The Journal of craniofacial surgery · 2022
Using the Random Forest Algorithm to Detect the Activity of Graves Orbitopathy.
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.
Wang Minghui, Zhang Hanqiao, Dong Li, Li Yang, Hou Zhijia, Li Dongmei
Аннотация
PURPOSE: The aim of this study is to establish a random forest model to detect active and quiescent phases of patients with Graves Orbitopathy (GO).
METHODS: A total of 243 patients (486 eyes) diagnosed with GO in Beijing TongRen hospital were included in the study. The Clinical Activity Score of GO was regarded as the golden standard, whereas sex, age, smoking status, radioactive I131 treatment history, thyroid nodules, thyromegaly, thyroid hormone, and Thyroid-stimulating hormone receptor antibodies were chosen as predictive characteristic variables in the model. The random forest model was established and compared with logistic regression analysis, Naive Bayes, and Support vector machine metrics.
RESULTS: Our model has a sensitivity of 0.81, a specificity of 0.90, a positive predictive value of 0.87, a negative predictive value of 0.86, an F1 score of 0.85, and an out-of-bag error of 0.15. The random forest algorithm showed a more precise performance compared with 3 other models based on the area under receiver operating characteristic curve (0.92 versus 0.77 versus 0.76 versus 0.75) and accuracy (0.86 versus 0.71 versus 0.69 versus 0.66).
CONCLUSIONS: By integrating these high-risk factors, the random forest algorithm may be used as a complementary method to determine the activity of GO, with accurate and reliable performance.
METHODS: A total of 243 patients (486 eyes) diagnosed with GO in Beijing TongRen hospital were included in the study. The Clinical Activity Score of GO was regarded as the golden standard, whereas sex, age, smoking status, radioactive I131 treatment history, thyroid nodules, thyromegaly, thyroid hormone, and Thyroid-stimulating hormone receptor antibodies were chosen as predictive characteristic variables in the model. The random forest model was established and compared with logistic regression analysis, Naive Bayes, and Support vector machine metrics.
RESULTS: Our model has a sensitivity of 0.81, a specificity of 0.90, a positive predictive value of 0.87, a negative predictive value of 0.86, an F1 score of 0.85, and an out-of-bag error of 0.15. The random forest algorithm showed a more precise performance compared with 3 other models based on the area under receiver operating characteristic curve (0.92 versus 0.77 versus 0.76 versus 0.75) and accuracy (0.86 versus 0.71 versus 0.69 versus 0.66).
CONCLUSIONS: By integrating these high-risk factors, the random forest algorithm may be used as a complementary method to determine the activity of GO, with accurate and reliable performance.