Cluster analysis for the prevention of hospital readmission of diabetic patients

Análisis de clústeres para la prevención del reingreso hospitalario de pacientes diabéticos

Authors

Keywords:

clustering analysis, hospital readmission, diabetes, machine learning, feature selection (en).

Keywords:

análisis de agrupamiento, reingreso hospitalario, diabetes, aprendizaje automático, selección de características (es).

Abstract (en)

Objective: Hospital readmission in diabetic patients represents a significant challenge for both healthcare systems and patients’ quality of life. That is why the main objective of this work is to identify common patterns associated with a higher risk of readmission. Methodology: This study presents a clustering analysis applied to a clinical dataset of diabetic patients who were readmitted to hospitals across 130 medical institutions in the United States. The analysis employs unsupervised clustering algorithms, such as k-means and PAM, to segment patients based on their clinical and demographic characteristics . The study also evaluates different feature selection methods, identifying Simulated Annealing (SA)as the most effective for selecting optimal subsets of variables.
Results: Recurring factors such as length of hospital stay, associated medical conditions, and types of treatment received, significantly influence the probability of readmission.
Conclusions: The clustering results provide valuable insights to guide the development of personalized intervention strategies aimed at reducing hospital readmission rates among diabetic patients.

Abstract (es)

Objetivo: el reingreso hospitalario en pacientes con diabetes representa un reto significativo tanto para los sistemas de salud como para la calidad de vida del paciente. El objetivo principal de este trabajo es identificar patrones comunes asociados a un mayor riesgo de reingreso.
Metodología: Este estudio presenta un análisis de conglomerados (clusters) aplicado a un conjunto de datos clínicos de pacientes con diabetes que fueron reingresados en hospitales de 130 instituciones médicas en Estados Unidos. El análisis emplea algoritmos de conglomerados no supervisados, como k-means y PAM, con el fin de segmentar a los pacientes según sus características clínicas y demográficas. Este estudio también evalúa diferentes métodos de selección de características, identificando el Recocido Simulado (Simulated Annealing) como el más efectivo para seleccionar subconjuntos óptimos de variables. Resultados: factores recurrentes, tales como: duración de la estancia hospitalaria, afecciones médicas asociadas y los tipos de tratamiento recibido, influyen significativamente en la probabilidad de reingreso.
Conclusiones: los resultados del conglomerado proporcionan información valiosa para guiar el desarrollo de intervenciones personalizadas dirigidas a reducir las tasas de reingreso hospitalario en pacientes con diabetes.

Author Biographies

César G. Villanueva-Rueda, Universidad Juarez Autonoma de Tabasco

Estudiante de la Maestría en Ciencias de la Computación, División Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán, Tabasco, México

Óscar Chávez-Bosquez, Universidad Juárez Autónoma de Tabasco,

Profesor-Investigador, División Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán, Tabasco, México. 

Betania Hernández-Ocaña, Universidad Juárez Autónoma de Tabasco

Profesora-Investigadora, División Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán, Tabasco, México

José Hernández-Torruco, Universidad Juárez Autónoma de Tabasco

Profesor-Investigador, División Académica de Ciencias y Tecnologías de la Información, Universidad Juárez Autónoma de Tabasco, Cunduacán, Tabasco, México.

References

[1] International Diabetes Federation (IDF). "International diabetes federation website." idf.org. https://idf.org/ (accessed Nov. 13, 2025)

[2] Statista. "Global diabetes percentage." es.statista.com. https://es.statista.com/grafico/6698/la-expansion-de-la-diabetes/ (accessed Nov. 13, 2025)

[3] Sociedad Española de Diabetes (SED). "Artificial intelligence for improving diabetes treatment." revistadiabetes.org. https://www.revistadiabetes.org/tecnologia/el-papel-de-la-inteligencia-artificial-en-el-tratamiento-de-la-diabetes-promesas-y-realidad/ (accessed Nov. 13, 2025).

[4] B. Strack, J. P. Deshazo, C. Gennings, C. A. Olmo, S. Ventura, K. J. Cios, and J. N. Clore, “Impact of hba1c measurement on hospital readmission rates in patients with diabetes,” Biomedical Engineering Online, vol. 13, no. 1, pp. 1–22, 2014.

[5] W. Zeng, J. Li, X. He, and T. Xu, “Unsupervised learning for diabetes subgroup identification based on clinical features and glycemic control,” BMC Medical Informatics and Decision Making, vol. 21, no. 1, p. 210, 2021.

[6] M. Huang, L. Zhao, and C. Wang, “Enhanced clinical interpretation of diabetes clustering via pam and pca integration,” Computers in Biology and Medicine, vol. 145, pp. 105–142, 2022.

[7] P. Li and Y. Zhang, “Optimization of medical data clustering using simulated annealing,” Expert Systems with Applications, vol. 212, p. 118716, 2023.

[8] C. K. D. J. Clore, John and B. Strack, “Diabetes 130-US Hospitals for Years 1999-2008,” 2014, DOI: https://doi.org/10.24432/C5230J

[9] R. Xu and D. Wunsch, “Survey of clustering algorithms,” IEEE Transactions on Neural Networks, vol. 16, no. 3, pp. 645–678, 2005.

[10] D. J. Ketchen and C. L. Shook, “The application of cluster analysis in strategic management research: an analysis and critique,” Strategic management journal, vol. 17, no. 6, pp. 441–458, 1996.

[11] P. J. Rousseeuw, “Silhouettes: a graphical aid to the interpretation and validation of cluster analysis,” Journal of computational and applied mathematics, vol. 20, pp. 53–65, 1987.

[12] R. G. Downey and C. V. King, “Missing data in likert ratings: A comparison of replacement methods,” The Journal of general psychology, vol. 125, no. 2, pp. 175–191, 1998.

[13] M. Suyal and S. Sharma, “A review on analysis of k-means clustering machine learning algorithm based on unsupervised learning,” Journal of Artificial Intelligence and Systems, vol. 6, pp. 8–95, 2024.

[14] L. Kaufman, “Partitioning around medoids (program pam),” Finding groups in data, vol. 344, pp. 68–125, 1990.

[15] P. Romanski, L. Kotthoff, and M. L. Kotthoff, “Package ‘fselector’,” URL http://cran.rproject.org/web/packages/FSelector/index.html, 2013.

How to Cite

APA

Villanueva-Rueda, C. G., Chávez-Bosquez, Óscar, Hernández-Ocaña, B., and Hernández-Torruco, J. (2025). Cluster analysis for the prevention of hospital readmission of diabetic patients. Tecnura, 29(86). https://doi.org/10.14483/22487638.24061

ACM

[1]
Villanueva-Rueda, C.G. et al. 2025. Cluster analysis for the prevention of hospital readmission of diabetic patients. Tecnura. 29, 86 (Dec. 2025). DOI:https://doi.org/10.14483/22487638.24061.

ACS

(1)
Villanueva-Rueda, C. G.; Chávez-Bosquez, Óscar; Hernández-Ocaña, B.; Hernández-Torruco, J. Cluster analysis for the prevention of hospital readmission of diabetic patients. Tecnura 2025, 29.

ABNT

VILLANUEVA-RUEDA, César G.; CHÁVEZ-BOSQUEZ, Óscar; HERNÁNDEZ-OCAÑA, Betania; HERNÁNDEZ-TORRUCO, José. Cluster analysis for the prevention of hospital readmission of diabetic patients. Tecnura, [S. l.], v. 29, n. 86, 2025. DOI: 10.14483/22487638.24061. Disponível em: https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/24061. Acesso em: 8 apr. 2026.

Chicago

Villanueva-Rueda, César G., Óscar Chávez-Bosquez, Betania Hernández-Ocaña, and José Hernández-Torruco. 2025. “Cluster analysis for the prevention of hospital readmission of diabetic patients”. Tecnura 29 (86). https://doi.org/10.14483/22487638.24061.

Harvard

Villanueva-Rueda, C. G. (2025) “Cluster analysis for the prevention of hospital readmission of diabetic patients”, Tecnura, 29(86). doi: 10.14483/22487638.24061.

IEEE

[1]
C. G. Villanueva-Rueda, Óscar Chávez-Bosquez, B. Hernández-Ocaña, and J. Hernández-Torruco, “Cluster analysis for the prevention of hospital readmission of diabetic patients”, Tecnura, vol. 29, no. 86, Dec. 2025.

MLA

Villanueva-Rueda, César G., et al. “Cluster analysis for the prevention of hospital readmission of diabetic patients”. Tecnura, vol. 29, no. 86, Dec. 2025, doi:10.14483/22487638.24061.

Turabian

Villanueva-Rueda, César G., Óscar Chávez-Bosquez, Betania Hernández-Ocaña, and José Hernández-Torruco. “Cluster analysis for the prevention of hospital readmission of diabetic patients”. Tecnura 29, no. 86 (December 31, 2025). Accessed April 8, 2026. https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/24061.

Vancouver

1.
Villanueva-Rueda CG, Chávez-Bosquez Óscar, Hernández-Ocaña B, Hernández-Torruco J. Cluster analysis for the prevention of hospital readmission of diabetic patients. Tecnura [Internet]. 2025 Dec. 31 [cited 2026 Apr. 8];29(86). Available from: https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/24061

Download Citation

Visitas

22

Dimensions


PlumX


Downloads

Download data is not yet available.
Loading...