An AI-powered smartphone application for universal and standardized reading and interpretation of lateral flow assays
PLOS Global Public Health · 16.11.2026 · 6 (11) · e0005817
DOI: 10.1371/journal.pgph.0005817 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Global Public Health, online erschienen am 16.11.2026. Verfasst von David Bermejo-Peláez und 21 weiteren Autor:innen. Beteiligte Einrichtung: Spotlab, Madrid, Spain. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Innovation In SMEs, Bill and Melinda Gates Foundation, Comunidad de Madrid.
Abstract (Originalsprache)
Lateral flow assays (LFAs) are indispensable rapid diagnostic tools in healthcare, enabling point-of-care diagnosis critical for patient management and support disease burden assessment and surveillance when results are properly recorded. However, misinterpretation errors and unreported cases remain a concern. A quality-assured, affordable Ai-powered tool, supporting the decision-making during result interpretation could promote proper disease monitoring and epidemiological surveillance. Here, we describe the performance of a universal AI model to digitize and interpret results from multiple LFA types through a smartphone application, a step that could support for standardized and digitally reportable test outcomes. The AI algorithm was evaluated in 17 LFA types, including both 2-band and 3-band tests for different diseases and manufacturers. The model was trained on a dataset of 22,576 images captured under diverse lighting conditions with different smartphone models and using a custom mobile application, TiraSpot (Spotlab, Madrid, Spain). To assess generalizability, a leave-one-out cross-validation was applied, wherein each LFA type was iteratively excluded from training and used for testing. Model performance was evaluated using bootstrapping on the inference dataset. In the assessment of the model’s ability to generalize to new LFA types not previously analyzed (not included during development), the model achieved an overall AUC of 95.3% for second band detection. This overall performance was enhanced to 99.4% (Sensitivity = 98.8%; Specificity = 98.2%) after training with 50 images of each LFA type, highlighting the benefit of additional data for specific LFA types. For the third band detection, where less training data was available, the system achieved an overall AUC of 83.6% for unseen LFAs, improving to 94.05% (Sensitivity = 93.08%; Specificity = 87.87%) after training with 50 images of each LFA type. This system demonstrates the feasibility of an AI-powered universal digital reader for interpreting LFA results from diverse test types using smartphone-captured images. Its adaptability across various infections and capture devices highlights its potential to improve diagnostic consistency and support disease management in diverse healthcare settings. This system could support more consistent LFA interpretation and digital reporting, particularly where standardized result capture is needed for surveillance or quality assurance.
Autor:innen und Institutionen
- Spotlab, Madrid, Spain.
- Microbiology Department, Hospital Universitario Ramón y Cajal and Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), Madrid, Spain.
- CIBER de Epidemiología y Salud Pública (CIBERESP), Instituto de Salud Carlos III, Madrid, Spain.
- CIBER de Enfermedades Infecciosas (CIBERINFEC), Instituto de Salud Carlos III, Madrid, Spain.
- Global Action for Fungal Infections, Geneva, Switzerland.
- Mycology Reference Laboratory, National Center for Microbiology, Instituto de Salud Carlos III, Madrid, Spain.
ORCID-Profile: David Bermejo-Peláez, Lucia Pastor, Lin Lin, Jaime García-Villena, Mario Rodriguez-Dominguez, Rafael Cantón, Andrea Marchiol, Laura C Bohorquez, Jose Miguel Rubio, Elena Dacal, Miguel Luengo-Oroz
Förderung
- H2020 Innovation In SMEs
- Bill and Melinda Gates Foundation
- Comunidad de Madrid
- Ministerio de Ciencia, Innovación y Universidades
Zitieren
APA
Bermejo-Peláez, D., Darias, O., Pastor, L., Vallés, R., Diez, N., Lin, L., García-Villena, J., Cuadrado, D., Vladimirov, A., Álamo, E., Postigo, M., Rodriguez-Dominguez, M., Cantón, R., Rodriguez-Tudela, J. L., Alastruey Izquierdo, A., Marchiol, A., Segura Alba, M. L., Cortés Cortés, L. J., Bohorquez, L. C., …, & Luengo-Oroz, M. (2026). An AI-powered smartphone application for universal and standardized reading and interpretation of lateral flow assays. PLOS Global Public Health, 6(11), e0005817. https://doi.org/10.1371/journal.pgph.0005817
Vancouver
Bermejo-Peláez D, Darias O, Pastor L, Vallés R, Diez N, Lin L, et al. An AI-powered smartphone application for universal and standardized reading and interpretation of lateral flow assays. PLOS Global Public Health. 2026;6(11):e0005817. doi:10.1371/journal.pgph.0005817
BibTeX
@article{BermejoPelez2026,
author = {Bermejo-Peláez, David and Darias, Oscar and Pastor, Lucia and Vallés, Ramón and Diez, Nuria and Lin, Lin and García-Villena, Jaime and Cuadrado, Daniel and Vladimirov, Alexander and Álamo, Elisa and Postigo, Maria and Rodriguez-Dominguez, Mario and Cantón, Rafael and Rodriguez-Tudela, Juan Luis and Alastruey Izquierdo, Ana and Marchiol, Andrea and Segura Alba, Maryi Lorena and Cortés Cortés, Liliana Jazmín and Bohorquez, Laura C and Rubio, Jose Miguel and Dacal, Elena and Luengo-Oroz, Miguel},
title = {An AI-powered smartphone application for universal and standardized reading and interpretation of lateral flow assays},
journal = {PLOS Global Public Health},
year = {2026},
volume = {6},
number = {11},
pages = {e0005817},
doi = {10.1371/journal.pgph.0005817}
}
EUVIMED