Purpose: Subdural hematoma (SDH) is the most common form of traumatic intracranial hemorrhage, and radiographic characteristics of SDH are predictive of complications and patient outcomes. We created a natural language processing (NLP) algorithm to extract structured data from cranial computed tomography (CT) scan reports for patients with SDH.
Methods: CT scan reports from patients with SDH were collected from a single center. All reports were based on cranial CT scan interpretations by board-certified attending radiologists. Reports were then coded by a pair of physicians for four variables: number of SDH, size of midline shift, thickness of largest SDH, and side of largest SDH. Inter-rater reliability was assessed. The annotated reports were divided into training (80%) and test (20%) datasets. Relevant information was extracted from text using a pattern-matching approach, due to the lack of a mention-level gold-standard corpus. Then, the NLP pipeline components were integrated using the Apache Unstructured Information Management Architecture. Output performance was measured as algorithm accuracy compared to the data coded by the two ED physicians.
Results: A total of 643 scans were extracted. The NLP algorithm accuracy was high: 0.84 for side of largest SDH, 0.88 for thickness of largest SDH, and 0.92 for size of midline shift.
Conclusion: A NLP algorithm can structure key data from non-contrast head CT reports with high accuracy. The NLP is a potential tool to detect important radiographic findings from electronic health records, and, potentially, add decision support capabilities.
Keywords: Cranial CT reports; Intracranial hemorrhage; Natural language processing; Subdural hematoma.