Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Scalable information extraction from free text electronic health records using large language models.
BMC Med Res Methodol
January 2025
Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, 1620 Tremont Street, Suite 3030-R, Boston, MA, 02120, USA.
Article Synopsis
- A study examined the efficacy of open-source large language models (LLMs) in extracting social determinants of health (SDoH) data from free-text clinical notes in electronic health records (EHRs).
- The methodology involved analyzing free-text notes from a sample of 200 patients, applying LLMs and comparing their performance with a baseline pattern-matching model, achieving high inter-rater reliability among human reviewers.
- Results showed LLMs significantly outperformed traditional methods, with one model achieving up to 40% higher accuracy, indicating that LLMs could enhance research and address health disparities if further refined and trained for specific applications.
Isolated subsegmental pulmonary embolism identification based on international classification of diseases (ICD)-10 codes and imaging reports.
Thromb Res
January 2025
Thrombosis Research Group, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA; YNHH/Yale Center for Outcomes Research and Evaluation (CORE), New Haven, CT, USA; Division of Cardiovascular Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. Electronic address:
Background: Isolated subsegmental pulmonary embolism (issPE) is a commonly encountered diagnosis. Although the International Classification of Diseases (ICD)-10 codes are used for research, their validity for identifying issPE is unknown. Moreover, issPE diagnosis is challenging, and the findings from radiology reports may conflict with those from expert radiologists.
View Article and Find Full Text PDFEvaluating Meta-Learners to Analyze Treatment Heterogeneity in Survival Data: Application to Electronic Health Records of Pediatric Asthma Care in COVID-19 Pandemic.
Stat Med
February 2025
Department of Biostatistics and Health Data Science, University of Pittsburgh, Pittsburgh, Pennsylvania.
An important aspect of precision medicine focuses on characterizing diverse responses to treatment due to unique patient characteristics, also known as heterogeneous treatment effects (HTE) or individualized treatment effects (ITE), and identifying beneficial subgroups with enhanced treatment effects. Estimating HTE with right-censored data in observational studies remains challenging. In this paper, we propose a pseudo-ITE-based framework for analyzing HTE in survival data, which includes a group of meta-learners for estimating HTE, a variable importance metric for identifying predictive variables to HTE, and a data-adaptive procedure to select subgroups with enhanced treatment effects.
View Article and Find Full Text PDFMachine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis.
Eur Heart J Digit Health
January 2025
School of Life Course & Population Sciences, King's College London, SE1 1UL London, UK.
Cardiovascular disease (CVD) remains a major cause of mortality in the UK, prompting the need for improved risk predictive models for primary prevention. Machine learning (ML) models utilizing electronic health records (EHRs) offer potential enhancements over traditional risk scores like QRISK3 and ASCVD. To systematically evaluate and compare the efficacy of ML models against conventional CVD risk prediction algorithms using EHR data for medium to long-term (5-10 years) CVD risk prediction.
View Article and Find Full Text PDFHigh-dimensional multiple imputation (HDMI) for partially observed confounders including natural language processing-derived auxiliary covariates.
Am J Epidemiol
January 2025
Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
Multiple imputation (MI) models can be improved with auxiliary covariates (AC), but their performance in high-dimensional data remains unclear. We aimed to develop and compare high-dimensional MI (HDMI) methods using structured and natural language processing (NLP)-derived AC in studies with partially observed confounders. We conducted a plasmode simulation with acute kidney injury as outcome and simulated 100 cohorts with a null treatment effect, incorporating creatinine labs, atrial fibrillation (AFib), and other investigator-derived confounders in the outcome generation.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!