Verificación Secundaria del Protocolo Charité-Berlín de SARS-CoV-2 en la UPTC: Integrando la IA en las Consideraciones Epidemiológicas

Abstract

The secondary verification of the Charit.-Berl.n protocol was a crucial step in ensuring the accuracy and reliability of SARS-CoV-2 detection at the GEBIMOL laboratory. Methodology: The Luna Universal Probe One-Step RT-qPCR kit was optimized to amplify the viral E gene, utilizing a total of 89 samples previously characterized by a national health entity (NHE). The test’s reproducibility, clinical agreement, sensitivity, and specificity were evaluated through triplicate processing of all samples. Additionally, artificial intelligence (AI) tools, including ChatGPT, Blackbox, and Perplexity AI, were employed to develop an algorithm that classified patient status based on their Ct values. Results and Discussion: No significant differences were observed in the Ct values of positive samples (p = 0.806) across the three RT-qPCR replicates. The concordance rate was 99% with a Kappa index exceeding 0.9 (p < 0.001). The ROC curve analysis revealed an area under the curve of 0.97 with sensitivity and specificity values of 100% and 97%, respectively. Conclusion: The Charit.-Berl.n protocol is validated for delivering reliable results, and the integration of AI enhances the rapid classification of epidemiological data at the university.

Ähnliche Arbeiten