Dear Colleagues,

This Special Issue is the second edition of “Diagnostic Strategy in Medicine in the Era of Digital Assistance and Machine Learning”.

https://0-www-mdpi-com.brum.beds.ac.uk/journal/ijerph/special_issues/DSMEDAML

Diagnosis is one of the essential parts of clinical expertise in medicine. The mastery of diagnostic (clinical) reasoning is a crucial mission of physicians who practice medicine since ascertaining the correct diagnosis is vital to proper treatment and the health management of patients. The Institute of Medicine concluded that diagnostic error occurs in nearly every patient throughout their lifetime. The phenomena are observed in any clinical setting, ranging from rural to urban, clinic to a tertiary hospital, and community to university. Today, physicians can enjoy digital assistance and the support of artificial intelligence in daily clinical practices. These cutting-edge technologies allow us to access the needed information swiftly and ultimately uncover hidden or unknown diagnoses. These “artificial” systems are seemingly powerful tools in diagnosis, but they have their disadvantages. For example, they may often be designed not to work independently, specifically to utilize information from external input acquired by human medical professionals.

It is reasonable to say that it is very challenging for the digital system to obtain subtle signs and history information because every patient has a unique history, background, and personality. On obtaining a clinical history and physical examination, physicians should account for a patient’s clinical context, perception of symptoms, and potentially hidden complaints or signs which are not apparent through routine data gathering methods. Identifying and eliciting case-by-case information can be a hurdle for statistical patterns induced by current machine learning systems. The other disadvantage of artificial intelligence is that machine learning systems replace humans’ intuitive diagnostic processes. Dual processing theory (DPT) has been the leading theory in humans’ diagnostic decision making, which comprises an intuitive process (system 1) and analytical process (system 2). Machine learning is categorized as part of system 2, and human clinical reasoning covers both systems 1 and 2. At present, this system is considered to be the most widely accepted way of thinking about the human diagnostic process. For learning and practicing diagnostic thinking, the diagnostic thinking principle, known as “diagnostic strategy (DS),” has been advocated and clinically applied among frontline physicians internationally. This strategy is designed for humans and can be installed in digital systems, augmenting diagnostic accuracy. In this manner, humans and machines can collaborate and establish better diagnostic outcomes.

The term “technological singularity” has been used since the book The Singularity is Near by Raymond Kurzweil was published in 1998. Initially, the term “singularity” is used to describe infinite sizes, and this term was applied to the development of AI, advocated by a statistician named IJ Good.

Kurzweil defined the year 2045 as the point of technological singularity. The singularity would imply unimaginable social changes, leading to the unpredictable change in the scene of diagnosis. However, in the field of diagnosis, the day occurs at a more distant point in time. This phenomenon is because the medical diagnosis process is a highly complicated field involving human cognitive psychology and situational factors, which act as a barrier that the singularity will take a little longer to adopt. In any case, the turning point will undoubtedly come. The singularity does not come naturally but is achieved through human and technological progress. Therefore, we need to guide evolution in a better direction while guaranteeing the augmentation of humans and technology.

In this Special Issue, authors report the current concept and scope of humans’ diagnostic thinking systems and diagnostic systems with a wide range of technology, elucidating future perspectives for augmentation between both systems.

Dr. Taro Shimizu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Environmental Research and Public Health is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2500 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• diagnostic strategy
• clinical reasoning
• diagnostic error
• artificial intelligence
• machine learning
• deep learning
• medical education
• pivot and cluster strategy