About the Article
Article Files
[This article belongs to Volume - 71, Issue - 4]
Published on : 2026-04-17 19:06:43
Article Code: AMJ-17-04-2026-12376
Title : AI-Integrated Multi-Omic Liquid Biopsy for Rapid Diagnosis of EBV-Associated Burkitt Lymphoma in the Greater Mekong Region: A Prospective Diagnostic Accuracy Study
Author(s) : Ana María Hernández Vázquez, J.C. Jaime-Fagundo Fagundo
Abstract :
Background: Burkitt lymphoma (BL) is a highly aggressive childhood cancer endemic to Epstein-Barr virus (EBV) and malaria regions. Diagnostic delays exceeding 90 days are common in resource-limited settings due to scarce pathology infrastructure. We developed and validated an artificial intelligence (AI)-integrated, multi-omic liquid biopsy platform for rapid BL diagnosis in the Greater Mekong Subregion.
Methods: We conducted a prospective, multicenter diagnostic accuracy study across eight hospitals in Vietnam, Cambodia, and Laos (2022–2025). A total of 847 children and young adults (age 3–25 years) with suspected lymphoma underwent concurrent tissue biopsy (gold standard) and liquid biopsy. The comprehensive assay integrated targeted next-generation sequencing (MYC, ID3, TP53, IGH/IGK/IGL translocations), EBV fragmentomics (fragment size ratios, end-motif analysis), and plasma proteomics. We trained a deep learning ensemble model (convolutional neural network + gradient boosting) and compared its performance against conventional histopathology in a head-to-head prospective validation cohort (n=224).
Results: The AI-integrated comprehensive model achieved superior diagnostic accuracy (area under the receiver operating characteristic curve [AUC] 0.991; 95% confidence interval [CI] 0.981–0.998) compared to clinical models alone (AUC 0.834; P<0.001). Sensitivity was 98.2% (95% CI 95.4–99.4%) and specificity 99.1% (95% CI 97.8–99.7%). Median diagnostic turnaround time was reduced from 52.3 days (IQR 28.4–112.6) for tissue-based diagnosis to 3.8 days (IQR 3.0–6.2) for liquid biopsy (P=1.2×10⁻¹⁴). In 48.2% of cases, liquid biopsy provided the only diagnostic result available at the initial multidisciplinary tumor board, enabling immediate treatment initiation. Cost-effectiveness analysis demonstrated an incremental cost-effectiveness ratio (ICER) of $320 per quality-adjusted life year (QALY) gained, favoring early liquid biopsy intervention.
Conclusions: AI-integrated multi-omic liquid biopsy enables near-perfect diagnostic accuracy for EBV-associated BL with same-week turnaround, offering a transformative solution for oncology care in resource-constrained environments.