An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data.
Dengue shock syndrome (DSS) is a serious complication of dengue infection which occurs when critical plasma leakage results in haemodynamic shock. Treatment is challenging as fluid therapy must balance the risk of hypoperfusion with volume overload. In this study, we investigate the potential utilit...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-07-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://doi.org/10.1371/journal.pdig.0000924 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849714329838944256 |
|---|---|
| author | Ngan Nguyen Lyle Ho Quang Chanh Hao Nguyen Van James Anibal Stefan Karolcik Damien Ming Giang Nguyen Thi Huyen Vu Ngo Thanh Huy Nguyen Quang Hai Ho Bich Khoa Le Dinh Van Van Hoang Minh Tu Khanh Phan Nguyen Quoc Huynh Trung Trieu Qui Tu Phan Tho Phan Vinh Tai Luong Thi Hue Pantelis Georgiou Louise Thwaites Sophie Yacoub Vietnam ICU Translational Applications Laboratory (VITAL) investigators |
| author_facet | Ngan Nguyen Lyle Ho Quang Chanh Hao Nguyen Van James Anibal Stefan Karolcik Damien Ming Giang Nguyen Thi Huyen Vu Ngo Thanh Huy Nguyen Quang Hai Ho Bich Khoa Le Dinh Van Van Hoang Minh Tu Khanh Phan Nguyen Quoc Huynh Trung Trieu Qui Tu Phan Tho Phan Vinh Tai Luong Thi Hue Pantelis Georgiou Louise Thwaites Sophie Yacoub Vietnam ICU Translational Applications Laboratory (VITAL) investigators |
| author_sort | Ngan Nguyen Lyle |
| collection | DOAJ |
| description | Dengue shock syndrome (DSS) is a serious complication of dengue infection which occurs when critical plasma leakage results in haemodynamic shock. Treatment is challenging as fluid therapy must balance the risk of hypoperfusion with volume overload. In this study, we investigate the potential utility of wearable photoplethysmography (PPG) to determine volume status in DSS. In this prospective observational study, we enrolled 250 adults and children with a clinical diagnosis of dengue admitted to the Hospital for Tropical Diseases, Ho Chi Minh City. PPG monitoring using a wearable device was applied for a 24-hour period. Clinical events were then matched to the PPG data by date and time. We predefined two clinical states for comparison: (1) the 2-hour period before a shock event was an "empty" volume state and (2) the 2-hour period between 1 and 3 hours after a fluid initiation event was a "full" volume state. PPG data were sampled from these states for analysis. Variability and waveform morphology features were extracted and analyzed using principal components analysis and random forest. Waveform images were used to develop a computer vision model. Of the 250 patients enrolled, 90 patients experienced the predefined outcomes, and had sufficient data for the analysis. Principal components analysis identified four principal components (PCs), from the 23 pulse wave features. Logistic regression using these PCs showed that the empty state is associated with PCs 1 (p = 0.016) and 4 (p = 0.036) with both PCs denoting increased sympathetic activity. Random forest showed that heart rate and the LF-HF ratio are the most important features. A computer vision model had a sensitivity of 0.81 and a specificity of 0.70 for the empty state. These results provide proof of concept that an artificial intelligence-based approach using continuous PPG monitoring can provide information on volume states in DSS. |
| format | Article |
| id | doaj-art-cb4fd8bdca2e499ba112fe9c2b2eb690 |
| institution | DOAJ |
| issn | 2767-3170 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj-art-cb4fd8bdca2e499ba112fe9c2b2eb6902025-08-20T03:13:44ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702025-07-0147e000092410.1371/journal.pdig.0000924An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data.Ngan Nguyen LyleHo Quang ChanhHao Nguyen VanJames AnibalStefan KarolcikDamien MingGiang Nguyen ThiHuyen Vu Ngo ThanhHuy Nguyen QuangHai Ho BichKhoa Le Dinh VanVan Hoang Minh TuKhanh Phan Nguyen QuocHuynh Trung TrieuQui Tu PhanTho Phan VinhTai Luong Thi HuePantelis GeorgiouLouise ThwaitesSophie YacoubVietnam ICU Translational Applications Laboratory (VITAL) investigatorsDengue shock syndrome (DSS) is a serious complication of dengue infection which occurs when critical plasma leakage results in haemodynamic shock. Treatment is challenging as fluid therapy must balance the risk of hypoperfusion with volume overload. In this study, we investigate the potential utility of wearable photoplethysmography (PPG) to determine volume status in DSS. In this prospective observational study, we enrolled 250 adults and children with a clinical diagnosis of dengue admitted to the Hospital for Tropical Diseases, Ho Chi Minh City. PPG monitoring using a wearable device was applied for a 24-hour period. Clinical events were then matched to the PPG data by date and time. We predefined two clinical states for comparison: (1) the 2-hour period before a shock event was an "empty" volume state and (2) the 2-hour period between 1 and 3 hours after a fluid initiation event was a "full" volume state. PPG data were sampled from these states for analysis. Variability and waveform morphology features were extracted and analyzed using principal components analysis and random forest. Waveform images were used to develop a computer vision model. Of the 250 patients enrolled, 90 patients experienced the predefined outcomes, and had sufficient data for the analysis. Principal components analysis identified four principal components (PCs), from the 23 pulse wave features. Logistic regression using these PCs showed that the empty state is associated with PCs 1 (p = 0.016) and 4 (p = 0.036) with both PCs denoting increased sympathetic activity. Random forest showed that heart rate and the LF-HF ratio are the most important features. A computer vision model had a sensitivity of 0.81 and a specificity of 0.70 for the empty state. These results provide proof of concept that an artificial intelligence-based approach using continuous PPG monitoring can provide information on volume states in DSS.https://doi.org/10.1371/journal.pdig.0000924 |
| spellingShingle | Ngan Nguyen Lyle Ho Quang Chanh Hao Nguyen Van James Anibal Stefan Karolcik Damien Ming Giang Nguyen Thi Huyen Vu Ngo Thanh Huy Nguyen Quang Hai Ho Bich Khoa Le Dinh Van Van Hoang Minh Tu Khanh Phan Nguyen Quoc Huynh Trung Trieu Qui Tu Phan Tho Phan Vinh Tai Luong Thi Hue Pantelis Georgiou Louise Thwaites Sophie Yacoub Vietnam ICU Translational Applications Laboratory (VITAL) investigators An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. PLOS Digital Health |
| title | An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. |
| title_full | An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. |
| title_fullStr | An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. |
| title_full_unstemmed | An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. |
| title_short | An artificial intelligence-based approach to identify volume status in patients with severe dengue using wearable PPG data. |
| title_sort | artificial intelligence based approach to identify volume status in patients with severe dengue using wearable ppg data |
| url | https://doi.org/10.1371/journal.pdig.0000924 |
| work_keys_str_mv | AT ngannguyenlyle anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT hoquangchanh anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT haonguyenvan anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT jamesanibal anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT stefankarolcik anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT damienming anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT giangnguyenthi anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huyenvungothanh anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huynguyenquang anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT haihobich anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT khoaledinhvan anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT vanhoangminhtu anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT khanhphannguyenquoc anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huynhtrungtrieu anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT quituphan anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT thophanvinh anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT tailuongthihue anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT pantelisgeorgiou anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT louisethwaites anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT sophieyacoub anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT vietnamicutranslationalapplicationslaboratoryvitalinvestigators anartificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT ngannguyenlyle artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT hoquangchanh artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT haonguyenvan artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT jamesanibal artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT stefankarolcik artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT damienming artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT giangnguyenthi artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huyenvungothanh artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huynguyenquang artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT haihobich artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT khoaledinhvan artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT vanhoangminhtu artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT khanhphannguyenquoc artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT huynhtrungtrieu artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT quituphan artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT thophanvinh artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT tailuongthihue artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT pantelisgeorgiou artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT louisethwaites artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT sophieyacoub artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata AT vietnamicutranslationalapplicationslaboratoryvitalinvestigators artificialintelligencebasedapproachtoidentifyvolumestatusinpatientswithseveredengueusingwearableppgdata |