Potential Problems and Uses for Artificial Intelligence in Clinical Medicine

Artificial intelligence (AI) is being widely used, with trial systems already in use in the medical field, where there are high expectations for its potential for use in the future. Studies have shown that AI diagnosis is almost as accurate as that of human experts. However, problems with the use of AI in clinical medicine must be identified and carefully examined to insure that it can be used safely. Herein, I illustrate various concerns related to the use of AI and show how it can be put to practical use in clinical medicine. The concerns about the use of AI include the following: differences in expectations for AI, failure to correctly diagnose disease because of a lack of data available for learning, and over dependence by physicians using it to make a diagnosis. AI can also be useful to hospital staff other than physicians. We should not leave the business of medicine and healthcare to AI systems, but use it to assist with decision-making and to raise labor efficiency and effectiveness. *Corresponding Author: Prof. Eisuke Hanada, Department of Information Science, Faculty of Science and Engineering, Saga University, Saga, Japan; E-mail: hanada@cc.saga-u.ac.jp Citation: Hanada E (2020) Potential Problems and Uses for Artificial Intelligence in Clinical Medicine. Int J Comput Softw Eng 5: 154. doi: https://doi. org/10.15344/2456-4451/2020/154 Copyright: © 2020 Hanada. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. From a developers’ viewpoint, AI is limited because it can search only in its learned data. This means that AI cannot associate knowledge from domains that it has not learned or does not have access to. Performance of AI in Clinical Diagnosis Although there are differences by country, a physician's license is granted on the premise of having studied the fundamentals of medicine across all domains. However, almost all physicians have a specialty as their main focus, and physicians who work in large hospitals tend to be highly (and narrowly) specialized. Often when building an AI system for use in clinical medicine, one or several of these highly specialized physicians take the initiative. In such cases, AI will tend to learn only knowledge based on the specialty of the physician(s) involved. This means that such specialized AI will overlook the existence of illnesses that have not had the chance to learn or that are out of the scope of the AI system. AI on which two or more clinical departments have co-operated is seldom seen. Some symptoms are associated with a broad range of diseases and may differ by patient, even patients with the same disease. An example of a problematic case is a patient who has had their primary disease diagnosed but who newly contracts another disease, the symptoms of which may differ from those of other patients with the same primary disease. In such cases, AI would probably not be useful for assisting with diagnosis or treatment. In contrast, for some diseases the mechanism is clear and differentiation using symptoms is easy. The use of AI could be problematic in cases where the correct disease is not output because there were too few candidate diseases input. Such cases show the potential weakness of using AI for the screening of patients and making the final determination of a patient’s disease. As I stated previously, I think that highly specialized AI can be used for assisting with detailed diagnosis after screening, but the disease candidates it has available to choose from must be wide ranging and the amount of data limited to that which is necessary. Providing AI with the data necessary to achieve this high level of performance is International Journal of Computer & Software Engineering Eisuke Hanada Department of Information Science, Faculty of Science and Engineering, Saga University, Saga, Japan Int J Comput Softw Eng IJCSE, an open access journal ISSN: 2456-4451 Volume 5. 2020. 154 Hanada,. Int J Comput Softw Eng 2020, 5: 154 https://doi.org/10.15344/2456-4451/2020/154