Penetration of Deep Learning in Human Health Care and Pharmaceutical Industries; the Opportunities and Challenges

Abstract

Computational medicine has emerged as a result of the advancement of medical technology, which has led to the emergence of the big data era in the biomedical area, which is supported by artificial intelligence technology. To advance the development of precision medicine, people must be able to extract the valuable information from this vast biomedical data. In the past, professionals in the field of feature engineering and domain knowledge were typically utilised to extract the features from the biological data using machine learning techniques, which took a lot of time and resources. Modern machine learning techniques like deep learning (DL) have an advantage over them in that they can automatically find strong, complex features from fresh data without the necessity for succeeding engineering. The study of DL's applications in the fields of genomics, drug development, electronic health records, and medical imaging suggests that deep learning has clear advantages in maximising the use of biomedical data. Deep learning is becoming increasingly important in the field of medicine and health due to its large range of potential applications. The lack of data, interpretability, data privacy, and heterogeneity are some of the limitations of deep learning in computational medical health. A resource for improving the use of deep learning in medical health is provided by the analysis and discussion of these difficulties.