Abstract
Accurate pharmaceutical demand forecasting is essential to ensure timely drug availability, reduce inventory costs, and improve operational efficiency in healthcare supply chains. However, existing statistical, machine learning, and deep learning approaches often struggle to capture the nonlinear and dynamic demand patterns arising from drug substitutions, comorbidity treatments, and seasonal disease fluctuations. To address this challenge, we propose KG-GCN-LSTM, a novel hybrid model that integrates a pharmaceutical knowledge graph (KG) with deep learning techniques. A clipped Graph Convolutional Network (GCN) is employed to extract feature representations from both the historical demand of the target drug and the related drugs encoded in the knowledge graph. The outputs of the GCN are subsequently processed by a Long Short-Term Memory (LSTM) network to capture temporal dynamics in drug demand. Experiments on real-world pharmacy sales data demonstrate that KG-GCN-LSTM consistently outperforms established benchmarks—including ARIMA, SVR, XGBoost, RNN, CNN-LSTM, TimeMixer and NBEATS, achieving a 3.62% reduction in Symmetric Mean Absolute Percentage Error (SMAPE) relative to NBEATS, while delivering performance comparable to the state-of-the-art TimeMixer. These results highlight the effectiveness of knowledge graph–enhanced deep learning in improving the accuracy and robustness of pharmaceutical demand forecasting, which can support data-driven decision-making in healthcare supply chain management.
Similar content being viewed by others
Data availability
The datasets generated and analyzed during the current study are available from the corresponding author on reasonable request.
References
Bilal, A. I., Bititci, U. S. & Fenta, T. G. Challenges and the Way Forward in Demand-Forecasting Practices within the Ethiopian Public Pharmaceutical Supply Chain. Pharmacy 12, 86 (2024).
Bilal, A. I., Rostami-Tabar, B., Hewage, H. H., Bititci, U. S. & Fenta, T. G. The missing puzzle piece: contextual insights for enhanced pharmaceutical supply chain forecasting. Int. J. Prod. Res. 63, 10189–10207 (2025).
Gers, F. A., Schmidhuber, J. & Cummins, F. Learning to forget: continual prediction with LSTM. Neural Comput. 12, 2451–2471 (2000).
Zhao, L. et al. T-GCN: A Temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 21, 3848–3858 (2019).
Shi, Y., Wang, Y., Qu, Y. & Chen, Z. Integrated GCN-LSTM stock prices movement prediction based on knowledge-incorporated graphs construction. Int. J. Mach. Learn. Cybernet. 15, 161–176 (2024).
Yang, C., Li, S. & Gou, Z. Spatiotemporal prediction of urban Building rooftop photovoltaic potential based on GCN-LSTM. Energy Build. 334, 115522 (2025).
Wei, M., Wen, M. & Zhang, Y. A novel Spatial electric load forecasting method based on LDTW and GCN. IET Generation Transmission Distribution. 18, 491–505 (2024).
Wang, X. et al. Distributed LSTM-GCN-based spatial–temporal indoor temperature prediction in multizone buildings. IEEE Trans. Industr. Inf. 20, 482–491 (2023).
Gilbert, K. An ARIMA supply chain model. Manage. Sci. 51, 305–310 (2005).
Kareem, Y. & Majeed, A. R. Monthly Peak-load Demand Forecasting for Sulaimany Governorate Using SARIMA. In 2006 IEEE/PES Transmission & Distribution Conference and Exposition: Latin America. 1–5 (2006).
Jian, Y. et al. ARIMA model for predicting chronic kidney disease and estimating its economic burden in China. BMC Public. Health. 22, 2456 (2022).
Vairagade, N., Logofatu, D., Leon, F. & Muharemi, F. Demand forecasting using random forest and artificial neural network for supply chain management. In Computational Collective Intelligence: 11th International Conference, ICCCI Hendaye, France, September 4–6, 2019, Proceedings, Part I 11, 328–339 (2019).
Ji, S., Wang, X., Zhao, W. & Guo, D. An application of a three-stage XGBoost-based model to sales forecasting of a cross-border e-commerce enterprise. Mathematical Problems in Engineering (2019).
Yani, L. P. E. & Aamer, A. Demand forecasting accuracy in the pharmaceutical supply chain: a machine learning approach. Int. J. Pharm. Healthc. Mark. 17, 1–23 (2023).
Douaioui, K., Oucheikh, R., Benmoussa, O. & Mabrouki, C. Machine learning and deep learning models for demand forecasting in supply chain management: A critical review. Appl. Syst. Innov. 7, 93 (2024).
Yildiz, O. & Sucuoglu, H. S. Development of Real-Time IoT-Based air quality forecasting system using machine learning approach. Sustainability 17, 8531 (2025).
Cao, B. et al. Daily peak load prediction method based on XGBoost and MLR. Appl. Sci. 15, 11180 (2025).
Alsmadi, L., Lei, G. & Li, L. Forecasting Day-Ahead electricity demand in Australia using a CNN-LSTM model with an attention mechanism. Appl. Sci. 15, 3829 (2025).
Punia, S., Nikolopoulos, K., Singh, S. P., Madaan, J. K. & Litsiou, K. Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail. Int. J. Prod. Res. 58, 4964–4979 (2020).
Oreshkin, B. N., Carpov, D., Chapados, N. & Bengio, Y. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:.10437 (2019). (2019). (1905).
Zhang, Z., Zhang, Q., Liang, H. & Gorbani, B. Optimizing electric load forecasting with support vector regression/LSTM optimized by flexible Gorilla troops algorithm and neural networks a case study. Sci. Rep. 14, 22092 (2024).
Jeon, Y. & Seong, S. Robust recurrent network model for intermittent time-series forecasting. Int. J. Forecast. 38, 1415–1425 (2022).
Zha, W. et al. Forecasting monthly gas field production based on the CNN-LSTM model. Energy 260, 124889 (2022).
Tian, Y., Cao, H., Yan, D., Chen, J. & Hua, Y. Spatiotemporal pattern evolution and quantitative prediction of electrical carbon emissions from a demand-side perspective in urban areas. Sci. Rep. 15, 25097 (2025).
Farhadi, A., Zamanifar, A., Alipour, A., Taheri, A. & Asadolahi, M. A hybrid LSTM-GRU model for stock price prediction. IEEE Access 13, 117594–117618 (2025).
Wang, S. et al. Timemixer: Decomposable multiscale mixing for time series forecasting. arXiv preprint arXiv:2405.14616 (2024).
Fourkiotis, K. P. & Tsadiras, A. Applying machine learning and statistical forecasting methods for enhancing pharmaceutical sales predictions. Forecasting 6, 170–186 (2024).
Zhu, X., Ninh, A., Zhao, H. & Liu, Z. Demand forecasting with supply-chain information and machine learning: evidence in the pharmaceutical industry. Prod. Oper. Manage. 30, 3231–3252 (2021).
Rathipriya, R., Abdul Rahman, A. A., Dhamodharavadhani, S., Meero, A. & Yoganandan, G. Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model. Neural Comput. Appl. 35, 1945–1957 (2023).
Hapsari, I. Cluster-specific Bi-LSTM models for improved pharmaceutical sales forecasting. J. Industrial Servicess (JISS). 10, 259–270 (2024).
Mbonyinshuti, F., Nkurunziza, J., Niyobuhungiro, J. & Kayitare, E. Health supply chain forecasting: a comparison of ARIMA and LSTM time series models for demand prediction of medicines. Acta Logistica. 11, 269–280 (2024).
Priyadharshini, P., Keerthana, S. & Devi, G. K. Optimizing Pharmaceutical Supply Chains using a Hybrid CNN-LSTM Model for Accurate Medicine Demand Forecasting. In 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS). 1525–1532 (2025).
Amiri, B., Haddadi, A. & Mojdehi, K. F. A novel hybrid GCN-LSTM algorithm for energy stock price prediction: leveraging Temporal dynamics and inter-stock relationships. IEEE Access 13, 24815–24832 (2025).
Zhang, Y., Xu, S., Zhang, L., Jiang, W., Alam, S. & Xue, D. Short-term multi-step-ahead sector-based traffic flow prediction based on the attention-enhanced graph convolutional LSTM network (AGC-LSTM). Neural Comput. Appl. 37, 14869–14888 (2025).
Mishra, R. & Shridevi, S. Knowledge graph driven medicine recommendation system using graph neural networks on longitudinal medical records. Sci. Rep. 14, 25449 (2024).
Dara, O. N., Ibrahim, A. A. & Mohammed, T. A. Advancing medical imaging: detecting polypharmacy and adverse drug effects with graph convolutional networks (GCN). BMC Med. Imaging. 24, 174 (2024).
Li, A. et al. KGSCS—a smart care system for elderly with geriatric chronic diseases: a knowledge graph approach. BMC Med. Inf. Decis. Mak. 24, 73 (2024).
Yang, L., Guo, Q. & Zhang, L. AI-assisted chemistry research: a comprehensive analysis of evolutionary paths and hotspots through knowledge graphs. Chem. Commun. 60, 6977–6987 (2024).
Rendra & Gustriansyah Retail sales dataset of a pharmacy in Indonesia, Mendeley Data, V1, doi:https://doi.org/10.17632/2ym7v78wtd.1 (2022).
Knox, C. et al. DrugBank 6.0: the drugbank knowledgebase for 2024. Nucleic Acids Res. 52, D1265–D1275 (2024).
Hyndman, R. J. & Khandakar, Y. Automatic time series forecasting: the forecast package for R. J. Stat. Softw. 27, 1–22 (2008).
Aghelpour, P., Mohammadi, B. & Biazar, S. M. Long-term monthly average temperature forecasting in some climate types of Iran, using the models SARIMA, SVR, and SVR-FA. Theoret. Appl. Climatol. 138, 1471–1480 (2019).
Abbasi, R. A. et al. Short term load forecasting using XGBoost. In Workshops of the International Conference on Advanced Information Networking and Applications. 1120–1131 (2019).
Tokgöz, A. & Ünal, G. A RNN based time series approach for forecasting turkish electricity load. In 2018 26th Signal processing and communications applications conference (SIU). 1–4 (2018).
Bertolotti, F., Schettini, F., Ferrario, L., Bellavia, D. & Foglia, E. A prediction framework for pharmaceutical drug consumption using short time-series. Expert Syst. Appl. 253, 124265 (2024).
Liu, Y. et al. itransformer: Inverted transformers are effective for time series forecasting. arXiv preprint arXiv:2310.06625 (2023).
Yan, X. et al. The WOA–CNN–LSTM–Attention model for predicting GNSS water vapor. IEEE Trans. Geosci. Remote Sens. 62, 1–15 (2024).
Funding
This work was supported by National Key R&D. Program of China (2023YFE0208300, 2023YFE0197900), National Natural Science Foundation of China (72172113, 52272337, 71901165), Humanities and Social Sciences Research Planning Fund of the Ministry of Education of China (21YJAZH008, 25YJA790083), Wuhan Pilot construction of a strong Transportation Country Science and Technology Joint Research Projects (Grant No. 2023-2-9, 2024-2-9), Fundamental Research Funds for the Central Universities (104972024KFYzxk0035, 104972025KFYjc0140, 2024IVA063).
Author information
Authors and Affiliations
Contributions
Gang Lu: Writing original draft, Visualization, Validation, Software, Investigation, Formal analysis, Data curation. Xiaofang Chen: Conceptualization, Validation, Investigation, Funding acquisition. Hao Zhang: Conceptualization, Methodology, Validation, Investigation, Data curation. Junmin Wan: Validation, Investigation, Data curation.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, 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 licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Chen, X., Lu, G., Zhang, H. et al. Knowledge graph-enhanced deep learning for pharmaceutical demand forecasting. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35113-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35113-4
