Christopher Richard Bilder

1 Timely and efficient testing is essential to identify individuals who have an infectious disease. This was abundantly clear early on during the COVID-19 pandemic when testing was delayed or even ...

When screening for low‐prevalence diseases, pooling specimens (e.g., blood, urine, swabs, etc.) through group testing has the potential to substantially reduce costs when compared to testing specimens individually. A common goal in group testing applications is to estimate the relationship between an individual's true disease status and their individual‐level covariate information. However, estimating such a relationship is a non‐trivial problem because true individual disease statuses are unknown due to the group testing protocol and the possibility of imperfect testing. While several regression methods have been developed in recent years to accommodate the complexity of group testing data, the functional form of covariate effects is typically assumed to be known. To avoid model misspecification and to provide a more flexible approach, we propose a Bayesian additive regression trees framework to model the individual‐level probability of disease with potentially misclassified group testing data. Our methods can be used to analyze data arising from any group testing protocol with the goal of estimating unknown functions of covariates and assay classification accuracy probabilities.

This study evaluated the performance of urine reagent strips (URSs) in detecting Schistosoma haematobium infection in individual and pooled urine samples. Between June 2022 and April 2023, 2634 urine samples (10 mL each) from school-age children (5–15 years) in 15 villages across Ethiopia’s Afar, Benishangul-Gumuz, and Gambella regions were tested using urine filtration microscopy (UFM) and URSs for blood, a marker of S. haematobium eggs. Pooled samples from 5, 10, 20, and 40 individuals (one positive, others negative) were examined with both methods. UFM results were used to calculate URSs’ sensitivity, specificity, and predictive values for detecting infection. A total of 2634 children were screened for S. haematobium infection. UFM detected S. haematobium eggs in 370 samples, while URSs identified infection in 414 children. URSs showed 64% sensitivity and 92% specificity for individual samples. The positive and negative predictive values for individual samples were 57% and 94%, respectively. Sensitivity for pooled samples ranged from 47% (pools of 40) to 53% (pools of 20). In pools with one positive sample, URSs misclassified 220 (50%), 109 (49.5%), 52 (47.0%), and 28 (50.9%) pools as negative for S. haematobium eggs for pool sizes 5, 10, 20, and 40, respectively. Sensitivity for individual samples was higher in children with heavy infection (92.5%) compared to light infection (55.9%), and sensitivity in pooled samples increased with infection intensity (p < 0.001). In conclusion, URSs may misclassify S. haematobium infection in children when samples are examined individually or in pools, potentially leading to unnecessary treatment or missed cases. However, URSs shows promise as a screening tool for detecting S. haematobium infection in areas with high infection intensity.

The accumulation of technical knowledge is the central focus of graduate programs in statistics. However, student success does not depend solely on acquiring such knowledge. Rather, students must also understand the rigors of graduate study to complete their degree. And, they need to understand the statistics profession to prepare for a career after graduation. The purpose of the one-credit hour Alpha Seminar course at the University of Nebraska-Lincoln is to educate graduate students in these non-technical areas. Students are required to enroll in Alpha Seminar during their first semester of study. In addition to advisement on courses and graduation requirements, Alpha Seminar features topics on career paths, ethics, professional accreditation, internships, and professional societies. Alumni also meet with the class to discuss how to be successful in the program and in a future career. This paper discusses course topics, examines assignments, and provides evaluations from student cohorts. The corresponding course website is available at www.chrisbilder.com/stat810.

High‐volume testing of clinical specimens for sexually transmitted diseases is performed frequently by a process known as group testing. This algorithmic process involves testing portions of specimens from separate individuals together as one unit (or “group”) to detect diseases. Retesting is performed on groups that test positively in order to differentiate between positive and negative individual specimens. The overall goal is to use the least number of tests possible across all individuals without sacrificing diagnostic accuracy. One of the most efficient group testing algorithms is array testing. In its simplest form, specimens are arranged into a grid‐like structure so that row and column groups can be formed. Positive‐testing rows/columns indicate which specimens to retest. With the growing use of multiplex assays, the increasing number of diseases tested by these assays, and the availability of subject‐specific risk information, opportunities exist to make this testing process even more efficient. We propose specific specimen arrangements within an array that can reduce the number of retests needed when compared with other array testing algorithms. We examine how to calculate operating characteristics, including the expected number of tests and the SD for the number of tests, and then subsequently find a best arrangement. Our methods are illustrated for chlamydia and gonorrhea detection with the Aptima Combo 2 Assay. We also provide R functions to make our research accessible to laboratories.

When screening for infectious diseases, group testing has proven to be a cost efficient alternative to individual level testing. Cost savings are realized by testing pools of individual specimens (eg, blood, urine, saliva, and so on) rather than by testing the specimens separately. However, a common concern that arises in group testing is the so‐called “dilution effect.” This occurs if the signal from a positive individual's specimen is diluted past an assay's threshold of detection when it is pooled with multiple negative specimens. In this article, we propose a new statistical framework for group testing data that merges estimation and case identification, which are often treated separately in the literature. Our approach considers analyzing continuous biomarker levels (eg, antibody levels, antigen concentrations, and so on) from pooled samples to estimate both a binary regression model for the probability of disease and the biomarker distributions for cases and controls. To increase case identification accuracy, we then show how estimates of the biomarker distributions can be used to select diagnostic thresholds on a pool‐by‐pool basis. Our proposals are evaluated through numerical studies and are illustrated using hepatitis B virus data collected on a prison population in Ireland.

Christopher R Bilder, Peter C Iwen, Baha Abdalhamid; Pool size selection when testing for SARS-CoV-2, Clinical Infectious Diseases, , ciaa774, https://doi.org/

Objectives: To establish the optimal parameters for group testing of pooled specimens for the detection of SARS-CoV-2. Methods: The most efficient pool size was determined to be five specimens using a web-based application. From this analysis, 25 experimental pools were created using 50 µL from one SARS-CoV-2 positive nasopharyngeal specimen mixed with 4 negative patient specimens (50 µL each) for a total volume of 250 µL. Viral RNA was subsequently extracted from each pool and tested using the CDC SARS-CoV-2 RT-PCR assay. Positive pools were consequently split into individual specimens and tested by extraction and PCR. This method was also tested on an unselected group of 60 nasopharyngeal specimens grouped into 12 pools. Results: All 25 pools were positive with cycle threshold (Ct) values within 0 and 5.03 Ct of the original individual specimens. The analysis of 60 specimens determined that 2 pools were positive followed by identification of 2 individual specimens among the 60 tested. This testing was accomplished while using 22 extractions/PCR tests, a savings of 38 reactions. Conclusions: When the incidence rate of SARS-CoV-2 infection is 10% or less, group testing will result in the saving of reagents and personnel time with an overall increase in testing capability of at least 69%.