Home

My co-authored article, “Unveiling Insights from Hematobiometry Data: A Data Science Approach Using Data from a Quito Clinical Laboratory”, has just been published. This work was presented at the Eleventh International Conference on Information and Communication Technologies for Ageing Well and e-Health
(ICT4AWE 2025) in Porto, Portugal.

This work is a follow-up to the master’s thesis of my former student and colleague, Miguel Ortíz Navarrete, from the Pontificia Universidad Católica del Ecuador (PUCE). We also had the pleasure of collaborating with Paúl Campaña and Dora Rosero from the Pura Vida Clinical Laboratory. The article provides valuable insights into the use of clinical laboratory test results for predicting the presence of diseases such as anemia and polycythemia.

The article is now available in the SciTePress Digital Library, alongside other outstanding papers from ICT4AWE 2025.

Abstract:

In this applied research study, a data science approach is employed to analyze anonymized hematological data obtained from a clinical laboratory located in Quito, Ecuador. The analysis aims to examine machine learning models that could potentially be used to aid in early anemia and polycythemia detection, ultimately contributing to improved healthcare decision-making. A rigorous MLOps-driven methodology is employed, and well-established techniques such as clustering, decision trees, and neural networks are applied. These methods are evaluated to identify the most suitable approach for the specific characteristics of the data. The findings showed that clustering methods were not advisable for the type of data used for the exploration and no significative results could be obtained. However, decision trees and neural networks demonstrated superior performance in predicting the presence of these blood disorders. Additionally, the outcomes of this research have the potential to be particu larly significant for Ecuador, a nation facing challenges in healthcare access and malnutrition, where early anemia detection could be highly impactful

Some impressions: