Demand Forecasts for Chronic Cardiovascular Diseases Medication Based on Markov Chains
DOI:
https://doi.org/10.69681/lajae.v4i1.20Keywords:
Markov Chains, Inventory management, Demand planning, Stochastic Processes, Healthcare supply chainAbstract
In this work, we propose and evaluate models to predict the demand for cardiovascular drugs using Markov chains. The models use transactional data of patient medication delivery to identify consumption levels. These levels are considered as Markov chain states. Four model configurations were evaluated, differing on the arrival/departure nature of patients to the system and the inclusion of an idle state. The models were trained with 12 months of real data and tested with a four-month horizon. Also, the models were sequentially applied to an 18-month Losartan consumption data, simulating thus the chained implementation in a real scenario. The MAPE of two months ahead forecasts ranged from 3.92% to 5.55% in three of the four evaluated models. As well, our results showed that variations of the consumption level could be modeled using Markov chains, and in low inventory levels situations, these tools are usable to prioritize patients with higher levels of consumption.
Downloads
Downloads
Published
How to Cite
License
Copyright (c) 2021 Latin American Journal of Applied Engineeringg
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with Latin American Journal of Applied Engineering agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
