Forecasting Disease Burden In Philippines: A Symbolic Regression Analysis

TL;DR

This study develops a mathematical model using symbolic regression to forecast disease burden in the Philippines from 1990 to 2016, highlighting trends and future projections for various disease categories.

Contribution

It introduces a novel application of symbolic regression combined with PCA to model and predict disease burden trends in the Philippines.

Findings

Disease burden is projected to decrease until 2020 for most categories.

Non-communicable diseases are an exception, with increasing burden.

The model provides insights for health policy planning.

Abstract

Burden of disease measures the impact of living with illness and injury and dying prematurely and it is increasing worldwide leading cause of death both global and national. This paper aimed to propose an index of diseases and evaluate a mathematical model to describe the number of burden of disease by cause in the Philippines from 1990 - 2016. Through Principal Component Analysis (PCA) the diseases categorized as: passed on diseases, vector born diseases, non-communicable diseases, accident, and intentional. Symbolic Regression Analysis was carried out, the study revealed that the number of burden of disease as categorized using CPA will continue decrease up to year 2020 except on non-communicable disease.