Key result
The addition of NLP-derived social risk factors to clinical variables did not significantly improve model performance for predicting 30-day readmission following acute myocardial infarction.
Why the study?
Social risk factors affect rehospitalization rates but are challenging to incorporate into prediction models, and it was unknown whether integrating them via natural language processing and machine learning improves 30-day post-AMI readmission prediction.
Does the addition of NLP-derived social risk factors to clinical machine learning models improve the prediction of 30-day readmission in patients with acute myocardial infarction?
Cohort (n=10,189)
Yes
Does the addition of NLP-derived social risk factors to clinical machine learning models improve the prediction of 30-day readmission in patients with acute myocardial infarction?
The extraction of social risk factors using natural language processing from clinical notes did not significantly improve the prediction of 30-day readmission following acute myocardial infarction.
NLP social factors add no value to post-MI readmission models; leaves open their role in other outcomes or refined extraction methods.
Background Social risk factors influence rehospitalization rates yet are challenging to incorporate into prediction models. Integration of social risk factors using natural language processing (NLP) and machine learning could improve risk prediction of 30-day readmission following an acute myocardial infarction. Methods and Results Patients were enrolled into derivation and validation cohorts. The derivation cohort included inpatient discharges from Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary diagnosis of acute myocardial infarction, who were discharged alive, and not transferred from another facility. The validation cohort included patients from Dartmouth-Hitchcock Health Center between April 2, 2011, and December 31, 2016, meeting the same eligibility criteria described above. Data from both sites were linked to Centers for Medicare & Medicaid Services administrative data to supplement 30-day hospital readmissions. Clinical notes from each cohort were extracted, and an NLP model was deployed, counting mentions of 7 social risk factors. Five machine learning models were run using clinical and NLP-derived variables. Model discrimination and calibration were assessed, and receiver operating characteristic comparison analyses were performed. The 30-day rehospitalization rates among the derivation (n=6165) and validation (n=4024) cohorts were 15.1% (n=934) and 10.2% (n=412), respectively. The derivation models demonstrated no statistical improvement in model performance with the addition of the selected NLP-derived social risk factors. Conclusions Social risk factors extracted using NLP did not significantly improve 30-day readmission prediction among hospitalized patients with acute myocardial infarction. Alternative methods are needed to capture social risk factors.
No takes yet. Share an insight, caveat, or question.
A 2022 study conducted a cohort in Acute myocardial infarction (n=10,189). NLP-derived social risk factors vs. Clinical variables alone was evaluated on 30-day hospital readmission. The addition of NLP-derived social risk factors to clinical variables did not significantly improve model performance for predicting 30-day readmission following acute myocardial infarction.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: