Introduction

Sleep disorders, including sleep apnea, have become one of the significant health problems in the United States. Some statistics claim that about 22 million Americans have sleep apnea. The main problem is that 80% of the cases are not diagnosed, leading to severe consequence health problems such as high blood pressure, chronic heart failure, atrial fibrillation, stroke, and other cardiovascular problems. The American Academy of Sleep Medicine (AASM) released a new analysis, named "Hidden health crisis costing America billions," that exposes the tremendous economic cost of undiagnosed OSA. Untreated sleep apnea heightens the risk of costly health complications such as hypertension, heart disease, diabetes, and depression. The report considered 506 patients who were diagnosed with OSA. The results show the potential progress on the patients' quality of life when traded from OSA in sleep quality and productivity and a 40% decline in workplace absences. Roughly 78% of patients testified that their treatment was a significant investment. Frost & Sullivan calculated that the annual economic burden of undiagnosed sleep apnea among U.S. adults is approximately $149.6 billion. The estimated costs include $86.9 billion in lost productivity, $26.2 billion in motor vehicle accidents, and $6.5 billion in workplace accidents. OSA is the most common apnea. It is characterized by a reduction of 30% in the airflow continuously for 10 seconds. It is also associated with a 4% oxygen desaturation/decrease by 50% in the airflow for 10 seconds. Obstructive sleep apnea (OSA) has many side effects. For example, OSA can reduce human attention and concentration, lower the quality of life, increase absenteeism rates with reduced productivity, and raise the possibility of accidents at work, home, or on the road. We are currently collaborating with Torr Sleep Center, Corpus Christi, TX, USA, to collect various OSA datasets (i.e., ECG and Demographic) and explore the use of many machine learning approaches to develop prediction models for sleep apnea.

• To continue this research, we received a research grant entitled, "Machine Learning-based Sleep Classification for Aging in Place," Texas A&M University-Corpus Christi, TX, USA, 2018-2019. We explored a wide range of anthropometric features, including weight, height, body mass index (BMI), hip, waist, age, neck circumference, modified Friedman, snoring, Epworth sleepiness scale (ESS), sex, and daytime sleepiness for building classification models. Our findings help to reduce the patient's need to spend a night at a laboratory and make the study of sleep apnea implemented at home [1-4].

• Recently, Dr. Sheta had a successfully funded research grant entitled, "Diagnosis of Obstructive Sleep Apnea: A Computer-Aided Tool Based on Deep Learning" by the START Preliminary Proof of Concept Fund, University of Connecticut (UCONN), made possible by a generous grant from the C.T. Next Higher Education Fund (CTNext), Connecticut, USA 2020-2021.

• Dr. Sheta formed a team of researchers from the USA, Jordan, China, Palestine, and Saudi Arabia to implement the research goals. The research team focused on developing a mobile application system for easy diagnosis and accessibility for a patient.

• The research results were published at the 11^th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON2020) [5] and the Applied Science Journal [6].

Publications

1. S. Surani, A. Sheta, H. Turabieh, J. Park, S. Mathur, and A. Katangur, “Diagnosis of sleep apnea using artificial neural network and binary particle swarm optimization for feature selection,” Chest, vol. 156,p. A136, 10, 2019.

2. A. Sheta, H. Turabieh, M. Braik, and S. Surani, “Diagnosis of obstructive sleep apnea using logistic regression and artificial neural networks models,” in Proceedings of the Future Technologies Conference, pp. 766–784, 2020.

3. J. Park, A. Sheta, and S. Surani, “Statistical models for predicting a patient’s respiratory disturbance index”, Chest, vol. 156, p. A138, 10, 2019.

4. S. Surani, A. Sheta, H. Turabieh, and S. Subramanian, “Adaboosting model for detecting OSA”, Chest, vol. 156, pp. A134–A135, 10, 2019.

5. C. Haberfeld, A. Sheta, M. S. Hossain, H. Turabieh, and S. Surani, “SAS mobile application for diagnosis of obstructive sleep apnea utilizing machine learning models,” in 2020 11th IEEE Annual Ubiquitous Computing, Electronics Mobile Communication Conference (UEMCON), pp. 0522–0529, 2020.

6. A. Sheta, H. Turabieh, T. Thaher, J. Too, M. Mafarja, M. S. Hossain, and S. R. Surani, “Diagnosis of obstructive sleep apnea from ECG signals using machine learning and deep learning classifiers,” Applied Sciences, vol. 11, no. 14, 2021