The application of artificial intelligence (AI) in the diagnosis of platelet disorders

Artificial intelligence (AI), machine learning, and deep learning are emerging technologies with the potential to revolutionize the diagnosis and treatment of various diseases, ranging from cancer to cardiovascular disorders. These advanced algorithms have the ability to learn patterns and associations, enabling them to make predictions and enhance therapeutic approaches. Among the conditions that can benefit from AI's capabilities are platelet disorders, which at least in some cases may lead to life-threatening excessive bleeding. The conventional methods to diagnose these disorders mainly rely on manual or automated blood cell counting and morphology analysis that are prone to errors. In recent years, researchers have turned to machine learning models to predict platelet disorders, including drug-induced immune thrombocytopenia (DITP), sepsis-associated thrombocytopenia (SAT), immune thrombocytopenic purpura (ITP), disseminated intravascular coagulation (DIC), as well as thrombocytosis. These studies have yielded promising results, demonstrating satisfactory efficacy and accuracy. Our analysis revealed that key predictive parameters include the patient's medical history, platelet counts, and coagulation factors. Notably, the support vector machine (SVM) algorithm exhibited the highest performance in predicting platelet disorders, achieving the highest accuracy score while analyzing a relatively lower number of parameters.