Use of an algorithm based on routine blood laboratory tests to exclude COVID-19 in a screening-setting of healthcare workers.
Ontology highlight
ABSTRACT: Background
COVID-19 is an ongoing pandemic leading to exhaustion of the hospital care system. Our health care system has to deal with a high level of sick leave of health care workers (HCWs) with COVID-19 related complaints, in whom an infection with SARS-CoV-2 has to be ruled out before they can return back to work. The aim of the present study is to investigate if the recently described CoLab-algorithm can be used to exclude COVID-19 in a screening setting of HCWs.Methods
In the period from January 2021 till March 2021, HCWs with COVID-19-related complaints were prospectively collected and included in this study. Next to the routinely performed SARS-CoV-2 RT-PCR, using a set of naso- and oropharyngeal swab samples, two blood tubes (one EDTA- and one heparin-tube) were drawn for analysing the 10 laboratory parameters required for running the CoLab-algorithm.Results
In total, 726 HCWs with a complete CoLab-laboratory panel were included in this study. In this group, 684 HCWs were tested SARS-CoV-2 RT-PCR negative and 42 cases RT-PCR positive. ROC curve analysis showed an area under the curve (AUC) of 0.853 (95% CI: 0.801-0.904). At a safe cut-off value for excluding COVID-19 of -6.525, the sensitivity was 100% with a specificity of 34% (95% CI: 21 to 49%). No SARS-CoV-2 RT-PCR cases were missed with this cut-off and COVID-19 could be safely ruled out in more than one third of HCWs.Conclusion
The CoLab-score is an easy and reliable algorithm that can be used for screening HCWs with COVID-19 related complaints. A major advantage of this approach is that the results of the score are available within 1 hour after collecting the samples. This results in a faster return to labour process of a large part of the COVID-19 negative HCWs (34%), next to a reduction in RT-PCR tests (reagents and labour costs) that can be saved.
SUBMITTER: Leers MPG
PROVIDER: S-EPMC9239486 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundRecent studies suggest that routine postoperative laboratory tests are not necessary after primary elective total hip arthroplasty (THA). This study aims to evaluate the utility of routine postoperative laboratory tests in patients undergoing THA for hip fracture in a semi-urgent clinical setting.Materials and methodsThis retrospective study included 213 consecutive patients who underwent primary unilateral THA for hip fractures. Patient demographics, clinical information, and laboratory tests were obtained from the electronic medical record system. Multivariate logistic regression analysis was performed to identify risk factors associated with abnormal laboratory test-related interventions.ResultsA total of 207 patients (97.18%) had abnormal postoperative laboratory results, which were mainly due to anemia (190/213, 89.20%) and hypoalbuminemia (154/213, 72.30%). Overall, 54 patients (25.35%) underwent a clinical intervention, 18 patients received blood transfusion, and 42 patients received albumin supplementation. Factors associated with blood transfusion were long operative time and low preoperative hemoglobin levels. Factors associated with albumin supplementation were long operative time and low preoperative albumin levels. Of the 33 patients with abnormal postoperative creatinine levels, 7 patients underwent a clinical intervention. For electrolyte abnormalities, sodium supplementation was not given for hyponatremia, three patients received potassium supplementation, and one patient received calcium supplementation.ConclusionsThis study demonstrated a high incidence of abnormal postoperative laboratory tests and a significant clinical intervention rate in patients who underwent THA for hip fracture in a semi-urgent clinical setting, which indicates that routine laboratory tests after THA for hip fracture are still necessary for patients with certain risk factors.Level of evidenceLevel III. Trial registration Clinical trial registry number ChiCTR1900020690.
| S-EPMC7655881 | biostudies-literature
Project description:Objective: The accurate evaluation of outcomes at a personalized level in patients with intracerebral hemorrhage (ICH) is critical clinical implications. This study aims to evaluate how machine learning integrates with routine laboratory tests and electronic health records (EHRs) data to predict inpatient mortality after ICH. Methods: In this machine learning-based prognostic study, we included 1,835 consecutive patients with acute ICH between October 2010 and December 2018. The model building process incorporated five pre-implant ICH score variables (clinical features) and 13 out of 59 available routine laboratory parameters. We assessed model performance according to a range of learning metrics, such as the mean area under the receiver operating characteristic curve [AUROC]. We also used the Shapley additive explanation algorithm to explain the prediction model. Results: Machine learning models using laboratory data achieved AUROCs of 0.71-0.82 in a split-by-year development/testing scheme. The non-linear eXtreme Gradient Boosting model yielded the highest prediction accuracy. In the held-out validation set of development cohort, the predictive model using comprehensive clinical and laboratory parameters outperformed those using clinical alone in predicting in-hospital mortality (AUROC [95% bootstrap confidence interval], 0.899 [0.897-0.901] vs. 0.875 [0.872-0.877]; P <0.001), with over 81% accuracy, sensitivity, and specificity. We observed similar performance in the testing set. Conclusions: Machine learning integrated with routine laboratory tests and EHRs could significantly promote the accuracy of inpatient ICH mortality prediction. This multidimensional composite prediction strategy might become an intelligent assistive prediction for ICH risk reclassification and offer an example for precision medicine.
| S-EPMC8761736 | biostudies-literature
Project description:ObjectivesThe present study aimed to develop a clinical decision support tool to assist coronavirus disease 2019 (COVID-19) diagnoses with machine learning (ML) models using routine laboratory test results.MethodsWe developed ML models using laboratory data (n = 1,391) composed of six clinical chemistry (CC) results, 14 CBC parameter results, and results of a severe acute respiratory syndrome coronavirus 2 real-time reverse transcription-polymerase chain reaction as a gold standard method. Four ML algorithms, including random forest (RF), gradient boosting (XGBoost), support vector machine (SVM), and logistic regression, were used to build eight ML models using CBC and a combination of CC and CBC parameters. Performance evaluation was conducted on the test data set and external validation data set from Brazil.ResultsThe accuracy values of all models ranged from 74% to 91%. The RF model trained from CC and CBC analytes showed the best performance on the present study's data set (accuracy, 85.3%; sensitivity, 79.6%; specificity, 91.2%). The RF model trained from only CBC parameters detected COVID-19 cases with 82.8% accuracy. The best performance on the external validation data set belonged to the SVM model trained from CC and CBC parameters (accuracy, 91.18%; sensitivity, 100%; specificity, 84.21%).ConclusionsML models presented in this study can be used as clinical decision support tools to contribute to physicians' clinical judgment for COVID-19 diagnoses.
| S-EPMC8690000 | biostudies-literature
Project description:A growing body of evidence demonstrates that asymptomatic and pre-symptomatic transmission of SARS-CoV-2 is a major contributor to the COVID-19 pandemic. Frontline healthcare workers in COVID-19 hotspots have faced numerous challenges, including shortages of personal protective equipment (PPE) and difficulties acquiring clinical testing. The magnitude of the exposure of healthcare workers and the potential for asymptomatic transmission makes it critical to understand the incidence of infection in this population. To determine the prevalence of asymptomatic SARS-CoV-2 infection amongst healthcare workers, we studied frontline staff working in the Montefiore Health System in New York City. All participants were asymptomatic at the time of testing and were tested by RT-qPCR and for anti-SARS-CoV-2 antibodies. The medical, occupational, and COVID-19 exposure histories of participants were recorded via questionnaires. Of the 98 asymptomatic healthcare workers tested, 19 (19.4%) tested positive by RT-qPCR and/or ELISA. Within this group, four (4.1%) were RT-qPCR positive, and four (4.1%) were PCR and IgG positive. Notably, an additional 11 (11.2%) individuals were IgG positive without a positive PCR. Two PCR positive individuals subsequently developed COVID-19 symptoms, while all others remained asymptomatic at 2-week follow-up. These results indicate that there is considerable asymptomatic infection with SARS-CoV-2 within the healthcare workforce, despite current mitigation policies. Furthermore, presuming that asymptomatic staff are not carrying SARS-CoV-2 is inconsistent with our results, and this could result in amplified transmission within healthcare settings. Consequently, aggressive testing regiments, such as testing frontline healthcare workers on a regular, multi-modal basis, may be required to prevent further spread within the workforce and to patients.
| S-EPMC7472984 | biostudies-literature
Project description:Routine blood test results are assumed to contain much more information than is usually recognised even by the most experienced clinicians. Using routine blood tests from 15,176 neurological patients we built a machine learning predictive model for the diagnosis of brain tumours. We validated the model by retrospective analysis of 68 consecutive brain tumour and 215 control patients presenting to the neurological emergency service. Only patients with head imaging and routine blood test data were included in the validation sample. The sensitivity and specificity of the adapted tumour model in the validation group were 96% and 74%, respectively. Our data demonstrate the feasibility of brain tumour diagnosis from routine blood tests using machine learning. The reported diagnostic accuracy is comparable and possibly complementary to that of imaging studies. The presented machine learning approach opens a completely new avenue in the diagnosis of these grave neurological diseases and demonstrates the utility of valuable information obtained from routine blood tests.
| S-EPMC6785553 | biostudies-literature
Project description:Physicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.
| S-EPMC8144373 | biostudies-literature
Project description:Background and objectives:The pandemic of novel coronavirus disease 2019 (COVID-19) has severely impacted human society with a massive death toll worldwide. There is an urgent need for early and reliable screening of COVID-19 patients to provide better and timely patient care and to combat the spread of the disease. In this context, recent studies have reported some key advantages of using routine blood tests for initial screening of COVID-19 patients. In this article, first we present a review of the emerging techniques for COVID-19 diagnosis using routine laboratory and/or clinical data. Then, we propose ERLX which is an ensemble learning model for COVID-19 diagnosis from routine blood tests. Method:The proposed model uses three well-known diverse classifiers, extra trees, random forest and logistic regression, which have different architectures and learning characteristics at the first level, and then combines their predictions by using a second level extreme gradient boosting (XGBoost) classifier to achieve a better performance. For data preparation, the proposed methodology employs a KNNImputer algorithm to handle null values in the dataset, isolation forest (iForest) to remove outlier data, and a synthetic minority oversampling technique (SMOTE) to balance data distribution. For model interpretability, features importance are reported by using the SHapley Additive exPlanations (SHAP) technique. Results:The proposed model was trained and evaluated by using a publicly available data set from Albert Einstein Hospital in Brazil, which consisted of 5644 data samples with 559 confirmed COVID-19 cases. The ensemble model achieved outstanding performance with an overall accuracy of 99.88% [95% CI: 99.6-100], AUC of 99.38% [95% CI: 97.5-100], a sensitivity of 98.72% [95% CI: 94.6-100] and a specificity of 99.99% [95% CI: 99.99-100]. Discussion:The proposed model revealed better performance when compared against existing state-of-the-art studies (Banerjee et al., 2020; de Freitas Barbosa et al., 2020; de Moraes Batista et al., 2020; Soares et al., 2020) [3,22,56,71] for the same set of features employed by them. As compared to the best performing Bayes Net model (de Freitas Barbosa et al., 2020) [22] average accuracy of 95.159%, ERLX achieved an average accuracy of 99.94%. In comparison with AUC of 85% reported by the SVM model (de Moraes Batista et al., 2020) [56], ERLX obtained AUC of 99.77% in addition to improvements in sensitivity, and specificity. As compared with ER-COV model (Soares et al., 2020) [71] average sensitivity of 70.25% and specificity of 85.98%, ERLX model achieved sensitivity of 99.47% and specificity of 99.99%. The ERLX model obtained a considerably higher score as compared with ANN model (Banerjee et al., 2020) [3] in all performance metrics. Therefore, the model presented is robust and can be deployed for reliable early and rapid screening of COVID-19 patients.
| S-EPMC7572278 | biostudies-literature
Project description:To evaluate the value of blood testing after elective laparoscopic cholecystectomy and its association with procedure related complications.Charts of all patients undergoing elective laparoscopic cholecystectomy from January 2013 through December 2014 were reviewed retrospectively for demographics, indication for surgery, operative course and outcome. In our institution the decision to perform postoperative blood analysis is left for the discretion of the surgeon, therefore we had the possibility to compare the results of those who had blood analyses results to those who did not. Analysis was performed to identify variables associated with the decision to perform postoperative blood tests. Subsequently a univariate and multivariate analyses was performed comparing the two cohorts. Secondary subgroup analysis was performed to identify factors associated with procedure related complications.Five hundred and thirty-two elective laparoscopic cholecystectomies for symptomatic gallstones were performed during the study period. Sixty-four percent of the patients (n = 340) had blood tests taken post operatively. Patients that had laboratory tests taken were older (P = 0.006, OR = 1.01), had longer surgery (P < 0.001, OR = 3.22) had more drains placed (P < 0.001, OR = 3.2) and stayed longer in the hospital (P < 0.001, OR = 1.2). A subgroup analysis of the patients who experienced complications revealed longer stay in the hospital (P < 0.001), higher body mass index (BMI) (P = 0.04, OR = 1.08), increased rates of drain placement (P = 0.006, OR = 3.1) and higher conversion rates (P = 0.01, OR = 14.6). Postoperative blood tests withdrawals were not associated with complications (P = 0.44). On Multivariate analysis BMI and drain placement were independently associated with complications.The current study indicate that routine postoperative blood tests after elective laparoscopic cholecystectomy for symptomatic gallstones does not predict complications and may have an added benefit in diagnosis and management of cases were the surgeon encountered true technical difficulty during surgery.
| S-EPMC5483414 | biostudies-other
Project description:PurposeIndirect immunofluorescence (IIF) on the human epithelial cell-line HEp-2 (or derivatives) serves as the gold standard in antinuclear antibody (ANA) screening. IIF, and its evaluation, is a labor-intensive method, making ANA testing a major challenge for present clinical laboratories. Nowadays, several automated ANA pattern recognition systems are on the market. In the current study, the EUROPattern Suite is evaluated for its use in daily practice in a routine setting.MethodsA total of 1033 consecutive routine samples was used to screen for ANA. Results (positive/negative ANA screening, pattern identification and titer) were compared between software-generated results (EUROPattern) and visual interpretation (observer) of automatically acquired digital images.ResultsConsidering the visual interpretation as reference, a relative sensitivity of 99.3% and a relative specificity of 88.9% were obtained for negative and positive discrimination by the software (EPa). A good agreement between visual and software-based interpretation was observed with respect to pattern recognition (mean kappa: for 7 patterns: 0.7). Interestingly, EPa software distinguished more patterns per positive sample than the observer (on average 1.5 and 1.2, respectively). Finally, a concordance of 99.3% was observed within the range of 1 titer step difference between EPa and observer.ConclusionsThe ANA IIF results reported by the EPa software are in very good agreement with the results reported by the observer with respect to being negative/positive, pattern recognition and titer, making automated ANA IIF evaluation an objective and time-efficient tool for routine testing.
| S-EPMC6147779 | biostudies-literature
Project description:INTRODUCTION:Early diagnosis and prompt and effective treatment is one of the pillars of malaria control. Malaria case management guidelines recommend diagnostic testing before treatment using malaria Rapid Diagnostic Test (mRDT) or microscopy and this was adopted in Nigeria in 2010. However, despite the deployment of mRDT, the use of mRDTs by health workers varies by settings. This study set out to assess factors influencing utilisation of mRDT among healthcare workers in Zamfara State, Nigeria. METHODS:A cross-sectional study was carried out among 306 healthcare workers selected using multistage sampling from six Local Government Areas between January and February 2017. Mixed method was used for data collection. A pre-tested self-administered questionnaire was used to collect information on knowledge, use of mRDT and factors influencing utilization. An observational checklist was used to assess the availability of mRDT in the six months prior to this study. Data were analyzed using descriptive statistics such as means and proportions. Association between mRDT use and independent variables was tested using Chi square while multiple regression was used to determine predictors of use at 5% level of significance. RESULTS:Mean age of respondents was 36.0 ± 9.4years. Overall, 198 (64.7%) of health workers had good knowledge of mRDT; mRDT was available in 33 (61.1%) facilities. Routine use of mRDT was reported by 253 (82.7%) healthcare workers. This comprised 89 (35.2%) laboratory scientists/technicians, 89 (35.2%) community health extension workers/community health officers; 59 (23.3%) nurses and 16 (6.3%) doctors. Health workers' good knowledge of mRDT, trust in mRDT results, having received prior training on mRDT, and non-payment for mRDT were predictors of mRDT utilisation. CONCLUSION:This study demonstrated that healthcare worker utilisation of mRDT was associated with health worker and health system-related factors that are potentially modifiable. There is need to sustain training of healthcare workers on benefits of using mRDT and provision of free mRDT in health facilities.
| S-EPMC6294357 | biostudies-literature