Bermejo-Peláez David, Alastruey-Izquierdo Ana, Medina Narda, Capellán-Martín Daniel, Bonilla Oscar, Luengo-Oroz Miguel, Rodríguez-Tudela Juan Luis
Spotlab, Madrid, Spain.
Mycology Reference Laboratory, National Center for Microbiology, Instituto de Salud Carlos III, Madrid, Spain.
IMA Fungus. 2024 Aug 30;15(1):27. doi: 10.1186/s43008-024-00158-5.
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.
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.
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).
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.
隐球菌病仍然是一个严重的全球健康问题，凸显了对快速可靠诊断解决方案的迫切需求。即时检测（POCT），如隐球菌抗原半定量（CrAgSQ）侧向流动分析（LFA），有望应对这一挑战。然而，其主观解读存在局限性。我们的目标包括开发和验证一个基于人工智能（AI）的数字平台，评估其对LFA半定量解读的性能，并探索其直接从LFA图像定量CrAg浓度的潜力。
我们测试了53种浓度范围从0到5000 ng/ml的隐球菌抗原（CrAg）。共接种了318个CrAgSQ LFA，并使用两部不同的智能手机对其进行了两次系统拍照，得到了一个包含1272张图像的数据集。我们开发了一种用于自动解读CrAgSQ LFA的AI算法。同时，我们探索了定量检测线强度与CrAg浓度之间的关系。
我们的算法在灵敏度上超过了目视读数，且差异更少（p < 0.0001）。该系统展示了仅基于LFA照片预测CrAg浓度的能力（Pearson相关系数为0.85）。
这项技术对各种LFA的适应性表明其具有更广泛的应用前景。人工智能驱动的解读具有变革潜力，将彻底改变隐球菌病的诊断方式，提供标准化、可靠且高效的POCT结果。
