Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy
Abstract When children are discharged from the hospital after surgery, their caregivers often rely on subjective assessments (e.g., appetite, fatigue) to monitor postoperative recovery as objective assessment tools are scarce at home. Such imprecise and one-dimensional evaluations can result in unwa...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-023-00890-z |
| _version_ | 1797451352770609152 |
|---|---|
| author | Hassan M. K. Ghomrawi Megan K. O’Brien Michela Carter Rebecca Macaluso Rushmin Khazanchi Michael Fanton Christopher DeBoer Samuel C. Linton Suhail Zeineddin J. Benjamin Pitt Megan Bouchard Angie Figueroa Soyang Kwon Jane L. Holl Arun Jayaraman Fizan Abdullah |
| author_facet | Hassan M. K. Ghomrawi Megan K. O’Brien Michela Carter Rebecca Macaluso Rushmin Khazanchi Michael Fanton Christopher DeBoer Samuel C. Linton Suhail Zeineddin J. Benjamin Pitt Megan Bouchard Angie Figueroa Soyang Kwon Jane L. Holl Arun Jayaraman Fizan Abdullah |
| author_sort | Hassan M. K. Ghomrawi |
| collection | DOAJ |
| description | Abstract When children are discharged from the hospital after surgery, their caregivers often rely on subjective assessments (e.g., appetite, fatigue) to monitor postoperative recovery as objective assessment tools are scarce at home. Such imprecise and one-dimensional evaluations can result in unwarranted emergency department visits or delayed care. To address this gap in postoperative monitoring, we evaluated the ability of a consumer-grade wearable device, Fitbit, which records multimodal data about daily physical activity, heart rate, and sleep, in detecting abnormal recovery early in children recovering after appendectomy. One hundred and sixty-two children, ages 3–17 years old, who underwent an appendectomy (86 complicated and 76 simple cases of appendicitis) wore a Fitbit device on their wrist for 21 days postoperatively. Abnormal recovery events (i.e., abnormal symptoms or confirmed postoperative complications) that arose during this period were gathered from medical records and patient reports. Fitbit-derived measures, as well as demographic and clinical characteristics, were used to train machine learning models to retrospectively detect abnormal recovery in the two days leading up to the event for patients with complicated and simple appendicitis. A balanced random forest classifier accurately detected 83% of these abnormal recovery days in complicated appendicitis and 70% of abnormal recovery days in simple appendicitis prior to the true report of a symptom/complication. These results support the development of machine learning algorithms to predict onset of abnormal symptoms and complications in children undergoing surgery, and the use of consumer wearables as monitoring tools for early detection of postoperative events. |
| first_indexed | 2024-03-09T14:53:28Z |
| format | Article |
| id | doaj.art-a2d31abe72bc4e91ac9a0c45ff1d379e |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T14:53:28Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-a2d31abe72bc4e91ac9a0c45ff1d379e2023-11-26T14:19:55ZengNature Portfolionpj Digital Medicine2398-63522023-08-016111210.1038/s41746-023-00890-zApplying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomyHassan M. K. Ghomrawi0Megan K. O’Brien1Michela Carter2Rebecca Macaluso3Rushmin Khazanchi4Michael Fanton5Christopher DeBoer6Samuel C. Linton7Suhail Zeineddin8J. Benjamin Pitt9Megan Bouchard10Angie Figueroa11Soyang Kwon12Jane L. Holl13Arun Jayaraman14Fizan Abdullah15Department of Surgery, Northwestern University Feinberg School of MedicineShirley Ryan AbilityLabDepartment of Surgery, Northwestern University Feinberg School of MedicineShirley Ryan AbilityLabShirley Ryan AbilityLabShirley Ryan AbilityLabDepartment of Surgery, Northwestern University Feinberg School of MedicineDepartment of Surgery, Northwestern University Feinberg School of MedicineDepartment of Surgery, Northwestern University Feinberg School of MedicineDepartment of Surgery, Northwestern University Feinberg School of MedicineDepartment of Surgery, Northwestern University Feinberg School of MedicineDivision of Pediatric Surgery, Ann and Robert H. Lurie Children’s Hospital of ChicagoDepartment of Pediatrics, Northwestern University Feinberg School of MedicineDepartment of Neurology and Center for Healthcare Delivery Science and Innovation, Biological Sciences Division, University of ChicagoShirley Ryan AbilityLabDepartment of Surgery, Northwestern University Feinberg School of MedicineAbstract When children are discharged from the hospital after surgery, their caregivers often rely on subjective assessments (e.g., appetite, fatigue) to monitor postoperative recovery as objective assessment tools are scarce at home. Such imprecise and one-dimensional evaluations can result in unwarranted emergency department visits or delayed care. To address this gap in postoperative monitoring, we evaluated the ability of a consumer-grade wearable device, Fitbit, which records multimodal data about daily physical activity, heart rate, and sleep, in detecting abnormal recovery early in children recovering after appendectomy. One hundred and sixty-two children, ages 3–17 years old, who underwent an appendectomy (86 complicated and 76 simple cases of appendicitis) wore a Fitbit device on their wrist for 21 days postoperatively. Abnormal recovery events (i.e., abnormal symptoms or confirmed postoperative complications) that arose during this period were gathered from medical records and patient reports. Fitbit-derived measures, as well as demographic and clinical characteristics, were used to train machine learning models to retrospectively detect abnormal recovery in the two days leading up to the event for patients with complicated and simple appendicitis. A balanced random forest classifier accurately detected 83% of these abnormal recovery days in complicated appendicitis and 70% of abnormal recovery days in simple appendicitis prior to the true report of a symptom/complication. These results support the development of machine learning algorithms to predict onset of abnormal symptoms and complications in children undergoing surgery, and the use of consumer wearables as monitoring tools for early detection of postoperative events.https://doi.org/10.1038/s41746-023-00890-z |
| spellingShingle | Hassan M. K. Ghomrawi Megan K. O’Brien Michela Carter Rebecca Macaluso Rushmin Khazanchi Michael Fanton Christopher DeBoer Samuel C. Linton Suhail Zeineddin J. Benjamin Pitt Megan Bouchard Angie Figueroa Soyang Kwon Jane L. Holl Arun Jayaraman Fizan Abdullah Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy npj Digital Medicine |
| title | Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| title_full | Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| title_fullStr | Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| title_full_unstemmed | Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| title_short | Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| title_sort | applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy |
| url | https://doi.org/10.1038/s41746-023-00890-z |
| work_keys_str_mv | AT hassanmkghomrawi applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT megankobrien applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT michelacarter applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT rebeccamacaluso applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT rushminkhazanchi applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT michaelfanton applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT christopherdeboer applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT samuelclinton applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT suhailzeineddin applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT jbenjaminpitt applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT meganbouchard applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT angiefigueroa applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT soyangkwon applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT janelholl applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT arunjayaraman applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy AT fizanabdullah applyingmachinelearningtoconsumerwearabledatafortheearlydetectionofcomplicationsafterpediatricappendectomy |