Doctors advocate the use of routine clinical data for medical research for the practical use of artificial intelligence in healthcare
Paper published in the Journal of Medical Internet Research
Media Recommendation: Journal of Medical Internet Research, Vol 23, No 3 (2021)
Paper “Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey“
Artificial intelligence (AI) and adaptive learning systems are creating completely new treatment methods in medicine. May it evaluating data, recognizing patterns or comparing symptoms. The increasing development goes hand in hand with enormous expectations for the progress of medical care. The University Hospital RWTH Aachen, consortium partner of the SMITH Consortium of the Medical Informatics Initiative, conducted a web-based survey on the requirements and expectations of physicians for the use of future medical applications in health care. The results have now been published in the Journal of Medical Internet Research.
Physicians from all medical disciplines at eight university hospitals of the SMITH Consortium were surveyed. The study also investigated the attitudes towards the secondary use of patient data for biomedical and medical research, e.g. to develop algorithms for machine learning. A total of 303 persons took part in the online survey. In general, the medical staff in inpatient care are positive about the use of most AI applications in medicine. Over 90 percent of the participating physicians assume that the future of medicine will be shaped by a mix of human and artificial intelligence, but at the same time demand a scientific evaluation of AI-based systems before they are implemented in everyday clinical practice.
Availability and simplified access to large, clinical research databases is a fundamental requirement for AI development in medicine. 80 percent of the physicians surveyed were in favor of integrating clinical routine care with medical research in order to optimize patient care as well as biomedical and medical research in the long term. Initiatives such as the German Medical Informatics Initiative, the EOSC (European Open Science Cloud) and the FAIR Data Principles (findable, accessible, interoperable and reusable) create the conditions for research and care to move closer together. In the long term, this will lead to improved analysis of clinical data and more accurate diagnosis and treatment decisions for patients.
To the publication: