Artificial Intelligence and Mapping a New Direction in Laboratory Medicine: A Review

Background Modern artificial intelligence (AI) and machine learning (ML) methods are now capable of completing tasks with performance characteristics that are comparable to those of expert human operators. As a result, many areas throughout healthcare are incorporating these technologies, including in vitro diagnostics and, more broadly, laboratory medicine. However, there are limited literature reviews of the landscape, likely future, and challenges of the application of AI/ML in laboratory medicine. Content In this review, we begin with a brief introduction to AI and its subfield of ML. The ensuing sections describe ML systems that are currently in clinical laboratory practice or are being proposed for such use in recent literature, ML systems that use laboratory data outside the clinical laboratory, challenges to the adoption of ML, and future opportunities for ML in laboratory medicine. Summary AI and ML have and will continue to influence the practice and scope of laboratory medicine dramatically. This has been made possible by advancements in modern computing and the widespread digitization of health information. These technologies are being rapidly developed and described, but in comparison, their implementation thus far has been modest. To spur the implementation of reliable and sophisticated ML-based technologies, we need to establish best practices further and improve our information system and communication infrastructure. The participation of the clinical laboratory community is essential to ensure that laboratory data are sufficiently available and incorporated conscientiously into robust, safe, and clinically effective ML-supported clinical diagnostics.

Trends in Multiplex Immunoassays for In Vitro Diagnostics and Point-of-Care Testing

The tremendous advances in multiplex immunoassays (MIAs) are leading to novel in vitro diagnostics (IVD) and point-of-care testing (POCT). MIAs can simultaneously detect numerous analytes in a single sample, which facilitates the diagnosis of many complex diseases. Various clinical score-based diagnostic algorithms have already been developed for several complex diseases, where the clinical score is determined by assigning appropriate weightage to various biomarkers based on their contribution to the disease. Despite a wide range of MIA formats being developed, only a few have been commercialized. There is a need for considerable improvements in MIAs so that they are analytically superior and can compete with the most extensively used automated IAs. The readout of most MIAs is still completed by bulky and expensive reader devices, which emphasizes the need for compact, handheld multiplex readers. Further, the clinical utility, reimbursement models, pathophysiological range of analytes, nature and dilution of samples, and the reagents used to develop an MIA need to be analyzed stringently. This manuscript provides guided insights into MIA formats and discusses the challenges and future directions.

The Dynamics of SARS-CoV-2 (RT-PCR) Testing

The COVID-19 pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is estimated to have affected 6.2 million people in the United States and 27.5 million people worldwide as of September 9, 2020. On February 2, 2020, the Secretary of the Department of Health and Human Services (HHS) determined that the public health emergency justified the development and emergency use of “in vitro diagnostics for the detection and/or diagnosis of the virus that causes COVID-19” by activating the Emergency Use Authorization (EUA) authority under section 564 of the Federal Food, Drug, and Cosmetic Act. Unfortunately, effective mitigation efforts were thwarted early in the outbreak resulting in an expansion of the initial EUA on February 29, 2020, to improve accessibility to in vitro diagnostic testing. Expectantly, the development and deployment of SARS-CoV-2 testing including RT-PCR expanded rapidly in the weeks following the EUA expansion. These newly developed and approved SARS-CoV-2 RT-PCR tests boast impressive positive and negative agreement rates nearing 100%. Despite the exceptionally high rates of agreement, caution is advised as the RT-PCR tests approved under the COVID-19 EUA are in vitro analyses developed with samples artificially doped with SARS-CoV-2 RNA. These tests therefore do not have clinically applicable sensitivity and specificity because they lack a “gold standard” for diagnosis. Here we present three challenging cases requiring cautious interpretation of the newest generation of RT-PCR molecular detection assays, highlighting the major challenges faced by providers treating patients potentially infected with SARS-CoV-2.

In Vitro Diagnostics for COVID-19: State-of-the-Art, Future Directions and Role in Pandemic Response

There have been tremendous advances in in vitro diagnostics (IVD) for coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Although the confirmatory clinical diagnosis is made by real-time reverse transcriptase polymerase chain reaction (RT-PCR), lateral flow immunoassay (LFIA) based viral antigen (Ag) detection is used for mass population screening at point-of-care (POC) settings. The rapid RT-PCR tests (such as from Cepheid and Bosch) have an assay duration of less than 40 min, while most rapid Ag tests (such as Abbott’s BinaxNOW™ COVID-19 Ag card) have an assay duration of about 15 min. Of interest is the POC molecular test (ID NOW™) from Abbott that takes less than13 min. Similarly, many immunoassays (IAs), i.e., automated chemiluminescent IA (CLIA), manual ELISA, and LFIA, have been developed to detect immunoglobulin G (IgG), immunoglobulin M (IgM), and immunoglobulin A (IgA) produced in subjects after SARS-CoV-2 infection. Many IVD tests have been approved by the United States Food and Drug Administration (FDA) under emergency use authorization (EUA), and almost all IVD tests are Conformité Européenne (CE) certified.

Molecular allergology and its impact in specific allergy diagnosis and therapy

Progressive knowledge of allergenic structures resulted in a broad availability of allergenic molecules for diagnosis. Component resolved diagnosis allowed a better understanding of patient sensitization patterns, facilitating allergen immunotherapy decisions. In parallel to the discovery of allergenic molecules, there was a progressive development of a regulation framework that affected both in vitro diagnostics and Allergen Immunotherapy products. With a progressive understanding of underlying mechanisms associated to Allergen immunotherapy and an increasing experience of application of molecular diagnosis in daily life, we focus in analyzing the evidences of the value provided by molecular allergology in daily clinical practice, with a focus on Allergen Immunotherapy decissions.