Arjun K. Manrai
YOU?
Author Swipe
View article: Advancing Medical Artificial Intelligence Using a Century of Cases
Advancing Medical Artificial Intelligence Using a Century of Cases Open
BACKGROUND: For over a century, the New England Journal of Medicine Clinicopathological Conferences (CPCs) have tested the reasoning of expert physicians and, recently, artificial intelligence (AI). However, prior AI evaluations have focus…
View article: The architecture of exposome-phenome associations
The architecture of exposome-phenome associations Open
Non-genetic exposures including nutrients, lifestyle factors, consumables, and pollutants substantially contribute to phenotypic variation. Most studies assess only a few exposures or phenotypes, yielding fragmented exposome-phenome relati…
View article: Comparison of Frontier Open-Source and Proprietary Large Language Models for Complex Diagnoses
Comparison of Frontier Open-Source and Proprietary Large Language Models for Complex Diagnoses Open
This comparative effectiveness research assesses the performance of newer open-source large language models (LLMs) with that of closed-source proprietary large LLMs.
View article: Discordance between a deep learning model and clinical-grade variant pathogenicity classification in a rare disease cohort
Discordance between a deep learning model and clinical-grade variant pathogenicity classification in a rare disease cohort Open
Genetic testing is essential for diagnosing and managing clinical conditions, particularly rare Mendelian diseases. Although efforts to identify rare phenotype-associated variants have focused on protein-truncating variants, interpreting m…
View article: Tackling algorithmic bias and promoting transparency in health datasets: the STANDING Together consensus recommendations
Tackling algorithmic bias and promoting transparency in health datasets: the STANDING Together consensus recommendations Open
View article: Superhuman performance of a large language model on the reasoning tasks of a physician
Superhuman performance of a large language model on the reasoning tasks of a physician Open
A seminal paper published by Ledley and Lusted in 1959 introduced complex clinical diagnostic reasoning cases as the gold standard for the evaluation of expert medical computing systems, a standard that has held ever since. Here, we report…
View article: Biobank-scale exposome-wide risk factors in CAD and T2D: observational, predictive, and potentially causative evidence
Biobank-scale exposome-wide risk factors in CAD and T2D: observational, predictive, and potentially causative evidence Open
Cardiovascular disease and diabetes are intricately related and influenced by factors within the “exposome”. The exposome refers to a broad assessment of cumulative environmental exposures, including physical-chemical, biological, behavior…
View article: Projected Changes in Statin and Antihypertensive Therapy Eligibility With the AHA PREVENT Cardiovascular Risk Equations
Projected Changes in Statin and Antihypertensive Therapy Eligibility With the AHA PREVENT Cardiovascular Risk Equations Open
Importance Since 2013, the American College of Cardiology (ACC) and American Heart Association (AHA) have recommended the pooled cohort equations (PCEs) for estimating the 10-year risk of atherosclerotic cardiovascular disease (ASCVD). An …
View article: Discordance between a deep learning model and clinical-grade variant pathogenicity classification in a rare disease cohort
Discordance between a deep learning model and clinical-grade variant pathogenicity classification in a rare disease cohort Open
Genetic testing has become an essential component in the diagnosis and management of a wide range of clinical conditions, from cancer to developmental disorders, especially in rare Mendelian diseases. Efforts to identify rare phenotype-ass…
View article: Implications of Race Adjustment in Lung-Function Equations
Implications of Race Adjustment in Lung-Function Equations Open
The use of race-based and race-neutral equations generated similarly accurate predictions of respiratory outcomes but assigned different disease classifications, occupational eligibility, and disability compensation for millions of persons…
View article: Heterogeneity in elevated glucose and A1C as predictors of the prediabetes to diabetes transition: Framingham Heart Study, Multi-Ethnic Study on Atherosclerosis, Jackson Heart Study, and Atherosclerosis Risk In Communities
Heterogeneity in elevated glucose and A1C as predictors of the prediabetes to diabetes transition: Framingham Heart Study, Multi-Ethnic Study on Atherosclerosis, Jackson Heart Study, and Atherosclerosis Risk In Communities Open
Introduction There are a number of glycemic definitions for prediabetes; however, the heterogeneity in diabetes transition rates from prediabetes across different glycemic definitions in major US cohorts has been unexplored. We estimate th…
View article: Assessing the genetic contribution of cumulative behavioral factors associated with longitudinal type 2 diabetes risk highlights adiposity and the brain-metabolic axis
Assessing the genetic contribution of cumulative behavioral factors associated with longitudinal type 2 diabetes risk highlights adiposity and the brain-metabolic axis Open
While genetic factors, behavior, and environmental exposures form a complex web of interrelated associations in type 2 diabetes (T2D), their interaction is poorly understood. Here, using data from ∼500K participants of the UK Biobank, we i…
View article: Decoding the exposome: data science methodologies and implications in exposome-wide association studies (ExWASs)
Decoding the exposome: data science methodologies and implications in exposome-wide association studies (ExWASs) Open
This paper explores the exposome concept and its role in elucidating the interplay between environmental exposures and human health. We introduce two key concepts critical for exposomics research. Firstly, we discuss the joint impact of ge…
View article: Prediction and stratification of longitudinal risk for chronic obstructive pulmonary disease across smoking behaviors
Prediction and stratification of longitudinal risk for chronic obstructive pulmonary disease across smoking behaviors Open
Smoking is the leading risk factor for chronic obstructive pulmonary disease (COPD) worldwide, yet many people who never smoke develop COPD. We perform a longitudinal analysis of COPD in the UK Biobank to derive and validate the Socioecono…
View article: Why We Support and Encourage the Use of Large Language Models in <i>NEJM AI</i> Submissions
Why We Support and Encourage the Use of Large Language Models in <i>NEJM AI</i> Submissions Open
Large language models (LLMs) promise to revolutionize many aspects of the creation and dissemination of scientific knowledge; however, their use in scientific writing remains controversial, because of concerns about authorship, originality…
View article: Artificial Intelligence vs Clinician Performance in Estimating Probabilities of Diagnoses Before and After Testing
Artificial Intelligence vs Clinician Performance in Estimating Probabilities of Diagnoses Before and After Testing Open
This diagnostic study compares the performance of artificial intelligence (AI) with that of human clinicians in estimating the probability of diagnoses before and after testing.
View article: Multimodal Foundation Models Exploit Text to Make Medical Image Predictions
Multimodal Foundation Models Exploit Text to Make Medical Image Predictions Open
Multimodal foundation models have shown compelling but conflicting performance in medical image interpretation. However, the mechanisms by which these models integrate and prioritize different data modalities, including images and text, re…
View article: Publisher Correction: Scientific discovery in the age of artificial intelligence
Publisher Correction: Scientific discovery in the age of artificial intelligence Open
View article: Augmenting medical image classifiers with synthetic data from latent diffusion models
Augmenting medical image classifiers with synthetic data from latent diffusion models Open
While hundreds of artificial intelligence (AI) algorithms are now approved or cleared by the US Food and Drugs Administration (FDA), many studies have shown inconsistent generalization or latent bias, particularly for underrepresented popu…
View article: Prediction and stratification of longitudinal risk for chronic obstructive pulmonary disease across smoking behaviors
Prediction and stratification of longitudinal risk for chronic obstructive pulmonary disease across smoking behaviors Open
Smoking is the leading risk factor for chronic obstructive pulmonary disease (COPD) worldwide, yet many people who never smoke develop COPD. We hypothesize that considering other socioeconomic and environmental factors can better predict a…
View article: Artificial Intelligence in Medicine
Artificial Intelligence in Medicine Open
View article: Improving dermatology classifiers across populations using images generated by large diffusion models
Improving dermatology classifiers across populations using images generated by large diffusion models Open
Dermatological classification algorithms developed without sufficiently diverse training data may generalize poorly across populations. While intentional data collection and annotation offer the best means for improving representation, new…
View article: National Projections for Clinical Implications of Race-Free Creatinine-Based GFR Estimating Equations
National Projections for Clinical Implications of Race-Free Creatinine-Based GFR Estimating Equations Open
Significance Statement A national task force convened by the NKF-ASN recently recommended a new race-free creatinine equation for calculating eGFR. Although this equation is expected to be widely adopted, its broad effect on recommended cl…
View article: Leveraging vibration of effects analysis for robust discovery in observational biomedical data science
Leveraging vibration of effects analysis for robust discovery in observational biomedical data science Open
Hypothesis generation in observational, biomedical data science often starts with computing an association or identifying the statistical relationship between a dependent and an independent variable. However, the outcome of this process de…
View article: Foundational Considerations for Artificial Intelligence Using Ophthalmic Images
Foundational Considerations for Artificial Intelligence Using Ophthalmic Images Open
View article: Race-Free Equations for eGFR: Comparing Effects on CKD Classification
Race-Free Equations for eGFR: Comparing Effects on CKD Classification Open
Medical centers nationwide are considering race-free equations to improve the reporting of eGFR.[1][1] Numerous alternatives[2][2] have been proposed and implemented—including removal of the coefficient for Black race—with substantial impl…
View article: Data Mining Approaches to Reference Interval Studies
Data Mining Approaches to Reference Interval Studies Open
View article: Empowering clinical research in a decentralized world
Empowering clinical research in a decentralized world Open
View article: PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training Open
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train model…
View article: PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency\n Training
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency\n Training Open
Unsupervised domain adaptation is a promising technique for semantic\nsegmentation and other computer vision tasks for which large-scale data\nannotation is costly and time-consuming. In semantic segmentation, it is\nattractive to train mo…