Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 55
Filter
1.
PLoS One ; 17(2): e0263736, 2022.
Article in English | MEDLINE | ID: covidwho-1674020

ABSTRACT

Sudden emergence and rapid spread of COVID-19 created an inevitable need for expansion of the COVID-19 laboratory testing network across the world. The strategy to test-track-treat was advocated for quick detection and containment of the disease. Being the second most populous country in the world, India was challenged to make COVID-19 testing available and accessible in all parts of the country. The molecular laboratory testing network was augmented expeditiously, and number of laboratories was increased from one in January 2020 to 2951 till mid-September, 2021. This rapid expansion warranted the need to have inbuilt systems of quality control/ quality assurance. In addition to the ongoing inter-laboratory quality control (ILQC), India implemented an External Quality Assurance Program (EQAP) with assistance from World Health Organization (WHO) and Royal College of Pathologists, Australasia. Out of the 953 open system rRTPCR laboratories in both public and private sector who participated in the first round of EQAP, 891(93.4%) laboratories obtained a passing score of > = 80%. The satisfactory performance of Indian COVID-19 testing laboratories has boosted the confidence of the public and policy makers in the quality of testing. ILQC and EQAP need to continue to ensure adherence of the testing laboratories to the desired quality standards.


Subject(s)
COVID-19 Testing/standards , COVID-19/diagnosis , Clinical Laboratory Techniques/standards , Laboratories/standards , Mass Screening/standards , Quality Assurance, Health Care/standards , Reverse Transcriptase Polymerase Chain Reaction/standards , COVID-19/epidemiology , COVID-19/genetics , COVID-19/virology , Humans , India/epidemiology , Quality Control , SARS-CoV-2/genetics , SARS-CoV-2/isolation & purification , Specimen Handling/methods
2.
J Infect Dev Ctries ; 15(12): 1833-1837, 2021 12 31.
Article in English | MEDLINE | ID: covidwho-1633510

ABSTRACT

At the beginning of the coronavirus disease 2019 (COVID-19) pandemic in Bangladesh, there was a scarcity of ideal biocontainment facilities to detect the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), a risk group of 3 organisms. Molecular detection of SARS-CoV-2 must be performed in a BSL-2 laboratory with BSL-3-equivalent infection prevention and control practices. Establishing these facilities within a short timeframe proved to be an enormous challenge, including locating a remote space distant from the university campus to establish a laboratory, motivating the laboratory staff to work with a novel pathogen without any prior experience, allocation of funds for essential equipment and accessories, and arrangement of a safe waste management system for environmental hazard reduction. This report also highlights several limitations, such as the facility's architectural design that did not follow the biosafety guidelines, lack of continuous flow of funds, and an inadequate number of laboratory personnel. This article describes various efforts taken to overcome the challenges during the establishment of this facility that may be adopted to create similar facilities in other regions of the country. Establishing a BSL-2 laboratory with BSL-3-equivalent infection prevention and control practices will aid in the early detection of a large number of cases, thereby isolating persons with COVID-19, limiting the transmission of SARS-CoV-2, and promoting a robust public health response to contain the pandemic.


Subject(s)
COVID-19 Testing/methods , COVID-19/diagnosis , Containment of Biohazards/standards , Facility Design and Construction/methods , Laboratories/standards , Bangladesh/epidemiology , COVID-19/epidemiology , Humans , Pandemics/prevention & control , SARS-CoV-2
3.
Viruses ; 14(2)2022 01 19.
Article in English | MEDLINE | ID: covidwho-1625191

ABSTRACT

Whole-genome sequencing of viral isolates is critical for informing transmission patterns and for the ongoing evolution of pathogens, especially during a pandemic. However, when genomes have low variability in the early stages of a pandemic, the impact of technical and/or sequencing errors increases. We quantitatively assessed inter-laboratory differences in consensus genome assemblies of 72 matched SARS-CoV-2-positive specimens sequenced at different laboratories in Sydney, Australia. Raw sequence data were assembled using two different bioinformatics pipelines in parallel, and resulting consensus genomes were compared to detect laboratory-specific differences. Matched genome sequences were predominantly concordant, with a median pairwise identity of 99.997%. Identified differences were predominantly driven by ambiguous site content. Ignoring these produced differences in only 2.3% (5/216) of pairwise comparisons, each differing by a single nucleotide. Matched samples were assigned the same Pango lineage in 98.2% (212/216) of pairwise comparisons, and were mostly assigned to the same phylogenetic clade. However, epidemiological inference based only on single nucleotide variant distances may lead to significant differences in the number of defined clusters if variant allele frequency thresholds for consensus genome generation differ between laboratories. These results underscore the need for a unified, best-practices approach to bioinformatics between laboratories working on a common outbreak problem.


Subject(s)
Computational Biology/standards , Consensus , Genome, Viral , Laboratories/standards , Public Health , SARS-CoV-2/genetics , Australia , Computational Biology/methods , Humans , Phylogeny , SARS-CoV-2/classification , Whole Genome Sequencing
4.
J Virol ; 96(3): e0183721, 2022 02 09.
Article in English | MEDLINE | ID: covidwho-1546443

ABSTRACT

Research activities with infectious severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are currently permitted only under biosafety level 3 (BSL3) containment. Here, we report the development of a single-cycle infectious SARS-CoV-2 virus replicon particle (VRP) system with a luciferase and green fluorescent protein (GFP) dual reporter that can be safely handled in BSL2 laboratories to study SARS-CoV-2 biology. The spike (S) gene of SARS-CoV-2 encodes the envelope glycoprotein, which is essential for mediating infection of new host cells. Through deletion and replacement of this essential S gene with a luciferase and GFP dual reporter, we have generated a conditional SARS-CoV-2 mutant (ΔS-VRP) that produces infectious particles only in cells expressing a viral envelope glycoprotein of choice. Interestingly, we observed more efficient production of infectious particles in cells expressing vesicular stomatitis virus (VSV) glycoprotein G [ΔS-VRP(G)] than in cells expressing other viral glycoproteins, including S. We confirmed that infection from ΔS-VRP(G) is limited to a single round and can be neutralized by anti-VSV serum. In our studies with ΔS-VRP(G), we observed robust expression of both luciferase and GFP reporters in various human and murine cell types, demonstrating that a broad variety of cells can support intracellular replication of SARS-CoV-2. In addition, treatment of ΔS-VRP(G)-infected cells with either of the anti-CoV drugs remdesivir (nucleoside analog) and GC376 (CoV 3CL protease inhibitor) resulted in a robust decrease in both luciferase and GFP expression in a drug dose- and cell-type-dependent manner. Taken together, our findings show that we have developed a single-cycle infectious SARS-CoV-2 VRP system that serves as a versatile platform to study SARS-CoV-2 intracellular biology and to perform high-throughput screening of antiviral drugs under BSL2 containment. IMPORTANCE Due to the highly contagious nature of SARS-CoV-2 and the lack of immunity in the human population, research on SARS-CoV-2 has been restricted to biosafety level 3 laboratories. This has greatly limited participation of the broader scientific community in SARS-CoV-2 research and thus has hindered the development of vaccines and antiviral drugs. By deleting the essential spike gene in the viral genome, we have developed a conditional mutant of SARS-CoV-2 with luciferase and fluorescent reporters, which can be safely used under biosafety level 2 conditions. Our single-cycle infectious SARS-CoV-2 virus replicon system can serve as a versatile platform to study SARS-CoV-2 intracellular biology and to perform high-throughput screening of antiviral drugs under BSL2 containment.


Subject(s)
Genetic Engineering , Recombination, Genetic , Replicon , SARS-CoV-2/genetics , COVID-19/virology , Cell Culture Techniques , Cell Line , Containment of Biohazards/standards , Genes, Reporter , Humans , Laboratories/standards , Viral Proteins/genetics , Virus Replication
6.
Comput Math Methods Med ; 2021: 6636396, 2021.
Article in English | MEDLINE | ID: covidwho-1476878

ABSTRACT

Group testing (or pool testing), for example, Dorfman's method or grid method, has been validated for COVID-19 RT-PCR tests and implemented widely by most laboratories in many countries. These methods take advantages since they reduce resources, time, and overall costs required for a large number of samples. However, these methods could have more false negative cases and lower sensitivity. In order to maintain both accuracy and efficiency for different prevalence, we provide a novel pooling strategy based on the grid method with an extra pool set and an optimized rule inspired by the idea of error-correcting codes. The mathematical analysis shows that (i) the proposed method has the best sensitivity among all the methods we compared, if the false negative rate (FNR) of an individual test is in the range [1%, 20%] and the FNR of a pool test is closed to that of an individual test, and (ii) the proposed method is efficient when the prevalence is below 10%. Numerical simulations are also performed to confirm the theoretical derivations. In summary, the proposed method is shown to be felicitous under the above conditions in the epidemic.


Subject(s)
COVID-19 Testing/methods , COVID-19 Testing/standards , COVID-19/diagnosis , Algorithms , Computer Simulation , False Negative Reactions , Humans , Laboratories/standards , Models, Theoretical , Prevalence , Probability , Reproducibility of Results
7.
Cytometry A ; 99(1): 60-67, 2021 01.
Article in English | MEDLINE | ID: covidwho-1384157

ABSTRACT

Data management is essential in a flow cytometry (FCM) shared resource laboratory (SRL) for the integrity of collected data and its long-term preservation, as described in the Cytometry publication from 2016, ISAC Flow Cytometry Shared Resource Laboratory (SRL) Best Practices (Barsky et al.: Cytometry Part A 89A(2016): 1017-1030). The SARS-CoV-2 pandemic introduced an array of challenges in the operation of SRLs. The subsequent laboratory shutdowns and access restrictions brought to the forefront well-established practices that withstood the impact of a sudden change in operations and illuminated areas that need improvement. The most significant challenges from a data management perspective were data access for remote analysis and workstation management. Notably, lessons learned from this challenge emphasize the importance of safeguarding collected data from loss in various emergencies such as fire or natural disasters where the physical hardware storing data could be directly affected. Here, we describe two data management systems that have been successful during the current emergency created by the pandemic, specifically remote access and automated data transfer. We will discuss other situations that could arise and lead to data loss or challenges in interpreting data. © 2020 International Society for Advancement of Cytometry.


Subject(s)
COVID-19/epidemiology , Data Management/trends , Flow Cytometry/trends , Laboratories/trends , Teleworking/trends , COVID-19/prevention & control , Data Management/standards , Flow Cytometry/standards , Humans , Laboratories/standards , Teleworking/standards
8.
Clin Chem ; 67(9): 1188-1200, 2021 09 01.
Article in English | MEDLINE | ID: covidwho-1381002

ABSTRACT

BACKGROUND: The clinical laboratory continues to play a critical role in managing the coronavirus pandemic. Numerous US Food and Drug Administration emergency use authorization (EUA) and laboratory-developed test (LDT) serologic assays have become available. The performance characteristics of these assays and their clinical utility continue to be defined in real time during this pandemic. The AACC convened a panel of experts from clinical chemistry, microbiology, and immunology laboratories; the in vitro diagnostics industry; and regulatory agencies to provide practical recommendations for implementation and interpretation of these serologic tests in clinical laboratories. CONTENT: The currently available EUA serologic tests and platforms, information on assay design, antibody classes including neutralizing antibodies, and the humoral immune responses to SARS-CoV-2 are discussed. Verification and validation of EUA and LDT assays are described, along with a quality management approach. Four indications for serologic testing are outlined. Recommendations for result interpretation, reporting comments, and the role of orthogonal testing are also presented. SUMMARY: This document aims to provide a comprehensive reference for laboratory professionals and healthcare workers to appropriately implement SARS-CoV-2 serologic assays in the clinical laboratory and to interpret test results during this pandemic. Given the more frequent occurrence of outbreaks associated with either vector-borne or respiratory pathogens, this document will be a useful resource in planning for similar scenarios in the future.


Subject(s)
COVID-19 Serological Testing/methods , COVID-19/diagnosis , Laboratories/standards , SARS-CoV-2/isolation & purification , Antibodies, Viral/biosynthesis , Antibodies, Viral/immunology , COVID-19/virology , Humans , SARS-CoV-2/immunology
10.
Bioanalysis ; 13(15): 1177-1182, 2021 Aug.
Article in English | MEDLINE | ID: covidwho-1346628

ABSTRACT

Robust surveillance testing is a key strategic plan to prevent COVID-19 outbreaks and slow the spread of the SARS-CoV-2 pandemic; however, limited resources, facilities and time often impair the implementation of a widespread surveillance effort. To mitigate these resource limitations, we employed a strategy of pooling samples, reducing reagent cost and processing time. Through utilizing academic faculty and labs, successful pooled surveillance testing was conducted throughout Fall 2020 semester to detect positive SARS-CoV-2 infections in a population of 4400 students. During the semester, over 25,000 individual COVID status evaluations were made by pooling eight individual samples into one quantitative reverse transcription polymerase chain reaction. This pooled surveillance strategy was highly effective at detecting infection and significantly reduced financial burden and cost by $3.6 million.


Subject(s)
COVID-19 Testing/methods , COVID-19/epidemiology , Disease Outbreaks/prevention & control , Laboratories/standards , Mass Screening/methods , Epidemiological Monitoring , Humans , Pandemics , SARS-CoV-2
11.
PLoS One ; 16(8): e0255417, 2021.
Article in English | MEDLINE | ID: covidwho-1341503

ABSTRACT

Due to the sheer number of COVID-19 (coronavirus disease 2019) cases there is a need for increased world-wide SARS-CoV-2 testing capability that is both efficient and effective. Having open and easy access to detailed information about these tests, their sensitivity, the types of samples they use, etc. would be highly useful to ensure their reproducibility, to help clients compare and decide which tests would be best suited for their applications, and to avoid costs of reinventing similar or identical tests. Additionally, this resource would provide a means of comparing the many innovative diagnostic tools that are currently being developed in order to provide a foundation of technologies and methods for the rapid development and deployment of tests for future emerging diseases. Such a resource might thus help to avert the delays in testing and screening that was observed in the early stages of the pandemic and plausibly led to more COVID-19-related deaths than necessary. We aim to address these needs via a relational database containing standardized ontology and curated data about COVID-19 diagnostic tests that have been granted Emergency Use Authorizations (EUAs) by the FDA (US Food and Drug Administration). Simple queries of this actively growing database demonstrate considerable variation among these tests with respect to sensitivity (limits of detection, LoD), controls and targets used, criteria used for calling results, sample types, reagents and instruments, and quality and amount of information provided.


Subject(s)
COVID-19 Testing , Databases, Factual , Emergencies , United States Food and Drug Administration/organization & administration , COVID-19/diagnosis , COVID-19 Testing/methods , COVID-19 Testing/standards , Data Management/organization & administration , Data Management/standards , Databases, Factual/supply & distribution , Emergencies/classification , Emergency Treatment/classification , Emergency Treatment/methods , Humans , Internet , Laboratories/standards , Reference Standards , Sensitivity and Specificity , United States , User-Computer Interface
12.
Ann Glob Health ; 87(1): 56, 2021 06 25.
Article in English | MEDLINE | ID: covidwho-1296122

ABSTRACT

Background: The adherence of medical laboratory technicians (MLT) to infection control guidelines is essential for reducing the risk of exposure to infectious agents. This study explored the adherence of MLT towards infection control practices during the COVID-19 pandemic. Method: The study population consisted of MLT (n = 444) who worked in private and government health sectors in Jordan. A self-reported survey was used to collect data from participants. Findings: More than 87% of the participants reported adherence to hand-washing guidelines and using personal protective equipment (PPE) when interacting with patients (74.5%), and handling clinical samples (70.0%). Besides, 88.1%, 48.2%, and 7.7% reported wearing of lab coats, face masks, and goggles, at all times, respectively. The majority reported increased adherence to infection control practices during the COVID-19 pandemic. This includes increased PPE use at the workplace (94.2%), increased frequency of disinfection of laboratory surfaces (92.4%) and laboratory equipment (86.7%), and increased frequency of handwashing/use of antiseptics (94.6%). Having a graduate degree was significantly associated with increased adherence of participants to the daily use of goggles/eye protection (p = 0.002), and the use of PPE while handling clinical samples (p = 0.011). Having work experience of >10 years was associated with increased adherence to the use of PPE while handling clinical samples (p = 0.001). Conclusion: MLT reported very good adherence with most assessed infection control practices. In addition, they reported increased conformity with infection control guidelines during the COVID-19 pandemic.


Subject(s)
COVID-19 , Guideline Adherence , Infection Control , Laboratories , Medical Laboratory Personnel , Personal Protective Equipment , Adult , COVID-19/epidemiology , COVID-19/prevention & control , Female , Guideline Adherence/standards , Guideline Adherence/statistics & numerical data , Hand Disinfection/methods , Hand Disinfection/standards , Health Care Surveys , Humans , Infection Control/instrumentation , Infection Control/methods , Infection Control/standards , Jordan/epidemiology , Laboratories/organization & administration , Laboratories/standards , Male , Medical Laboratory Personnel/standards , Medical Laboratory Personnel/statistics & numerical data , Personal Protective Equipment/statistics & numerical data , Personal Protective Equipment/supply & distribution , Practice Guidelines as Topic , SARS-CoV-2 , Self Report
13.
PLoS One ; 16(6): e0253334, 2021.
Article in English | MEDLINE | ID: covidwho-1286868

ABSTRACT

By the time the etiologic agent of the COVID-19 was identified as a novel coronavirus, no country in the Americas Region had laboratory capacity for detecting this new virus. A strategic multilevel approach with specific reagent purchase and delivery, regional trainings, in-country missions, and the provision of technical support was established for timely preparedness of national reference laboratories for SARS-CoV-2 detection. All countries should be prepared to timely detect any potential pandemic emerging agent. The rapid SARS-CoV-2 molecular detection implementation throughout the Americas showed the importance of an efficient and coordinated laboratory response for preparedness. Here we present how in 25 days the Americas Region went from no SARS-CoV-2 diagnostic capacity, to molecular detection fully implemented in 28 Member States, under the coordinated strategy of the Pan American Health Organization and collaborative work at regional and country level with national authorities and public health laboratories.


Subject(s)
COVID-19/diagnosis , Laboratories/statistics & numerical data , COVID-19/virology , Central America , Humans , Laboratories/standards , Regional Health Planning , SARS-CoV-2/isolation & purification , South America
14.
J Vet Diagn Invest ; 33(3): 457-468, 2021 May.
Article in English | MEDLINE | ID: covidwho-1264088

ABSTRACT

Every day, thousands of samples from diverse populations of animals are submitted to veterinary diagnostic laboratories (VDLs) for testing. Each VDL has its own laboratory information management system (LIMS), with processes and procedures to capture submission information, perform laboratory tests, define the boundaries of test results (i.e., positive or negative), and report results, in addition to internal business and accounting applications. Enormous quantities of data are accumulated and stored within VDL LIMSs. There is a need for platforms that allow VDLs to exchange and share portions of laboratory data using standardized, reliable, and sustainable information technology processes. Here we report concepts and applications for standardization and aggregation of data from swine submissions to multiple VDLs to detect and monitor porcine enteric coronaviruses by RT-PCR. Oral fluids, feces, and fecal swabs were the specimens submitted most frequently for enteric coronavirus testing. Statistical algorithms were used successfully to scan and monitor the overall and state-specific percentage of positive submissions. Major findings revealed a consistently recurrent seasonal pattern, with the highest percentage of positive submissions detected during December-February for porcine epidemic diarrhea virus, porcine deltacoronavirus, and transmissible gastroenteritis virus (TGEV). After 2014, very few submissions tested positive for TGEV. Monitoring VDL data proactively has the potential to signal and alert stakeholders early of significant changes from expected detection. We demonstrate the importance of, and applications for, data organized and aggregated by using LOINC and SNOMED CTs, as well as the use of customized messaging to allow inter-VDL exchange of information.


Subject(s)
Coronaviridae Infections/veterinary , Coronaviridae/isolation & purification , Laboratories/standards , Swine Diseases/virology , Animals , COVID-19 Testing/veterinary , Coronaviridae Infections/diagnosis , Coronaviridae Infections/virology , Disease Outbreaks , Feces/virology , Reference Standards , Seasons , Swine , Swine Diseases/diagnosis
16.
J Clin Lab Anal ; 35(6): e23804, 2021 Jun.
Article in English | MEDLINE | ID: covidwho-1241506

ABSTRACT

BACKGROUND: Before public health emergencies became a major challenge worldwide, the scope of laboratory management was only related to developing, maintaining, improving, and sustaining the quality of accurate laboratory results for improved clinical outcomes. Indeed, quality management is an especially important aspect and has achieved great milestones during the development of clinical laboratories. CURRENT STATUS: However, since the coronavirus disease 2019 (COVID-19) pandemic continues to be a threat worldwide, previous management mode inside the separate laboratory could not cater to the demand of the COVID-19 public health emergency. Among emerging new issues, the prominent challenges during the period of COVID-19 pandemic are rapid-launched laboratory-developed tests (LDTs) for urgent clinical application, rapid expansion of testing capabilities, laboratory medicine resources, and personnel shortages. These related issues are now impacting on clinical laboratory and need to be effectively addressed. CONCLUSION: Different from traditional views of laboratory medicine management that focus on separate laboratories, present clinical laboratory management must be multidimensional mode which should consider consolidation of the efficient network of regional clinical laboratories and reasonable planning of laboratories resources from the view of overall strategy. Based on relevant research and our experience, in this review, we retrospect the history trajectory of laboratory medicine management, and also, we provide existing and other feasible recommended management strategies for laboratory medicine in future.


Subject(s)
COVID-19 Testing , COVID-19/diagnosis , Clinical Laboratory Services , Clinical Laboratory Techniques/standards , Laboratories , Clinical Laboratory Services/organization & administration , Clinical Laboratory Services/standards , Humans , Laboratories/organization & administration , Laboratories/standards , Point-of-Care Testing , Public Health , Quality Assurance, Health Care
19.
Diagn Microbiol Infect Dis ; 101(3): 115412, 2021 Nov.
Article in English | MEDLINE | ID: covidwho-1201522

ABSTRACT

The COVID-19 pandemic has led to the influx of immunoassays for the detection of antibodies towards severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) into the global market. The Canadian Public Health Laboratory Network Serology Task Force undertook a nationwide evaluation of twelve laboratory and 6 point-of-care based commercial serological assays for the detection of SARS-CoV-2 antibodies. We determined that there was considerable variability in the performance of individual tests and that an orthogonal testing algorithm should be prioritized to maximize the accuracy and comparability of results across the country. The manual enzyme immunoassays and point-of-care tests evaluated had lower specificity and increased coefficients of variation compared to automated enzyme immunoassays platforms putting into question their utility for large-scale sero-surveillance. Overall, the data presented here provide a comprehensive approach for applying accurate serological assays for longitudinal sero-surveillance and vaccine trials while informing Canadian public health policy.


Subject(s)
Antibodies, Viral/blood , COVID-19/epidemiology , Laboratories/standards , Public Health , SARS-CoV-2/immunology , Serologic Tests/standards , COVID-19/blood , Canada/epidemiology , High-Throughput Screening Assays , Humans , Immunoenzyme Techniques , SARS-CoV-2/isolation & purification , Serologic Tests/methods
20.
J Med Internet Res ; 23(4): e26211, 2021 04 14.
Article in English | MEDLINE | ID: covidwho-1190246

ABSTRACT

BACKGROUND: The COVID-19 pandemic is probably the greatest health catastrophe of the modern era. Spain's health care system has been exposed to uncontrollable numbers of patients over a short period, causing the system to collapse. Given that diagnosis is not immediate, and there is no effective treatment for COVID-19, other tools have had to be developed to identify patients at the risk of severe disease complications and thus optimize material and human resources in health care. There are no tools to identify patients who have a worse prognosis than others. OBJECTIVE: This study aimed to process a sample of electronic health records of patients with COVID-19 in order to develop a machine learning model to predict the severity of infection and mortality from among clinical laboratory parameters. Early patient classification can help optimize material and human resources, and analysis of the most important features of the model could provide more detailed insights into the disease. METHODS: After an initial performance evaluation based on a comparison with several other well-known methods, the extreme gradient boosting algorithm was selected as the predictive method for this study. In addition, Shapley Additive Explanations was used to analyze the importance of the features of the resulting model. RESULTS: After data preprocessing, 1823 confirmed patients with COVID-19 and 32 predictor features were selected. On bootstrap validation, the extreme gradient boosting classifier yielded a value of 0.97 (95% CI 0.96-0.98) for the area under the receiver operator characteristic curve, 0.86 (95% CI 0.80-0.91) for the area under the precision-recall curve, 0.94 (95% CI 0.92-0.95) for accuracy, 0.77 (95% CI 0.72-0.83) for the F-score, 0.93 (95% CI 0.89-0.98) for sensitivity, and 0.91 (95% CI 0.86-0.96) for specificity. The 4 most relevant features for model prediction were lactate dehydrogenase activity, C-reactive protein levels, neutrophil counts, and urea levels. CONCLUSIONS: Our predictive model yielded excellent results in the differentiating among patients who died of COVID-19, primarily from among laboratory parameter values. Analysis of the resulting model identified a set of features with the most significant impact on the prediction, thus relating them to a higher risk of mortality.


Subject(s)
COVID-19/epidemiology , Laboratories/standards , Machine Learning/standards , Adolescent , Adult , Aged , Aged, 80 and over , Child , Child, Preschool , Female , Humans , Infant , Infant, Newborn , Male , Middle Aged , Pandemics , Prognosis , Reproducibility of Results , Research Design , Retrospective Studies , SARS-CoV-2/isolation & purification , Spain/epidemiology , Treatment Outcome , Young Adult
SELECTION OF CITATIONS
SEARCH DETAIL