Predicting nodal metastases in squamous cell carcinoma of the oral tongue using artificial intelligence.

OBJECTIVE: The presence of occult nodal metastases in patients with squamous cell carcinoma (SCC) of the oral tongue has implications for treatment. Upwards of 30% of patients will have occult nodal metastases, yet a significant number of patients undergo unnecessary neck dissection to confirm nodal status. This study sought to predict the presence of nodal metastases in patients with SCC of the oral tongue using a convolutional neural network (CNN) that analyzed visual histopathology from the primary tumor alone. METHODS: Cases of SCC of the oral tongue were identified from the records of a single institution. Only patients with complete pathology data were included in the study. The primary tumors were randomized into 2 groups for training and testing, which was performed at 2 different levels of supervision. Board-certified pathologists annotated each slide. HALO-AI convolutional neural network and image software was used to perform training and testing. Receiver operator characteristic (ROC) curves and the Youden J statistic were used for primary analysis. RESULTS: Eighty-nine cases of SCC of the oral tongue were included in the study. The best performing algorithm had a high level of supervision and a sensitivity of 65% and specificity of 86% when identifying nodal metastases. The area under the curve (AUC) of the ROC curve for this algorithm was 0.729. CONCLUSION: A CNN can produce an algorithm that is able to predict nodal metastases in patients with squamous cell carcinoma of the oral tongue by analyzing the visual histopathology of the primary tumor alone.

Advanced frailty assessment tool predicts successful awake craniotomy in a 92-year-old patient: A case report.

Background: The awake craniotomy (AC) procedure allows for safe and maximal resection of brain tumors from highly eloquent regions. However, geriatric patients are often viewed as poor candidates for AC due to age and medical comorbidities. Frailty assessments gauge physiological reserve for surgery and are valuable tools for preoperative decision-making. Here, we present a novel case illustrating how frailty scoring enabled an elderly but otherwise healthy female to undergo successful AC for tumor resection. Case Description: A 92-year-old right-handed female with history of hypertension and basal cell skin cancer presented with a 1-month history of progressive aphasia and was found to have a ring-enhancing left frontoparietal mass abutting the rolandic cortex concerning for malignant neoplasm. Frailty scoring with the recalibrated risk analysis index (RAI-C) tool revealed a score of 30 (of 81) indicating low surgical risk. The patient and family were counseled appropriately that, despite advanced chronological age, a low frailty score predicts favorable surgical outcomes. The patient underwent left-sided AC for resection of tumor and experienced immediate improvement of speech intraoperatively. After surgery, the patient was neurologically intact and had an unremarkable postoperative course with significant improvements from preoperatively baseline at follow-up. Conclusion: To the best of our knowledge, this case represents the oldest patient to undergo successful AC for brain tumor resection. Nonfrail patients over 90 years of age with the proper indications may tolerate cranial surgery. Frailty scoring is a powerful tool for preoperative risk assessment in the geriatric neurosurgery population.