A machine learning model of microscopic agglutination test for diagnosis of leptospirosis

Abstract

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.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

“…A deep learning method using hyperspectral microscope images was also described for the identification of non-O157 Shiga toxin-producing Escherichia coli [ 63 ]. On the other hand, ML has also been applied to the analysis of microscopic agglutination tests (MATs) used to diagnose leptospirosis, an infectious disease caused by the pathogenic bacterial species of Leptospira, and it has been suggested to provide an opportunity for the automatization of MATs [ 64 ]. In this research, the authors trained an SVM-based ML using MAT images created with sera of Leptospira-infected (positive) and non-infected (negative) hamsters, and they reported a sensitivity and specificity of 0.99 for the confirmed diagnosis.…”

Serodynamics: a review of methods for epidemiological inference using serological data

“…First, there are many pathogens or diseases which lack validated biomarkers for exposure recency or correlates of protection, and thus supervised machine learning approaches are useful for algorithmically identifying minimal sets of biomarkers from panels of measurements for accurate prediction or classification using labeled data (e.g., from observations where true exposure or immunity status is known) [30,78,186,187]. A common application of machine learning is for binary diagnosis where there are currently no validated biomarkers for exposure and where cross-reactivity with off-target pathogens is likely [188][189][190][191][192].…”

Reproducing Human Subjective Evaluation in the Microscopic Agglutination Test with Deep Learning

“…As a first step in the computerization of MAT, we have researched machine learning adaptation of MAT based on traditional machine learning techniques [5]. The proposed method is a binary classification that classifies a dark-field microscopy image into either agglutinated or not agglutinated according to free leptospires' appearance on the image.…”