Leveraging AI-Generated Content for Synthetic Electronic Health Record Generation With Deep Learning-Based Diagnosis Model

Consumer electronics have transformed the way we interact with technology, improving convenience and connectivity in day-to-day lives. In the healthcare sector, recent technologies have resulted in enhanced diagnosis, treatment, and patient care. Wearables, artificial intelligence-based data analytics, and telemedicine transform the way of monitoring and managing health, fostering a proactive approach to well-being. The popularity of ChatGPT is proven great potential for AI-generated content (AIGC) that has formed a major impact on the artificial intelligence (AI) community and accelerates the reconsidering of the prospects of general AI. The AIGC is also exposed as a considerable scope to impulse healthcare electronics (HE). Although generative AI has achieved popularity like the formation of images, it could be employed for producing synthetic tabular information. The production of synthetic electronic health records (EHR) undertakes to increase the utilization of machine learning (ML) methods that commonly function with massive quantities of data. ML will identify non-intuitive classifier patterns that permit a new integration of patient feature predictive ability. Currently, deep learning (DL) techniques are effectively utilized in EHR data from medical domains. DL methods excellently captured the significant and beneficial features and patterns from the comprehensive medical information in EHR data. This study presents AI-generated content for Synthetic Electronic Health Record Generation with a Deep Learning-based Diagnosis (SEHRG-DLD) Model. The focus of the SEHRG-DLD technique is to initially generate the synthetic EHR data and then analyze the medical data for disease diagnosis using the DL model. The SEHRG-DLD technique comprises a two-stage process: synthetic data generation and disease diagnosis. At the initial stage, the SEHRG-DLD technique uses the ChatGPT tool to generate synthetic EHR data. Then, the SEHRG-DLD technique undergoes the disease diagnosis process using three sub-processes namely Harris Hawks Optimization (HHO) based feature selection, deep belief network (DBN) based classification, and Golden Jackal Optimization (GJO) based hyperparameter tuning. The application of the HHO and GJO algorithms helps in accomplishing enhanced diagnostic performance of the SEHRG-DLD technique. The performance analysis of the SEHRG-DLD technique is examined by employing the ChatGPT-generated dataset. The experimental results clearly stated the supremacy of the SEHRG-DLD technique over other recent methods for different measures.