• Sri Vasudev R Pyati
• Jayashree M Kudari
• Aditya Kumar
• AnInish S Shenai
• Abdullah Gafori, Eze Ejiofor Isaiah

This Bipolar occurrence predictive system draws on a wide range of innovative technologies that are based on the powerful applications of Deep Learning and Machine Learning in analysing medical data and making an informative prediction to assist health professionals in treating Bipolar disease as early as possible. The types of input data available are quite helpful in making accurate forecasts. In this case, the answer to the problem statement might be implemented by the (Convoluted Neural Networks), KNN (K-nearest Neighbours), and Decision tree, which could be quite effective in identifying the disease. A wide variety of diseases have symptoms that can be found in electronic health records (EHRs), making it necessary to create models that can detect these difficulties early on and accurately diagnose the disorders. Other methods for finding hidden patterns in patient data include the use of deep neural networks and machine learning techniques including multi-layer perception, SVM, random forest, and decision trees (DT). Other methods for finding hidden patterns in patient data include the use of deep neural networks and machine learning techniques including multi-layer perception, SVM, random forest, and decision trees (DT). The study also looks at the symptoms linked with different forms of psychotic disorders and handles class imbalance from a multi-label classification standpoint. Models were assessed and compared based on their accuracy using this metric. Class imbalance accuracy was 85.17 percent better for deep neural networks compared to MLP models (58.44 percent better for MLP models). In terms of machine learning methodologies, the random forest model provided the best outcomes, with 64.1 percent and 55.87 percent, respectively, when compared to deep learning. Analysis can be improved by using a {Decision Tree Classifier–} Machine Learning algorithm

bipolar disorder, deep learning, psychotic disorders, forecasting

"A SURVEY ON BIPOLAR OCCURRENCE PREDICTION USING MACHINE LEARNING AND DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.34-37, June-2022, Available :http://www.jetir.org/papers/JETIRFM06008.pdf

"A SURVEY ON BIPOLAR OCCURRENCE PREDICTION USING MACHINE LEARNING AND DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. pp34-37, June-2022, Available at : http://www.jetir.org/papers/JETIRFM06008.pdf