Natural Language Processing models accurately identified and classified abdominal aortic aneurysm repairs from unstructured electronic health records, achieving up to 0.99 accuracy and 1.00 AUC.
Observational (n=4,870)
No
NLP models, particularly Bio-clinicalBERT, can accurately identify and classify AAA repair cases from unstructured EHRs, demonstrating potential for automating patient identification in vascular registries.
Patient identification for national registries often relies upon clinician recognition of cases or retrospective searches using potentially inaccurate clinical codes, leading to incomplete data capture and inefficiencies. Natural Language Processing (NLP) offers a promising solution by automating analysis of electronic health records (EHRs). This study aimed to develop NLP models for identifying and classifying abdominal aortic aneurysm (AAA) repairs from unstructured EHRs, demonstrating a proof-of-concept for automated patient identification in registries like the National Vascular Registry. Using the MIMIC-IV-Note dataset, a multi-tiered approach was developed to identify vascular patients (Task 1), AAA repairs (Task 2), and classify repairs as primary or revision (Task 3). Four NLP models were trained and evaluated using 4870 annotated records: scispaCy, BERT-base, Bio-clinicalBERT, and a scispaCy/Bio-clinicalBERT ensemble. Models were compared using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The scispaCy model demonstrated the fastest training (2 min/epoch) and inference times (2.87 samples/sec). For Task 1, scispaCy and ensemble models achieved the highest accuracy (0.97). In Task 2, all models performed exceptionally well, with ensemble, scispaCy, and Bio-clinicalBERT models achieving 0.99 accuracy and 1.00 AUC. For Task 3, Bio-clinicalBERT and the ensemble model achieved an AUC of 1.00, with Bio-clinicalBERT displaying the best overall accuracy (0.98). This study demonstrates that NLP models can accurately identify and classify AAA repair cases from unstructured EHRs, suggesting significant potential for automating patient identification in vascular surgery and other medical registries, reducing administra.
Thompson et al. (Mon,) conducted a observational in Abdominal aortic aneurysm (AAA) repairs (n=4,870). Natural Language Processing (NLP) models vs. Comparison between different NLP models was evaluated on Accuracy and Area Under the Curve (AUC) for identifying and classifying AAA repairs. Natural Language Processing models accurately identified and classified abdominal aortic aneurysm repairs from unstructured electronic health records, achieving up to 0.99 accuracy and 1.00 AUC.