Jonathan H. Chen
YOU?
Author Swipe
View article: Operationalizing machine-assisted translation in healthcare
Operationalizing machine-assisted translation in healthcare Open
Over 25 million U.S. patients with a non-English language preference face unsafe care because discharge instructions and other materials are rarely translated in time. Advances in translation assisted by large language models can close thi…
View article: Optimizing large language models for detecting symptoms of depression/anxiety in chronic diseases patient communications
Optimizing large language models for detecting symptoms of depression/anxiety in chronic diseases patient communications Open
Patients with diabetes are at increased risk of comorbid depression or anxiety, complicating their management. This study evaluated the performance of large language models (LLMs) in detecting these symptoms from secure patient messages. W…
View article: Fine-Tuning Methods for Large Language Models in Clinical Medicine by Supervised Fine-Tuning and Direct Preference Optimization: Comparative Evaluation
Fine-Tuning Methods for Large Language Models in Clinical Medicine by Supervised Fine-Tuning and Direct Preference Optimization: Comparative Evaluation Open
Background Large language model (LLM) fine-tuning is the process of adjusting out-of-the-box model weights using a dataset of interest. Fine-tuning can be a powerful technique to improve model performance in fields like medicine, where LLM…
View article: MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries
MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries Open
Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with …
View article: Quantization-aware matrix factorization for low bit rate image compression
Quantization-aware matrix factorization for low bit rate image compression Open
View article: Predicting treatment retention in medication for opioid use disorder: a machine learning approach using NLP and LLM-derived clinical features
Predicting treatment retention in medication for opioid use disorder: a machine learning approach using NLP and LLM-derived clinical features Open
Objective Building upon our previous work on predicting treatment retention in medications for opioid use disorder, we aimed to improve 6-month retention prediction in buprenorphine-naloxone (BUP-NAL) therapy by incorporating features deri…
View article: Real time machine learning prediction of next generation sequencing test results in live clinical settings
Real time machine learning prediction of next generation sequencing test results in live clinical settings Open
View article: Leveraging Large Language Models and Patient Portal Messages for Early Identification of Depression
Leveraging Large Language Models and Patient Portal Messages for Early Identification of Depression Open
Importance Large language model (LLM)-assisted early warning system may help overcome existing barriers to timely depression diagnosis in patients with cardiovascular disease (CVD). This novel application of LLMs to screen patient messages…
View article: MedAgentBench: A Virtual EHR Environment to Benchmark Medical LLM Agents
MedAgentBench: A Virtual EHR Environment to Benchmark Medical LLM Agents Open
View article: Contrast-induced acute kidney injury and nephrogenic systemic fibrosis in children
Contrast-induced acute kidney injury and nephrogenic systemic fibrosis in children Open
Intravascular contrast media plays an important role in improving tissue and vascular characterisation in diagnostic imaging and image-guided intervention. Iodinated contrast media are commonly used in imaging modalities which utilise ioni…
View article: Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs
Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs Open
The Antibiotic Resistance Microbiology Dataset (ARMD) is a de-identified resource derived from electronic health records (EHR) that facilitates research in antimicrobial resistance (AMR). ARMD encompasses big data from adult patients colle…
View article: A typology of physician input approaches to using AI chatbots for clinical decision-making: a mixed methods study
A typology of physician input approaches to using AI chatbots for clinical decision-making: a mixed methods study Open
Background: Large language model (LLM) chatbots demonstrate high degrees of accuracy, yet recent studies found that physicians using these same chatbots may score no better to worse on clinical reasoning tests compared to the chatbot perfo…
View article: From Tool to Teammate: A Randomized Controlled Trial of Clinician-AI Collaborative Workflows for Diagnosis
From Tool to Teammate: A Randomized Controlled Trial of Clinician-AI Collaborative Workflows for Diagnosis Open
Early studies of large language models (LLMs) in clinical settings have largely treated artificial intelligence (AI) as a tool rather than an active collaborator. As LLMs now demonstrate expert-level diagnostic performance, the focus shift…
View article: MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks
MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks Open
While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. We introduce MedHELM, an extensible evaluation …
View article: Discrete-Event Simulation Modeling Framework for Cancer Interventions and Population Health in R (DESCIPHR): An Open-Source Pipeline
Discrete-Event Simulation Modeling Framework for Cancer Interventions and Population Health in R (DESCIPHR): An Open-Source Pipeline Open
Simulation models inform health policy decisions by integrating data from multiple sources and forecasting outcomes when there is a lack of comprehensive evidence from empirical studies. Such models have long supported health policy for ca…
View article: Artificial intelligence tools in supporting healthcare professionals for tailored patient care
Artificial intelligence tools in supporting healthcare professionals for tailored patient care Open
Artificial intelligence (AI) tools to support clinicians in providing patient-centered care can contribute to patient empowerment and care efficiency. We aimed to draft potential AI tools for tailored patient support corresponding to patie…
View article: Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs
Antibiotic Resistance Microbiology Dataset (ARMD): A Resource for Antimicrobial Resistance from EHRs Open
The Antibiotic Resistance Microbiology Dataset (ARMD) is a de-identified resource derived from electronic health records (EHR) that facilitates research in antimicrobial resistance (AMR). ARMD encompasses big data from adult patients colle…
View article: Red teaming ChatGPT in medicine to yield real-world insights on model behavior
Red teaming ChatGPT in medicine to yield real-world insights on model behavior Open
View article: Physician clinical decision modification and bias assessment in a randomized controlled trial of AI assistance
Physician clinical decision modification and bias assessment in a randomized controlled trial of AI assistance Open
Background Artificial intelligence assistance in clinical decision making shows promise, but concerns exist about potential exacerbation of demographic biases in healthcare. This study aims to evaluate how physician clinical decisions and …
View article: The improved prognosis of <i>FLT3</i>-internal tandem duplication but not tyrosine kinase domain mutations in acute myeloid leukemia in the era of targeted therapy: a realworld study using large-scale electronic health record data
The improved prognosis of <i>FLT3</i>-internal tandem duplication but not tyrosine kinase domain mutations in acute myeloid leukemia in the era of targeted therapy: a realworld study using large-scale electronic health record data Open
Not available.
View article: Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation
Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation Open
Accurate classification of clinical text often requires fine-tuning pre-trained language models, a process that is costly and time-consuming due to the need for high-quality data and expert annotators. Synthetic data generation offers an a…
View article: Clinical entity augmented retrieval for clinical information extraction
Clinical entity augmented retrieval for clinical information extraction Open
Large language models (LLMs) with retrieval-augmented generation (RAG) have improved information extraction over previous methods, yet their reliance on embeddings often leads to inefficient retrieval. We introduce CLinical Entity Augmente…
View article: Toward expert-level medical question answering with large language models
Toward expert-level medical question answering with large language models Open
View article: powerROC: An Interactive Web Tool for Sample Size Calculation in Assessing Models' Discriminative Abilities
powerROC: An Interactive Web Tool for Sample Size Calculation in Assessing Models' Discriminative Abilities Open
Rigorous external validation is crucial for assessing the generalizability of prediction models, particularly by evaluating their discrimination (AUROC) on new data. This often involves comparing a new model's AUROC to that of an establish…
View article: Constrained Design of a Binary Instrument in a Partially Linear Model
Constrained Design of a Binary Instrument in a Partially Linear Model Open
We study the question of how best to assign an encouragement in a randomized encouragement study. In our setting, units arrive with covariates, receive a nudge toward treatment or control, acquire one of those statuses in a way that need n…
View article: Feasibility of Automated Precharting using GPT-4 in New Specialty Referrals.
Feasibility of Automated Precharting using GPT-4 in New Specialty Referrals. Open
This study evaluates the feasibility of using GPT-4 to automate precharting for specialty referrals, focusing on new patients referred to an otolaryngology clinic for nasal congestion. We describe the design decisions and strategies tested…
View article: Establishing best practices in large language model research: an application to repeat prompting
Establishing best practices in large language model research: an application to repeat prompting Open
Objectives We aimed to demonstrate the importance of establishing best practices in large language model research, using repeat prompting as an illustrative example. Materials and Methods Using data from a prior study investigating potenti…
View article: Learning from the EHR to implement AI in healthcare
Learning from the EHR to implement AI in healthcare Open
View article: Recommendations for Clinicians, Technologists, and Healthcare Organizations on the Use of Generative Artificial Intelligence in Medicine: A Position Statement from the Society of General Internal Medicine
Recommendations for Clinicians, Technologists, and Healthcare Organizations on the Use of Generative Artificial Intelligence in Medicine: A Position Statement from the Society of General Internal Medicine Open
View article: Large Language Model Influence on Diagnostic Reasoning
Large Language Model Influence on Diagnostic Reasoning Open
Importance Large language models (LLMs) have shown promise in their performance on both multiple-choice and open-ended medical reasoning examinations, but it remains unknown whether the use of such tools improves physician diagnostic reaso…