Fully automated 3D machine learning model for HPV status characterization in oropharyngeal squamous cell carcinomas based on CT images.

BACKGROUND: Human papillomavirus (HPV) status plays a major role in predicting oropharyngeal squamous cell carcinoma (OPSCC) survival. This study assesses the accuracy of a fully automated 3D convolutional neural network (CNN) in predicting HPV status using CT images. METHODS: Pretreatment CT images from OPSCC patients were used to train a 3D DenseNet-121 model to predict HPV-p16 status. Performance was evaluated by the ROC Curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: The network achieved a mean AUC of 0.80 ± 0.06. The best-preforming fold had a sensitivity of 0.86 and specificity of 0.92 at the Youden's index. The PPV, NPV, and F1 scores are 0.97, 0.71, and 0.82, respectively. CONCLUSIONS: A fully automated CNN can characterize the HPV status of OPSCC patients with high sensitivity and specificity. Further refinement of this algorithm has the potential to provide a non-invasive tool to guide clinical management.

Long-Term Satisfaction of Oral Sedation versus Standard-of-Care Intravenous Sedation for Ocular Surgery.

Purpose: Long-term patient satisfaction may influence patients' perspectives of the quality of care and their relationship with their providers. This is a follow up to a comparative effectiveness study investigating oral to intravenous sedation (OIV study). The OIV study found that oral sedation was noninferior in patient satisfaction to standard intravenous (IV) sedation for anterior segment and vitreoretinal surgeries. This study aims to determine if patient satisfaction with oral sedation remained noninferior long term. Patients and Methods: Patients were re-interviewed using the same satisfaction survey given during the OIV study. Statistical analysis involved t-tests for noninferiority of the long-term mean satisfaction score of oral and IV sedation. We also compared the original mean satisfaction score and the follow-up mean satisfaction score for each type of sedation and for both groups combined. Results: Participants were interviewed at a median of 1225.5 days (range 754-1675 days) from their surgery. The original mean satisfaction score was 5.26 ± 0.79 for the oral treatment group (n = 52) and 5.27 ± 0.64 for the intravenous treatment group (n = 46), demonstrating noninferiority with a difference in mean satisfaction score of 0.015 (p < 0.0001). The follow-up mean satisfaction score was 5.23 ± 0.90 for oral sedation and 5.60 ± 0.61 for IV sedation, with a difference in the mean satisfaction score of 0.371 (p = 0.2071). Satisfaction scores did not differ between the original mean satisfaction score and the follow-up mean satisfaction score for the oral treatment group alone (p = 0.8367), but scores in the intravenous treatment group increased longitudinally (p = 0.0004). Conclusion: In this study, long-term patient satisfaction with oral sedation was not noninferior to satisfaction with IV sedation, unlike our findings with short-term patient satisfaction in our original study. Patient satisfaction also remained unchanged over time for the oral treatment group, but patients in the intravenous treatment group reported higher long-term satisfaction with their anesthesia experience compared to the immediate post-operative period.

Multiparametric machine learning algorithm for human papillomavirus status and survival prediction in oropharyngeal cancer patients.

BACKGROUND: Human papillomavirus (HPV) status influences prognosis in oropharyngeal cancer (OPC). Identifying high-risk patients are critical to improving treatment. We aim to provide a noninvasive opportunity for managing OPC patients by training multiple machine learning pipelines to determine the best model for characterizing HPV status and survival. METHODS: Multi-parametric algorithms were designed using a 492 OPC patient database. HPV status incorporated age, sex, smoking/drinking habits, cancer subsite, TNM, and AJCC 7th edition staging. Survival considered HPV model inputs plus HPV status. Patients were split 4:1 training: testing. Algorithm efficacy was assessed through accuracy and area under the receiver operator characteristic curve (AUC). RESULTS: From 31 HPV status models, ensemble yielded 0.83 AUC and 78.7% accuracy. From 38 survival models, ensemble yielded 0.91 AUC and 87.7% accuracy. CONCLUSION: Results reinforce artificial intelligence's potential to use tumor imaging and patient characterizations for HPV status and outcome prediction. Utilizing these algorithms can optimize clinical guidance and patient care noninvasively.