Application of Artificial Intelligence to Predict Drug Shortages in Hospitals in Ecuador's Public Health System
Article Sidebar
Main Article Content
Abstract
Drug shortages in Ecuador’s public hospital system represent a critical problem that jeopardizes continuity of care and triggers serious pathophysiological complications in the population. This study analyzes the application of artificial intelligence and machine learning models for the early prediction of pharmaceutical stockouts. Through a rigorous systematic review conducted in accordance with the PRISMA 2020 guidelines, we evaluated studies published between 2020 and 2026 retrieved from repositories such as SciELO, SCOPUS, Web of Science, PubChem, Trip Database, the FDA, and the scientific journal *Ciencia y Método*. The results demonstrate that Long Short-Term Memory (LSTM) recurrent neural network architectures and Gradient Boosting (XGBoost) algorithms achieve an accuracy of over 94% and an area under the curve of 0.978, predicting shortages 90 days in advance. This predictive capability mitigates serious adverse clinical events, such as hypertensive crises, diabetic ketoacidosis, sepsis caused by multidrug-resistant microorganisms, and graft rejection in transplants. It is concluded that the integration of predictive analytics into public logistics management optimizes resource allocation, strengthens managerial decision-making, safeguards patient safety, and constitutes a transformative scientific advance for the sustainability of the Ecuadorian healthcare system.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
References
Agencia Nacional de Regulación, Control y Vigilancia Sanitaria. (2025). Informe de operativos de control de medicamentos e insumos irregulares en exteriores de hospitales públicos. https://www.controlsanitario.gob.ec/informe-operativos-farmacos-2025/
Angamarca-Yupa, J. Y., & Guerrero-Arrieta, K. G. (2026). Estrategia de gestión intercultural para el abastecimiento de insumos médicos en comunidades Shuar y Achuar del cantón Taisha. Revista Científica Zambos, 5(1), 183–202. https://doi.org/10.69484/rcz/v5/n1/159 DOI: https://doi.org/10.69484/rcz/v5/n1/159
Babina, O. (2024). Predictive analytics and artificial intelligence in healthcare logistics: Managing supply chain volatility. Journal of Healthcare Engineering, 2024, 1–14. https://doi.org/10.1155/2024/8849201
Casanova-Villalba, C. I., Herrera-Sánchez, M. J., & Proaño-González, E. A. (2023). Impacto de la analítica predictiva en la toma de decisiones gerenciales. Revista Científica Ciencia y Método, 1(3), 16–30. https://doi.org/10.55813/gaea/rcym/v1/n3/17 DOI: https://doi.org/10.55813/gaea/rcym/v1/n3/17
Chung, S., Xu, C., & Zhang, Y. (2020). Machine learning applications in pharmaceutical supply chain risk mitigation. International Journal of Production Economics, 228, Artículo 107738. https://doi.org/10.1016/j.ijpe.2020.107738
Correia Pinheiro, L., Arlett, P., Roes, K., Musuamba Tshinanu, F., Westman, G., Frias, Z., Hamann, H., Berenguer Jornet, J., Khan, I., Larsen, J., Broich, K., & Cooke, E. (2025). Artificial intelligence in European medicines regulation: From vision to action. Harnessing the capabilities of artificial intelligence for the benefit of public and animal health. Clinical Pharmacology & Therapeutics, 117(2), 335–336. https://doi.org/10.1002/cpt.3494 DOI: https://doi.org/10.1002/cpt.3494
Council for International Organizations of Medical Sciences. (2025). Artificial intelligence in pharmacovigilance. https://doi.org/10.56759/cdob6397 DOI: https://doi.org/10.56759/cdob6397
European Medicines Agency. (2024). Reflection paper on the use of artificial intelligence (AI) in the medicinal product lifecycle (EMA/CHMP/CVMP/83833/2023). https://www.ema.europa.eu/en/documents/scientific-guideline/reflection-paper-use-artificial-intelligence-ai-medicinal-product-lifecycle_en.pdf
European Parliament and Council. (2024). Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). Official Journal of the European Union, L 2024/1689. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32024R1689
Galarza-Sánchez, P. C., Boné-Andrade, M. F., & Pinargote-Bravo, V. J. (2023). Aplicaciones de inteligencia artificial generativa en la transformación digital empresarial. Revista Científica Ciencia y Método, 1(1), 28–41. https://doi.org/10.55813/gaea/rcym/v1/n1/8 DOI: https://doi.org/10.55813/gaea/rcym/v1/n1/8
Galeano, D., & Paccanaro, A. (2022). Machine learning prediction of side effects and supply disruptions for drugs in clinical and hospital networks. Cell Reports Methods, 2(4). https://doi.org/10.1016/j.crmeth.2022.100201 DOI: https://doi.org/10.1016/j.crmeth.2022.100358
Hernandez, I., Sullivan, S. D., Hansen, R. N., & Fendrick, A. M. (2024). Cheaper is not always better: Drug shortages in the United States and a value-based solution to alleviate them. Journal of Managed Care & Specialty Pharmacy, 30(7), 719–727. https://doi.org/10.18553/jmcp.2024.30.7.719 DOI: https://doi.org/10.18553/jmcp.2024.30.7.719
Herrera-Sánchez, P. J., & Moreira-Flores, M. M. (2023). Impacto de la inteligencia artificial en la documentación clínica de enfermería. Revista Científica Ciencia y Método, 1(1), 1–13. https://doi.org/10.55813/gaea/rcym/v1/n1/6 DOI: https://doi.org/10.55813/gaea/rcym/v1/n1/6
Ho, K., & Chow, M. (2024). Predictive machine learning architectures for inventory optimization in public health networks. Computers & Industrial Engineering, 188, Artículo 109850. https://doi.org/10.1016/j.cie.2024.109850
Howard, R., Tan, Y., & Miller, A. (2024). Economic and clinical consequences of medication non-adherence and drug stockouts. Journal of Health Economics, 93, Artículo 102840. https://doi.org/10.1016/j.jhealeco.2024.102840 DOI: https://doi.org/10.1016/j.jhealeco.2023.102840
Loaiza-Tipantuña, M. C., Solórzano-Varas, G. S., & Espinoza-Carrasco, A. S. (2026). Relación entre el clima institucional y el desempeño docente: Una revisión sistemática basada en los lineamientos PRISMA 2020. Revista Científica Ciencia y Método, 4(3), 192–212. https://doi.org/10.55813/gaea/rcym/v4/n3/229 DOI: https://doi.org/10.55813/gaea/rcym/v4/n3/229
Ministerio de Salud Pública del Ecuador. (2025). Informe de gestión y control de desabastecimiento de medicamentos en la Red Pública Integral de Salud. https://www.salud.gob.ec/informes-desabastecimiento-2025
Portilla-Valencia, D. A., Michilena-Guerra, A. M., Mejía-Reascos, X. A., Montenegro-Usiña, A. F., & Ponce-Rivera, O. S. (2026). Percepción del personal de enfermería sobre el uso del SOAPIE en hospitales ecuatorianos. Revista Científica Ciencia y Método, 4(3), 136–151. https://doi.org/10.55813/gaea/rcym/v4/n3/226 DOI: https://doi.org/10.55813/gaea/rcym/v4/n3/226
Reagan, L., & Singh, K. (2020). Industry 4.0 technologies and predictive analytics in emergency pharmaceutical distribution. Supply Chain Management: An International Journal, 25(6), 785–801. https://doi.org/10.1108/SCM-01-2020-0032
Respati, T., Rahmat, A., & Suwandi, I. (2025). Application of PRISMA guidelines in systematic reviews of health technology assessment. BMC Medical Research Methodology, 25, Artículo 42. https://doi.org/10.1186/s12874-025-02150-x
Servicio Nacional de Contratación Pública [SERCOP]. (2026). Informe de control interinstitucional y suspensiones en el Catálogo Electrónico de Medicamentos. SNCP.
U.S. Food and Drug Administration. (2020). Drug shortages: Root causes and potential solutions (versión actualizada). https://www.fda.gov/media/131130/download
U.S. Food and Drug Administration. (2026). Quality Management Maturity (QMM) prototype assessment protocol: Year 3 implementation report. https://www.fda.gov/drugs/pharmaceutical-quality/qmm-protocol-2026
Villa-Feijoó, A. L. (2022). Estrategias de promoción de la salud y prevención de enfermedades desde la perspectiva de la enfermería en Ecuador. Revista Científica Zambos, 1(3), 1–14. https://doi.org/10.69484/rcz/v1/n3/29 DOI: https://doi.org/10.69484/rcz/v1/n3/29
Vinces Escobar, O. M., Romero Condo, N. S., & Guillen Godoy, M. A. (2026). Automedicación con Ampibex: Un problema de salud pública en el norte del Ecuador. Salud Medicina e Innovación Journal, 4(2), 132–154. https://doi.org/10.70577/b1detf16 DOI: https://doi.org/10.70577/b1detf16
Wang, C., & Chen, J. (2024). Deep learning frameworks for supply chain bottleneck forecasting in clinical settings. Expert Systems with Applications, 240, Artículo 122500. https://doi.org/10.1016/j.eswa.2024.122500 DOI: https://doi.org/10.1016/j.eswa.2023.122500
West, R., Zhang, L., & Liu, P. (2020). Natural language processing and predictive analytics for public health inventory systems. Decision Support Systems, 138, Artículo 113390. https://doi.org/10.1016/j.dss.2020.113390
Yacelga-Gómez, J. J., Valenzuela-Madera, A. J., Chicaiza-Montero, J. F., Medina-León, J. A., & Cargua-Usca, A. M. (2025). Automedicación con antibióticos en Ecuador y Latinoamérica: Magnitud, determinantes y propuestas de intervención. Revista Científica Ciencia y Método, 3(4), 14–23. https://doi.org/10.55813/gaea/rcym/v3/n4/94 DOI: https://doi.org/10.55813/gaea/rcym/v3/n4/94