David Bermejo-Peláez, Ana Alastruey-Izquierdo, Narda Medina, Daniel Capellán-Martín, Oscar Bonilla, Miguel Luengo-Oroz, Juan Luis Rodríguez-Tudela
{"title":"Artificial intelligence-driven mobile interpretation of a semi-quantitative cryptococcal antigen lateral flow assay.","authors":"David Bermejo-Peláez, Ana Alastruey-Izquierdo, Narda Medina, Daniel Capellán-Martín, Oscar Bonilla, Miguel Luengo-Oroz, Juan Luis Rodríguez-Tudela","doi":"10.1186/s43008-024-00158-5","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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).</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":54345,"journal":{"name":"Ima Fungus","volume":null,"pages":null},"PeriodicalIF":5.2000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11365246/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ima Fungus","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s43008-024-00158-5","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MYCOLOGY","Score":null,"Total":0}
引用次数: 0
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.
Ima FungusAgricultural and Biological Sciences-Agricultural and Biological Sciences (miscellaneous)
CiteScore
11.00
自引率
3.70%
发文量
18
审稿时长
20 weeks
期刊介绍:
The flagship journal of the International Mycological Association. IMA Fungus is an international, peer-reviewed, open-access, full colour, fast-track journal. Papers on any aspect of mycology are considered, and published on-line with final pagination after proofs have been corrected; they are then effectively published under the International Code of Nomenclature for algae, fungi, and plants. The journal strongly supports good practice policies, and requires voucher specimens or cultures to be deposited in a public collection with an online database, DNA sequences in GenBank, alignments in TreeBASE, and validating information on new scientific names, including typifications, to be lodged in MycoBank. News, meeting reports, personalia, research news, correspondence, book news, and information on forthcoming international meetings are included in each issue