Abstract Obstructive Sleep Apnea (OSA) is a highly prevalent sleep disorder linked to considerable public health burdens and comorbidities. However, its heterogeneous presentation and the limited accessibility of traditional diagnostic tools such as polysomnography (PSG) lead to widespread underdiagnosis. As a result, artificial intelligence (AI) approaches, including machine learning (ML) and deep learning (DL) models, have attracted attention as an alternative pathway to detection. This paper first provides a comprehensive review of AI-driven OSA diagnosis, covering different diagnosis problems, input-data types, data biases, pre-processing techniques, and model performance. We then leverage the largest clinical dataset used in OSA prediction to date, approximately 110,000 patients with 22,000 having complete entries for all 50 features, to systematically compare the performance of 39 ML/DL models. Our findings highlight the challenging nature of OSA prediction, with accuracies ranging from 29.66% to 46.9% for 4-class prediction and 46.04% to 87.18% for binary tasks. DL models such as DANet and GATE scored highest, whereas ensemble approaches such as LGBM and AdaBoost displayed more consistent performance across folds. However, as severe cases of OSA are easier to predict and over-represented in datasets, accuracy alone is insufficient for model evaluation and we explore a variety of metrics. Finally, imbalance correction and feature selection improved weaker models, but had only marginal effects on the best-performing models. Looking forwards, the development of more sophisticated and tailored DL models and large, high-quality datasets may help to break current performance barriers. We hope that our work can attract more attention to this challenging but interesting research problem.

OBJECTIVE: In obstructive sleep apnea patients on continuous positive airway pressure (CPAP) treatment there is growing evidence for a significant impact of the type of mask on the residual apnea-hypopnea index (rAHI). Here, we propose a method for automatically classifying the impact of mask changes on rAHI. METHODS: From a CPAP telemonitoring database of 3,581 patients, an interrupted time series design was applied to rAHI time series at a patient level to compare the observed rAHI after a mask-change with what would have occurred without the mask-change. rAHI time series before mask changes were modelled using different approaches. Mask changes were classified as: no effect, harmful, beneficial. The best model was chosen based on goodness-of-fit metrics and comparison with blinded classification by an experienced respiratory physician. RESULTS: Bayesian structural time series with synthetic controls was the best approach in terms of agreement with the physician.s classification, with an accuracy of 0.79. Changes from nasal to facial mask were more often harmful than beneficial: 13.4% vs 7.6% (p-value < 0.05), with a clinically relevant increase in average rAHI greater than 8 events/hour in 4.6% of cases. Changes from facial to nasal mask were less often harmful: 6.0% vs 11.4% (p-value < 0.05). CONCLUSION: We propose an end-to-end method to automatically classify the impact of mask changes over fourteen days after a switchover. SIGNIFICANCE: The proposed automated analysis of the impact of changes in health device settings or accessories presents a novel tool to include in remote monitoring platforms for raising alerts after harmful interventions.

The identification of Obstructive Sleep Apnea (OSA) relies on laborious and expensive polysomnography (PSG) exams. However, it is known that other factors, easier to measure, can be good indicators of OSA and its severity. In this work, we extensively investigate the use of Machine Learning techniques in the task of determining which factors are more revealing with respect to OSA along with a discussion of the challenges to perform such a task. We ran extensive experiments over 1,042 patients from the Centre Hospitalier Universitaire of the city of Grenoble, France. The data included ordinary clinical information, and PSG results as baseline. We employed data preparation techniques including cleaning of outliers, imputation of missing values, and synthetic data generation. Following, we performed an exhaustive attribute selection scheme to find the most representative features. We found that the prediction of OSA depends largely on variables related to age, body mass, and sleep habits more than the ones related to alcoholism, tabagism, and depression. Next, we tested 60 regression/classification algorithms to predict the Apnea-Hypopnea Index (AHI), and the AHI-based severity of OSA. We achieved performances significantly superior to the state of the art both for AHI regression and classification. Our results can benefit the development of tools for the automatic screening of patients who should go through polysomnography and further treatments of OSA -- currently, our work in under consideration for production by the Centre Hospitalier Universitaire of Grenoble. Our thorough methodology enables experimental reproducibility on similar OSA-detection problems, and more generally, on other problems with similar data models.

We demonstrate COVIZ, an interactive system to visually form and explore patient cohorts. COVIZ seamlessly integrates visual cohort formation and exploration, making it a single destination for hypothesis generation. COVIZ is easy to use by medical experts and offers many features: (1) It provides the ability to isolate patient demographics (e.g., their age group and location), health markers (e.g., their body mass index), and treatments (e.g., Ventilation for respiratory problems), and hence facilitates cohort formation; (2) It summarizes the evolution of treatments of a cohort into health trajectories, and lets medical experts explore those trajectories; (3) It guides them in examining different facets of a cohort and generating hypotheses for future analysis; (4) Finally, it provides the ability to compare the statistics and health trajectories of multiple cohorts at once. COVIZ relies on QDS, a novel data structure that encodes and indexes various data distributions to enable their efficient retrieval. Additionally, COVIZ visualizes air quality data in the regions where patients live to help with data interpretations. We demonstrate two key scenarios, ecological scenario and case cross-over scenario . A video demonstration of COVIZ is accessible via http://bit.ly/video-coviz.

We introduce a novel interactive framework to handle both instance-level and temporal smoothness constraints for clustering large longitudinal data and for tracking the cluster evolutions over time. It consists of a constrained clustering algorithm, called CVQE+ , which optimizes the clustering quality, constraint violation and the historical cost between consecutive data snapshots. At the center of our framework is a simple yet effective active learning technique, named Border , for iteratively selecting the most informative pairs of objects to query users about, and updating the clustering with new constraints. Those constraints are then propagated inside each data snapshot and between snapshots via two schemes, called constraint inheritance and constraint propagation , to further enhance the results. Moreover, a historical constraint is enforced between consecutive snapshots to ensure the consistency of results among them. Experiments show better or comparable clustering results than state-of-the-art techniques as well as high scalability for large datasets. Finally, we apply our algorithm for clustering phenotypes in patients with Obstructive Sleep Apnea as well as for tracking how these clusters evolve over time.

We have developed robust embedded algorithms for the real-time classification of activity detected by our wearable inertial device. We collected 224 h of accelerometric signals from 28 subjects [22 suffering from chronic obstructive pulmonary disease (COPD)] to develop and then evaluate our algorithms. We describe the process for determining the most robust parameters of the algorithms. Our results with COPD patients show the feasibility of conducting real-time classification of their activities in everyday situations, with high fidelity.

Chronic Obstructive Pulmonary Disease (COPD) reduces airflow in and out of the lungs, causing dyspnea during physical exercises. Therefore it is interesting to monitor the blood saturation during a physical exercise. Such monitoring can benefit from a network of collaborative sensors. But to monitor the patient in his daily life, it is mandatory that the system can be used autonomously at the patient's home. We therefore propose a system composed of multiple wirelessly interconnected medical sensors, and a master device to acquire medical data in daily life or in supervised medical exams.