High-performing Multi-task Model of Urinary Tract Dilation (UTD) Classification for Neonatal Ultrasound Reports Through Natural Language Processing

Abstract

Objective: The urinary tract dilation (UTD) classification system provides objective assessment relevant to hydronephrosis management for children. However, the lack of uniform language regarding UTD in radiology reports leads to significant difficulty in both clinical management and research. We seek to develop a unified multi-task/multi-class model that can effectively extract UTD components and classifications from early postnatal ultrasound (US) reports. Methods: Radiology records from our institution were reviewed to identify infants aged 0-90 days undergoing early ultrasound for antenatal UTD. The report and images were reviewed by the study team to create the ground truth of UTD classification and components (primary outcome). Bio_ClinicalBERT, a variant of the Bidirectional Encoder Representations from Transformers (BERT) model, was used as the embedding layers of the classification model. The model was fine-tuned with 11 linear classification layers. All but the last BERT layer were frozen during the fine-tuning process. The model performance was evaluated with five-fold cross-validation with an 80:20 train-test ratio. Results: 2460 early (0-90 days) US reports were included. The five-fold cross-validated model performance is satisfactory (Weighted F1 > 0.9 for all UTD components). We report the weighted F1 scores, accuracies, and standard deviations for all 11 tasks and their average performance. Conclusions: By applying deep state-of-the-art NLP neural networks, we developed a high-performing, efficient, and scalable solution to extract UTD components from unstructured ultrasound reports using one single multi-task model. This can potentially help standardize and facilitate large-scale computer vision research for pediatric hydronephrosis. Key Words: machine learning, efficiency, ambulatory care, forecasting