Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning
Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expe...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/9/11/1450 |
| _version_ | 1797510162563465216 |
|---|---|
| author | Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul |
| author_facet | Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul |
| author_sort | Jayroop Ramesh |
| collection | DOAJ |
| description | Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies. |
| first_indexed | 2024-03-10T05:27:42Z |
| format | Article |
| id | doaj.art-91bfed61427b4171beba97200c8ed0e0 |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-10T05:27:42Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-91bfed61427b4171beba97200c8ed0e02023-11-22T23:31:03ZengMDPI AGHealthcare2227-90322021-10-01911145010.3390/healthcare9111450Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine LearningJayroop Ramesh0Niha Keeran1Assim Sagahyroon2Fadi Aloul3Department of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab EmiratesDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab EmiratesDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab EmiratesDepartment of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab EmiratesObstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.https://www.mdpi.com/2227-9032/9/11/1450electronic health recordsmachine learningobstructivepolysomnographypredictionsleep apnea |
| spellingShingle | Jayroop Ramesh Niha Keeran Assim Sagahyroon Fadi Aloul Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning Healthcare electronic health records machine learning obstructive polysomnography prediction sleep apnea |
| title | Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning |
| title_full | Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning |
| title_fullStr | Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning |
| title_full_unstemmed | Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning |
| title_short | Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning |
| title_sort | towards validating the effectiveness of obstructive sleep apnea classification from electronic health records using machine learning |
| topic | electronic health records machine learning obstructive polysomnography prediction sleep apnea |
| url | https://www.mdpi.com/2227-9032/9/11/1450 |
| work_keys_str_mv | AT jayroopramesh towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT nihakeeran towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT assimsagahyroon towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning AT fadialoul towardsvalidatingtheeffectivenessofobstructivesleepapneaclassificationfromelectronichealthrecordsusingmachinelearning |