PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach
Version 1
: Received: 27 May 2024 / Approved: 28 May 2024 / Online: 28 May 2024 (11:56:27 CEST)
How to cite:
Hernandez-Nava, C.; Mata-Rivera, M.-F.; Flores-Hernandez, S. Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach. Preprints2024, 2024051844. https://doi.org/10.20944/preprints202405.1844.v1
Hernandez-Nava, C.; Mata-Rivera, M.-F.; Flores-Hernandez, S. Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach. Preprints 2024, 2024051844. https://doi.org/10.20944/preprints202405.1844.v1
Hernandez-Nava, C.; Mata-Rivera, M.-F.; Flores-Hernandez, S. Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach. Preprints2024, 2024051844. https://doi.org/10.20944/preprints202405.1844.v1
APA Style
Hernandez-Nava, C., Mata-Rivera, M. F., & Flores-Hernandez, S. (2024). Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach. Preprints. https://doi.org/10.20944/preprints202405.1844.v1
Chicago/Turabian Style
Hernandez-Nava, C., Miguel-Felix Mata-Rivera and Sergio Flores-Hernandez. 2024 "Comparison of Health and Data Science Methodologies for Identifying Avoidable Hospitalizations in Patients with Diabetes: An Interdisciplinary Approach" Preprints. https://doi.org/10.20944/preprints202405.1844.v1
Abstract
In the whole world, including Mexico, the rising prevalence of diabetes poses significant challenges to healthcare systems, with a notable impact on hospital admissions even being an ambulatory care sensitive condition, that means, hospital admissions are avoidable. Traditional healthcare methodologies have been instrumental in managing diabetes and preventing complications, yet they often face limitations such as merging, cleansing, and outlier analysis of health data to identify and address diseases effectively. This paper aims to address this gap by conducting a comprehensive comparison of the methodologies used in healthcare and data science for this purpose. This work uses hospital diabetes discharge records from 2010 to 2023, a total of 36,665,793 records, which belong to medical units of the Ministry of Health of Mexico. In this work, we seek to provide the arguments why as a data scientist it is mandatory to learn the field of knowledge of the problem and its implications if this is not done, and therefore to disclose insights that can help in policy decisions and reduce the burden of avoidable hospitalizations. The approach is mainly based on the standardization or adjust rates by sex and age groups. This study provides the foundations for a new way of data scientist must deal with health data.
Keywords
Methodology; Data Science; Public health; standardization; epidemiology, datasets, hospital discharges, adjusted rate
Subject
Computer Science and Mathematics, Other
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
