Division of Health AI

Introduction: Obstructive sleep apnea (OSA) can cause severe complications if left untreated. Several challenges hinder OSA identification in females, resulting in underdiagnosis and undertreatment in this population. This study aimed to develop a machine learning (ML) approach specifically tailored to screen for moderate-to-severe OSA in women. Methods: A retrospective study using clinical records of 1210 women who underwent polysomnography at our institution was conducted. Collected data included demographics, body metrics, nocturnal oxygen saturation levels, medical conditions, medications, laboratory measurements, and polysomnography results. Four ML algorithms to classify participants into moderate-to-severe and none-to-mild OSA groups were employed. Results: Due to the high missingness of laboratory values in the whole cohort, two sets of models were developed: one that considered all subjects but excluded lab tests and another that only used a subgroup of 383 participants and additionally incorporated hemoglobin and lipid profile levels alongside the other features. Without laboratory measurements, the best-performing model was adaptive boosting, which achieved an area under the receiver operating characteristic curve and accuracy of 0.811 and 76.03%, respectively. When lab tests were included, gradient boosting machine outperformed its competitors, with the above metrics reaching 0.872 and 84.42%, respectively. Conclusion: The promising performance of our approach underlines the potential of artificial intelligence in refining screening strategies for OSA in women. Nadir oxygen saturation during sleep emerged as a particularly strong predictor, reinforcing the central role of nocturnal hypoxemia in OSA risk stratification. Future research should focus on incorporating broader clinical inputs and using larger, diverse datasets to deploy a highly accurate and robust model that meets clinical standards and is suitable for real-world implementation.

Background: Responders to the September 11, 2001, WTC attacks experience high rates of PTSD, and existing treatments often lead to high dropout and low care use. Objectives: This randomized, double-blind, sham-controlled trial assesses the feasibility and acceptability of transcutaneous auricular vagus nerve stimulation (taVNS) as a potential PTSD treatment for 9/11 responders. Methods: A total of 32 WTC responders aged 18+ with PTSD, recruited via the World Trade Center Health Program, participated; those with current psychosis, unstable medical conditions, or recent trial involvement were excluded. Participants were randomly assigned to taVNS or sham groups and asked to use the device for 15 min daily for 8 weeks, with staff and participants blinded. Primary outcomes included recruitment, adherence, retention, and feedback. Secondary outcomes examined changes in depression (PHQ-9), anxiety (GAD-7), and sleep (PSQI). Data were analyzed with mixed-effects models focusing on PTSD and mental health symptoms. Results: The taVNS group showed modest PTSD improvement, with a 10-point CAPS-5 reduction in 40% of stimulation participants versus 28.5% sham; no significant differences in self-reported symptoms were found. Discussion: Daily taVNS over eight weeks is feasible and acceptable, warranting larger studies to detect differences and identify subgroups with greater benefit. Trial registration: “taVNS to Reduce PTSD Symptoms in WTC Responders” (NCT05212714); registered 9 September 2021.

Uveal melanoma (UM) is the most common intraocular malignancy in adults, with high metastatic risk and poor prognosis. Current screening and triaging methods for melanocytic choroidal tumors face inherent limitations, particularly in regions with limited access to specialized ocular oncologists. This systematic review and meta-analysis evaluated artificial intelligence-driven approaches for differentiating uveal melanoma from nevus based on fundus photographs. Analysis included machine learning models with pooled sensitivity of 85% (95% CI 82–87%), specificity of 86% (82–88%), and a C-index of 0.87 (0.84–0.90), with convolutional neural networks as the main method used. Deep learning models achieved AUC scores of 94-95%, outperforming ophthalmologists using standard risk assessment criteria.

Even though extensively documented in acute experiments, ongoing vagal activity has not been characterized longitudinally over days or weeks in mice, a preferred preclinical model. This study presents a chronic recording model to record compound action potentials (CAPs) from the mouse vagus nerve for up to 6 months in both anesthetized and awake animals, with stable signal-to-noise ratios and half-rise times. The approach allows for longitudinal analysis while tracking individual CAPs across multiple days, their firing rates and phase-locking characteristics with other physiological signals, and in the awake case, movement using unsupervised machine learning models. Results reveal diverse CAP populations with varying degrees of physiological coupling, providing a valuable platform to investigate how vagal activity may be modified based on disease severity and develop closed-loop VNS by predicting flare-ups and tracking stimulation efficacy.