Advances in clinical and experimental medicine : official organ Wroclaw Medical University · 2025
Epidemiological characteristics of thyroid cancer worldwide and construction of a machine learning diagnostic model.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Liu Yanqiong, Li Lian, Wang Shasha, Zhou Shuangyan, Zou Jianhui
Аннотация
BACKGROUND: Age and gender have been identified as significant factors contributing to the global rise in thyroid cancer (TC), with this disease predominantly affecting women. It is crucial to thoroughly investigate the trends of the disease over time to better understand its progression and potential risk factors.
OBJECTIVES: This study analyzed the global incidence of TC using data from the Global Burden of Disease (GBD) database from 1990 to 2021. Additionally, we aimed to develop a high-performance diagnostic model using machine-learning algorithms and to explore the tumor microenvironment through single-cell sequencing.
MATERIAL AND METHODS: To analyze trends in incidence, age-period cohort models were applied, with a particular focus on birth cohort and period effects. Machine learning algorithms, including least absolute shrinkage and selection operator (LASSO) and Ridge regression, were used for gene feature selection. Subsequently, cross-validation was conducted to validate the diagnostic model. For deeper insights, single-cell RNA sequencing was conducted to analyze myeloid cell subpopulations within the tumor microenvironment.
RESULTS: Age and period effects emerged as the primary drivers in our analysis of TC trends, particularly among women. Machine learning models, specifically LASSO and Ridge regression, demonstrated high predictive accuracy in diagnosing the disease. Additionally, single-cell RNA sequencing unveiled crucial interactions between myeloid cells and the tumor microenvironment.
CONCLUSIONS: This study provides a comprehensive analysis of TC trends and introduces a machine-learning-based diagnostic tool. Additionally, single-cell RNA sequencing offers novel insights into the tumor microenvironment, which may help shape future treatment strategies for TC.
OBJECTIVES: This study analyzed the global incidence of TC using data from the Global Burden of Disease (GBD) database from 1990 to 2021. Additionally, we aimed to develop a high-performance diagnostic model using machine-learning algorithms and to explore the tumor microenvironment through single-cell sequencing.
MATERIAL AND METHODS: To analyze trends in incidence, age-period cohort models were applied, with a particular focus on birth cohort and period effects. Machine learning algorithms, including least absolute shrinkage and selection operator (LASSO) and Ridge regression, were used for gene feature selection. Subsequently, cross-validation was conducted to validate the diagnostic model. For deeper insights, single-cell RNA sequencing was conducted to analyze myeloid cell subpopulations within the tumor microenvironment.
RESULTS: Age and period effects emerged as the primary drivers in our analysis of TC trends, particularly among women. Machine learning models, specifically LASSO and Ridge regression, demonstrated high predictive accuracy in diagnosing the disease. Additionally, single-cell RNA sequencing unveiled crucial interactions between myeloid cells and the tumor microenvironment.
CONCLUSIONS: This study provides a comprehensive analysis of TC trends and introduces a machine-learning-based diagnostic tool. Additionally, single-cell RNA sequencing offers novel insights into the tumor microenvironment, which may help shape future treatment strategies for TC.