A Novel and Accurate Method of Diagnosis via AI and ML for Smart HC System

Recent breakthroughs in the internet of Issues (IoT), computing through the cloud, and the use of AI have changed the standard healthcare system, making a case for smart health care. By combining key technologies including IoT and AI, there is a major improvement in medical services. The merging of IoT and AI offers multiple possibilities within the healthcare industry. This study piece presents a new artificial intelligence- and internet of things convergence-based framework for disease detection in smart health care systems, emphasizing especially on cardiovascular diseases and diabetes. The suggested model includes separate steps, including data collection, preparation, classification, and parameter modification. Utilizing Internet of Things devices like smartwatches along with sensors enables smooth collection of information, while AI methods harness this data for the detection of illnesses. The technique presents a new approach, applying to the Crowd Search Optimizer algorithm-based Flowed Long and Short-Term Memory (CSO-CLSTM) approach to disease detection. CSO is applied to improve both ‘weights’ while ‘bias’ factors of the CLSTM framework, while the isolation Fg (iForest) method is implemented to remove outliers. Through testing with health care information, the CSO-LSTM model got excellent accuracy ratings of 96.16% when 97.26% in identifying heart disease while diabetes, respectively. Consequently, the suggested CSO-LSTM model appears as a solid and reliable method of disease evaluation in digital healthcare systems, showing its potential for broad application.