Skip to main content
Dryad logo

Applications of machine learning tools for ultra-sensitive detection of lipoarabinomannan with plasmonic grating biosensors in clinical samples of tuberculosis

Citation

Bok, Sangho (2022), Applications of machine learning tools for ultra-sensitive detection of lipoarabinomannan with plasmonic grating biosensors in clinical samples of tuberculosis, Dryad, Dataset, https://doi.org/10.5061/dryad.63xsj3v5g

Abstract

Background

Tuberculosis is one of the top ten causes of death globally and the leading cause of death from a single infectious agent. Eradicating the Tuberculosis epidemic by 2030 is one of the top United Nations Sustainable Development Goals. Early diagnosis is essential to achieving this goal because it improves individual prognosis and reduces transmission rates of asymptomatic infected. We aim to support this goal by developing rapid and sensitive diagnostics using machine learning algorithms to minimize the need for expert intervention. 

Methods and Findings

A single-molecule fluorescence immunosorbent assay was used to detect the Tuberculosis biomarker lipoarabinomannan from a set of twenty clinical patient samples and a control set of spiked human urine. Tuberculosis status was separately confirmed by GeneXpert MTB/RIF and cell culture. Two machine learning algorithms, an automatic and a semiautomatic model, were developed and trained by the calibrated lipoarabinomannan titration assay data and then tested against the ground truth patient data. The semiautomatic model differed from the automatic model by an expert review step in the former, which calibrated the lower threshold to determine single molecules from background noise. The semiautomatic model was found to provide 88.89% clinical sensitivity, while the automatic model resulted in 77.78% clinical sensitivity.

Conclusions

The semiautomatic model outperformed the automatic model in clinical sensitivity as a result of the expert intervention applied during calibration and both models vastly outperformed manual expert counting in terms of time-to-detection and completion of analysis. Meanwhile, the clinical sensitivity of the automatic model could be improved significantly with a larger training dataset. In short, semiautomatic, and automatic Gaussian Mixture Models have a place in supporting rapid detection of Tuberculosis in resource-limited settings without sacrificing clinical sensitivity.

Methods

Fluorescence movies were collected on a BX51W1 Olympus microscope with Olympus UPlanSApo 60×/1.20 water-immersion objective using an ORCAFlash 2.8 CMOS camera with 5 s integration time. For all samples, at least 60 in-focus frames were collected per view, which varies from sample to sample due to lensing effects on the focus level of individual frames.

Usage Notes

ImageJ can be used for analysis of the images. Some samples drifted and the sample drift was corrected using the open-source ImageJ plugin Align slices in stack.