Smart pooling: AI-powered COVID-19 informative group testing

Abstract

Massive molecular testing for COVID-19 has been pointed out as fundamental to moderate the spread of the pandemic. Pooling methods can enhance testing efficiency, but they are viable only at low incidences of the disease. We propose Smart Pooling, a machine learning method that uses clinical and sociodemographic data from patients to increase the efficiency of informed Dorfman testing for COVID-19 by arranging samples into all-negative pools. To do this, we ran an automated method to train numerous machine learning models on a retrospective dataset from more than 8000 patients tested for SARS-CoV-2 from April to July 2020 in Bogotá, Colombia. We estimated the efficiency gains of using the predictor to support Dorfman testing by simulating the outcome of tests. We also computed the attainable efficiency gains of non-adaptive pooling schemes mathematically. Moreover, we measured the false-negative error rates in detecting the ORF1ab and N genes of the virus in RT-qPCR dilutions. Finally, we presented the efficiency gains of using our proposed pooling scheme on proof-of-concept pooled tests. We believe Smart Pooling will be efficient for optimizing massive testing of SARS-CoV-2.

Machine learning-driven COVID-19 early triage and large-scale testing strategies based on the 2021 Costa Rican Actualidades survey

“…The partition of the high and low risk group are defined through a machine learning algorithms (Escobar et al, 2022; Park et al, 2022). The classifier allows optimizing each strategy for each group reducing the overall number of tests applied and costs.…”

Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19

“…In 2021, “smart pooling” was proposed by Escobar et al . to overcome the problems of prevalence variability and failure in using group testing in settings with high prevalence 15 . Smart pooling uses a priori information about the patient to calculate the probability of an individual to be positive, based on the individual’s clinical information.…”

“…Escobar et al . showed that in an area with a COVID-19 prevalence of 50%, smart pooling still could be 6% more efficient than conventional testing 15 . In another study, Deckerts et al .…”

Integrating Magnetic-Bead-Based Sample Extraction and Molecular Barcoding for the One-Step Pooled RT-qPCR Assay of Viral Pathogens without Retesting

“…11 However, NGS requires labor-intensive protocols, expensive sequencing platforms, and a high-power computing device for data analysis, which makes it difficult to scale up, especially in resource-limited regions. Machine learning-powered pooling test 12 and digital PCR technology 13 have been studied to improve the efficiency and sensitivity of Dorfman group testing even during high disease prevalence, but these methods still require retest steps. Recently, our group developed a pooled assay for a largescale screening named Unique Barcoded Primer-Assisted Sample-Specific Pooled Testing (Uni-Pool), which can realize sample-specific testing of pooled samples without retesting.…”

“… 11 However, NGS requires labor-intensive protocols, expensive sequencing platforms, and a high-power computing device for data analysis, which makes it difficult to scale up, especially in resource-limited regions. Machine learning-powered pooling test 12 and digital PCR technology 13 have been studied to improve the efficiency and sensitivity of Dorfman group testing even during high disease prevalence, but these methods still require retest steps.…”