Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation
Abstract Background Measuring arterial partial pressure of carbon dioxide (PaCO2) is crucial for proper mechanical ventilation, but the current sampling method is invasive. End-tidal carbon dioxide (EtCO2) has been used as a surrogate, which can be measured non-invasively, but its limited accuracy i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-02-01
|
| Series: | BMC Pediatrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12887-024-04642-0 |
| _version_ | 1797273214117740544 |
|---|---|
| author | Hye-Ji Han Bongjin Lee June Dong Park |
| author_facet | Hye-Ji Han Bongjin Lee June Dong Park |
| author_sort | Hye-Ji Han |
| collection | DOAJ |
| description | Abstract Background Measuring arterial partial pressure of carbon dioxide (PaCO2) is crucial for proper mechanical ventilation, but the current sampling method is invasive. End-tidal carbon dioxide (EtCO2) has been used as a surrogate, which can be measured non-invasively, but its limited accuracy is due to ventilation-perfusion mismatch. This study aimed to develop a non-invasive PaCO2 estimation model using machine learning. Methods This retrospective observational study included pediatric patients (< 18 years) admitted to the pediatric intensive care unit of a tertiary children’s hospital and received mechanical ventilation between January 2021 and June 2022. Clinical information, including mechanical ventilation parameters and laboratory test results, was used for machine learning. Linear regression, multilayer perceptron, and extreme gradient boosting were implemented. The dataset was divided into 7:3 ratios for training and testing. Model performance was assessed using the R2 value. Results We analyzed total 2,427 measurements from 32 patients. The median (interquartile range) age was 16 (12−19.5) months, and 74.1% were female. The PaCO2 and EtCO2 were 63 (50−83) mmHg and 43 (35−54) mmHg, respectively. A significant discrepancy of 19 (12–31) mmHg existed between EtCO2 and the measured PaCO2. The R2 coefficient of determination for the developed models was 0.799 for the linear regression model, 0.851 for the multilayer perceptron model, and 0.877 for the extreme gradient boosting model. The correlations with PaCO2 were higher in all three models compared to EtCO2. Conclusions We developed machine learning models to non-invasively estimate PaCO2 in pediatric patients receiving mechanical ventilation, demonstrating acceptable performance. Further research is needed to improve reliability and external validation. |
| first_indexed | 2024-03-07T14:40:22Z |
| format | Article |
| id | doaj.art-02192b26d08e40e896dea534e0624902 |
| institution | Directory Open Access Journal |
| issn | 1471-2431 |
| language | English |
| last_indexed | 2024-03-07T14:40:22Z |
| publishDate | 2024-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pediatrics |
| spelling | doaj.art-02192b26d08e40e896dea534e06249022024-03-05T20:22:45ZengBMCBMC Pediatrics1471-24312024-02-012411810.1186/s12887-024-04642-0Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilationHye-Ji Han0Bongjin Lee1June Dong Park2Department of Pediatrics, Seoul National University College of Medicine, Seoul National University Children’s HospitalDepartment of Pediatrics, Seoul National University College of Medicine, Seoul National University Children’s HospitalDepartment of Pediatrics, Seoul National University College of Medicine, Seoul National University Children’s HospitalAbstract Background Measuring arterial partial pressure of carbon dioxide (PaCO2) is crucial for proper mechanical ventilation, but the current sampling method is invasive. End-tidal carbon dioxide (EtCO2) has been used as a surrogate, which can be measured non-invasively, but its limited accuracy is due to ventilation-perfusion mismatch. This study aimed to develop a non-invasive PaCO2 estimation model using machine learning. Methods This retrospective observational study included pediatric patients (< 18 years) admitted to the pediatric intensive care unit of a tertiary children’s hospital and received mechanical ventilation between January 2021 and June 2022. Clinical information, including mechanical ventilation parameters and laboratory test results, was used for machine learning. Linear regression, multilayer perceptron, and extreme gradient boosting were implemented. The dataset was divided into 7:3 ratios for training and testing. Model performance was assessed using the R2 value. Results We analyzed total 2,427 measurements from 32 patients. The median (interquartile range) age was 16 (12−19.5) months, and 74.1% were female. The PaCO2 and EtCO2 were 63 (50−83) mmHg and 43 (35−54) mmHg, respectively. A significant discrepancy of 19 (12–31) mmHg existed between EtCO2 and the measured PaCO2. The R2 coefficient of determination for the developed models was 0.799 for the linear regression model, 0.851 for the multilayer perceptron model, and 0.877 for the extreme gradient boosting model. The correlations with PaCO2 were higher in all three models compared to EtCO2. Conclusions We developed machine learning models to non-invasively estimate PaCO2 in pediatric patients receiving mechanical ventilation, demonstrating acceptable performance. Further research is needed to improve reliability and external validation.https://doi.org/10.1186/s12887-024-04642-0Machine learningBlood gas analysisCapnographyMechanical ventilationRespiratory Dead Space |
| spellingShingle | Hye-Ji Han Bongjin Lee June Dong Park Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation BMC Pediatrics Machine learning Blood gas analysis Capnography Mechanical ventilation Respiratory Dead Space |
| title | Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| title_full | Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| title_fullStr | Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| title_full_unstemmed | Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| title_short | Individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| title_sort | individualized estimation of arterial carbon dioxide partial pressure using machine learning in children receiving mechanical ventilation |
| topic | Machine learning Blood gas analysis Capnography Mechanical ventilation Respiratory Dead Space |
| url | https://doi.org/10.1186/s12887-024-04642-0 |
| work_keys_str_mv | AT hyejihan individualizedestimationofarterialcarbondioxidepartialpressureusingmachinelearninginchildrenreceivingmechanicalventilation AT bongjinlee individualizedestimationofarterialcarbondioxidepartialpressureusingmachinelearninginchildrenreceivingmechanicalventilation AT junedongpark individualizedestimationofarterialcarbondioxidepartialpressureusingmachinelearninginchildrenreceivingmechanicalventilation |