Open AccessA machine learning model of microscopic agglutination test for diagnosis of leptospirosis
Author(s) -
Yuji Oyamada,
Ryo Ozuru,
Toshiyuki Masuzawa,
Satoshi Miyahara,
Yasuhiko Nikaido,
Fumio Obata,
Mitsumasa Saito,
Sharon Y. A. M. Villanueva,
Jun Fujii
Publication year - 2021
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0259907
Subject(s) - leptospirosis , artificial intelligence , leptospira , direct agglutination test , pattern recognition (psychology) , gold standard (test) , support vector machine , computer science , serotype , computer vision , machine learning , medicine , serology , pathology , antibody , radiology , virology , immunology
Leptospirosis is a zoonosis caused by the pathogenic bacterium Leptospira . The Microscopic Agglutination Test (MAT) is widely used as the gold standard for diagnosis of leptospirosis. In this method, diluted patient serum is mixed with serotype-determined Leptospires, and the presence or absence of aggregation is determined under a dark-field microscope to calculate the antibody titer. Problems of the current MAT method are 1) a requirement of examining many specimens per sample, and 2) a need of distinguishing contaminants from true aggregates to accurately identify positivity. Therefore, increasing efficiency and accuracy are the key to refine MAT. It is possible to achieve efficiency and standardize accuracy at the same time by automating the decision-making process. In this study, we built an automatic identification algorithm of MAT using a machine learning method to determine agglutination within microscopic images. The machine learned the features from 316 positive and 230 negative MAT images created with sera of Leptospira -infected (positive) and non-infected (negative) hamsters, respectively. In addition to the acquired original images, wavelet-transformed images were also considered as features. We utilized a support vector machine (SVM) as a proposed decision method. We validated the trained SVMs with 210 positive and 154 negative images. When the features were obtained from original or wavelet-transformed images, all negative images were misjudged as positive, and the classification performance was very low with sensitivity of 1 and specificity of 0. In contrast, when the histograms of wavelet coefficients were used as features, the performance was greatly improved with sensitivity of 0.99 and specificity of 0.99. We confirmed that the current algorithm judges the positive or negative of agglutinations in MAT images and gives the further possibility of automatizing MAT procedure.