Towards a machine-learning assisted non-invasive classification of dengue severity using wearable PPG data: a prospective clinical study
Open accessAbstract
BACKGROUND: Dengue epidemics impose considerable strain on healthcare resources. Real-time continuous and non-invasive monitoring of patients admitted to the hospital could lead to improved care and outcomes. We evaluated the performance of a commercially available wearable (SmartCare) utilising photoplethysmography (PPG) to stratify clinical risk for a cohort of hospitalised patients with dengue in Vietnam. METHODS: We performed a prospective observational study for adult and paediatric patients with a clinical diagnosis of dengue at the Hospital for Tropical Disease, Ho Chi Minh City, Vietnam. Patients underwent PPG monitoring early during admission alongside standard clinical care. PPG waveforms were analysed using machine learning models. Adult patients were classified between 3 severity classes: i) uncomplicated (ward-based), ii) moderate-severe (emergency department-based), and iii) severe (ICU-based). Data from paediatric patients were split into 2 classes: i) severe (during ICU stay) and ii) follow-up (14-21 days after the illness onset). Model performances were evaluated using standard classification metrics and 5-fold stratified cross-validation. FINDINGS: We included PPG and clinical data from 132 adults and 15 paediatric patients with a median age of 28 (IQR, 21-35) and 12 (IQR, 9-13) years respectively. 1781 h of PPG data were available for analysis. The best performing convolutional neural network models (CNN) achieved a precision of 0.785 and recall of 0.771 in classifying adult patients according to severity class and a precision of 0.891 and recall of 0.891 in classifying between disease and post-disease state in paediatric patients. INTERPRETATION: We demonstrate that the use of a low-cost wearable provided clinically actionable data to differentiate between patients with dengue of varying severity. Continuous monitoring and connectivity to early warning systems could significantly benefit clinical care in dengue, particularly within an endemic setting. Work is currently underway to implement these models for dynamic risk predictions and assist in individualised patient care. FUNDING: EPSRC Centre for Doctoral Training in High-Performance Embedded and Distributed Systems (HiPEDS) (Grant: EP/L016796/1) and the Wellcome Trust (Grants: 215010/Z/18/Z and 215688/Z/19/Z).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Optical sensors detect blood flow and oxygenation changes using light absorption spectra and reflection principles, and are used for muscle movement detection, heart rate monitoring, blood pressure monitoring, respiratory, blood oxygen saturation, and heart rate monitoring.
“Detect blood flow and oxygenation changes using | light absorption spectra and reflection principles 215”
From Recent advances in intelligent wearable systems: from multiscale biomechanical features towards human motion intent prediction (2026) · cites this paper as [217]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430 · see citing works
Heart Rate Variability: Standards of Measurement, Physiological Interpretation, and Clinical Use
Electrophysiology, T. F. O. T. E. S. O. C. T. N. A. (1996) · Circulation · doi:10.1161/01.cir.93.5.1043 · Cited by 17,159 · see citing works
The global distribution and burden of dengue
Bhatt, S., Gething, P. W., Brady, O. J., Messina, J. P., Farlow, A. W., Moyes, C. L., Drake, J. M., Brownstein, J. S., Hoen, A. G., Sankoh, O., et al. (2013) · Nature · doi:10.1038/nature12060 · Cited by 10,037 · see citing works
Photoplethysmography and its application in clinical physiological measurement
Allen, J. (2007) · Physiological Measurement · doi:10.1088/0967-3334/28/3/r01 · Cited by 3,967 · see citing works
Simmons, C. P., Farrar, J., Châu, N. V. V., & Wills, B. A. (2012) · New England Journal of Medicine · doi:10.1056/nejmra1110265 · Cited by 1,736 · see citing works
Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks
Reiss, A., Indlekofer, I., Schmidt, P., & Laerhoven, K. V. (2019) · Sensors · doi:10.3390/s19143079 · Cited by 383 · see citing works
Optimal Signal Quality Index for Photoplethysmogram Signals
Elgendi, M. (2016) · Bioengineering · doi:10.3390/bioengineering3040021 · Cited by 338 · see citing works
An optimal filter for short photoplethysmogram signals
Liang, Y., Elgendi, M., Chen, Z., & Ward, R. (2018) · Scientific Data · doi:10.1038/sdata.2018.76 · Cited by 242 · see citing works
Ming, D., Sangkaew, S., Chanh, H. Q., Phung, N. T. H., Yacoub, S., Georgiou, P., & Holmes, A. (2020) · International Journal of Infectious Diseases · doi:10.1016/j.ijid.2020.05.086 · Cited by 76 · see citing works
Self-citationAllen, J., Liu, H., Iqbal, S., Zheng, D., & Stansby, G. P. (2021) · Physiological Measurement · doi:10.1088/1361-6579/abf9f3 · Cited by 72 · see citing works
Dengue Prediction using Machine Learning Algorithms
Sarma, D., Hossain, S., Mittra, T., Bhuiya, M. A. M., Saha, I., & Chakma, R. (2020) · IEEE Region Humanitarian Technology Conference · doi:10.1109/r10-htc49770.2020.9357035 · Cited by 54 · see citing works
Karolcik, S., Ming, D. K. Y., Yacoub, S., Holmes, A. H., & Georgiou, P. (2023) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2023.3254453 · Cited by 33 · see citing works
Self-citationConnectivity of rapid-testing diagnostics and surveillance of infectious diseases
Ming, D. K. Y., Rawson, T. M., Sangkaew, S., Rodríguez-Manzano, J., Georgiou, P., & Holmes, A. H. (2019) · Bulletin of the World Health Organization · doi:10.2471/blt.18.219691 · Cited by 30 · see citing works
Self-citationState-of-the-art monitoring in treatment of dengue shock syndrome: a case series
Moulton, S. L., Mulligan, J., Srikiatkhachorn, A., Kalayanarooj, S., Grudić, G. Z., Green, S., Gibbons, R. V., Muniz, G. W., Hinojosa‐Laborde, C., Rothman, A. L., et al. (2016) · Journal of Medical Case Reports · doi:10.1186/s13256-016-1019-z · Cited by 26 · see citing works
Ming, D. K. Y., Tuan, N. M., Hernandez, B., Sangkaew, S., Vuong, N. L., Chanh, H. Q., Chau, N. V., Simmons, C. P., Wills, B. A., Georgiou, P., et al. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2022.849641 · Cited by 23 · see citing works
Self-citationVIRDOCD : A VIRtual DOCtor to predict dengue fatality
Chattopadhyay, A. K., & Chattopadhyay, S. (2021) · Expert Systems · doi:10.1111/exsy.12796 · Cited by 18 · see citing works
Predicting Case Fatality of Dengue Epidemic: Statistical Machine Learning Towards a Virtual Doctor
Chattopadhyay, S., Chattopadhyay, A. K., & Aifantis, E. C. (2021) · Journal of Nanotechnology in Diagnosis and Treatment · doi:10.12974/2311-8792.2021.07.2 · Cited by 17 · see citing works
Severity detection tool for patients with infectious disease
Tadesse, G. A., Zhu, T., Thanh, N. L. N., et al. (2020) · Healthcare Technology Letters · doi:10.1049/htl.2019.0030 · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 23 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- [3]Organization W.H. Dengue guidelines for diagnosis, treatment, prevention and control new edition 2009 World Health Organization 23762963
- [6]Janak J. Howard J. Goei K. Predictors of the onset of Hemodynamic decompensation during progressive central hypovolemia: comparison of the peripheral perfusion index, pulse pressure variability, and compensatory reserve index Shock 11 2015 44 26529655
Cited by
Sorted by citations
Artificial Intelligence for Noninvasive Health Diagnostics
Wankhede, P., Bhuyar, D. L., Zanwar, S. R., Pawar, R., Jadhav, M. R., Gandhewar, N., Kulkarni, M. B., Bhaiyya, M. L., & Haick, H. (2025) · ACS Sensors · doi:10.1021/acssensors.5c03171 · Cited by 24 · see citing works
Hernandez, B., Ming, D. K. Y., Rawson, T. M., Bolton, W., Wilson, R. C., Vasikasin, V., Daniels, J., Rodríguez-Manzano, J., Davies, F., Georgiou, P., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.103008 · Cited by 13 · see citing works
Self-citationChen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9 · see citing works
Quero‐Delgado, M., Codina, H., Gómez, R., Terán, F. J., Muñoz‐Fernández, M. Á., Jiménez, J. L., Resino, S., Sepúlveda‐Crespo, D., & Martínez, I. (2025) · Medicinal Research Reviews · doi:10.1002/med.70006 · Cited by 6 · see citing works
Reliable wrist PPG monitoring by mitigating poor skin sensor contact
Pham, H. M., Ho, M. Y., Zhang, Y., Spathis, D., Saeed, A., & Ma, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-31883-5 · Cited by 10 · see citing works
Pennisi, F., Pinto, A., Cozzolino, C., Cozza, A., Rezza, G., Signorelli, C., Baldo, V., & Gianfredi, V. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8040093 · Cited by 5 · see citing works
Ahmed, M. M., Othman, Z. K., Mahamed, S. M., Okesanya, O. J., Musa, S. S., Branda, F., & Lucero‐Prisno, D. E. (2025) · Digital Health · doi:10.1177/20552076251396563 · Cited by 3 · see citing works
Lyle, N. N., Chanh, H. Q., Van, H. N., Anibal, J., Karolcik, S., Ming, D. K. Y., Thi, G. N., Thanh, H. V. N., Quang, H. N., Hai, H. B., et al. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000924 · Cited by 4 · see citing works
Self-citationSamant, M., & Pacharaney, U. S. (2025) · Sensors · doi:10.3390/s25206362 · Cited by 2 · see citing works
Agrawal, S., & Agbeyangi, A. O. (2026) · Computers in Human Behavior Artificial Humans · doi:10.1016/j.chbah.2026.100259 · Cited by 2 · see citing works
Critical care research in low- and middle-income countries: a narrative review
Salluh, J. I., Amado, F., Pisani, L., Quintairos, A., Nassar, A. P., Besen, B. A. M. P., Sendagire, C., de Souza, D. C., Bozza, F. A., Burghi, G., et al. (2025) · Thorax · doi:10.1136/thorax-2024-221988 · Cited by 1 · see citing works
Automated Coronary Heart Disease Diagnosis and Severity Classification Using Machine Learning
Kaur, K., Singh, C., & Kumar, Y. (2025) · International Conference on Sustainability, Innovation & Technology (ICSIT) · doi:10.1109/icsit65336.2025.11293865
Selvi, P. S., & Marimuthu, T. (2026) · International Conference on Communication, Computing and Electronics Systems (ICCCES) · doi:10.1109/iccces62661.2026.11437014
Wearable AI for continuous pediatric patient monitoring: a systematic review and meta-analysis
Fang, S.-S., & Chen, S.-H. (2026) · Egyptian Pediatric Association Gazette · doi:10.1186/s43054-026-00574-9
Wearable Sensors for Pediatrics: Evolution, Challenges, and Opportunities in Living Environments
Cosoli, G., Bencivenga, C., Arnesano, M., Verdini, F., & D’Alvia, L. (2026) · IEEE International Workshop on Metrology for Living Environment (MetroLivEnv) · doi:10.1109/metrolivenv70468.2026.11659921
Yılmaz, L. Z. B., Küçükakçalı, Z., & Akbulut, S. (2026) · Diagnostics · doi:10.3390/diagnostics16182966
Aziz, A., Kaçmaz, S., & Aladwani, A. (2026) · Diagnostics · doi:10.3390/diagnostics16193121
Ooi, Y. S., Cattrall, J. W. S., Brady, O. J., Kalimuddin, S., Lim, J. T., López‐Medina, E., Thomas, S. J., Yacoub, S., & Ooi, E. E. (2026) · Nature Reviews Disease Primers · doi:10.1038/s41572-026-00744-4
Self-citation
- Authors
- Karolcik, S., Manginas, V., Chanh, H. Q., Daniels, J., Giang, N. T., Huyen, V. N. T., Hoang, M. T. V., Phan Nguyen Quoc, K., Hernandez, B., Ming, D. K., Nguyen Van, H., Phan, T. Q., Trieu, H. T., Luong Thi Hue, T., Holmes, A. H., Thwaites, L., Phan Vinh, T., Yacoub, S., & Georgiou, P.
- Affiliations
- Imperial College London (GB)
- Oxford University Clinical Research Unit (VN)
- Corresponding author
- Karolcik, Stefan
- ORCID
- Venue
- eBioMedicine
- Publisher
- Elsevier BV
- Published
- 2024-06
- Volume
- 104
- Pages
- 105164
- ISSN
- 2352-3964 (ISSN-L)
- PMC
- PMC11167237
- OpenAlex
- W4399129797
- Cited by
- 18
- References
- 23
- Citations by year
- 2026: 9 · 2025: 8 · 2024: 1
- FWCI
- 1.97
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- EBioMedicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Wellcome Trust
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Mosquito-borne diseases and control
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- dengue, disease severity classification, continuous physiological monitoring, convolutional neural networks, pediatric dengue, hospitalized patients, clinical risk stratification, early warning systems, non-invasive monitoring, low-cost wearable device
- MeSH terms
- Machine Learning, Wearable Electronic Devices, Adolescent, Adult, Child, Dengue, Female, Humans, Male, Prospective Studies, Severity of Illness Index, Vietnam, Photoplethysmography, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
