Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study

Objectives Obstructive sleep apnoea (OSA) has received much attention as a risk factor for perioperative complications and 68.5% of OSA patients remain undiagnosed before surgery. Faciocervical characteristics may screen OSA for Asians due to smaller upper airways compared with Caucasians. Thus, our...

Full description

Saved in:
Bibliographic Details
Main Authors: Ning Li, Liu Zhang, Ya Ru Yan, Shi Qi Li, Hong Peng Li, Ying Ni Lin, Xian Wen Sun, Yong Jie Ding, Chuan Xiang Li, Qing Yun Li
Format: Article
Language:English
Published: BMJ Publishing Group 2021-09-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/11/9/e048482.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850179606650290176
author Ning Li
Liu Zhang
Ya Ru Yan
Shi Qi Li
Hong Peng Li
Ying Ni Lin
Xian Wen Sun
Yong Jie Ding
Chuan Xiang Li
Qing Yun Li
author_facet Ning Li
Liu Zhang
Ya Ru Yan
Shi Qi Li
Hong Peng Li
Ying Ni Lin
Xian Wen Sun
Yong Jie Ding
Chuan Xiang Li
Qing Yun Li
author_sort Ning Li
collection DOAJ
description Objectives Obstructive sleep apnoea (OSA) has received much attention as a risk factor for perioperative complications and 68.5% of OSA patients remain undiagnosed before surgery. Faciocervical characteristics may screen OSA for Asians due to smaller upper airways compared with Caucasians. Thus, our study aimed to explore a machine-learning model to screen moderate to severe OSA based on faciocervical and anthropometric measurements.Design A cross-sectional study.Setting Data were collected from the Shanghai Jiao Tong University School of Medicine affiliated Ruijin Hospital between February 2019 and August 2020.Participants A total of 481 Chinese participants were included in the study.Primary and secondary outcome (1) Identification of moderate to severe OSA with apnoea–hypopnoea index 15 events/hour and (2) Verification of the machine-learning model.Results Sex-Age-Body mass index (BMI)-maximum Interincisal distance-ratio of Height to thyrosternum distance-neck Circumference-waist Circumference (SABIHC2) model was set up. The SABIHC2 model could screen moderate to severe OSA with an area under the curve (AUC)=0.832, the sensitivity of 0.916 and specificity of 0.749, and performed better than the STOP-BANG (snoring, tiredness, observed apnea, high blood pressure, BMI, age, neck circumference, and male gender) questionnaire, which showed AUC=0.631, the sensitivity of 0.487 and specificity of 0.772. Especially for asymptomatic patients (Epworth Sleepiness Scale <10), the SABIHC2 model demonstrated better predictive ability compared with the STOP-BANG questionnaire, with AUC (0.824 vs 0.530), sensitivity (0.892 vs 0.348) and specificity (0.755 vs 0.809).Conclusion The SABIHC2 machine-learning model provides a simple and accurate assessment of moderate to severe OSA in the Chinese population, especially for those without significant daytime sleepiness.
format Article
id doaj-art-2e4d4976fde648c8a7923c2e180e26a1
institution OA Journals
issn 2044-6055
language English
publishDate 2021-09-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-2e4d4976fde648c8a7923c2e180e26a12025-08-20T02:18:27ZengBMJ Publishing GroupBMJ Open2044-60552021-09-0111910.1136/bmjopen-2020-048482Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional studyNing Li0Liu Zhang1Ya Ru Yan2Shi Qi Li3Hong Peng Li4Ying Ni Lin5Xian Wen Sun6Yong Jie Ding7Chuan Xiang Li8Qing Yun Li9Department of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Hospital Infection Management Office, Wuhu Hospital of Traditional Chinese Medicine, Wuhu, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaInstitute of Respiratory Medicine, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Respiratory and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaObjectives Obstructive sleep apnoea (OSA) has received much attention as a risk factor for perioperative complications and 68.5% of OSA patients remain undiagnosed before surgery. Faciocervical characteristics may screen OSA for Asians due to smaller upper airways compared with Caucasians. Thus, our study aimed to explore a machine-learning model to screen moderate to severe OSA based on faciocervical and anthropometric measurements.Design A cross-sectional study.Setting Data were collected from the Shanghai Jiao Tong University School of Medicine affiliated Ruijin Hospital between February 2019 and August 2020.Participants A total of 481 Chinese participants were included in the study.Primary and secondary outcome (1) Identification of moderate to severe OSA with apnoea–hypopnoea index 15 events/hour and (2) Verification of the machine-learning model.Results Sex-Age-Body mass index (BMI)-maximum Interincisal distance-ratio of Height to thyrosternum distance-neck Circumference-waist Circumference (SABIHC2) model was set up. The SABIHC2 model could screen moderate to severe OSA with an area under the curve (AUC)=0.832, the sensitivity of 0.916 and specificity of 0.749, and performed better than the STOP-BANG (snoring, tiredness, observed apnea, high blood pressure, BMI, age, neck circumference, and male gender) questionnaire, which showed AUC=0.631, the sensitivity of 0.487 and specificity of 0.772. Especially for asymptomatic patients (Epworth Sleepiness Scale <10), the SABIHC2 model demonstrated better predictive ability compared with the STOP-BANG questionnaire, with AUC (0.824 vs 0.530), sensitivity (0.892 vs 0.348) and specificity (0.755 vs 0.809).Conclusion The SABIHC2 machine-learning model provides a simple and accurate assessment of moderate to severe OSA in the Chinese population, especially for those without significant daytime sleepiness.https://bmjopen.bmj.com/content/11/9/e048482.full
spellingShingle Ning Li
Liu Zhang
Ya Ru Yan
Shi Qi Li
Hong Peng Li
Ying Ni Lin
Xian Wen Sun
Yong Jie Ding
Chuan Xiang Li
Qing Yun Li
Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
BMJ Open
title Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
title_full Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
title_fullStr Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
title_full_unstemmed Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
title_short Moderate to severe OSA screening based on support vector machine of the Chinese population faciocervical measurements dataset: a cross-sectional study
title_sort moderate to severe osa screening based on support vector machine of the chinese population faciocervical measurements dataset a cross sectional study
url https://bmjopen.bmj.com/content/11/9/e048482.full
work_keys_str_mv AT ningli moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT liuzhang moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT yaruyan moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT shiqili moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT hongpengli moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT yingnilin moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT xianwensun moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT yongjieding moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT chuanxiangli moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy
AT qingyunli moderatetosevereosascreeningbasedonsupportvectormachineofthechinesepopulationfaciocervicalmeasurementsdatasetacrosssectionalstudy