ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 12. Vol. 26. 2020

DOI: 10.17587/it.26.701-705

I. Lakman^1,2, PhD, Assotiate Professor, e-mail: lackmania@mail.ru, R. Akhmetvaleev¹, Data Analyst, D. Enikeev¹, Data Analyst, R. Khaziakhmetov¹, Software Engineer, O. Chernenko³, Cand. Medical Sciences, Deputy Director for Development,
¹LLC Lexema, Ufa, 450104, Russian Federation,
²Institute of Economics, Finance and Business, Bashkir State University, Ufa, 450076, Russian Federation,
³LLC "Laboratory of hemodialysis", Ufa, 450083, Russian Federation

Similarity Learning Algorithm Selection for Chronic Renal Failure Patients Treatment Strategy Optimization

One of the main methods on which the personalized approach in medicine is based is finding a pair of patients who are similar in the properties of the disease. The objective of the study is to select the most effective similarity learning instrument amongst three options anaemia treatment and phosphorus-calcium balance recovery in dialysis patients, ranked according to the highest similarity to the particular patient. As soon as methods for comparing instruments will achieve the goal, the algorithm of weight tagging is used, modified by the authors by adding more weights values to important features — the cosine measure, the soft cosine measure, considering the similarity of drug alternative and their bioavailability. As a metric that evaluates the quality of algorithms, a combined metric is used that takes into account the quality of treatment classification as effective and the rank order of the greatest correspondence of therapy to a specific patient. As a result, using the opinions of nephrologists as experts, it was shown that the best measure of similarity is the soft cosine measure.
Keywords: similarity learning, cosine measure, soft cosine measure, dialysis

P. 701–705

Acknowledgments. The study "Development of an intelligent decision support system for prescribing personalized dialysis and drug therapy to patients with chronic renal failure using artificial intelligence algorithms" was supported by a grant No. AAAA-A20-120011490126-5 from the Foundation for the Promotion of the Development of Small Forms of Enterprises in the Scientific and Technical Sphere.

To the contents