The rise of automation and AI has raised fears about job loss, but smart tools can also train workers rather than replace them. Meanwhile, a chronic shortage of trained personnel limits the reach of healthcare in both developing and developed countries.
Minkyo Lee, Rustem F. Ismagilov, and colleagues develop and describe a device that trains and assists laboratory-inexperienced personnel to perform laboratory workflows. Specifically, the device monitors a user's progress through the steps of sample pooling for nucleic acid amplification tests (NAATs), which can detect a wide range of infectious pathogens.
Sample pooling, in which equal volumes from multiple specimens are combined and tested together, can reduce per-sample costs and increase testing throughput while preserving clinical performance. However, pooling can be error-prone, as workers must transfer clinical specimens correctly, avoid cross-contamination, and maintain accurate documentation.
The authors aim to make pooling more practical in small- and medium-scale health settings, such as mobile or decentralized testing sites, where trained personnel or expensive automated liquid handlers may be unavailable. The device offers step-by-step guidance and tracks user progress, precisely weighing each sample tube and providing clear, real-time feedback if too much or not enough sample is added. The device helps users fix correctable mistakes, but if a detected mistake is uncorrectable, the device guides the user to terminate the process. To support broad accessibility, the entire apparatus is made from low-cost, off-the-shelf electronic components, 3D-printed modules, and open-source systems, for a total cost of ~$600 each.
The authors tested the device with 48 participants, 37 of whom had little or no prior laboratory experience. Compared with paper instructions, the device helped users pool mock clinical samples with high accuracy, reduced uncorrected handling errors, improved volume-transfer skills, and produced high-quality pools.
According to the authors, such tools could make pooled NAATs logistically and financially possible for large-scale surveillance programs, including programs that must estimate low disease prevalence and inform decisions about when mass drug administration can be stopped.
