Comparison of natural language processing algorithms in assessing the importance of head computed tomography reports written in Japanese.

PURPOSE: To propose a five-point scale for radiology report importance called Report Importance Category (RIC) and to compare the performance of natural language processing (NLP) algorithms in assessing RIC using head computed tomography (CT) reports written in Japanese. MATERIALS AND METHODS: 3728 Japanese head CT reports performed at Osaka University Hospital in 2020 were included. RIC (category 0: no findings, category 1: minor findings, category 2: routine follow-up, category 3: careful follow-up, and category 4: examination or therapy) was established based not only on patient severity but also on the novelty of the information. The manual assessment of RIC for the reports was performed under the consensus of two out of four neuroradiologists. The performance of four NLP models for classifying RIC was compared using fivefold cross-validation: logistic regression, bidirectional long-short-term memory (BiLSTM), general bidirectional encoder representations of transformers (general BERT), and domain-specific BERT (BERT for medical domain). RESULTS: The proportion of each RIC in the whole data set was 15.0%, 26.7%, 44.2%, 7.7%, and 6.4%, respectively. Domain-specific BERT showed the highest accuracy (0.8434 ± 0.0063) in assessing RIC and significantly higher AUC in categories 1 (0.9813 ± 0.0011), 2 (0.9492 ± 0.0045), 3 (0.9637 ± 0.0050), and 4 (0.9548 ± 0.0074) than the other models (p < .05). Analysis using layer-integrated gradients showed that the domain-specific BERT model could detect important words, such as disease names in reports. CONCLUSIONS: Domain-specific BERT has superiority over the other models in assessing our newly proposed criteria called RIC of head CT radiology reports. The accumulation of similar and further studies of has a potential to contribute to medical safety by preventing missed important findings by clinicians.

Prognostic factors for bone metastases from head and neck squamous cell carcinoma: A case series of 97 patients.

Although bone is the second-most frequent site of distant metastases of head and neck squamous cell carcinoma (HNSCC), variable prognostic factors in patients with bone metastases from HNSCC have not been fully investigated. The aim of the present study was to assess the prognostic factors affecting overall survival (OS) in these patients. The medical records of 97 patients at two institutions who developed bone metastases from HNSCC between January 2010 and December 2020 were retrospectively reviewed. A multivariate analysis using a Cox proportional hazards model was performed to identify potential clinical predictive factors for longer OS. The median OS was 7 months, and the 1- and 2-year OS rates for all patients were 35.4 and 19.2%, respectively. The independent predictive factors for longer OS were single bone metastasis, good performance status and administration of systemic chemotherapy. The median OS with each predictor was 10, 10 and 10.5 months, respectively. In a selected group of patients with these three factors, the OS was 14.5 months. In conclusion, single bone metastasis, a good performance status and systemic chemotherapy were independent predictors of longer OS in patients with HNSCC, but their contributions were limited.