focalinterest.net

AI Summary of Scholarly Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Machine learning models identified key drivers of tuberculosis incidence in Taiwan

Written by

editor@focalinterest.com

in

Research area:public-health-epidemiologyinfectious-diseases

What the study found

The study found that several machine learning and deep learning models could forecast monthly tuberculosis incidence across 19 cities and counties in Taiwan, China, and that the CatBoost, random forest, and gradient boosting models performed best. The authors also identified population size, sulfur dioxide levels, physician count, normalized difference vegetation index, wind velocity, and precipitation as the main influences on tuberculosis incidence.

Why the authors say this matters

The authors conclude that the framework and findings provide data support and a decision-making basis for tuberculosis mitigation initiatives on a global scale. The study suggests that identifying influential factors and their thresholds may help guide tuberculosis-related decision-making.

What the researchers tested

The researchers analyzed data from 19 cities and counties in Taiwan, China from 2014 to 2022. They used four machine learning models and four deep learning models, along with 12 drivers, to predict monthly tuberculosis incidence, and then applied post-hoc explainable machine learning techniques, stepwise regression, and statistical assessments.

What worked and what didn't

CatBoost, random forest, and gradient boosting emerged as the top-performing models. The study also reported nonlinear interactions and threshold effects between the identified determinants and tuberculosis incidence, and it used stepwise regression to find a model configuration that reduced the number of drivers while keeping high predictive accuracy.

What to keep in mind

The abstract does not describe detailed performance values, specific limitations, or uncertainty measures. It also focuses on Taiwan, China, so the scope described in the summary is geographically specific.

Key points

  • The study used data from 19 cities and counties in Taiwan, China between 2014 and 2022.
  • CatBoost, random forest, and gradient boosting were the best-performing models.
  • Population size, sulfur dioxide, physician count, vegetation index, wind velocity, and precipitation were identified as the main influences on tuberculosis incidence.
  • The authors reported nonlinear interactions and threshold effects between these factors and tuberculosis incidence.
  • Stepwise regression was used to reduce the number of drivers while keeping high predictive accuracy.

Disclosure

Research title:
Machine learning models identified key drivers of tuberculosis incidence in Taiwan
Authors:
Yiwen Tao, Jiaxin Zhao, Hao Cui, Zhanlue Liang, Jian Li, Jingli Ren, Huaiping Zhu
Institutions:
Sichuan University, The University of Queensland, West China Hospital of Sichuan University, York University, Zhengzhou University, Zhengzhou University, Zhengzhou University, Zhengzhou University, Zhengzhou University, Zhengzhou University of Science and Technology, Zhengzhou University of Science and Technology
Publication date:
2026-02-26
DOI:
10.1016/j.idm.2026.02.002
OpenAlex record:
View
AI provenance: This post was generated by gpt-5.4-mini (OpenAI). The original authors did not write or review this post.

More posts