Diagnostic performance of artificial intelligence in early diagnosis of mosquito-borne viral infections: Systematic review and meta-analysis
- 1Faculty of Medicine, University Vita-Salute San Raffaele, Milan, Italy
- 2PhD National Program in One Health Approaches to Infectious Diseases and Life Science Research, Department of Public Health, Experimental and Forensic Medicine, University of Pavia, Pavia, Italy
- 3Department of Cardiac, Thoracic, Vascular Sciences, and Public Health, University of Padua, Padua, Italy
Abstract
Early diagnosis of mosquito-borne viral infections is challenging because initial symptoms are often nonspecific and confirmatory testing may be delayed or unavailable. We synthesised evidence on artificial intelligence and machine learning models for the early diagnosis of dengue, chikungunya, and Zika. We conducted a PRISMA 2020-compliant systematic review and meta-analysis (PROSPERO CRD420251129670). PubMed/MEDLINE, Embase, and Scopus were searched from inception to 11 August 2025 for model-development or validation studies reporting diagnostic performance. Area under the receiver operating characteristic curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) were pooled using random-effects models, while sensitivity and specificity were jointly synthesised using a bivariate random-effects model. Risk of bias was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). Database searches identified 4,531 records, of which 43 studies met the inclusion criteria. The evidence was predominantly from Asia and overwhelmingly focused on dengue; no eligible studies evaluated West Nile virus, yellow fever, or Rift Valley fever. Pooled estimates were 0.954 (95% CI 0.936–0.968) for AUC, 0.904 (95% CI 0.888–0.918) for accuracy, 0.903 (95% CI 0.876–0.925) for PPV, and 0.882 (95% CI 0.859–0.902) for NPV. The bivariate pooled sensitivity was 0.861 (95% CI 0.809–0.900) and specificity was 0.902 (95% CI 0.871–0.927). Heterogeneity was substantial for the univariate outcomes (I2 95.8%–97.7%). Most studies were at high overall risk of bias, while calibration and external validation were uncommon. Artificial intelligence models showed encouraging diagnostic performance in the published literature, but the pooled estimates should be interpreted as descriptive summaries of a highly heterogeneous evidence base rather than as definitive estimates of real-world performance. Prospective, externally validated, well-calibrated, and geographically diverse studies are needed before routine clinical implementation can be recommended. Author summary: Mosquito-borne viral infections such as dengue, chikungunya, and Zika can be difficult to distinguish early because their initial symptoms often overlap and laboratory confirmation may not be immediately available. We reviewed 43 studies that tested artificial intelligence and machine-learning approaches for supporting early diagnosis. We found that published models generally reported high diagnostic performance, but the evidence was highly heterogeneous and was dominated by dengue studies conducted in Asia. Many studies were retrospective, most had important risks of bias, and external validation and calibration were uncommon. We also found that no single type of artificial intelligence model consistently performed better than the others. These findings suggest that artificial intelligence could eventually support earlier diagnosis and triage, but current performance estimates should not be interpreted as evidence that the models will work equally well in routine care or across different populations. We believe future research should prioritize prospective testing, external validation in diverse countries and healthcare settings, transparent reporting, calibration, and evaluation of how these tools perform when integrated into real clinical workflows.
Related
- Multiplex molecular respiratory diagnostic panels and antimicrobial use in paediatric respiratory infections: a systematic review and meta-analysis protocol.
- Early Detection of Red Palm Weevil Infestation: A Systematic Review of Sensing Technologies, Artificial Intelligence, and Field Readiness
- Metagenomic next-generation sequencing improves pathogen detection in culture-negative infections: a diagnostic performance study
- Diagnostic performance of cerebrospinal fluid examination in cases with suspected acute meningitis: a systematic review and meta-analysis
- Artificial intelligence and digital health in bronchoscopy: advances in diagnostic accuracy, real-time navigation and procedural skills training
BibTeX
@article{pennisi2026diagnostic,
title = {{Diagnostic performance of artificial intelligence in early diagnosis of mosquito-borne viral infections: Systematic review and meta-analysis}},
author = {Flavia Pennisi and Antonio Pinto and Claudia Cozzolino Cangiano and Giovanni Rezza and Carlo Signorelli and Vincenzo Baldo and Vincenza Gianfredi},
journal = {PLOS Digital Health},
year = {2026},
month = oct,
doi = {10.1371/journal.pdig.0001796},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001796},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Diagnostic performance of artificial intelligence in early diagnosis of mosquito-borne viral infections: Systematic review and meta-analysis
AU - Flavia Pennisi
AU - Antonio Pinto
AU - Claudia Cozzolino Cangiano
AU - Giovanni Rezza
AU - Carlo Signorelli
AU - Vincenzo Baldo
AU - Vincenza Gianfredi
PY - 2026
DA - 2026/10/27
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001796
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001796
AB - Early diagnosis of mosquito-borne viral infections is challenging because initial symptoms are often nonspecific and confirmatory testing may be delayed or unavailable. We synthesised evidence on artificial intelligence and machine learning models for the early diagnosis of dengue, chikungunya, and Zika. We conducted a PRISMA 2020-compliant systematic review and meta-analysis (PROSPERO CRD420251129670). PubMed/MEDLINE, Embase, and Scopus were searched from inception to 11 August 2025 for model-development or validation studies reporting diagnostic performance. Area under the receiver operating characteristic curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV) were pooled using random-effects models, while sensitivity and specificity were jointly synthesised using a bivariate random-effects model. Risk of bias was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). Database searches identified 4,531 records, of which 43 studies met the inclusion criteria. The evidence was predominantly from Asia and overwhelmingly focused on dengue; no eligible studies evaluated West Nile virus, yellow fever, or Rift Valley fever. Pooled estimates were 0.954 (95% CI 0.936–0.968) for AUC, 0.904 (95% CI 0.888–0.918) for accuracy, 0.903 (95% CI 0.876–0.925) for PPV, and 0.882 (95% CI 0.859–0.902) for NPV. The bivariate pooled sensitivity was 0.861 (95% CI 0.809–0.900) and specificity was 0.902 (95% CI 0.871–0.927). Heterogeneity was substantial for the univariate outcomes (I2 95.8%–97.7%). Most studies were at high overall risk of bias, while calibration and external validation were uncommon. Artificial intelligence models showed encouraging diagnostic performance in the published literature, but the pooled estimates should be interpreted as descriptive summaries of a highly heterogeneous evidence base rather than as definitive estimates of real-world performance. Prospective, externally validated, well-calibrated, and geographically diverse studies are needed before routine clinical implementation can be recommended. Author summary: Mosquito-borne viral infections such as dengue, chikungunya, and Zika can be difficult to distinguish early because their initial symptoms often overlap and laboratory confirmation may not be immediately available. We reviewed 43 studies that tested artificial intelligence and machine-learning approaches for supporting early diagnosis. We found that published models generally reported high diagnostic performance, but the evidence was highly heterogeneous and was dominated by dengue studies conducted in Asia. Many studies were retrospective, most had important risks of bias, and external validation and calibration were uncommon. We also found that no single type of artificial intelligence model consistently performed better than the others. These findings suggest that artificial intelligence could eventually support earlier diagnosis and triage, but current performance estimates should not be interpreted as evidence that the models will work equally well in routine care or across different populations. We believe future research should prioritize prospective testing, external validation in diverse countries and healthcare settings, transparent reporting, calibration, and evaluation of how these tools perform when integrated into real clinical workflows.
SN - 2767-3170
ER -