Performance evaluation of the machine learning algorithms used in inference mechanism of a medical decision support system.

The importance of the decision support systems is increasingly supporting the decision making process in cases of uncertainty and the lack of information and they are widely used in various fields like engineering, finance, medicine, and so forth, Medical decision support systems help the healthcare personnel to select optimal method during the treatment of the patients. Decision support systems are intelligent software systems that support decision makers on their decisions. The design of decision support systems consists of four main subjects called inference mechanism, knowledge-base, explanation module, and active memory. Inference mechanism constitutes the basis of decision support systems. There are various methods that can be used in these mechanisms approaches. Some of these methods are decision trees, artificial neural networks, statistical methods, rule-based methods, and so forth. In decision support systems, those methods can be used separately or a hybrid system, and also combination of those methods. In this study, synthetic data with 10, 100, 1000, and 2000 records have been produced to reflect the probabilities on the ALARM network. The accuracy of 11 machine learning methods for the inference mechanism of medical decision support system is compared on various data sets.

Analysis of 87 patients with Löfgren's syndrome and the pattern of seasonality of subacute sarcoidosis.

BACKGROUND AND OBJECTIVE: Sarcoidosis is a multisystem disease of unknown aetiology. The seasonality of sarcoidosis in symptomatic, recently diagnosed patients with Löfgren's syndrome was evaluated to help better understand the possible causative factor(s) in the pathogenesis of sarcoidosis. METHODS: Four hundred and ninety-two consecutive patients with sarcoidosis were investigated. The demographic and clinical features, course of the disease, initial diagnostic methods and both the month and age at initial diagnosis for each patient were analysed. Roger's test for cyclic variation was used to determine the significance of any seasonal variation of incidence. RESULTS: Löfgren's syndrome was diagnosed in 87 patients (18%). The diagnosis of sarcoidosis was delayed in 45% of subjects (mean: 11.2 weeks). The distribution of cumulative monthly presentations peaked in May (spring) and was the lowest in January (winter) and November (autumn) (P < 0.001). The seasonal pattern was also influenced by age and gender (P < 0.05). At the onset, arthralgia was present in 46%, cough or dyspnoea in 37%, constitutional symptoms in 32% and skin lesions in 30% of the patients. CONCLUSIONS: In this study, there were differences in the amplitude of the seasonal variation by age and by gender. Well-designed prospective studies are required to better understand the importance of the findings we respect to the pathogenesis of the disease.