Machine Learning Models for Classification of Cushing's Syndrome Using Retrospective Data

Abstract

Accurate classification of Cushing's Syndrome (CS) plays a critical role in providing the early and correct diagnosis of CS that may facilitate treatment and improve patient outcomes. Diagnosis of CS is a complex process, which requires careful and concurrent interpretation of signs and symptoms, multiple biochemical test results, and findings of medical imaging by physicians with a high degree of specialty and knowledge to make correct judgments. In this article, we explore the state of the art machine learning algorithms to demonstrate their potential as a clinical decision support system to analyze and classify CS to facilitate the diagnosis, prognosis, and treatment of CS. Prominent algorithms are compared using nested cross-validation and various class comparison strategies including multiclass, one vs. all, and one vs. one binary classification. Our findings show that Random Forest (RF) algorithm is most suitable for the classification of CS. We demonstrate that the proposed approach can classify CS with an average accuracy of 92% and an average F1 score of 91.5%, depending on the class comparison strategy and selected features. RF-based one vs. all binary classification model achieves sensitivity of 97.6%, precision of 91.1%, and specificity of 87.1% to discriminate CS from non-CS on the test dataset. RF-based multiclass classification model achieves average per class sensitivity of 91.8%, average per class specificity of 97.1%, and average per class precision of 92.1% to classify different subtypes of CS on the test dataset. Clinical performance evaluation suggests that the developed models can help improve physicians' judgment in diagnosing CS.

Machine learning methods in differential diagnosis of ACTH-dependent hypercortisolism

“…Isci S. и соавт. [ 10 ] впервые предложили способ дифференциальной диагностики различных форм эндогенного гиперкортицизма (БИК, синдром Иценко-Кушинга (СИК), субклинический гиперкортицизм) с использованием методов машинного обучения, основанный на данных 241 пациента и включивший 11 переменных-предикторов. Для создания прогностических моделей ученые применили различные методы машинного обучения, по результатам которых алгоритм случайного леса (Random Forest, RF) значительно превосходил прогностические способности других алгоритмов машинного обучения.…”

“…Для идентификации наилучшего алгоритма прогнозирования АКТГ-ЭС среди пациентов с АКТГ-зависимым эндогенным гиперкортицизмом применялась вложенная кросс-валидация с 5 внешними и 3 внутренними циклами (3x5 Nested Cross-Validation) по схеме, предложенной Isci S. и соавт. [ 10 ]. Данный подход обеспечивает более точную оценку ошибки обобщения (Generalization error) при одновременной оптимизации гиперпараметров и показал свою применимость в предметной области.…”

Hepatitis C Virus Detection Model by Using Random Forest, Logistic-Regression and ABC Algorithm

“…In particular, it is used in promoting treatments and improving prognosis for patients with Cushing's syndrome. A relevant study indicated that RF is the most suitable method for classifying the syndrome [31]. Regarding the high costs involved in the prediction of treatment fees for patients with asthma, the frequently used comorbidity portfolio design involves the recombination of comorbidities in different budgets, where the training for comorbidity portfolio design includes the training of RF prediction models [32].…”

Identification and interpretation of gait analysis features and foot conditions by explainable AI

“…Artificial Intelligence (AI), specifically ML, has shown exceptional promise in various fields, particularly in automating tasks and enhancing predictions. In the medical sphere, ML has contributed to more efficient diagnoses and treatment plans, and in certain areas, even surpassed human experts in diagnostic accuracy 4 , 5 .…”