An intelligent deep feature based metabolism syndrome prediction system for sleep disorder diseases.

The Obstructive Sleep Apnea (OSA) analysis and prediction is the hottest topic in the medical healthcare industry. However, identifying the sleep disorder and its Severity is too complex because of the unique biological parameters of every human. So, the current research plans to develop a novel Chimp-based Recurrent Mets Framework (CbRMF) for predicting metabolism syndrome features. It is functioned based on artificial intelligence and bio-inspired optimization principles. Hence, based on the abnormal metabolism syndrome density, the severity score of OSA has been forecasted. The noise features were removed in the hidden layer of the CbRMF, and then the feature analyzing and prediction function was performed. Moreover, the designed model is tested in the Python environment, and the performance has been measured based on prediction accuracy rate, sensitivity score, F-value, precision, and misclassification rate. Incorporating the chimp fitness function has afforded the finest OSA symptoms detection and severity classification outcome. The efficiency of the proposed technique is measured by testing it with different databases like metabolism syndrome data, stroke unit data and Polysomnography data. The proposed novel CbRMF has defined the finest outcome for the Polysomnography data, which is 99.3% accuracy for sleep disorder prediction and has recorded a 0.7% error rate. Hence, the presented novel CbRMF has earned the finest OSA severity categorization exactness than the other compared models. [ABSTRACT FROM AUTHOR]