Forecasting Drug Demand: A Review of Predictive Methods, Limitations, and Future Directions

DOI

10.2991/978-94-6239-762-0_18How to use a DOI?

Keywords

Forecasting; Predictive analysis; Drug consumption; Accuracy; Healthcare

Abstract

Accurate forecasting of pharmaceutical demand is critical for healthcare sustainability, yet it faces persistent challenges stemming from data limitations and contextual complexities. This review synthesizes evidence from 12 studies (2018–2023) identified through systematic searches of Scopus, Web of Science, and DOAJ, with a focus on methodological approaches and implementation barriers. Geographically, the analyzed studies originated predominantly from Indonesia and Thailand, utilizing retrospective analyses of hospital, pharmacy, and primary care datasets. Methodologies included statistical models (e.g., ARIMA, SES) for stable demand patterns, machine learning techniques (e.g., LSTM, Random Forest) for epidemic-driven demand surges, and hybrid frameworks integrating both approaches. Both traditional statistical models and machine learning demonstrated promising results in predicting drug demand across healthcare facilities; however, several limitations were identified. Key gaps include the exclusion of multifactorial influences (e.g., socioeconomic factors), inconsistent data quality and scope, limited algorithm comparisons, and challenges in translating model complexity into practical implementation. To address these issues, future research should prioritize the expansion of datasets to encompass diverse geographic and demographic contexts, rigorous evaluation of additional algorithms (e.g., transformer-based models), and the development of user-centered forecasting tools that balance computational complexity with real-world feasibility.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits any noncommercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if you modified the licensed material. You do not have permission under this license to share adapted material derived from this chapter or parts of it.

Download article (PDF)

TY  - CONF
AU  - Muhammad Qowiyul Amin
AU  - Satibi Satibi
AU  - Susi Ari Kristina
AU  - Fahad Saleem
PY  - 2026
DA  - 2026/09/04
TI  - Forecasting Drug Demand: A Review of Predictive Methods, Limitations, and Future Directions
BT  - Proceedings of the 6th International Conference on Bioinformatics, Biotechnology, and Biomedical Engineering (BIOMIC 2025)
PB  - Atlantis Press
SP  - 271
EP  - 286
SN  - 2468-5739
UR  - https://doi.org/10.2991/978-94-6239-762-0_18
DO  - 10.2991/978-94-6239-762-0_18
ID  - Amin2026
ER  -