ArticleNPJ digital medicine2022
Cohort design and natural language processing to reduce bias in electronic health records research.
Article in NPJ digital medicine, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 53 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
53 citing papers in PubMed, 1 synthesis or guideline pooled it, 78 citations in OpenAlex.
- Statin Use and Liver Cancer Risk: A Meta-Epidemiological Study of Retrospective Cohort Studies by the Types of Constructed Cohort.Asian Pacific journal of cancer prevention : APJCP · 2024Pooled it
- Polygenic Risk Based Detection and Treatment of Subclinical Coronary Atherosclerosis in the PROACT Clinical Trials.Journal of the American College of Cardiology · 2026Trial
- ECG-Based Deep Learning to Predict Incident Atrial Fibrillation Burden.Journal of the American Heart Association · 2026Article
- Impaired left atrial strain is associated with new-onset atrial fibrillation and adverse clinical outcomes in primary care patients.Heart rhythm O2 · 2026Article
- Cardiovascular and Cardiometabolic Outcomes in Adults with Fetal Alcohol Spectrum Disorders: A Retrospective Cohort Study.medRxiv : the preprint server for health sciences · 2026Article
- Systematic Review of Large Language Models and Natural Language Processing in Stroke Care: Applications, Challenges, and Future Directions.Stroke (Hoboken, N.J.) · 2026Review
- Predicting Recurrence and Outcomes After Stressor-Associated Atrial Fibrillation Using ECG-Based Deep Learning.Journal of the American Heart Association · 2026Article
- Artificial Intelligence-Enabled ECG Analysis to Predict Incident Heart Failure.Circulation. Heart failure · 2026Article
- Cardiovascular-Kidney-Metabolic Medication Eligibility Across National Survey, Community-Based, and Ambulatory Healthcare Samples.JAMA cardiology · 2026Article
- AI in the Hot Seat: Head-to-Head Comparison of Large Language Models and Cardiologists in Emergency Scenarios.Medical sciences (Basel, Switzerland) · 2026Article
- A Deep Learning Model to Identify Mitral Valve Prolapse From the Echocardiogram.JACC. Cardiovascular imaging · 2026Article
- Artificial intelligence-enabled analysis of handheld single-lead electrocardiograms to predict incident atrial fibrillation: an analysis of the VITAL-AF randomized trial.NPJ digital medicine · 2025Article
- Contemporary Burden of Cardiovascular Disease in Pregnancy: Insights From a Real-World Pregnancy Electronic Health Record Cohort.Circulation · 2025Article
- On the use of natural language processing to implement the target trial framework using unstructured data from the electronic health record.Global epidemiology · 2025Article
- Flexible imputation toolkit for electronic health records.Scientific reports · 2025Article
- Remdesivir associated with reduced mortality in hospitalized COVID-19 patients: treatment effectiveness using real-world data and natural language processing.BMC infectious diseases · 2025Article
- Identification of Patients With Congestive Heart Failure From the Electronic Health Records of Two Hospitals: Retrospective Study.JMIR medical informatics · 2025Article
- Improving Phenotyping of Patients With Immune-Mediated Inflammatory Diseases Through Automated Processing of Discharge Summaries: Multicenter Cohort Study.JMIR medical informatics · 2025Article
- Natural language processing of electronic medical records identifies cardioprotective agents for anthracycline induced cardiotoxicity.Scientific reports · 2025Observational
- A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram.NPJ digital medicine · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
29 authors at 5 institutions in 2 countries.
Funding
Abstract
Electronic health record (EHR) datasets are statistically powerful but are subject to ascertainment bias and missingness. Using the Mass General Brigham multi-institutional EHR, we approximated a community-based cohort by sampling patients receiving longitudinal primary care between 2001-2018 (Community Care Cohort Project [C3PO], n = 520,868). We utilized natural language processing (NLP) to recover vital signs from unstructured notes. We assessed the validity of C3PO by deploying established risk models for myocardial infarction/stroke and atrial fibrillation. We then compared C3PO to Convenience Samples including all individuals from the same EHR with complete data, but without a longitudinal primary care requirement. NLP reduced the missingness of vital signs by 31%. NLP-recovered vital signs were highly correlated with values derived from structured fields (Pearson r range 0.95-0.99). Atrial fibrillation and myocardial infarction/stroke incidence were lower and risk models were better calibrated in C3PO as opposed to the Convenience Samples (calibration error range for myocardial infarction/stroke: 0.012-0.030 in C3PO vs. 0.028-0.046 in Convenience Samples; calibration error for atrial fibrillation 0.028 in C3PO vs. 0.036 in Convenience Samples). Sampling patients receiving regular primary care and using NLP to recover missing data may reduce bias and maximize generalizability of EHR research.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.