Photoplethysmography (PPG) signals are used for preliminary analysis of heart diseases via processing of optical measurements. Existing methods for classification of PPG signals are either highly complex to deploy, or have lower accuracy levels, which limits their clinical applicability under real-time scenarios. To overcome these issues, this text proposes design of a novel hybrid bioinspired model for improving efficiency of PPG classification under clinical scenarios. The proposed model initially collects temporal PPG signals, and extracts Frequency & Gabor features for multidomain representations. These signals are processed via a hybrid Genetic Particle Swarm Optimizer (GPSO), that assists in identification of correlative features for different disease types. These temporal correlative features are used to find different diseases with higher efficiency, and lower complexity levels. Due to which the proposed model is able to identify Arrythmia, High Blood Pressure, and Myocardial Infraction conditions with 3.4% higher accuracy, 2.9% higher precision, 2.5% higher recall, and 8.3% lower delay when compared with existing methods