Today, an abundance of electronically stored medical image data and DL algorithms can be used to recognize and detect patterns and anomalies in this kind of dataset. Computers and algorithms can interpret the imaging data as a very qualified radiologist can see irregular skin, lesions, tumours and brain bleeds. Consequently, the use of AI/ML tools/platforms to help radiologists is poised to grow exponentially. This approach addresses a vital issue in the healthcare sector as well-trained radiologists are challenging to come by worldwide. These professional professionals are, in most cases, under tremendous pressure due to the influx of digital medical data. We analyze and address the current state of A.I. applications in healthcare. A.I. can be applied to various healthcare data forms (structured and unstructured). Popular A.I. techniques include machine learning for structured data such as classic support vectors and neural networks, modern in-depth learning unstructured data natural language processing.
CITATION STYLE
Usmani, U. A., & Jaafar, J. (2022). Machine Learning in Healthcare: Current Trends and the Future. In Lecture Notes in Electrical Engineering (Vol. 758, pp. 659–675). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-16-2183-3_64
Mendeley helps you to discover research relevant for your work.