An online intelligent electronic medical record system via speech recognition

Traditional electronic medical record systems in hospitals rely on healthcare workers to manually enter patient information, resulting having spend a significant amount of time each day filling out records. This inefficient interaction seriously affects the communication between doctors and patients reduces speed at which can diagnose patients’ conditions. The rapid development deep learning–based speech recognition technology promises improve this situation. In work, we build an online system based interaction. integrates linguistic knowledge base, specialized language model, personalized acoustic fault-tolerance mechanism. Hence, propose develop advanced approach with multi-accent adaptive for avoiding mistakes caused by accents, it improves accuracy obviously. For testing proposed system, construct data sets using audio records from real environments. On clinical scenarios, our algorithm significantly outperforms other machine learning algorithms. Furthermore, compared traditional that keyboard inputs, is much more efficient, its rate increases increasing system. Our results show expected revolutionize working departments, serves efficient clinics low consumption depending has less recording lows down modification recordings; due built database terms, so good generalized application adaption scenarios hospitals.