Vivek A. Rudrapatna
YOU?
Author Swipe
View article: Large Language Models can Identify the Presence of MASH and Extract VCTE Measurements from Unstructured Documentation
Large Language Models can Identify the Presence of MASH and Extract VCTE Measurements from Unstructured Documentation Open
Introduction Metabolic dysfunction-associated steatohepatitis (MASH) is a leading cause of cirrhosis. Vibration Controlled Transient Elastography (VCTE) measurements are often captured in text-based reports and not readily accessible for c…
View article: Risk factors for immune checkpoint inhibitor colitis: a retrospective multi-center cohort study using electronic health records
Risk factors for immune checkpoint inhibitor colitis: a retrospective multi-center cohort study using electronic health records Open
Background Immune checkpoint inhibitors (ICIs) are effective for many cancers but often cause immune-related adverse events, particularly gastrointestinal (GI) complications such as colitis. Identifying risk factors for ICI colitis (CIC) c…
View article: Learning the Phenotype of Medical Hallucinations
Learning the Phenotype of Medical Hallucinations Open
The clinical deployment of powerful general-purpose large language models (LLMs) is fundamentally limited by their propensity for unreliable generation ("hallucination"), posing a significant safety risk in high-stakes domains. Here, we in…
View article: Monitoring atopic dermatitis using mobile-app based photography and surveys
Monitoring atopic dermatitis using mobile-app based photography and surveys Open
Overall, these findings show that SkinTracker is both reliable and feasible for monitoring atopic dermatitis disease activity remotely.
View article: Quantifying barriers to diabetic eye screening: a two-center study at the University of California
Quantifying barriers to diabetic eye screening: a two-center study at the University of California Open
Objective:This study aimed to evaluate the diabetic eye disease screening continuum at two academic centers and identify its barriers.Research Design and Methods:We analyzed health records from UCSF and UCI to identify primary care patient…
View article: Quantifying Barriers to Diabetic Eye Screening: A Two-Center Study at the University of California
Quantifying Barriers to Diabetic Eye Screening: A Two-Center Study at the University of California Open
OBJECTIVE This study aimed to evaluate the diabetic eye disease screening continuum at two academic centers and identify its barriers. RESEARCH DESIGN AND METHODS We analyzed health records from the University of California, San Francisco,…
View article: Optimising large language models for clinical information extraction: a benchmarking study in the context of ulcerative colitis research
Optimising large language models for clinical information extraction: a benchmarking study in the context of ulcerative colitis research Open
Objective Closed-source large language models (LLMs) like generative pre-trained transformer 4o (GPT-4o) have shown promise for clinical information extraction but are potentially limited by cost, data security concerns and inflexibility. …
View article: MetaMind: A Multi-Agent Transformer-Driven Framework for Automated Network Meta-Analyses
MetaMind: A Multi-Agent Transformer-Driven Framework for Automated Network Meta-Analyses Open
Background Network meta-analysis (NMA) enables simultaneous comparison of multiple interventions by integrating direct and indirect evidence from randomized controlled trials and observational studies, but traditional workflows require ext…
View article: Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK
Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK Open
Large language models (LLMs) show promise in healthcare, but hallucinations remain a major barrier to clinical use. We present CHECK, a continuous-learning framework that integrates structured clinical databases with a classifier grounded …
View article: From trial data to personalized medicine: a validated framework with an application to Crohn’s disease
From trial data to personalized medicine: a validated framework with an application to Crohn’s disease Open
Clinical practice is currently guided by studies that average over patient outcomes. This may not be the best approach, as different patients may have different treatment responses. Here we extend a method for simulating clinical trials to…
View article: Extracting TNFi Switching Reasons and Trajectories From Real-World Data Using Large Language Models
Extracting TNFi Switching Reasons and Trajectories From Real-World Data Using Large Language Models Open
Importance Tumor necrosis factor inhibitors (TNFi) are widely used for auto-immune conditions. Despite their efficacy, many patients switch TNFis due to lack of efficacy, cost-related reasons, or adverse events. Understanding why switches …
View article: TheBlueScrubs-v1, a comprehensive curated medical dataset derived from the internet
TheBlueScrubs-v1, a comprehensive curated medical dataset derived from the internet Open
The need for robust and diverse data sets to train clinical large language models (cLLMs) is critical given that currently available public repositories often prove too limited in size or scope for comprehensive medical use. While resource…
View article: A Comparative Environmental Impact Analysis of Screening Tests for Colorectal Cancer
A Comparative Environmental Impact Analysis of Screening Tests for Colorectal Cancer Open
BACKGROUND Healthcare is a major contributor to global greenhouse gas emissions. Colorectal cancer (CRC) screening is one of the most widely used healthcare services in the US, indicated for approximately 134 million adults. Recommended sc…
View article: Risk Prediction in Patients With Metabolic Dysfunction–Associated Steatohepatitis Using Natural Language Processing
Risk Prediction in Patients With Metabolic Dysfunction–Associated Steatohepatitis Using Natural Language Processing Open
We described a cohort of real-world MASH patients using a new NLP algorithm and found several potential predictors of progression to all-cause mortality, cirrhosis, and liver transplantation. The use of NLP to characterize these patients c…
View article: Recommendations for recognizing and diagnosing Acute Hepatic Porphyria in atypical patient populations
Recommendations for recognizing and diagnosing Acute Hepatic Porphyria in atypical patient populations Open
View article: Optimal strategies for adapting open-source large language models for clinical information extraction: a benchmarking study in the context of ulcerative colitis research
Optimal strategies for adapting open-source large language models for clinical information extraction: a benchmarking study in the context of ulcerative colitis research Open
Background Closed-source large language models (LLMs) like GPT-4o have shown promise for clinical information extraction but are potentially limited by cost, data security concerns, and inflexibility. Open-source models have emerged as an …
View article: Large Language Models Outperform Traditional Natural Language Processing Methods in Extracting Patient-Reported Outcomes in Inflammatory Bowel Disease
Large Language Models Outperform Traditional Natural Language Processing Methods in Extracting Patient-Reported Outcomes in Inflammatory Bowel Disease Open
View article: Large language models outperform traditional natural language processing methods in extracting patient-reported outcomes in IBD
Large language models outperform traditional natural language processing methods in extracting patient-reported outcomes in IBD Open
Background and Aims Patient-reported outcomes (PROs) are vital in assessing disease activity and treatment outcomes in inflammatory bowel disease (IBD). However, manual extraction of these PROs from the free-text of clinical notes is burde…
View article: Reducing diagnostic delays in acute hepatic porphyria using health records data and machine learning
Reducing diagnostic delays in acute hepatic porphyria using health records data and machine learning Open
Background Acute hepatic porphyria (AHP) is a group of rare but treatable conditions associated with diagnostic delays of 15 years on average. The advent of electronic health records (EHR) data and machine learning (ML) may improve the tim…
View article: #955 Real-world validation of the mortality box score to predict death following kidney transplantation: an international study
#955 Real-world validation of the mortality box score to predict death following kidney transplantation: an international study Open
Background and Aims The mortality box score (mBox) is a validated risk prediction score developed by the Paris Transplant Group (NCT03474003), aimed at predicting mortality after kidney transplantation (KT) using data available at the time…
View article: Zero-Shot Prompting is the Most Accurate and Scalable Strategy for Abstracting the Mayo Endoscopic Subscore from Colonoscopy Reports Using GPT-4
Zero-Shot Prompting is the Most Accurate and Scalable Strategy for Abstracting the Mayo Endoscopic Subscore from Colonoscopy Reports Using GPT-4 Open
Structured Abstract Introduction Large-language models can help extract information from clinical notes, making them potentially useful for research in ulcerative colitis. However, it remains unclear if these models will scale well in prac…
View article: Real‐world effectiveness of ustekinumab and vedolizumab in TNF‐exposed pediatric patients with ulcerative colitis
Real‐world effectiveness of ustekinumab and vedolizumab in TNF‐exposed pediatric patients with ulcerative colitis Open
Objectives Vedolizumab (VDZ) and ustekinumab (UST) are second‐line treatments in pediatric patients with ulcerative colitis (UC) refractory to antitumor necrosis factor (anti‐TNF) therapy. Pediatric studies comparing the effectiveness of t…
View article: Algorithmic Identification of Treatment‐Emergent Adverse Events From Clinical Notes Using Large Language Models: A Pilot Study in Inflammatory Bowel Disease
Algorithmic Identification of Treatment‐Emergent Adverse Events From Clinical Notes Using Large Language Models: A Pilot Study in Inflammatory Bowel Disease Open
Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large language models (LLMs)…
View article: Characterisation of digital therapeutic clinical trials: a systematic review with natural language processing
Characterisation of digital therapeutic clinical trials: a systematic review with natural language processing Open
Digital therapeutics (DTx) are a somewhat novel class of US Food and Drug Administration-regulated software that help patients prevent, manage, or treat disease. Here, we use natural language processing to characterise registered DTx clini…
View article: Personalizing treatment selection in Crohn’s disease: a meta-analysis of individual participant data from fifteen randomized controlled trials
Personalizing treatment selection in Crohn’s disease: a meta-analysis of individual participant data from fifteen randomized controlled trials Open
BACKGROUND Meta-analyses have found anti-TNF drugs to be the best treatment, on average, for Crohn’s disease. We performed a subgroup analysis to determine if it is possible to achieve more efficacious outcomes by individualizing treatment…
View article: Sequential regression and simulation: a method for estimating causal effects from heterogeneous clinical trials without a common control group
Sequential regression and simulation: a method for estimating causal effects from heterogeneous clinical trials without a common control group Open
Background The advent of clinical trial data sharing platforms has created opportunities for making new discoveries and answering important questions using already collected data. However, existing methods for meta-analyzing these data req…
View article: Algorithmic identification of treatment-emergent adverse events from clinical notes using large language models: a pilot study in inflammatory bowel disease
Algorithmic identification of treatment-emergent adverse events from clinical notes using large language models: a pilot study in inflammatory bowel disease Open
Background and Aims Outpatient clinical notes are a rich source of information regarding drug safety. However, data in these notes are currently underutilized for pharmacovigilance due to methodological limitations in text mining. Large la…
View article: Reducing diagnostic delays in Acute Hepatic Porphyria using electronic health records data and machine learning: a multicenter development and validation study
Reducing diagnostic delays in Acute Hepatic Porphyria using electronic health records data and machine learning: a multicenter development and validation study Open
Importance Acute Hepatic Porphyria (AHP) is a group of rare but treatable conditions associated with diagnostic delays of fifteen years on average. The advent of electronic health records (EHR) data and machine learning (ML) may improve th…
View article: ALK Inhibitor Treatment Patterns and Outcomes in Real-World Patients with ALK-Positive Non-Small-Cell Lung Cancer: A Retrospective Cohort Study
ALK Inhibitor Treatment Patterns and Outcomes in Real-World Patients with ALK-Positive Non-Small-Cell Lung Cancer: A Retrospective Cohort Study Open
View article: Assessing the Impact of COVID-19 on IBD Outcomes Among Vulnerable Patient Populations in a Large Metropolitan Center
Assessing the Impact of COVID-19 on IBD Outcomes Among Vulnerable Patient Populations in a Large Metropolitan Center Open
BACKGROUND With the onset of COVID-19, there were rapid changes in healthcare delivery as remote access became the norm. The aim of this study was to determine the impact of changes in healthcare delivery during the COVID-19 pandemic on pa…