Hormones (Athens, Greece) · 2025
A novel approach for classifying patients with adrenal tumors based on decision support systems and artificial intelligence.
СтатьяНазвание и аннотация: Перевод в очереди
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.
Binas Dimitrios A, Betsi Grigoria, Economopoulos Theodore, Mytareli Chrysoula, Bourgioti Charis, Xekouki Paraskevi, Angelousi Anna, Matsopoulos George K
Аннотация
AIMS: Adrenal incidentalomas (AIs) encompass a wide range of clinical entities, from incidental benign neoplasms that need to be monitored to aggressive malignancies requiring urgent medical intervention and treatment. The incidence of adrenal tumors is steadily rising, reflecting a growing trend in their prevalence and highlighting the necessity for heightened awareness and advanced diagnostic strategies to address this escalating health concern. This retrospective study was undertaken in order to explore the possibility of developing a decision support system for classifying adrenal tumors as benign and malignant or suspicious for malignancy.
METHODS: A powerful combination of 12 clinical, biochemical, epidemiological, and radiological features of 256 patients with adrenal tumors was analyzed to make predictions and various machine learning models were trained and compared to identify the model that consistently achieves the highest accuracy.
RESULTS: An average accuracy of over 91% and a balanced accuracy surpassing 94% was achieved based on a small amount of data and a small number of patients, without using imaging radiomics.
CONCLUSION: The present study provided a decision-making process in healthcare systems permitting reliable automated classification of adrenal tumors. This is a promising candidate for integration into an initial screening tool for adrenal cancer, offering clinicians a valuable resource for early detection and intervention.
METHODS: A powerful combination of 12 clinical, biochemical, epidemiological, and radiological features of 256 patients with adrenal tumors was analyzed to make predictions and various machine learning models were trained and compared to identify the model that consistently achieves the highest accuracy.
RESULTS: An average accuracy of over 91% and a balanced accuracy surpassing 94% was achieved based on a small amount of data and a small number of patients, without using imaging radiomics.
CONCLUSION: The present study provided a decision-making process in healthcare systems permitting reliable automated classification of adrenal tumors. This is a promising candidate for integration into an initial screening tool for adrenal cancer, offering clinicians a valuable resource for early detection and intervention.