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.

The Role of Oxidative Stress in the Aging Eye.

Given the expanding elderly population in the United States and the world, it is important to understand the processes underlying both natural and pathological age-related changes in the eye. Both the anterior and posterior segment of the eye undergo changes in biological, chemical, and physical properties driven by oxidative stress. With advancing age, changes in the anterior segment include dermatochalasis, blepharoptosis, thickening of the sclera, loss of corneal endothelial cells, and stiffening of the lens. Changes in the posterior segment include lowered viscoelasticity of the vitreous body, photoreceptor cell loss, and drusen deposition at the macula and fovea. Age-related ocular pathologies including glaucoma, cataracts, and age-related macular degeneration are largely mediated by oxidative stress. The prevalence of these diseases is expected to increase in the coming years, highlighting the need to develop new therapies that address oxidative stress and slow the progression of age-related pathologies.

The Scholarly Impact of Student Authorship in Ophthalmology.

Purpose The H-index (H i ), an author-level metric of scholarly impact, is predictive of future scientific achievement. We sought to analyze the scholarly impact of student authorship on the H i of corresponding authors (CAs) within a major academic journal in the specialty of ophthalmology. Materials and Methods We compared the H i of all unique CAs for manuscripts published in Ophthalmology (Journal of the American Academy of Ophthalmology) in 2008, 2012, and 2016. Data abstraction was completed twice: in October 2018 and March 2021. We further grouped published articles for CAs into those with student authors (StA) and those without (nStA). Primary analysis involved a linear regression analysis with change in H i from October 2018 to March 2021 as the outcome variable, CA groups as the predictor variable, adjusting for the covariates of baseline H i , the year when the CA published his or her article, number of research items published in October 2018, and the academic appointment of the CAs. Secondary analysis involved a linear regression analysis with change in H i from October 2018 to March 2021 as the outcome variable, total number of student authors per CA as the predictor variable, adjusting for the covariates of baseline H i , the year CA published his or her article, number of research items published in October 2018, and the academic appointment of the CAs. Results The number of student authors increased from 168 in 2008 to 192 in 2016. Of the 902 articles, 316 articles were co-authored by one or more student authors. The average change in H i of CAs publishing with student authors (StA, 11.0 ± 14.7) was significantly greater ( p < 0.0001) than the change in H i of CAs publishing without student authors (nStA, 6.2 ± 6.2). As the total number of student authors increased, the change in H i of CAs increased linearly for all years combined (regression coefficient = 1.70, p -value < 0.0001). Conclusion CAs publishing with students in the field of ophthalmology have a higher scholarly impact than those publishing without students. The development of programs to integrate students into ophthalmology research early on may encourage their pursuit of a career in ophthalmology, while advancing the careers of their mentors.