Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19
Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/23/9597 |
| _version_ | 1827591974675283968 |
|---|---|
| author | Jin-Yeong Kang Ye Seul Bae Eui Kyu Chie Seung-Bo Lee |
| author_facet | Jin-Yeong Kang Ye Seul Bae Eui Kyu Chie Seung-Bo Lee |
| author_sort | Jin-Yeong Kang |
| collection | DOAJ |
| description | Coronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices and clinical questionnaires. The derivation cohort consisted of people diagnosed with COVID-19 between September and December 2021, and the external validation cohort collected between March and June 2022. To develop the model, a total of 50 participants wore the device for an average of 77 h. To evaluate the model, a total of 181 infected participants wore the device for an average of 65 h. We designed machine learning-based models that predict deterioration in patients with mild COVID-19. The prediction model, 10 min in advance, showed an area under the receiver characteristic curve (AUC) of 0.99, and the prediction model, 8 h in advance, showed an AUC of 0.84. We found that certain variables that are important to model vary depending on the point in time to predict. Efficient deterioration monitoring in many patients is possible by utilizing data collected from wearable sensors and symptom self-reports. |
| first_indexed | 2024-03-09T01:42:10Z |
| format | Article |
| id | doaj.art-876cad5ce4884ed4933afa091d44d66f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T01:42:10Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-876cad5ce4884ed4933afa091d44d66f2023-12-08T15:26:32ZengMDPI AGSensors1424-82202023-12-012323959710.3390/s23239597Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19Jin-Yeong Kang0Ye Seul Bae1Eui Kyu Chie2Seung-Bo Lee3Department of Medical Informatics, Keimyung University, Daegu 42601, Republic of KoreaDepartment of Family Medicine, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul 03181, Republic of KoreaDepartment of Radiation Oncology, Seoul National University College of Medicine, Seoul 03080, Republic of KoreaDepartment of Medical Informatics, Keimyung University, Daegu 42601, Republic of KoreaCoronavirus has caused many casualties and is still spreading. Some people experience rapid deterioration that is mild at first. The aim of this study is to develop a deterioration prediction model for mild COVID-19 patients during the isolation period. We collected vital signs from wearable devices and clinical questionnaires. The derivation cohort consisted of people diagnosed with COVID-19 between September and December 2021, and the external validation cohort collected between March and June 2022. To develop the model, a total of 50 participants wore the device for an average of 77 h. To evaluate the model, a total of 181 infected participants wore the device for an average of 65 h. We designed machine learning-based models that predict deterioration in patients with mild COVID-19. The prediction model, 10 min in advance, showed an area under the receiver characteristic curve (AUC) of 0.99, and the prediction model, 8 h in advance, showed an AUC of 0.84. We found that certain variables that are important to model vary depending on the point in time to predict. Efficient deterioration monitoring in many patients is possible by utilizing data collected from wearable sensors and symptom self-reports.https://www.mdpi.com/1424-8220/23/23/9597monitoringwearable sensorsmachine learningmild COVID-19 |
| spellingShingle | Jin-Yeong Kang Ye Seul Bae Eui Kyu Chie Seung-Bo Lee Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 Sensors monitoring wearable sensors machine learning mild COVID-19 |
| title | Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 |
| title_full | Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 |
| title_fullStr | Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 |
| title_full_unstemmed | Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 |
| title_short | Predicting Deterioration from Wearable Sensor Data in People with Mild COVID-19 |
| title_sort | predicting deterioration from wearable sensor data in people with mild covid 19 |
| topic | monitoring wearable sensors machine learning mild COVID-19 |
| url | https://www.mdpi.com/1424-8220/23/23/9597 |
| work_keys_str_mv | AT jinyeongkang predictingdeteriorationfromwearablesensordatainpeoplewithmildcovid19 AT yeseulbae predictingdeteriorationfromwearablesensordatainpeoplewithmildcovid19 AT euikyuchie predictingdeteriorationfromwearablesensordatainpeoplewithmildcovid19 AT seungbolee predictingdeteriorationfromwearablesensordatainpeoplewithmildcovid19 |