Dataset Information

Artificial intelligence-driven mobile interpretation of a semi-quantitative cryptococcal antigen lateral flow assay.

ABSTRACT:

Objectives

Cryptococcosis remains a severe global health concern, underscoring the urgent need for rapid and reliable diagnostic solutions. Point-of-care tests (POCTs), such as the cryptococcal antigen semi-quantitative (CrAgSQ) lateral flow assay (LFA), offer promise in addressing this challenge. However, their subjective interpretation poses a limitation. Our objectives encompass the development and validation of a digital platform based on Artificial Intelligence (AI), assessing its semi-quantitative LFA interpretation performance, and exploring its potential to quantify CrAg concentrations directly from LFA images.

Methods

We tested 53 cryptococcal antigen (CrAg) concentrations spanning from 0 to 5000 ng/ml. A total of 318 CrAgSQ LFAs were inoculated and systematically photographed twice, employing two distinct smartphones, resulting in a dataset of 1272 images. We developed an AI algorithm designed for the automated interpretation of CrAgSQ LFAs. Concurrently, we explored the relationship between quantified test line intensities and CrAg concentrations.

Results

Our algorithm surpasses visual reading in sensitivity, and shows fewer discrepancies (p < 0.0001). The system exhibited capability of predicting CrAg concentrations exclusively based on a photograph of the LFA (Pearson correlation coefficient of 0.85).

Conclusions

This technology's adaptability for various LFAs suggests broader applications. AI-driven interpretations have transformative potential, revolutionizing cryptococcosis diagnosis, offering standardized, reliable, and efficient POCT results.

SUBMITTER: Bermejo-Pelaez D

PROVIDER: S-EPMC11365246 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial intelligence-driven mobile interpretation of a semi-quantitative cryptococcal antigen lateral flow assay.

Bermejo-Peláez David D Alastruey-Izquierdo Ana A Medina Narda N Capellán-Martín Daniel D Bonilla Oscar O Luengo-Oroz Miguel M Rodríguez-Tudela Juan Luis JL

IMA fungus 20240830 1

<h4>Objectives</h4>Cryptococcosis remains a severe global health concern, underscoring the urgent need for rapid and reliable diagnostic solutions. Point-of-care tests (POCTs), such as the cryptococcal antigen semi-quantitative (CrAgSQ) lateral flow assay (LFA), offer promise in addressing this challenge. However, their subjective interpretation poses a limitation. Our objectives encompass the development and validation of a digital platform based on Artificial Intelligence (AI), assessing its s ...[more]

PMID: 39215368

Similar Datasets

Project description:Higher cryptococcal antigen (CrAg) titers are strongly associated with mortality risk in individuals with HIV-associated cryptococcal disease. Rapid tests to quantify CrAg levels may provide important prognostic information and enable treatment stratification. We performed a laboratory-based validation of the IMMY semiquantitative cryptococcal antigen (CrAgSQ) lateral flow assay (LFA) against the current gold standard CrAg tests. We assessed the diagnostic accuracy of the CrAgSQ in HIV-positive individuals undergoing CrAg screening, determined the relationship between CrAgSQ scores and dilutional CrAg titers, assessed interrater reliability, and determined the clinical correlates of CrAgSQ scores. A total of 872 plasma samples were tested using both the CrAgSQ LFA and the conventional IMMY CrAg LFA, of which 692 were sequential samples from HIV-positive individuals undergoing CrAg screening and an additional 180 were known CrAg-positive plasma samples archived from prior studies. Interrater agreement in CrAgSQ reading was excellent (98.17% agreement, Cohen's kappa 0.962, P < 0.001). Using the IMMY CrAg LFA as a reference standard, CrAgSQ was 93.0% sensitive (95% confidence interval [CI] 80.9% to 98.5%) and 93.8% specific (95% CI, 91.7% to 95.6%). After reclassification of discordant results using CrAg enzyme immunoassay testing, the sensitivity was 98.1% (95% CI, 90.1% to 100%) and specificity 95.8% (95% CI, 93.9% to 97.2%). The median CrAg titers for semiquantitative score categories (1+ to 4+) were 1:10 (interquartile range [IQR], 1:5 to 1:20) in the CrAgSQ 1+ category, 1:40 (IQR, 1:20 to 1:80) in the CrAgSQ 2+ category, 1:640 (IQR, 1:160 to 1:2,560) in the CrAgSQ 3+ category, and 1:5,120 (IQR, 1:2,560 to 1:30,720) in the CrAgSQ 4+ category. Increasing CrAgSQ scores were strongly associated with 10-week mortality. The IMMY CrAgSQ test had high sensitivity and specificity compared to the results for the IMMY CrAg LFA and provided CrAg scores that were associated with both conventional CrAg titers and clinical outcomes.

Dataset Information

Artificial intelligence-driven mobile interpretation of a semi-quantitative cryptococcal antigen lateral flow assay.

Objectives

Methods

Results

Conclusions

Publications

Artificial intelligence-driven mobile interpretation of a semi-quantitative cryptococcal antigen lateral flow assay.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets