SafeSwab, a sample collection and dispensing device for near-patient testing (preprint)

Background The COVID-19 pandemic has accelerated the pace of innovation around virtual care visits and testing technology. Here we present the SafeSwab (Safe Health Systems, Los Angeles, CA), an integrated, universal sample collection and dispensing device that is designed to minimize user error and enable rapid testing in a point of care or self-testing format. Methods The SafeSwab was used with the Safe Health Systems HealthCheck digital health application to enable self-testing by patients using lateral flow tests for SARS-CoV-2 antigen or for antibodies against SARS-CoV-2. Results Patients (n=74) using the SafeSwab produced a valid rapid test result in 96% of attempts, and 96% of patients felt confident that they had collected a good sample. The Safe HealthCheck app has an integrated image analysis algorithm, AutoAdapt LFA, that interprets a picture of a rapid test result, and the algorithm interpreted the result correctly 100% of the time. Conclusion The SafeSwab was found to be versatile and easy to use for both self-collected nasal sampling as well as fingerstick blood sampling. The use of Safe Health Systems HealthCheck app allows an integrated solution for patient instruction and test interpretation

Adaptable Automated Interpretation of Rapid Diagnostic Tests Using Few-Shot Learning (preprint)

Point-of-care lateral-flow assays (LFAs) are becomingly increasingly prevalent for diagnosing individual patient disease status and surveying population disease prevalence in a timely, scalable, and cost-effective manner, but a central challenge is to assure correct assay operation and results interpretation as the assays are manually performed in decentralized settings. A smartphone-based software can automate interpretation of an LFA kit, but such algorithms typically require a very large number of images of assays tested with validated specimens, which is challenging to collect for different assay kits, especially for those released during a pandemic. Here, we present an approach – AutoAdapt LFA – that uses few-shot learning, an approach used in other applications such as computer vision and robotics, for accurate and automated interpretation of LFA kits that requires a small number of validated images for training. The approach consists of three components: extraction of membrane and zone areas from an image of the LFA kit, a self-supervised encoder that employs a feature extractor trained with edge-filtered patterns, and few-shot adaptation that enables generalization to new kits using limited validated images. From a base model pre-trained on a commercial LFA kit, we demonstrated the ability of adapted models to interpret results from five new COVID-19 LFA kits (three detecting antigens for diagnosing active infection, and two detecting antibodies for diagnosing past infection). Specifically, using just 10 to 20 images of each new kit, we achieved accuracies of 99% to 100% for each kit. The server-hosted algorithm has an execution time of approximately 4 seconds, which can potentially enable quality assurance and linkage to care for users operating new LFAs in decentralized settings.

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (preprint)

To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions. We have developed a novel and comprehensive knowledge discovery framework, COVID-KG to extract fine-grained multimedia knowledge elements (entities and their visual chemical structures, relations, and events) from scientific literature. We then exploit the constructed multimedia knowledge graphs (KGs) for question answering and report generation, using drug repurposing as a case study. Our framework also provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence.