Machine learning approaches for screening the risk of obstructive sleep apnea in the Taiwan population based on body profile. (2nd October 2022)

• Record Type: Journal Article
• Authors: Tsai, Cheng-Yu; Liu, Wen-Te; Lin, Yin-Tzu; Lin, Shang-Yang; Houghton, Robert; Hsu, Wen-Hua; Wu, Dean; Lee, Hsin-Chien; Wu, Cheng-Jung; Li, Lok Yee Joyce; Hsu, Shin-Mei; Lo, Chen-Chen; Lo, Kang; Chen, You-Rong; Lin, Feng-Ching; Majumdar, Arnab
• Is Part Of: Informatics for health & social care. Volume 47:Number 4(2022)
• Page Start: 373
• Page End: 388
• Publication Date: 2022-10-02
• Subjects: Obstructive sleep apnea syndrome -- polysomnography -- apnea-hypopnea index -- anthropometric features -- sleep disorder indexes -- random forest model; Medicine -- Information services -- Periodicals; Medical informatics -- Periodicals; Medicine -- Data processing -- Periodicals; 025.0661
• DOI: 10.1080/17538157.2021.2007930
• Languages: English
• ISSNs: 1753-8157

Abstract

ABSTRACT: (a) Objective: Obstructive sleep apnea syndrome (OSAS) is typically diagnosed through polysomnography (PSG). However, PSG incurs high medical costs. This study developed new models for screening the risk of moderate-to-severe OSAS (apnea-hypopnea index, AHI ≥15) and severe OSAS (AHI ≥30) in various age groups and sexes by using anthropometric features in the Taiwan population. (b) Participants: Data were derived from 10, 391 northern Taiwan patients who underwent PSG. (c) Methods: Patients' characteristics – namely age, sex, body mass index (BMI), neck circumference, and waist circumference – was obtained. To develop an age- and sex-independent model, various approaches – namely logistic regression, k-nearest neighbor, naive Bayes, random forest (RF), and support vector machine – were trained for four groups based on sex and age (men or women; aged <50 or ≥50 years). Dataset was separated independently (training:70%; validation: 10%; testing: 20%) and Cross-validated grid search was applied for model optimization. Models demonstrating the highest overall accuracy in validation outcomes for the four groups were used to predict the testing dataset. (d) Results: The RF models showed the highest overall accuracy. BMI was the most influential parameter in both types of OSAS severity screening models. (e) Conclusion: The established models can be applied to screen OSAS risk in the Taiwan population and those with similar craniofacial features.