Design, Integration, and Evaluation of a Demand Forecasting Service in the Context of Primary Healthcare
Resumo
Context: Efficient management of Primary Healthcare (PHC) within Brazil’s Unified Health System is essential for ensuring quality healthcare services, particularly in addressing challenges related to resource allocation and workforce planning. Ensuring an equitable and sustainable distribution of healthcare resources is crucial to meeting the diverse needs of Brazil’s population. Problem: A key challenge in PHC is accurately forecasting demand, which is vital for optimizing resource allocation and preventing facility overcrowding. In the absence of precise projections, healthcare services may experience overburdened facilities and prolonged wait times, ultimately compromising the quality of care. Proposed Solution: This study presents a demand forecasting service tailored to Brazil’s PHC. By leveraging regression techniques, the system facilitates data-driven decision-making in resource allocation and workforce planning. Predictive analytics enable public health managers to anticipate demand more effectively, ensuring a better-prepared healthcare system capable of delivering effective services. Information Systems (IS) Theory: This research is grounded in the Theory of Socio-Technical Systems, as the proposed solution integrates diverse datasets and predictive models into an information system that actively interacts with existing humans workflows in PHC. By influencing decision-making and resource allocation, the system fosters a seamless integration between technological automation and human expertise, enhancing the adaptability and efficiency of healthcare services. Method: Following a prescriptive approach, the study evaluates the forecasting service through a detailed case study. A quantitative analysis assesses its accuracy and practical applicability, ensuring its effectiveness in supporting decision-making in PHC. Summary of Results: Experimental results demonstrate that the proposed service accurately predicts PHC demand by leveraging real-world data, which can lead to more timely and efficient resource allocation. Contributions and Impact on IS: This research contributes to the Information Systems field by offering a scalable and adaptable tool for Brazil’s public healthcare context, enabling efficient healthcare planning and enhancing resource management.
Palavras-chave:
Primary Health Care, Demand Forecasting, Regression, Artificial Intelligence
Referências
A Okay Akyuz, Mitat Uysal, Berna Atak Bulbul, and M Ozan Uysal. 2017. Ensemble approach for time series analysis in demand forecasting: Ensemble learning. In 2017 IEEE International Conference on INnovations in Intelligent SysTems and Applications (INISTA). IEEE, 7–12.
Noura Al Nuaimi. 2014. Data mining approaches for predicting demand for healthcare services in Abu Dhabi. In 2014 10th International Conference on Innovations in Information Technology (IIT). IEEE, 42–47.
Luiza Bolsoni, Leandro Pereira Garcia, and Daniela Baumgart de Liz Calderón. 2022. Predição de visitas domiciliares na atenção primária: uma abordagem de séries temporais com o modelo Autoregressive Integrated Moving Average. Revista Brasileira de Medicina de Família e Comunidade 17, 44 (2022), 3012–3012.
Franciele Guimarães de Brito et al. 2019. Aplicação do modelo ARIMA na previsão de atendimentos em pontos de atenção com alta demanda da Rede de Assistência à Saúde do município de Monte Carmelo, MG. (2019).
Rafael Calegari, Flavio S Fogliatto, Filipe R Lucini, Jeruza Neyeloff, Ricardo S Kuchenbecker, and Beatriz D Schaan. 2016. Forecasting daily volume and acuity of patients in the emergency department. Computational and mathematical methods in medicine 2016, 1 (2016), 3863268.
Chen-Yang Cheng, Kuo-Liang Chiang, and Meng-Yin Chen. 2016. Intermittent demand forecasting in a tertiary pediatric intensive care unit. Journal of medical systems 40 (2016), 1–12.
Shuo-Chen Chien, Yu-Hung Chang, Chia-Ming Yen, Ying-Erh Chen, Chia-Chun Liu, Yu-Ping Hsiao, Ping-Yen Yang, Hong-Ming Lin, Xing-Hua Lu, I-Chien Wu, et al. 2023. Predicting long-term care service demands for cancer patients: A machine learning approach. Cancers 15, 18 (2023), 4598.
Kyunghyun Cho. 2014. Learning phrase representations using RNN encoderdecoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014).
Murray J Cote, Marlene A Smith, David R Eitel, and Elif Akçali. 2013. Forecasting emergency department arrivals: a tutorial for emergency department directors. Hospital topics 91, 1 (2013), 9–19.
Murray J Cote and Stephen L Tucker. 2001. Four methodologies to improve healthcare demand forecasting. Healthcare Financial Management 55, 5 (2001), 54–54.
Juan J Cubillas, María I Ramos, and Francisco R Feito. 2022. Use of Data Mining to Predict the Influx of Patients to Primary Healthcare Centres and Construction of an Expert System. Applied Sciences 12, 22 (2022), 11453.
Oberdan Santos da Costa and Luis Borges Gouveia. 2023. Plataforma inteligente de predição do risco de doenças crônicas não transmissíveis de apoio à decisão clínica na atenção primária de saúde, usando Inteligência Artificial. Revista Fontes Documentais 6, Ed. Especial (2023), 67–69.
Stephen DeLurgio, Brian Denton, Rosa L Cabanela, Sandra Bruggeman, Arthur R Williams, Sarah Ward, Ned Groves, and John Osborn. 2009. Forecasting weekly outpatient demands at clinics within a large medical center. Prod Invent Manag J 45, 2 (2009), 35–46.
Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179–211.
Jades Fernando Hammes et al. 2018. Dashboard e um modelo de análise preditiva para doenças cerebrovasculares na atenção primária em saúde. Masther thesis. Universidade Federal de Santa Catarina, Santa Catarina, Brasil.
S Hochreiter. 1997. Long Short-term Memory. Neural Computation MIT-Press (1997).
Brian Klute, Andrew Homb, Wei Chen, and Aaron Stelpflug. 2019. Predicting outpatient appointment demand using machine learning and traditional methods. Journal of medical systems 43 (2019), 1–10.
Mayara Regina Lorenzi, Cristiano da Cunha Ribas, and Luiz Gomes Jr. 2018. Predição do volume de atendimentos de saúde na cidade de Curitiba utilizando dados abertos. In Escola Regional de Banco de Dados (ERBD). SBC.
Li Luo, Le Luo, Xinli Zhang, and Xiaoli He. 2017. Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models. BMC health services research 17 (2017), 1–13.
François Mbonyinshuti, Joseph Nkurunziza, Japhet Niyobuhungiro, and Egide Kayitare. 2022. Application of random forest model to predict the demand of essential med. Pan African Medical Journal 42, 1 (2022).
Sriram Ramgopal, Ted Westling, Nalyn Siripong, David D Salcido, and Christian Martin-Gill. 2021. Use of a metalearner to predict emergency medical services demand in an urban setting. Computer Methods and Programs in Biomedicine 207 (2021), 106201.
Joaquim Assis Araújo Rangel. 2023. Risco de desenvolvimento de doenças cardiovasculares em usuários da atenção primária à saúde. B.S. thesis. Universidade Federal do Rio Grande do Norte, Rio Grande do Norte, Brasil.
MINISTÉRIO DA SAÚDE. 2024. SAPS - Secretaria de Atenção Primária à Saúde. Retrieved November 10, 2024 from [link]
Jolene Skordis-Worrall, Kara Hanson, and Anne Mills. 2011. Estimating the demand for health services in four poor districts of Cape Town, South Africa. International health 3, 1 (2011), 44–49.
Yan Sun, Bee Hoon Heng, Yian Tay Seow, and Eillyne Seow. 2009. Forecasting daily attendances at an emergency department to aid resource planning. BMC emergency medicine 9 (2009), 1–9.
Melanie Villani, Arul Earnest, Natalie Nanayakkara, Karen Smith, Barbora De Courten, and Sophia Zoungas. 2017. Time series modelling to forecast prehospital EMS demand for diabetic emergencies. BMC health services research 17 (2017), 1–9.
David H Wolpert and William G Macready. 2005. Coevolutionary free lunches. IEEE Transactions on evolutionary computation 9, 6 (2005), 721–735.
Noura Al Nuaimi. 2014. Data mining approaches for predicting demand for healthcare services in Abu Dhabi. In 2014 10th International Conference on Innovations in Information Technology (IIT). IEEE, 42–47.
Luiza Bolsoni, Leandro Pereira Garcia, and Daniela Baumgart de Liz Calderón. 2022. Predição de visitas domiciliares na atenção primária: uma abordagem de séries temporais com o modelo Autoregressive Integrated Moving Average. Revista Brasileira de Medicina de Família e Comunidade 17, 44 (2022), 3012–3012.
Franciele Guimarães de Brito et al. 2019. Aplicação do modelo ARIMA na previsão de atendimentos em pontos de atenção com alta demanda da Rede de Assistência à Saúde do município de Monte Carmelo, MG. (2019).
Rafael Calegari, Flavio S Fogliatto, Filipe R Lucini, Jeruza Neyeloff, Ricardo S Kuchenbecker, and Beatriz D Schaan. 2016. Forecasting daily volume and acuity of patients in the emergency department. Computational and mathematical methods in medicine 2016, 1 (2016), 3863268.
Chen-Yang Cheng, Kuo-Liang Chiang, and Meng-Yin Chen. 2016. Intermittent demand forecasting in a tertiary pediatric intensive care unit. Journal of medical systems 40 (2016), 1–12.
Shuo-Chen Chien, Yu-Hung Chang, Chia-Ming Yen, Ying-Erh Chen, Chia-Chun Liu, Yu-Ping Hsiao, Ping-Yen Yang, Hong-Ming Lin, Xing-Hua Lu, I-Chien Wu, et al. 2023. Predicting long-term care service demands for cancer patients: A machine learning approach. Cancers 15, 18 (2023), 4598.
Kyunghyun Cho. 2014. Learning phrase representations using RNN encoderdecoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014).
Murray J Cote, Marlene A Smith, David R Eitel, and Elif Akçali. 2013. Forecasting emergency department arrivals: a tutorial for emergency department directors. Hospital topics 91, 1 (2013), 9–19.
Murray J Cote and Stephen L Tucker. 2001. Four methodologies to improve healthcare demand forecasting. Healthcare Financial Management 55, 5 (2001), 54–54.
Juan J Cubillas, María I Ramos, and Francisco R Feito. 2022. Use of Data Mining to Predict the Influx of Patients to Primary Healthcare Centres and Construction of an Expert System. Applied Sciences 12, 22 (2022), 11453.
Oberdan Santos da Costa and Luis Borges Gouveia. 2023. Plataforma inteligente de predição do risco de doenças crônicas não transmissíveis de apoio à decisão clínica na atenção primária de saúde, usando Inteligência Artificial. Revista Fontes Documentais 6, Ed. Especial (2023), 67–69.
Stephen DeLurgio, Brian Denton, Rosa L Cabanela, Sandra Bruggeman, Arthur R Williams, Sarah Ward, Ned Groves, and John Osborn. 2009. Forecasting weekly outpatient demands at clinics within a large medical center. Prod Invent Manag J 45, 2 (2009), 35–46.
Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179–211.
Jades Fernando Hammes et al. 2018. Dashboard e um modelo de análise preditiva para doenças cerebrovasculares na atenção primária em saúde. Masther thesis. Universidade Federal de Santa Catarina, Santa Catarina, Brasil.
S Hochreiter. 1997. Long Short-term Memory. Neural Computation MIT-Press (1997).
Brian Klute, Andrew Homb, Wei Chen, and Aaron Stelpflug. 2019. Predicting outpatient appointment demand using machine learning and traditional methods. Journal of medical systems 43 (2019), 1–10.
Mayara Regina Lorenzi, Cristiano da Cunha Ribas, and Luiz Gomes Jr. 2018. Predição do volume de atendimentos de saúde na cidade de Curitiba utilizando dados abertos. In Escola Regional de Banco de Dados (ERBD). SBC.
Li Luo, Le Luo, Xinli Zhang, and Xiaoli He. 2017. Hospital daily outpatient visits forecasting using a combinatorial model based on ARIMA and SES models. BMC health services research 17 (2017), 1–13.
François Mbonyinshuti, Joseph Nkurunziza, Japhet Niyobuhungiro, and Egide Kayitare. 2022. Application of random forest model to predict the demand of essential med. Pan African Medical Journal 42, 1 (2022).
Sriram Ramgopal, Ted Westling, Nalyn Siripong, David D Salcido, and Christian Martin-Gill. 2021. Use of a metalearner to predict emergency medical services demand in an urban setting. Computer Methods and Programs in Biomedicine 207 (2021), 106201.
Joaquim Assis Araújo Rangel. 2023. Risco de desenvolvimento de doenças cardiovasculares em usuários da atenção primária à saúde. B.S. thesis. Universidade Federal do Rio Grande do Norte, Rio Grande do Norte, Brasil.
MINISTÉRIO DA SAÚDE. 2024. SAPS - Secretaria de Atenção Primária à Saúde. Retrieved November 10, 2024 from [link]
Jolene Skordis-Worrall, Kara Hanson, and Anne Mills. 2011. Estimating the demand for health services in four poor districts of Cape Town, South Africa. International health 3, 1 (2011), 44–49.
Yan Sun, Bee Hoon Heng, Yian Tay Seow, and Eillyne Seow. 2009. Forecasting daily attendances at an emergency department to aid resource planning. BMC emergency medicine 9 (2009), 1–9.
Melanie Villani, Arul Earnest, Natalie Nanayakkara, Karen Smith, Barbora De Courten, and Sophia Zoungas. 2017. Time series modelling to forecast prehospital EMS demand for diabetic emergencies. BMC health services research 17 (2017), 1–9.
David H Wolpert and William G Macready. 2005. Coevolutionary free lunches. IEEE Transactions on evolutionary computation 9, 6 (2005), 721–735.
Publicado
19/05/2025
Como Citar
PEREIRA, Luis F. Alves; FERREIRA, Luann Bento; NASCIMENTO, Dimas Cassimiro; VANDERLEI, Igor Medeiros; SILVA, Daliton; SANTOS, Veruska Borges; GOMES, Mágno Sillas; MELO, Ines Alessandra.
Design, Integration, and Evaluation of a Demand Forecasting Service in the Context of Primary Healthcare. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 21. , 2025, Recife/PE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 506-514.
DOI: https://doi.org/10.5753/sbsi.2025.246552.
