In recent years, there has been a lot of research interest in the growing use of artificial intelligence (AI) in health and medicine. This study attempts to provide a global, verified picture of research on AI in medicine and health. There are vast informational resources available, but there are also devices that can't decide examples precisely or predict the future. The conventional methods for diagnosing illnesses are manual and prone to error. When compared to elite human ability, the use of artificial intelligence's predictive approaches improves auto determination and reduces identification errors. A thorough analysis of those articles convinced the ordering party to order the most complex AI processes for clinical symptomatic frameworks. This research report seeks to unearth some key information on the flow and past of many AI techniques in the clinical setting used in the current clinical investigation, particularly in the areas of coronary disease prediction, brain illness, prostate, liver illness, and kidney infection. In order to ensure that Childs are well-informed and guided, this study uses the coordination examination calculation to distinguish Childs' mental health difficulties and applies the reconciliation examination calculation to Childs' mental health inquiry. A thorough analysis and exploration of children's mental health is completed in light of the framework design approach and information mining grouping technique.