COVID-19 Infection Wave Mortality from Surveillance Data in the Philippines Using Machine Learning

Aug 4, 2026

Upload by Eden

The Philippines experienced multiple COVID-19 infection waves driven by different SARS-CoV-2 strains and variants. This study uses cross-sectional surveillance data from the DOH COVID DataDrop dataset as of September 24, 2022 to compare outcomes across four wave intervals: ancestral (A0), Alpha/Beta (AB), Delta (D), and Omicron (O). Descriptive statistics and machine learning models evaluate recovery and death proportions and measure predictive performance, highlighting age and region-related differences in mortality risk.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Objective

Methods

Results

Discussion

Introduction

Background and epidemiologic context

Factors influencing COVID-19 mortality

Ateneo de Manila University Archī um Ateneo | Ateneo School of Medicine and Public Health Publications | Ateneo School of Medicine and Public Health | | --- | --- | | 8-30-2024
COVID-19 Infection Wave Mortality from Surveillance Data in the Philippines Using Machine Learning
Julius Migriño Jr
Ateneo School of Medicine and Public Health, Ateneo de Manila University, [jmigrino@ateneo.edu](jmigrino@ateneo.edu)
Ani Regina U. Batangan San Beda University
Rizal Michael R. Abello San Beda University
Follow this and additional works at: [https://archium.ateneo.edu/asmph-pubs](https://archium.ateneo.edu/asmph-pubs)
Part of the COVID-19 Commons | | Custom Citation Migriño, J. R., Batangan, A. R. U., & Abello, R. M. R. (2024) . COVID-19 Infection Wave Mortality from Surveillance Data in The Philippines Using Machine Learning. Diversity: Disease Preventive of Research Integrity, 5(1), 10-21 . [https://doi.org/10.24252/diversity.v5i1.49508](https://doi.org/10.24252/diversity.v5i1.49508) This Article is brought to you for free and open access by the Ateneo School of Medicine and Public Health at Archīum Ateneo. It has been accepted for inclusion in Ateneo School of Medicine and Public Health Publications by an authorized administrator of Archīum Ateneo. For more information, [please contact oadrcw.ls@ateneo.edu](please contact oadrcw.ls@ateneo.edu). medRxiv preprint doi: [https://doi.org/10.1101/2023.11.28.23299037](https://doi.org/10.1101/2023.11.28.23299037); this version posted November 30, 2023. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . COVID-19 infection wave mortality from surveillance data in the Philippines using machine learning Short Title: COVID-19 infection wave mortality in the Philippines Authors: Julius R Migriño, Jra,b, Ani Regina U Batangana and Rizal Michael R Abelloa a b San Beda University College of Medicine, Manila, Philippines Ateneo de Manila University School of Medicine and Public Health, Pasig, Philippines Correspondence to: Julius R. Migriño, Jr. (email: [j](jrmjrmd-1@yahoo.com)[rmjrmd-1@yahoo.com](jrmjrmd-1@yahoo.com) ) ABSTRACT Objective: The Philippines has had several COVID-19 infection waves brought about by different strainsand variants of SARS-CoV-2 . This study aimed to describe COVID-19 outcomes by infection waves using machine learning. Methods: We used a cross-sectional surveillance data review design using the DOH COVID DataDrop data set as of September 24, 2022. We divided the data set into infection wave data sets based on the predominant COVID-19 variant(s) of concern during the identified time intervals: ancestral strain (A0), Alpha/Beta variant (AB), Delta variant (D), and Omicron variant (O) . Descriptive statistics and machine learning models were generated from each infection wave data set. Results: Our final data set consisted of 3 896 206 cases and ten attributes including one label attribute. Overall, 98.39% of cases recovered while 1.61% died. The Delta wave reported the most deaths (43 .52%), while the Omicron wave reported the least (10 .36%) . The highest CFR was observed during the ancestral wave (2 .49%), while the lowest was seen during the Omicron wave (0 .61%) . Higher age groups generally had higher CFRs across all infection waves. The A0, AB and D models had up to four levels with two or three splits for each node. The O model had eight levels, with up to 16 splits in some nodes . Of the ten attributes, only age was included in all the decision tree models, while region of residence was included in the O model. F-score and specificity were highest using naïve Bayes in all four data sets. Area under the curve (AUC) was highest in the naïve Bayes models for the A0, AB and D models, while sensitivity was highest in the d

FAQs

What data and time basis are used to analyze infection-wave mortality?

The study analyzes cross-sectional surveillance data from the DOH COVID DataDrop dataset, using the dataset as of September 24, 2022, and divides it into wave intervals by predominant variants of concern.

How does mortality burden differ across the infection waves?

Overall, 98.39% of cases recovered and 1.61% died. The Delta wave reported the most deaths (43.52%), while Omicron reported the least (10.36%), with the ancestral wave showing the highest CFR and Omicron the lowest.

Which factors and models are most associated with predicting death?

Across decision tree models, age is included in all four waves, while region of residence is added in the Omicron model. Naïve Bayes achieves the highest F-score and specificity across all datasets, while AUC is highest for Naïve Bayes in A0/AB/D and sensitivity is highest for decision trees in A0/AB/O.

Aug 4, 2026

Upload by Eden