Machine learning in laboratory medicine: waiting for the flood?

Abstract

This review focuses on machine learning and on how methods and models combining data analytics and artificial intelligence have been applied to laboratory medicine so far. Although still in its infancy, the potential for applying machine learning to laboratory data for both diagnostic and prognostic purposes deserves more attention by the readership of this journal, as well as by physician-scientists who will want to take advantage of this new computer-based support in pathology and laboratory medicine.

Machine Learning in Orthopedics: A Literature Review

“…Delving into the details of the most common model, families would be beyond the scope of this review, as well as of the main challenges entailed by the “learning” process. Good introductory papers to the main ML techniques and the related challenges can also be found in the medical literature, e.g., (Tomar and Agarwal, 2013 ; Deo, 2015 ; Madelin et al, 2015 ; cab, 2017 ), which this contribution does not want to replicate. In fact, this introductory section was intended to merely make the reader more acquainted with the terms that we will use in reporting the results of our literature review.…”

Machine learning in laboratory diagnostics: valuable resources or a big hoax?

“…By adding the keyword "laboratory medicine", the search output approximates 200 documents, following an even better exponential fitting during the past 10 years (r = 0.994; p < 0.001). This enormously boosted interest in machine learning, along with its potential applications in laboratory medicine, is generating great enthusiasm in the scientific community, as well as among laboratory professionals [5][6][7]. The possibility that machine learning may partially or entirely replace physician's brain is indeed an intriguing perspective, whereby machines tend to be virtually foolproof when correctly trained.…”

“…Unlike machines, the human brain is vulnerable to leaps, lapses and mistakes, especially when dealing with complex and multifaceted issues, such as integrating a large volume of demographic, clinical, environmental and instrumental information for making a final diagnosis. Although such a recent excitement in machine learning is substantially understandable, as the favorable support of AI to the clinical decision-making cannot be denied [5][6][7], many other reasons persuade me that its current value in laboratory diagnostics is maybe overrated.…”

Towards a Gamete Matching Platform: Using Immunogenetics and Artificial Intelligence to Predict Recurrent Miscarriage

“…Recent advances in machine learning techniques applied to medicine have showed their potential to analyze the joint effect of multiple variables and to consider their interactions. For a recent review of how machine learning can contribute to comprehensive, inexpensive, and accurate diagnostics, see 15 .…”