Title: Machine learning applied in blood laboratory database for identification of an obesogenic/diabetogenic diet consumption: a preclinical modelling approach

Authors: Laize D.L. Trindade; Diovana G. de Batista; Maira S. Brigo; Matias N. Frizzo; Rafael Z. Frantz; Fabricia Roos-Frantz; Thiago G. Heck; Sandro Sawicki

Addresses: Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil ' Unijuí University – Rua do Comércio, Rua do Comércio, Rio Grande do Sul, Brazil

Abstract: Routine blood tests usually do not show changes during the development of diseases, nor indicate the quality of food being digested. In this study, we tested whether it is possible to use machine learning techniques to identify the type of diet intake from laboratory tests. For doing so, seven different machine learning techniques were used to analyse CBC data, with 15 variables from 44 laboratory animals consuming either a standard diet or a high fat diet. In the analyses, the metrics accuracy, precision, recall and f1-score were considered. The results presented by the techniques proved effective in identifying the type of diet, with accuracy above 88% making it a good alternative to support decision-making by health professionals.

Keywords: obesity; chronic non-communicable diseases; haematological parameters; artificial intelligence.

DOI: 10.1504/IJCAT.2024.144663

International Journal of Computer Applications in Technology, 2024 Vol.75 No.1, pp.22 - 34

Received: 17 Apr 2023
Accepted: 19 Mar 2024
Published online: 26 Feb 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article