Large Language Models to Identify Social Determinants of Health in Electronic Health RecordsMarco Guevara, Shan Chen, Spencer Thomas et al. · harvard
Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free text in EHRs, where they are most commonly documented, and explored the role of synthetic clinical text for improving the extraction of these scarcely documented, yet extremely valuable, clinical data. 800 patient notes were annotated for SDoH categories, and several transformer-based models were evaluated. The study also experimented with synthetic data generation and assessed for algorithmic bias. Our best-performing models were fine-tuned Flan-T5 XL (macro-F1 0.71) for any SDoH, and Flan-T5 XXL (macro-F1 0.70). The benefit of augmenting fine-tuning with synthetic data varied across model architecture and size, with smaller Flan-T5 models (base and large) showing the greatest improvements in performance (delta F1 +0.12 to +0.23). Model performance was similar on the in-hospital system dataset but worse on the MIMIC-III dataset. Our best-performing fine-tuned models outperformed zero- and few-shot performance of ChatGPT-family models for both tasks. These fine-tuned models were less likely than ChatGPT to change their prediction when race/ethnicity and gender descriptors were added to the text, suggesting less algorithmic bias (p<0.05). At the patient-level, our models identified 93.8% of patients with adverse SDoH, while ICD-10 codes captured 2.0%. Our method can effectively extracted SDoH information from clinic notes, performing better compare to GPT zero- and few-shot settings. These models could enhance real-world evidence on SDoH and aid in identifying patients needing social support.
Deep learning-based detection of intravenous contrast in computed tomography scansZezhong Ye, Jack M. Qian, Ahmed Hosny et al.
Purpose: Identifying intravenous (IV) contrast use within CT scans is a key component of data curation for model development and testing. Currently, IV contrast is poorly documented in imaging metadata and necessitates manual correction and annotation by clinician experts, presenting a major barrier to imaging analyses and algorithm deployment. We sought to develop and validate a convolutional neural network (CNN)-based deep learning (DL) platform to identify IV contrast within CT scans. Methods: For model development and evaluation, we used independent datasets of CT scans of head, neck (HN) and lung cancer patients, totaling 133,480 axial 2D scan slices from 1,979 CT scans manually annotated for contrast presence by clinical experts. Five different DL models were adopted and trained in HN training datasets for slice-level contrast detection. Model performances were evaluated on a hold-out set and on an independent validation set from another institution. DL models was then fine-tuned on chest CT data and externally validated on a separate chest CT dataset. Results: Initial DICOM metadata tags for IV contrast were missing or erroneous in 1,496 scans (75.6%). The EfficientNetB4-based model showed the best overall detection performance. For HN scans, AUC was 0.996 in the internal validation set (n = 216) and 1.0 in the external validation set (n = 595). The fine-tuned model on chest CTs yielded an AUC: 1.0 for the internal validation set (n = 53), and AUC: 0.980 for the external validation set (n = 402). Conclusion: The DL model could accurately detect IV contrast in both HN and chest CT scans with near-perfect performance.