Integrating domain knowledge with machine learning to detect obstructive sleep apnea: Snore as a significant bio‐feature

Abstract

Our study's main purpose is to emphasise the significance of medical knowledge of pathophysiology before machine learning. We investigated whether combining domain knowledge with machine learning results might increase accuracy and minimise the number of bio-features used to detect obstructive sleep apnea (OSA). The present study analysed data on 36 self-reported symptoms and 24 clinical features obtained from 3,495 patients receiving polysomnography at a regional hospital and a medical centre. The area under the receiver operating characteristic (AUC) curve was used to evaluate patients with and without moderate or severe OSA using three prediction models on the basis of various estimation methods: the multiple logistic regression (MLR), support vector machine (SVM), and neural network (NN) methods. Odds ratios stratified by gender and age were also measured to account for clinicians' common sense. We discovered that adding the self-reported snoring item improved the AUC by 0.01-0.10 and helped us to rapidly achieve the optimum level. The performance of four items (gender, age, body mass index [BMI], and snoring) was comparable with that of adding two or more items (neck and waist circumference) for predicting moderate to severe OSA (Apnea-Hypopnea Index ≥15 events/hr) in all three prediction models, demonstrating the medical knowledge value of pathophysiology. The four-item test sample AUCs were 0.83, 0.84, and 0.83 for MLR, SVM, and NN, respectively.Participants with regular snoring and a BMI of ≥25 kg/m 2 had a greater chance of moderate to severe OSA according to the stratified adjusted odds ratios. Combining domain knowledge into machine learning could increase efficiency and enable primary care physicians to refer for an OSA diagnosis earlier.

Classification of severe obstructive sleep apnea with cognitive impairment using degree centrality: A machine learning analysis

“…Due to the overall scarcity and financial burden of PSG, methods combining multidimensional clinical parameters and machine learning have been widely used to distinguish OSA, OSA severity, and OSA prognosis ( 2 , 38 , 39 ). However, studies using DC to distinguish OSA are relatively rare.…”

DeepBiomarker2: Prediction of Alcohol and Substance Use Disorder Risk in Post-Traumatic Stress Disorder Patients Using Electronic Medical Records and Multiple Social Determinants of Health

“…Examples include disease pathophysiology, treatment guidelines, patient care protocols, medical terminologies, diagnostic criteria, pharmacology, epidemiology, patient history analysis, clinical research methods, and familiarity with healthcare workflows. Integrating clinical domain knowledge is crucial for designing effective healthcare solutions, interpreting medical data, and ensuring artificial intelligence models align with real-world clinical scenarios [24][25][26][27][28][29][30][31].…”

Utilization of the GOAL questionnaire as a standardized screening tool for obstructive sleep apnea

“…There are now a large number of clinical alternatives that can screen OSA. And these are broadly divided into clinical prediction models 12 , 13 and questionnaires. Clinical models designed to screen OSA require specific techniques such as cephalometric, morphometric measurements and the assistance of a computer.…”