency under a large number of spatial locations, we implemented a Hilbert space low-rank approximation of the GP. We modeled the baseline hazard curves as piecewise constant, and introduced a novel multiplicative gamma process prior to induce shrinkage and smoothing. A loss-based clustering method was then used on the spatial random effects to identify high-risk regions. We demonstrate the utility of this method through simulation and a real-world analysis of EHR data from Duke Hospital to study readmission risk of elderly patients with upper extremity fractures. Our results showed that the proposed method improved inference efficiency and provided valuable insights for downstream policy decisions.

  PublisherOA PDFDOI

• Development of Common Data Elements for Organ Transplantation

  JAMA Network Open · 2025-04-28 · 2 citations

  articleOpen access

  This cohort study examines the validity of an electronic health record data model for organ transplantation.

  PublisherOA PDFDOI

• Scalable Bayesian Inference for Generalized Linear Mixed Models via Stochastic Gradient MCMC

  arXiv (Cornell University) · 2024-03-05

  preprintOpen access1st authorCorresponding

  The generalized linear mixed model (GLMM) is widely used for analyzing correlated data, particularly in large-scale biomedical and social science applications. Scalable Bayesian inference for GLMMs is challenging because the marginal likelihood is intractable and conventional Markov chain Monte Carlo (MCMC) methods become computationally prohibitive as the number of subjects grows. We develop a stochastic gradient MCMC (SGMCMC) algorithm tailored to GLMMs that enables accurate posterior inference in the large-sample regime. Our approach uses Fisher's identity to construct an unbiased Monte Carlo estimator of the gradient of the marginal log-likelihood, making SGMCMC feasible when direct gradient computation is impossible. We analyze the additional variability introduced by both minibatching and gradient approximation, and derive a post-hoc covariance correction that yields properly calibrated posterior uncertainty. Through simulations, we show that the proposed method provides accurate posterior means and variances, outperforming existing approaches, including control variate methods, in large-$n$ settings. We further demonstrate the method's practical utility in an analysis of electronic health records data, where accounting for variance inflation materially changes scientific conclusions.

  PublisherOA PDFDOI

• Defining the learning curve for robotic pancreaticoduodenectomy for a single surgeon following experience with laparoscopic pancreaticoduodenectomy

  Journal of Robotic Surgery · 2024-03-16 · 8 citations

  article
  PublisherDOI

• Use of Predictive Models to Determine Transplant Eligibility

  Current Transplantation Reports · 2024-10-08 · 1 citations

  articleOpen access1st authorCorresponding
  PublisherOA PDFDOI

• Predictive Value of Early Autism Detection Models Based on Electronic Health Record Data Collected Before Age 1 Year

  JAMA Network Open · 2023-02-02 · 23 citations

  articleOpen access

  Importance: Autism detection early in childhood is critical to ensure that autistic children and their families have access to early behavioral support. Early correlates of autism documented in electronic health records (EHRs) during routine care could allow passive, predictive model-based monitoring to improve the accuracy of early detection. Objective: To quantify the predictive value of early autism detection models based on EHR data collected before age 1 year. Design, Setting, and Participants: This retrospective diagnostic study used EHR data from children seen within the Duke University Health System before age 30 days between January 2006 and December 2020. These data were used to train and evaluate L2-regularized Cox proportional hazards models predicting later autism diagnosis based on data collected from birth up to the time of prediction (ages 30-360 days). Statistical analyses were performed between August 1, 2020, and April 1, 2022. Main Outcomes and Measures: Prediction performance was quantified in terms of sensitivity, specificity, and positive predictive value (PPV) at clinically relevant model operating thresholds. Results: Data from 45 080 children, including 924 (1.5%) meeting autism criteria, were included in this study. Model-based autism detection at age 30 days achieved 45.5% sensitivity and 23.0% PPV at 90.0% specificity. Detection by age 360 days achieved 59.8% sensitivity and 17.6% PPV at 81.5% specificity and 38.8% sensitivity and 31.0% PPV at 94.3% specificity. Conclusions and Relevance: In this diagnostic study of an autism screening test, EHR-based autism detection achieved clinically meaningful accuracy by age 30 days, improving by age 1 year. This automated approach could be integrated with caregiver surveys to improve the accuracy of early autism screening.

  PublisherOA PDFDOI

• Intraocular Pressure and Rates of Macular Thinning in Glaucoma

  Ophthalmology Glaucoma · 2023-04-08 · 4 citations

  articleOpen access
  PublisherOA PDFDOI

Frequent coauthors

• Felipe A. Medeiros

  University of Miami

  43 shared

• Alessandro A. Jammal

  University of Miami

  38 shared

• Eduardo B. Mariottoni

  Universidade Federal de São Paulo

  23 shared

• Sayan Mukherjee

  11 shared

• Tais Estrela

  Boston Children's Hospital

  10 shared

• Atalie C. Thompson

  9 shared

• Swarup S. Swaminathan

  University of Miami

  9 shared

• Joshua L. Warren

  Yale University

  7 shared