ABSTRACT
Introduction: The development of medical artificial intelligence (AI) is related to programs intended to help clinicians formulate diagnoses, make therapeutic decisions and predict outcomes. It is bringing a paradigm shift to healthcare, powered by the increasing availability of healthcare data and rapid progress in analytical techniques (1). Artificial intelligence techniques include machine learning methods for structured data, such as classical support vector machines and neural networks, modern deep learning (DL), and natural language processing for unstructured data. Methodology:More than 50 articles were reviewed and 41 of them were shortlisted. The review was based on a literature search in PubMed, Embase, Google Scholar, and Scopus databases. Review:Laboratory medicine incorporates new technologies to aid in clinical decision-making, disease monitoring, and patient safety. Clinical microbiology informatics is progressively using AI. Genomic information from isolated bacteria, metagenomic microbial results from original specimens, mass spectra recorded from grown bacterial isolates and large digital photographs are examples of enormous datasets in clinical microbiology that may be used to build AI diagnoses. Conclusion:Technological innovation in healthcare is accelerating and has become increasingly interwoven with our daily lives and medical practices such as smart health trackers and diagnostic algorithms.
ABSTRACT
Introduction The SARS-CoV-2 illness (COVID-19) has spread around the world, primarily through person-to-person transmission, and is a serious public health concern. Based on the severity of illness symptoms, SARS-CoV-2 infection can be classified as either apparent or occult. To date, real-time reverse transcription polymerase chain reaction (RT-PCR) on respiratory specimens, particularly nasopharyngeal and oropharyngeal swabs, or nasopharyngeal wash or aspirate, has been the gold standard for the identification of COVID-19. A negative RT-PCR does not necessarily rule out SARS-CoV-2 infection. Occult COVID-19 infections could least be identified with RT-PCR. Aims and objectives To assess the prevalence of possible occult COVID-19 infection in healthcare personnel by RT-PCR and serology testing for SARS-CoV-2 virus. Methods A cross-sectional study was conducted on health care workers at a tertiary care hospital in South India during the period from October 2020 to January 2021. None of the study participants were vaccinated against COVID-19 during the study period. Nasopharyngeal swabs collected for RT-PCR were tested using Cobas 480 platform (Roche, Basel, Switzerland). Peripheral blood venous sampling was performed to collect EDTA (ethylenediaminetetraacetic acid) and plain samples. SARS-CoV-2 IgG antibodies against spike proteins were estimated using ECI Vitros platform (Ortho Clinical Diagnostics, Raritan, USA). Results The mean age of study participants was 34.78 years (SD±9.51) with an age range of 19-69 years. The study participants were stratified into age groups of 19-25 years, 26-40 years, 41-60 years, and above 60 years, gender, ABO and Rh blood groups, and occupational and further based on their area of work as Covid and Non-Covid for the purpose of statistical analysis. Total 190 samples from healthcare workers (HCWs) were tested for RT-PCR using nasopharyngeal swabs collected at the time of enrolment into the study, and all the 190 samples tested negative for RT-PCR. Among 190 HCW samples screened for SARS-CoV-2-IgG antibodies, 48 (25.3%) were found reactive for IgG antibodies while 142 (74.7%) were found non-reactive. Conclusion Our study findings suggested that using RT-PCR testing, which may only identify those with a prolonged viral shedding period and minimum viral loads, the proportion of asymptomatic/occult infections could be underestimated.
