Scholars@Duke
Matthew M. Engelhard

Matthew M. Engelhard

Assistant Professor of Biostatistics & Bioinformatics
Biostatistics & Bioinformatics, Division of Translational Biomedical
2424 Erwin Rd, Durham, NC 27705

Scholarly Works - Journal articles

Building a Global Research Network for Fair, Accountable, Interpretable, and Responsible AI in Emergency Care: Protocol for a FAIR-EC Study.

Journal article JMIR Res Protoc · August 4, 2026 BACKGROUND: The current landscape of emergency care (EC) is marked by high demand, leading to issues such as emergency department boarding, overcrowding, and subsequent delays that impact the quality and safety of patient care. Integrating data science int ... Full text Link to item Cite

Understanding end-user contexts and identifying design preferences of an artificial intelligence-based clinical decision support tool for early autism detection.

Journal article JAMIA Open · August 2026 OBJECTIVES: Building on innovations for autism detection-where artificial intelligence (AI)-based models monitor clinical data within electronic health records-this study evaluates the context for clinical decision support (CDS) deployment and identifies d ... Full text Link to item Cite

Multinational validation of the PREVENT and SCORE2 cardiovascular risk equations across 6.4 million individuals.

Journal article Nat Med · July 2026 The American Heart Association's PREVENT equations estimate risk of total cardiovascular disease (CVD), atherosclerotic cardiovascular disease (ASCVD) and heart failure (HF) to guide lipid-lowering and blood pressure-lowering therapy in people ages 30-79 y ... Full text Link to item Cite

Using clinical notes to identify children with speech-language delay and understand differences in diagnostic timing.

Journal article JAMIA Open · June 2026 OBJECTIVE: Speech-language delay (SLD) is a developmental condition often identified by pediatricians. While early intervention is recommended, it is common for pediatricians to take a "watch and wait" approach. We sought to assess whether there is discord ... Full text Link to item Cite

Can Large Language Models Predict Patient Treatment Choices? A Discrete Choice Experiment Framework.

Journal article Value Health · May 5, 2026 OBJECTIVES: This study evaluated the viability of large language models, specifically GPT-4, in predicting patient health preference-consistent choices using a discrete choice experiment framework. METHODS: Synthetic data were generated from real discrete ... Full text Link to item Cite

Early attention deficit hyperactivity disorder prediction from longitudinal electronic health records

Journal article Nature Mental Health · May 1, 2026 Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental condition that can negatively impact long-term outcomes for individuals. Early diagnosis is critical, yet demographic and clinical disparities can delay detection. Using electro ... Full text Cite

Performance of PREVENT Cardiovascular Risk in Electronic Health Record-Based Clinical Practice.

Journal article JAMA Netw Open · April 1, 2026 IMPORTANCE: In 2023, the American Heart Association Cardiovascular-Kidney-Metabolic Scientific Advisory Group introduced the Predicting Risk of Cardiovascular Disease Events (PREVENT) equations, a race-free, sex-specific model for cardiovascular disease (C ... Full text Link to item Cite

Can artificial intelligence pass the test? Evaluating chatbot scores on pediatric gastroenterology board-style questions.

Journal article JPGN Rep · February 2026 OBJECTIVES: The American Academy of Pediatrics (AAP) Pediatrics Review and Education Program (PREP)® Gastroenterology (GI) Self-Assessments help pediatric gastroenterologists and trainees prepare for subspecialty board exams by providing peer-reviewed ques ... Full text Link to item Cite

Discrete Time Neural Network Models to Address Time-Varying Predictor Importance: An Illustration in Predicting Mortality Over Different Time Horizons.

Journal article IEEE J Biomed Health Inform · January 2026 Clinical predictive models (CPMs) are crucial for forecasting patient outcomes using available electronic health record (EHR) data. Traditional time-to-event (TTE) models, like the Cox proportional hazards model, assume that hazard ratios remain constant o ... Full text Link to item Cite

Machine Learning Risk Prediction for Treated Retinopathy of Prematurity in Infants.

Journal article Neonatology · 2026 INTRODUCTION: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness. However, current screening guidelines may be overly broad, necessitating better models to detect high-risk infants. METHODS: From a multicenter cohort of 103,701 infa ... Full text Link to item Cite

Multimodal Training to Unimodal Deployment: Leveraging Unstructured Data During Training to Optimize Structured Data Only Deployment.

Journal article AMIA Jt Summits Transl Sci Proc · 2026 Unstructured Electronic Health Record (EHR) data-such as clinical notes-contain clinical contextual observations that are not directly reflected in structured data fields. This additional information can substantially improve model learning. However, due t ... Link to item Cite

Using mixture cure models to address algorithmic bias in diagnostic timing: autism as a test case.

Journal article JAMIA Open · December 2025 OBJECTIVES: To address algorithmic bias in clinical prediction models related to the timing of diagnosis, we evaluated the efficacy of mixture cure models that integrate time-to-event and binary classification frameworks to predict diagnoses. MATERIALS AND ... Full text Link to item Cite

FairPOT: Balancing AUC Performance and Fairness with Proportional Optimal Transport.

Journal article Proc AAAI ACM Conf AI Ethics Soc · October 2025 Fairness metrics utilizing the area under the receiver operator characteristic curve (AUC) have gained increasing attention in high-stakes domains such as healthcare, finance, and criminal justice. In these domains, fairness is often evaluated over risk sc ... Full text Open Access Link to item Cite

Development and Validation of a Predictive Model for Maternal Cardiovascular Morbidity Events in Patients With Hypertensive Disorders of Pregnancy.

Journal article Anesth Analg · August 1, 2025 BACKGROUND: Hypertensive disorders of pregnancy (HDP) are a major contributor to maternal morbidity, mortality, and accelerated cardiovascular (CV) disease. Comorbid conditions are likely important predictors of CV risk in pregnant people. Currently, there ... Full text Link to item Cite

Impact of Medical Conditions and Area Deprivation on Fundraising Success in Online Crowdfunding: Cross-Sectional Study.

Journal article J Med Internet Res · July 29, 2025 BACKGROUND: Web-based crowdfunding is commonly used to defray medical expenses, but it is not fully known which factors determine fundraising success. Previous studies have usually focused on a single disease category at a time or a small number of mutuall ... Full text Link to item Cite

Effects of initial nicotine exposure on cognition and nicotine reinforcement among non-smoking young adults with and without attention deficit hyperactivity disorder.

Journal article J Psychopharmacol · July 2025 BACKGROUND: People with attention deficit hyperactivity disorder (ADHD) use nicotine products at higher rates than those without. Greater initial sensitivity to nicotine's cognitive effects may explain this association. AIMS: This study examined associatio ... Full text Link to item Cite

IRIS: Interpretable Retrieval-Augmented Classification for Long Interspersed Document Sequences.

Journal article Proc Conf Assoc Comput Linguist Meet · July 2025 Transformer-based models have achieved state-of-the-art performance in document classification but struggle with long-text processing due to the quadratic computational complexity in the self-attention module. Existing solutions, such as sparse attention, ... Open Access Link to item Cite

Prediction of mental health risk in adolescents.

Journal article Nat Med · June 2025 Prospective prediction of mental health risk in adolescence can facilitate early preventive interventions. Here, using psychosocial questionnaires and neuroimaging measures from over 11,000 children in the Adolescent Brain and Cognitive Development Study, ... Full text Link to item Cite

Exploring trade-offs in equitable stroke risk prediction with parity-constrained and race-free models.

Journal article Artif Intell Med · June 2025 A recent analysis of common stroke risk prediction models showed that performance differs between Black and White subgroups, and that applying standard machine learning methods does not reduce these disparities. There have been calls in the clinical litera ... Full text Link to item Cite

Limitations of Binary Classification for Long-Horizon Diagnosis Prediction and Advantages of a Discrete-Time Time-to-Event Approach: Empirical Analysis.

Journal article JMIR AI · March 27, 2025 BACKGROUND: A major challenge in using electronic health records (EHR) is the inconsistency of patient follow-up, resulting in right-censored outcomes. This becomes particularly problematic in long-horizon event predictions, such as autism and attention-de ... Full text Link to item Cite

Improving Artificial Intelligence-based Microbial Keratitis Screening Tools Constrained by Limited Data Using Synthetic Generation of Slit-Lamp Photos.

Journal article Ophthalmol Sci · 2025 OBJECTIVE: We developed a novel slit-lamp photography (SLP) generative adversarial network (GAN) model using limited data to supplement and improve the performance of an artificial intelligence (AI)-based microbial keratitis (MK) screening model. DESIGN: C ... Full text Link to item Cite

A conditional multi-label model to improve prediction of a rare outcome: An illustration predicting autism diagnosis.

Journal article J Biomed Inform · September 2024 OBJECTIVE: This study aimed to develop a novel approach using routinely collected electronic health records (EHRs) data to improve the prediction of a rare event. We illustrated this using an example of improving early prediction of an autism diagnosis, gi ... Full text Link to item Cite

Incorporating informatively collected laboratory data from EHR in clinical prediction models.

Journal article BMC Med Inform Decis Mak · July 24, 2024 BACKGROUND: Electronic Health Records (EHR) are widely used to develop clinical prediction models (CPMs). However, one of the challenges is that there is often a degree of informative missing data. For example, laboratory measures are typically taken when ... Full text Open Access Link to item Cite

Maternal Morbidity According to Mode of Delivery Among Pregnant Patients With Pulmonary Hypertension.

Journal article Anesth Analg · May 1, 2024 BACKGROUND: Patients with pulmonary hypertension have a high risk of maternal morbidity and mortality. It is unknown if a trial of labor carries a lower risk of morbidity in these patients compared to a planned cesarean delivery. The objective of this stud ... Full text Link to item Cite

Adaptive Discretization for Event PredicTion (ADEPT).

Journal article Proc Mach Learn Res · May 2024 Recently developed survival analysis methods improve upon existing approaches by predicting the probability of event occurrence in each of a number pre-specified (discrete) time intervals. By avoiding placing strong parametric assumptions on the event dens ... Link to item Cite

RobOCTNet: Robotics and Deep Learning for Referable Posterior Segment Pathology Detection in an Emergency Department Population.

Journal article Transl Vis Sci Technol · March 1, 2024 PURPOSE: To evaluate the diagnostic performance of a robotically aligned optical coherence tomography (RAOCT) system coupled with a deep learning model in detecting referable posterior segment pathology in OCT images of emergency department patients. METHO ... Full text Link to item Cite

Sex differences in the age of childhood autism diagnosis and the impact of co-occurring conditions.

Journal article Autism Res · December 2023 Sex differences in the age of autism diagnosis during childhood have been documented consistently but remain poorly understood. In this study, we used electronic health records data from a diverse, academic medical center to quantify differences in the age ... Full text Link to item Cite

Severe Maternal Morbidity According to Mode of Delivery Among Pregnant Patients With Cardiomyopathies.

Journal article JACC Heart Fail · December 2023 BACKGROUND: Women with cardiomyopathies are at risk for pregnancy complications. The optimal mode of delivery in these patients is guided by expert opinion and limited small studies. OBJECTIVES: The objective of this study is to examine the association of ... Full text Link to item Cite

Enhancing early autism prediction based on electronic records using clinical narratives.

Journal article J Biomed Inform · August 2023 Recent work has shown that predictive models can be applied to structured electronic health record (EHR) data to stratify autism likelihood from an early age (<1 year). Integrating clinical narratives (or notes) with structured data has been shown to impro ... Full text Link to item Cite

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

Journal article JAMA Netw Open · February 1, 2023 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 all ... Full text Link to item Cite

Predictive Accuracy of Stroke Risk Prediction Models Across Black and White Race, Sex, and Age Groups.

Journal article JAMA · January 24, 2023 IMPORTANCE: Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention st ... Full text Link to item Cite

A Disease Identification Algorithm for Medical Crowdfunding Campaigns: Validation Study.

Journal article J Med Internet Res · June 21, 2022 BACKGROUND: Web-based crowdfunding has become a popular method to raise money for medical expenses, and there is growing research interest in this topic. However, crowdfunding data are largely composed of unstructured text, thereby posing many challenges f ... Full text Link to item Cite

Regularity and Timing of Sleep Patterns and Behavioral Health Among Adolescents.

Journal article J Dev Behav Pediatr · May 1, 2022 OBJECTIVE: Sleep is vital to supporting adolescent behavioral health and functioning; however, sleep disturbances remain under-recognized and undertreated in many health care settings. One barrier is the complexity of sleep, which makes it difficult for pr ... Full text Link to item Cite

Impact of daily caffeine intake and timing on electroencephalogram-measured sleep in adolescents.

Journal article J Clin Sleep Med · March 1, 2022 STUDY OBJECTIVES: Caffeine use is ubiquitous among adolescents and may be harmful to sleep, with downstream implications for health and development. Research has been limited by self-reported and/or aggregated measures of sleep and caffeine collected at a ... Full text Link to item Cite

Disentangling Whether from When in a Neural Mixture Cure Model for Failure Time Data.

Journal article Proc Mach Learn Res · March 2022 The mixture cure model allows failure probability to be estimated separately from failure timing in settings wherein failure never occurs in a subset of the population. In this paper, we draw on insights from representation learning and causal inference to ... Link to item Cite

Correction

Journal article Journal of the American Academy of Child & Adolescent Psychiatry · March 2022 Full text Cite

Prediction of Smoking Risk From Repeated Sampling of Environmental Images: Model Validation.

Journal article J Med Internet Res · November 1, 2021 BACKGROUND: Viewing their habitual smoking environments increases smokers' craving and smoking behaviors in laboratory settings. A deep learning approach can differentiate between habitual smoking versus nonsmoking environments, suggesting that it may be p ... Full text Link to item Cite

Patterns of Health Services Use Before Age 1 in Children Later Diagnosed With ADHD.

Journal article J Atten Disord · October 2021 Background: Children with ADHD have 2 to 3 times increased health care utilization and annual costs once diagnosed, but little is known about utilization patterns early in life, prior to diagnosis. Quantifying early health services use among children later ... Full text Link to item Cite

Identifying neural signatures of tobacco retail outlet exposure: Preliminary validation of a "community neuroscience" paradigm.

Journal article Addict Biol · September 2021 An extensive epidemiological literature indicates that increased exposure to tobacco retail outlets (TROs) places never smokers at greater risk for smoking uptake and current smokers at greater risk for increased consumption and smoking relapse. Yet resear ... Full text Link to item Cite

Prediction of Smoking Risk From Repeated Sampling of Environmental Images: Model Validation (Preprint)

Journal article · February 11, 2021 BACKGROUNDViewing their habitual smoking environments increases smokers’ craving and smoking behaviors in laboratory settings. A deep learning approach can differentiate between habitual ... Full text Cite

Review of Popularity and Quality Standards of Opioid-Related Smartphone Apps.

Journal article Curr Addict Rep · December 2020 PURPOSE OF REVIEW: Opioid misuse, addiction, and related harm is a global crisis that affects public health and social and economic welfare. Many of the strategies being used to combat the opioid crisis could benefit from improved access and dissemination, ... Full text Link to item Cite

Health system utilization before age 1 among children later diagnosed with autism or ADHD.

Journal article Sci Rep · October 19, 2020 Children with autism spectrum disorder (ASD) or attention deficit hyperactivity disorder (ADHD) have 2-3 times increased healthcare utilization and annual costs once diagnosed, but little is known about their utilization patterns early in life. Quantifying ... Full text Link to item Cite

Feasibility and Acceptability of Wearable Sleep Electroencephalogram Device Use in Adolescents: Observational Study.

Journal article JMIR Mhealth Uhealth · October 1, 2020 BACKGROUND: Adolescence is an important life stage for the development of healthy behaviors, which have a long-lasting impact on health across the lifespan. Sleep undergoes significant changes during adolescence and is linked to physical and psychiatric he ... Full text Link to item Cite

Feasibility and Acceptability of Wearable Sleep Electroencephalogram Device Use in Adolescents: Observational Study (Preprint)

Journal article · May 25, 2020 BACKGROUNDAdolescence is an important life stage for the development of healthy behaviors, which have a long-lasting impact on health across the lifespan. Sleep undergoes significant chan ... Full text Cite

Neural Conditional Event Time Models

Journal article · April 3, 2020 Event time models predict occurrence times of an event of interest based on known features. Recent work has demonstrated that neural networks achieve state-of-the-art event time predictions in a variety of settings. However, standard event time models supp ... Link to item Cite

Author Correction: Validation of the Sleep Regularity Index in Older Adults and Associations with Cardiometabolic Risk.

Journal article Sci Rep · February 14, 2020 An amendment to this paper has been published and can be accessed via a link at the top of the paper. ... Full text Link to item Cite

Sleep/Wake Regularity Associated with Default Mode Network Structure among Healthy Adolescents and Young Adults.

Journal article Scientific reports · January 2020 Sleep deprivation and disorders are linked to reduced DMN connectivity. Less is known about how naturalistic sleep patterns - specifically sleep irregularity - relate to the DMN, particularly among adolescents and young adults. Additionally, no studies hav ... Full text Cite

Digital envirotyping: quantifying environmental determinants of health and behavior.

Journal article NPJ Digit Med · 2020 Digital phenotyping efforts have used wearable devices to connect a rich array of physiologic data to health outcomes or behaviors of interest. The environmental context surrounding these phenomena has received less attention, yet is critically needed to u ... Full text Link to item Cite

The Many Channels of Screen Media Technology in ADHD: a Paradigm for Quantifying Distinct Risks and Potential Benefits.

Journal article Curr Psychiatry Rep · August 13, 2019 PURPOSE OF REVIEW: Individuals with attention-deficit hyperactivity disorder (ADHD) may be unusually sensitive to screen media technology (SMT), from television to mobile devices. Although an association between ADHD and SMT use has been confirmed, its imp ... Full text Link to item Cite

Identifying Smoking Environments From Images of Daily Life With Deep Learning.

Journal article JAMA Netw Open · August 2, 2019 IMPORTANCE: Environments associated with smoking increase a smoker's craving to smoke and may provoke lapses during a quit attempt. Identifying smoking risk environments from images of a smoker's daily life provides a basis for environment-based interventi ... Full text Link to item Cite

Structure Sensitivity of Acetylene Semi-Hydrogenation on Pt Single Atoms and Subnanometer Clusters

Journal article ACS Catalysis · January 1, 2019 Oxide-supported Pt-group single atoms and clusters in the subnanometer size regime maximize the metal utilization and have shown extraordinary catalytic properties for many reactions including selective hydrogenation. Establishing relations between the met ... Full text Cite

Validation of the Sleep Regularity Index in Older Adults and Associations with Cardiometabolic Risk.

Journal article Sci Rep · September 21, 2018 Sleep disturbances, including insufficient sleep duration and circadian misalignment, confer risk for cardiometabolic disease. Less is known about the association between the regularity of sleep/wake schedules and cardiometabolic risk. This study evaluated ... Full text Open Access Link to item Cite

Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model.

Journal article Proc Mach Learn Res · August 2018 Featured Publication Health risks from cigarette smoking - the leading cause of preventable death in the United States - can be substantially reduced by quitting. Although most smokers are motivated to quit, the majority of quit attempts fail. A number of studies have explored ... Link to item Cite

Real-world walking in multiple sclerosis: Separating capacity from behavior.

Journal article Gait Posture · January 2018 Featured Publication BACKGROUND: Habitual physical activity (HPA) measurement addresses the impact of MS on real-world walking, yet its interpretation is confounded by the competing influences of MS-associated walking capacity and physical activity behaviors. OBJECTIVE: To dev ... Full text Link to item Cite

Understanding the Physiological Significance of Four Inertial Gait Features in Multiple Sclerosis.

Journal article IEEE J Biomed Health Inform · January 2018 Gait impairment in multiple sclerosis (MS) can result from muscle weakness, physical fatigue, lack of coordination, and other symptoms. Walking speed, as measured by a number of clinician-administered walking tests, is the primary measure of gait impairmen ... Full text Link to item Cite

Optimising mHealth helpdesk responsiveness in South Africa: towards automated message triage.

Journal article BMJ Glob Health · 2018 In South Africa, a national-level helpdesk was established in August 2014 as a social accountability mechanism for improving governance, allowing recipients of public sector services to send complaints, compliments and questions directly to a team of Natio ... Full text Open Access Link to item Cite

Unpacking the performance of a mobile health information messaging program for mothers (MomConnect) in South Africa: evidence on program reach and messaging exposure.

Journal article BMJ Glob Health · 2018 Despite calls to address broader evidence gaps in linking digital technologies to outcome and impact level health indicators, limited attention has been paid to measuring processes pertaining to the performance of programs. In this paper, we assess the pro ... Full text Link to item Cite

Remotely engaged: Lessons from remote monitoring in multiple sclerosis.

Journal article International journal of medical informatics · April 2017 Featured Publication ObjectivesEvaluate web-based patient-reported outcome (wbPRO) collection in MS subjects in terms of feasibility, reliability, adherence, and subject-perceived benefits; and quantify the impact of MS-related symptoms on perceived well-being.Met ... Full text Cite

The e-MSWS-12: improving the multiple sclerosis walking scale using item response theory.

Journal article Qual Life Res · December 2016 BACKGROUND: The Multiple Sclerosis Walking Scale (MSWS-12) is the predominant patient-reported measure of multiple sclerosis (MS) -elated walking ability, yet it had not been analyzed using item response theory (IRT), the emerging standard for patient-repo ... Full text Link to item Cite

Fatigue and fluid hydration status in multiple sclerosis: A hypothesis.

Journal article Mult Scler · October 2016 Featured Publication BACKGROUND: Fatigue is a prevalent and functionally disabling symptom for individuals living with multiple sclerosis (MS) which is poorly understood and multifactorial in etiology. Bladder dysfunction is another common MS symptom which limits social engage ... Full text Link to item Cite

Quantifying six-minute walk induced gait deterioration with inertial sensors in multiple sclerosis subjects.

Journal article Gait Posture · September 2016 Featured Publication BACKGROUND: The six-minute walk (6MW) is a common walking outcome in multiple sclerosis (MS) thought to measure fatigability in addition to overall walking disability. However, direct evidence of 6MW induced gait deterioration is limited by the difficulty ... Full text Link to item Cite

Novel experience induces persistent sleep-dependent plasticity in the cortex but not in the hippocampus.

Journal article Front Neurosci · November 2007 Episodic and spatial memories engage the hippocampus during acquisition but migrate to the cerebral cortex over time. We have recently proposed that the interplay between slow-wave (SWS) and rapid eye movement (REM) sleep propagates recent synaptic changes ... Full text Link to item Cite