Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis
ObjectiveThe objective of this study was to investigate the effectiveness of a machine learning algorithm in diagnosing OSA in children based on clinical features that can be obtained in nonnocturnal and nonmedical environments.Patients and methodsThis study was conducted at Beijing Children's...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fped.2024.1328209/full |
| _version_ | 1797311651090792448 |
|---|---|
| author | Han Qin Liping Zhang Xiaodan Li Zhifei Xu Jie Zhang Shengcai Wang Li Zheng Tingting Ji Lin Mei Yaru Kong Xinbei Jia Yi Lei Yuwei Qi Jie Ji Xin Ni Qing Wang Qing Wang Jun Tai |
| author_facet | Han Qin Liping Zhang Xiaodan Li Zhifei Xu Jie Zhang Shengcai Wang Li Zheng Tingting Ji Lin Mei Yaru Kong Xinbei Jia Yi Lei Yuwei Qi Jie Ji Xin Ni Qing Wang Qing Wang Jun Tai |
| author_sort | Han Qin |
| collection | DOAJ |
| description | ObjectiveThe objective of this study was to investigate the effectiveness of a machine learning algorithm in diagnosing OSA in children based on clinical features that can be obtained in nonnocturnal and nonmedical environments.Patients and methodsThis study was conducted at Beijing Children's Hospital from April 2018 to October 2019. The participants in this study were 2464 children aged 3–18 suspected of having OSA who underwent clinical data collection and polysomnography(PSG). Participants’ data were randomly divided into a training set and a testing set at a ratio of 8:2. The elastic net algorithm was used for feature selection to simplify the model. Stratified 10-fold cross-validation was repeated five times to ensure the robustness of the results.ResultsFeature selection using Elastic Net resulted in 47 features for AHI ≥5 and 31 features for AHI ≥10 being retained. The machine learning model using these selected features achieved an average AUC of 0.73 for AHI ≥5 and 0.78 for AHI ≥10 when tested externally, outperforming models based on PSG questionnaire features. Linear Discriminant Analysis using the selected features identified OSA with a sensitivity of 44% and specificity of 90%, providing a feasible clinical alternative to PSG for stratifying OSA severity.ConclusionsThis study shows that a machine learning model based on children's clinical features effectively identifies OSA in children. Establishing a machine learning screening model based on the clinical features of the target population may be a feasible clinical alternative to nocturnal OSA sleep diagnosis. |
| first_indexed | 2024-03-08T02:02:45Z |
| format | Article |
| id | doaj.art-6d98b7115b7e4a9091fb60bd0ef30aad |
| institution | Directory Open Access Journal |
| issn | 2296-2360 |
| language | English |
| last_indexed | 2024-03-08T02:02:45Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj.art-6d98b7115b7e4a9091fb60bd0ef30aad2024-02-14T04:49:45ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602024-02-011210.3389/fped.2024.13282091328209Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysisHan Qin0Liping Zhang1Xiaodan Li2Zhifei Xu3Jie Zhang4Shengcai Wang5Li Zheng6Tingting Ji7Lin Mei8Yaru Kong9Xinbei Jia10Yi Lei11Yuwei Qi12Jie Ji13Xin Ni14Qing Wang15Qing Wang16Jun Tai17Department of Child Health Care, Children’s Hospital Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Capital Institute of Pediatrics, Beijing, ChinaPharmacovigilance Research Center for Information Technology and Data Science, Cross-strait Tsinghua Research Institute, Xiamen, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaRespiratory Department, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Child Health Care, Children’s Hospital Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Capital Institute of Pediatrics, Beijing, ChinaDepartment of Child Health Care, Children’s Hospital Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Capital Institute of Pediatrics, Beijing, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Children’s Hospital Capital Institute of Pediatrics, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, ChinaPharmacovigilance Research Center for Information Technology and Data Science, Cross-strait Tsinghua Research Institute, Xiamen, ChinaDepartment of Automation, Tsinghua University, Beijing, ChinaDepartment of Otolaryngology, Head and Neck Surgery, Children’s Hospital Capital Institute of Pediatrics, Beijing, ChinaObjectiveThe objective of this study was to investigate the effectiveness of a machine learning algorithm in diagnosing OSA in children based on clinical features that can be obtained in nonnocturnal and nonmedical environments.Patients and methodsThis study was conducted at Beijing Children's Hospital from April 2018 to October 2019. The participants in this study were 2464 children aged 3–18 suspected of having OSA who underwent clinical data collection and polysomnography(PSG). Participants’ data were randomly divided into a training set and a testing set at a ratio of 8:2. The elastic net algorithm was used for feature selection to simplify the model. Stratified 10-fold cross-validation was repeated five times to ensure the robustness of the results.ResultsFeature selection using Elastic Net resulted in 47 features for AHI ≥5 and 31 features for AHI ≥10 being retained. The machine learning model using these selected features achieved an average AUC of 0.73 for AHI ≥5 and 0.78 for AHI ≥10 when tested externally, outperforming models based on PSG questionnaire features. Linear Discriminant Analysis using the selected features identified OSA with a sensitivity of 44% and specificity of 90%, providing a feasible clinical alternative to PSG for stratifying OSA severity.ConclusionsThis study shows that a machine learning model based on children's clinical features effectively identifies OSA in children. Establishing a machine learning screening model based on the clinical features of the target population may be a feasible clinical alternative to nocturnal OSA sleep diagnosis.https://www.frontiersin.org/articles/10.3389/fped.2024.1328209/fullobstructive sleep apneamachine learningartificial intelligencecomputer-aided diagnosischildren |
| spellingShingle | Han Qin Liping Zhang Xiaodan Li Zhifei Xu Jie Zhang Shengcai Wang Li Zheng Tingting Ji Lin Mei Yaru Kong Xinbei Jia Yi Lei Yuwei Qi Jie Ji Xin Ni Qing Wang Qing Wang Jun Tai Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis Frontiers in Pediatrics obstructive sleep apnea machine learning artificial intelligence computer-aided diagnosis children |
| title | Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis |
| title_full | Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis |
| title_fullStr | Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis |
| title_full_unstemmed | Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis |
| title_short | Pediatric obstructive sleep apnea diagnosis: leveraging machine learning with linear discriminant analysis |
| title_sort | pediatric obstructive sleep apnea diagnosis leveraging machine learning with linear discriminant analysis |
| topic | obstructive sleep apnea machine learning artificial intelligence computer-aided diagnosis children |
| url | https://www.frontiersin.org/articles/10.3389/fped.2024.1328209/full |
| work_keys_str_mv | AT hanqin pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT lipingzhang pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT xiaodanli pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT zhifeixu pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT jiezhang pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT shengcaiwang pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT lizheng pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT tingtingji pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT linmei pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT yarukong pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT xinbeijia pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT yilei pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT yuweiqi pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT jieji pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT xinni pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT qingwang pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT qingwang pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis AT juntai pediatricobstructivesleepapneadiagnosisleveragingmachinelearningwithlineardiscriminantanalysis |