Skip to content
naulon
Not checkedNot checked for notices yet.

Intelligent prediction of thyroid cancer in China based on GBD data and hospital electronic medical records: disease burden analysis combined with multiple machine learning models

Lina Yang, Shixia Zhang, Xinguo Wang and 2 more

Frontiers in Endocrinology · 2025

doi:10.3389/fendo.2025.1644396 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

This study aims to conduct an in-depth analysis of the disease burden pattern and future trends of thyroid cancer in China, and constructed an intelligent prediction model in combination with hospital electronic medical record data. It comprehensively reveals the disease burden trend of thyroid cancer in China, predicts the mortality rate of thyroid cancer in China, and emphasizes the causal role of high BMI as an important controllable risk factor. And provided a high-precision prediction model for benign and malignant thyroid cancer. The results show that the prevalence of thyroid cancer in China has shown a significant upward trend from 1990 to 2021, especially among women, and the peak age of onset has shifted later. The mortality rate of men is on the rise, while that of women is on the decline. The risk of thyroid cancer mortality caused by high BMI significantly increases during this period, and MR analysis confirms that high BMI increases the risk of thyroid cancer. The ARIMA model predicts that the prevalence of thyroid cancer in China will continue to increase in the next ten years, while the mortality rate will remain relatively stable. Among the machine learning models, XGBoost achieved the highest predictive accuracy and identified BMI as the most influential clinical feature in distinguishing between benign and malignant thyroid tumors. This study provides a solid scientific basis for the development of more accurate and effective strategies for the prevention, early diagnosis, and management of thyroid cancer in China and even globally, and provides a feasible path for the use of artificial intelligence assisted diagnosis in clinical practice.

Abstract licence: CC BY

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.