Artificial intelligence (AI) for early identification of radiotherapy related toxicities from the electronic health records of patients with head and neck cancer.

We evaluated artificial intelligence (AI) for detecting osteoradionecrosis, fibrosis, trismus, and dysphagia in 207 head and neck cancer patient electronic health records. After adjudication and fine-tuning, accuracy reached 87% (F1 = 0.92). The model processed 20,835 sentences within seconds, demonstrating feasibility and efficiency for automating the identification of radiation-related late toxicities.