Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model
Abstract Background Breath‐holding spells (BHS) are common in infancy and early childhood and may appear like seizures. Factors such as autonomic dysfunction and iron deficiency anemia are thought to contribute to the incidence of BHS. In this study, electrocardiographic (ECG) parameters of patients...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Annals of Noninvasive Electrocardiology |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/anec.13093 |
| _version_ | 1797338737313579008 |
|---|---|
| author | Mohammad Reza Khalilian Saeed Tofighi Elham Zohur Attar Ali Nikkhah Mahmoud Hajipour Mohammad Ghazavi Sahar Samimi |
| author_facet | Mohammad Reza Khalilian Saeed Tofighi Elham Zohur Attar Ali Nikkhah Mahmoud Hajipour Mohammad Ghazavi Sahar Samimi |
| author_sort | Mohammad Reza Khalilian |
| collection | DOAJ |
| description | Abstract Background Breath‐holding spells (BHS) are common in infancy and early childhood and may appear like seizures. Factors such as autonomic dysfunction and iron deficiency anemia are thought to contribute to the incidence of BHS. In this study, electrocardiographic (ECG) parameters of patients with BHS were compared to those of healthy, normal children. Logistic regression and machine‐learning (ML) models were then created to predict these spells based on ECG characteristics. Methods In this case–control study, 52 BHS children have included as the case and 150 healthy children as the control group. ECG was taken from all children along with clinical examinations. Multivariate logistic regression model was used to predict BHS occurrence based on ECG parameters. ML model was trained and validated using the Gradient‐Boosting algorithm, in the R programming language. Results In BHS and control groups, the average age was 11.90 ± 6.63 and 11.33 ± 6.17 months, respectively (p = .58). Mean heart rate, PR interval, and QRS interval on ECGs did not differ significantly between the two groups. BHS patients had significantly higher QTc, QTd, TpTe, and TpTe/QT (all p‐values < .001). Evaluation of the ML model for prediction of BHS, fitting on the testing data showed AUC, specificity, and sensitivity of 0.94, 0.90, and 0.94 respectively. Conclusion There are repolarization changes in patients with BHS, as the QTc, QTd, TpTe, and TpTe/QT ratio were significantly higher in these patients, which might be noticeable for future arrhythmia occurrence. In this regard, we developed a successful ML model to predict the possibility of BHS in suspected subjects. |
| first_indexed | 2024-03-08T09:35:37Z |
| format | Article |
| id | doaj.art-39baad0652154238a3613a0fccff2854 |
| institution | Directory Open Access Journal |
| issn | 1082-720X 1542-474X |
| language | English |
| last_indexed | 2024-03-08T09:35:37Z |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Annals of Noninvasive Electrocardiology |
| spelling | doaj.art-39baad0652154238a3613a0fccff28542024-01-30T08:36:49ZengWileyAnnals of Noninvasive Electrocardiology1082-720X1542-474X2024-01-01291n/an/a10.1111/anec.13093Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning modelMohammad Reza Khalilian0Saeed Tofighi1Elham Zohur Attar2Ali Nikkhah3Mahmoud Hajipour4Mohammad Ghazavi5Sahar Samimi6Department of Pediatrics, School of Medicine Shahid Beheshti University of Medical Sciences Tehran IranDepartment of Cardiology, School of Medicine Tehran University of Medical Sciences Tehran IranDepartment of Pediatrics, Mofid Children Hospital Shahid Beheshti University of Medical Sciences Tehran IranMofid Children Hospital Shahid Beheshti University of Medical Sciences Tehran IranHepatology and Nutrition Research Center, Institute for Children's Health Shahid Beheshti University of Medical Sciences Tehran IranDepartment of Pediatrics, School of Medicine Kashan University of Medical Sciences and Health Services Kashan IranDepartment of Cardiology, School of Medicine Tehran University of Medical Sciences Tehran IranAbstract Background Breath‐holding spells (BHS) are common in infancy and early childhood and may appear like seizures. Factors such as autonomic dysfunction and iron deficiency anemia are thought to contribute to the incidence of BHS. In this study, electrocardiographic (ECG) parameters of patients with BHS were compared to those of healthy, normal children. Logistic regression and machine‐learning (ML) models were then created to predict these spells based on ECG characteristics. Methods In this case–control study, 52 BHS children have included as the case and 150 healthy children as the control group. ECG was taken from all children along with clinical examinations. Multivariate logistic regression model was used to predict BHS occurrence based on ECG parameters. ML model was trained and validated using the Gradient‐Boosting algorithm, in the R programming language. Results In BHS and control groups, the average age was 11.90 ± 6.63 and 11.33 ± 6.17 months, respectively (p = .58). Mean heart rate, PR interval, and QRS interval on ECGs did not differ significantly between the two groups. BHS patients had significantly higher QTc, QTd, TpTe, and TpTe/QT (all p‐values < .001). Evaluation of the ML model for prediction of BHS, fitting on the testing data showed AUC, specificity, and sensitivity of 0.94, 0.90, and 0.94 respectively. Conclusion There are repolarization changes in patients with BHS, as the QTc, QTd, TpTe, and TpTe/QT ratio were significantly higher in these patients, which might be noticeable for future arrhythmia occurrence. In this regard, we developed a successful ML model to predict the possibility of BHS in suspected subjects.https://doi.org/10.1111/anec.13093breath holdinigelectrocardiographymachine learning |
| spellingShingle | Mohammad Reza Khalilian Saeed Tofighi Elham Zohur Attar Ali Nikkhah Mahmoud Hajipour Mohammad Ghazavi Sahar Samimi Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model Annals of Noninvasive Electrocardiology breath holdinig electrocardiography machine learning |
| title | Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model |
| title_full | Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model |
| title_fullStr | Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model |
| title_full_unstemmed | Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model |
| title_short | Prediction of breath‐holding spells based on electrocardiographic parameters using machine‐learning model |
| title_sort | prediction of breath holding spells based on electrocardiographic parameters using machine learning model |
| topic | breath holdinig electrocardiography machine learning |
| url | https://doi.org/10.1111/anec.13093 |
| work_keys_str_mv | AT mohammadrezakhalilian predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT saeedtofighi predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT elhamzohurattar predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT alinikkhah predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT mahmoudhajipour predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT mohammadghazavi predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel AT saharsamimi predictionofbreathholdingspellsbasedonelectrocardiographicparametersusingmachinelearningmodel |