Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 211
Filter
Add filters

Document Type
Year range
1.
Eur Rev Med Pharmacol Sci ; 25(21): 6767-6774, 2021 11.
Article in English | MEDLINE | ID: covidwho-1524864

ABSTRACT

OBJECTIVE: We aimed to test the efficiency of CHA2DS2-VASc, CHA2DS2-VASc-HS, R2CHA2DS2-VASc score systems on the prediction of mortality in the patients with COVID-19. PATIENTS AND METHODS: The data were collected from 508 hospitalized patients with COVID-19. Comorbidity features including coronary artery disease, peripheral arterial disease, congestive heart failure, hypertension, atrial fibrillation, diabetes mellitus, hyperlipidemia, smoking, chronic obstructive pulmonary disease, cerebrovascular event, cancer status, and renal disease were recorded. The patients were divided as surviving group (n=440) and non-survivors (n=68). RESULTS: The in-hospital mortality rate of the patients with COVID-19 was 13.4%. Factors found to be associated with mortality in univariate analysis were CHA2DS2-VASc, CHA2DS2-VASc-HS, R2CHA2DS2-VASc, cancer state, atrial fibrillation, hemoglobin, lymphocyte count, CRP, albumin and ferritin. Model 1 multivariate cox regression analysis revealed CHA2DS2-VASc, hemoglobin, CRP and ferritin levels to be independently associated with mortality. Factors that were found to be independently associated with in-hospital mortality in Model 2 analysis were CHA2DS2-VASc-HS, R2CHA2DS2-VASc, hemoglobin, CRP and ferritin whereas except hemoglobin in Model 3 analysis, the other variables had been the same. Predictive power of R2CHA2DS2-VASc was better than of both CHA2DS2-VASc (p=0.002) and CHA2DS2-VASc-HS (p=0.034) in determining the in-hospital mortality. Patients with higher R2CHA2DS2-VASc (> 3 points), CHA2DS2-VASc-HS (> 3 points) and CHA2DS2-VASc (> 2 points) scores exhibited the highest mortality rate in survival analysis by using Kaplan-Meier and long-rank tests. CONCLUSIONS: CHA2DS2-VASc, CHA2DS2-VASc-HS, and R2CHA2DS2-VASc were found to be independent predictors of mortality in hospitalized COVID-19 patients. The current study revealed that the predictive ability of R2CHA2DS2-VASc was better than the both of CHA2DS2-VASc and CHA2DS2-VASc-HS score.


Subject(s)
COVID-19/mortality , Comorbidity , Severity of Illness Index , Adult , Aged , Aged, 80 and over , Area Under Curve , COVID-19/pathology , COVID-19/virology , Female , Hemoglobins/analysis , Hospital Mortality , Hospitalization , Humans , Kaplan-Meier Estimate , Lymphocyte Count , Male , Middle Aged , Proportional Hazards Models , ROC Curve , SARS-CoV-2/isolation & purification
2.
Eur Rev Med Pharmacol Sci ; 25(21): 6731-6740, 2021 Nov.
Article in English | MEDLINE | ID: covidwho-1524861

ABSTRACT

OBJECTIVE: The aim of the study was to determine the association between platelet indices and disease severity, and outcomes of the patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in a secondary hospital. PATIENTS AND METHODS: 722 hospitalized patients who had positive rRT-PCR for SARS-CoV-2 and/or typical findings of COVID-19 at chest computed tomography (CT) were enrolled in this study. Initial platelet count (PLT) and indices, including mean platelet volume (MPV), platelet distribution width (PDW), plateletcrit (PCT), MPV/PCT, MPV/PLT, PDW/PLT, PDW/PCT on admission and the third day of hospitalization, and their relationship with disease severity and outcomes were evaluated retrospectively. RESULTS: The mean age of the patients was 57.2±15.6 years (range: 16-94) and male/female ratio was 1.22. 81.9% of the patients had moderate and 11.8% had severe disease. 1.8% of the patients had thrombocytopenia at admission. The patients transferred to the intensive care unit (ICU) had significantly lower baseline lymphocyte counts, PLT, PCT, and 3rd day lymphocyte counts when compared with the patients in wards. ICU patients also had higher baseline CRP, LDH, ferritin, MPV/PCT, MPV/PLT, PDW/PLT, PDW/PCT ratios, and 3rd day PDW, CRP, LDH, and ferritin levels than the patients in wards. Mortality was associated with lower baseline lymphocyte counts, PLT, PCT, 3rd day lymphocyte counts and PCT. Higher baseline CRP, LDH, ferritin, MPV/PCT, PDW/PLT, PDW/PCT and 3rd day CRP, LDH, ferritin, procalcitonin, PDW, MPV/PCT, PDW/PLT, and PDW/PCT ratios were also associated with poor prognosis. CONCLUSIONS: Platelet count and ratios were significantly associated with mortality in patients with COVID-19.


Subject(s)
Blood Platelets/cytology , COVID-19/pathology , Adolescent , Adult , Aged , Aged, 80 and over , Area Under Curve , COVID-19/mortality , COVID-19/virology , Female , Humans , Intensive Care Units , Male , Middle Aged , Platelet Count , Prognosis , ROC Curve , Retrospective Studies , SARS-CoV-2/isolation & purification , Severity of Illness Index , Survival Analysis , Young Adult
3.
Int J Lab Hematol ; 43 Suppl 1: 137-141, 2021 Jul.
Article in English | MEDLINE | ID: covidwho-1526369

ABSTRACT

INTRODUCTION: Eosinopenia has been observed during infection with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative agent of COVID-19. This study evaluated the role of eosinopenia as a diagnostic and prognostic indicator in COVID-19 infection. METHODS: Information on 429 patients with confirmed COVID-19, admitted to Apollo Hospitals, Chennai, India between 04 June 2020 to 15 August 2020, was retrospectively collected through electronic records and analysed. RESULTS: 79.25% of the patients included in the study had eosinopenia on admission. The median eosinophil count in COVID-19-positive patients was 0.015 × 109 /L, and in negative patients, it was 0.249 × 109 /L. Eighteen per cent of the positive patients presented with 0 eosinophil count. Eosinopenia for early diagnosis of COVID-19 had a sensitivity of 80.68% and specificity of 100% with an accuracy of 85.24. Role of eosinopenia in prognostication of COVID-19 was found to be insignificant. There was no statistically significant difference between the median eosinophil counts in survivors and nonsurvivors. Eosinophil trends during the course of disease were found to be similar between survivors and nonsurvivors. CONCLUSIONS: Eosinopenia on admission is a reliable and convenient early diagnostic marker for COVID-19 infection, helping in early identification, triaging and isolation of the patients till nucleic acid test results are available. Role of eosinopenia as a prognostic indicator is insignificant.


Subject(s)
COVID-19 Testing/methods , COVID-19/blood , Eosinophils , Leukocyte Count , Leukopenia/etiology , Area Under Curve , Biomarkers , COVID-19/diagnosis , COVID-19/mortality , Eosinophilia/blood , Eosinophilia/etiology , Humans , India , Leukopenia/blood , Prognosis , ROC Curve , Retrospective Studies , Selection Bias , Sensitivity and Specificity , Survival Analysis
4.
Sci Rep ; 11(1): 7334, 2021 04 01.
Article in English | MEDLINE | ID: covidwho-1500696

ABSTRACT

To identify the risk factors of mortality for the coronavirus disease 19 (COVID-19) patients admitted to intensive care units (ICUs) through a retrospective analysis. The demographic, clinical, laboratory, and chest imaging data of patients admitted to the ICU of Huoshenshan Hospital from February 10 to April 10, 2020 were retrospectively analyzed. Student's t-test and Chi-square test were used to compare the continuous and categorical variables, respectively. The logistic regression model was employed to ascertain the risk factors of mortality. This retrospective study involved 123 patients, including 64 dead and 59 survivors. Among them, 57 people were tested for interleukin-6 (IL-6) (20 died and 37 survived). In all included patients, the oxygenation index (PaO2/FiO2) was identified as an independent risk factor (odd ratio [OR] = 0.96, 95% confidence interval [CI]: 0.928-0.994, p = 0.021). The area under the curve (AUC) was 0.895 (95% CI: 0.826-0.943, p < 0.0001). Among the patients tested for IL-6, the PaO2/FiO2 (OR = 0.955, 95%CI: 0.915-0.996, p = 0.032) and IL-6 (OR = 1.013, 95%CI: 1.001-1.025, p = 0.028) were identified as independent risk factors. The AUC was 0.9 (95% CI: 0.791-0.964, p < 0.0001) for IL-6 and 0.865 (95% CI: 0.748-0.941, p < 0.0001) for PaO2/FiO2. PaO2/FiO2 and IL-6 could potentially serve as independent risk factors for predicting death in COVID-19 patients requiring intensive care.


Subject(s)
COVID-19/mortality , Interleukin-6/analysis , Aged , Area Under Curve , COVID-19/pathology , COVID-19/virology , Comorbidity , Female , Humans , Intensive Care Units , Logistic Models , Male , Middle Aged , Oxygen Consumption , ROC Curve , Retrospective Studies , Risk Factors , SARS-CoV-2/isolation & purification
5.
Sci Rep ; 11(1): 21519, 2021 11 02.
Article in English | MEDLINE | ID: covidwho-1500511

ABSTRACT

A high neutrophil to lymphocyte ratio (NLR) is considered an unfavorable prognostic factor in various diseases, including COVID-19. The prognostic value of NLR in other respiratory viral infections, such as Influenza, has not hitherto been extensively studied. We aimed to compare the prognostic value of NLR in COVID-19, Influenza and Respiratory Syncytial Virus infection (RSV). A retrospective cohort of COVID-19, Influenza and RSV patients admitted to the Tel Aviv Medical Center from January 2010 to October 2020 was analyzed. Laboratory, demographic, and clinical parameters were collected. Two way analyses of variance (ANOVA) was used to compare the association between NLR values and poor outcomes among the three groups. ROC curve analyses for each virus was applied to test the discrimination ability of NLR. 722 COVID-19, 2213 influenza and 482 RSV patients were included. Above the age of 50, NLR at admission was significantly lower among COVID-19 patients (P < 0.001). NLR was associated with poor clinical outcome only in the COVID-19 group. ROC curve analysis was performed; the area under curve of poor outcomes for COVID-19 was 0.68, compared with 0.57 and 0.58 for Influenza and RSV respectively. In the COVID-19 group, multivariate logistic regression identified a high NLR (defined as a value above 6.82) to be a prognostic factor for poor clinical outcome, after adjusting for age, sex and Charlson comorbidity score (odds ratio of 2.9, P < 0.001). NLR at admission is lower and has more prognostic value in COVID-19 patients, when compared to Influenza and RSV.


Subject(s)
COVID-19/pathology , Influenza, Human/pathology , Respiratory Syncytial Virus Infections/pathology , Adult , Aged , Aged, 80 and over , Area Under Curve , COVID-19/immunology , COVID-19/virology , Female , Humans , Influenza, Human/immunology , Lymphocytes/cytology , Lymphocytes/metabolism , Male , Middle Aged , Neutrophils/cytology , Neutrophils/metabolism , Prognosis , ROC Curve , Respiratory Syncytial Virus Infections/immunology , Retrospective Studies , SARS-CoV-2/isolation & purification
6.
Medicine (Baltimore) ; 100(32): e26900, 2021 Aug 13.
Article in English | MEDLINE | ID: covidwho-1475915

ABSTRACT

ABSTRACT: Coronavirus disease 2019 (COVID-19) can lead to serious illness and death, and thus, it is particularly important to predict the severity and prognosis of COVID-19. The Sequential Organ Failure Assessment (SOFA) score has been used to predict the clinical outcomes of patients with multiple organ failure requiring intensive care. Therefore, we retrospectively analyzed the clinical characteristics, risk factors, and relationship between the SOFA score and the prognosis of COVID-19 patients.We retrospectively included all patients ≥18 years old who were diagnosed with COVID-19 in the laboratory continuously admitted to Jingzhou Central Hospital from January 16, 2020 to March 23, 2020. The demographic, clinical manifestations, complications, laboratory results, and clinical outcomes of patients infected with the severe acute respiratory syndrome coronavirus-2 were collected and analyzed. Clinical variables were compared between patients with mild and severe COVID-19. Univariate and multivariate logistic regression analyses were performed to identify the risk factors for severe COVID-19. The Cox proportional hazards model was used to analyze risk factors for hospital-related death. Survival analysis was performed by the Kaplan-Meier method, and survival differences were assessed by the log-rank test. Receiver operating characteristic (ROC) curves of the SOFA score in different situations were drawn, and the area under the ROC curve was calculated.A total of 117 patients with confirmed diagnoses of COVID-19 were retrospectively analyzed, of which 108 patients were discharged and 9 patients died. The median age of the patients was 50.0 years old (interquartile range [IQR], 35.5-62.0). 63 patients had comorbidities, of which hypertension (27.4%) was the most frequent comorbidities, followed by diabetes (8.5%), stroke (4.3%), coronary heart disease (3.4%), and chronic liver disease (3.4%). The most common symptoms upon admission were fever (82.9%) and dry cough (70.1%). Regression analysis showed that high SOFA scores, advanced age, and hypertension were associated with severe COVID-19. The median SOFA score of all patients was 2 (IQR, 1-3). Patients with severe COVID-19 exhibited a significantly higher SOFA score than patients with mild COVID-19 (3 [IQR, 2-4] vs 1 [IQR, 0-1]; P  < .001). The SOFA score can better identify severe COVID-19, with an odds ratio of 5.851 (95% CI: 3.044-11.245; P < .001). The area under the ROC curve (AUC) was used to evaluate the diagnostic accuracy of the SOFA score in predicting severe COVID-19 (cutoff value = 2; AUC = 0.908 [95% CI: 0.857-0.960]; sensitivity: 85.20%; specificity: 80.40%) and the risk of death in COVID-19 patients (cutoff value = 5; AUC = 0.995 [95% CI: 0.985-1.000]; sensitivity: 100.00%; specificity: 95.40%). Regarding the 60-day mortality rates of patients in the 2 groups classified by the optimal cutoff value of the SOFA score (5), patients in the high SOFA score group (SOFA score ≥5) had a significantly greater risk of death than those in the low SOFA score group (SOFA score < 5).The SOFA score could be used to evaluate the severity and 60-day mortality of COVID-19. The SOFA score may be an independent risk factor for in-hospital death.


Subject(s)
COVID-19/complications , Organ Dysfunction Scores , Adult , Area Under Curve , COVID-19/epidemiology , COVID-19/mortality , Female , Humans , Logistic Models , Male , Middle Aged , Prognosis , Proportional Hazards Models , ROC Curve , Retrospective Studies , Risk Factors , Severity of Illness Index , Statistics, Nonparametric
7.
Sci Rep ; 11(1): 20569, 2021 10 18.
Article in English | MEDLINE | ID: covidwho-1475480

ABSTRACT

The Brazilian Northern region registered a high incidence of COVID-19 cases, particularly in the state of Pará. The present study investigated the risk factors associated with the severity of COVID-19 in a Brazilian Amazon region of 100,819 cases. An epidemiological, cross-sectional, analytical and demographic study, analyzing data on confirmed cases for COVID-19 available at the Brazilian Ministry of Health's surveillance platform, was conducted. Variables such as, municipalities of residence, age, gender, signs and symptoms, comorbidities were included and associated with COVID-19 cases and outcomes. The spatial distribution was performed using the ArcGIS program. A total of 100,819 cases were evaluated. Overall, patients had the mean age of 42.3 years, were female (51.2%) and with lethality reaching 4.79% of cases. Main symptoms included fever (66.5%), cough (61.9%) and sore throat (39.8%). Regarding comorbidities, most of the patients presented cardiovascular disease (5.1%) and diabetes (4.2%). Neurological disease increased risk of death by nearly 15 times, followed by obesity (5.16 times) and immunodeficiency (5.09 time). The municipalities with the highest incidence rate were Parauapebas, Canaã dos Carajás and Jacareacanga. Similarity between the Lower Amazon, Marajó and Southwest mesoregions of Pará state were observed concerning the highest morbidity rates. The obtained data demonstrated that the majority of cases occurred among young adults, females, with the classic influenza symptoms and chronic diseases. Finally, data suggest that the highest incidences were no longer in the metropolitan region of the state. The higher lethality rate than in Brazil may be associated with the greater impacts of the disease in this Amazonian population, or factors associated with fragile epidemiological surveillance in the notification of cases of cure.


Subject(s)
COVID-19/diagnosis , COVID-19/epidemiology , Adult , Area Under Curve , Brazil/epidemiology , COVID-19/mortality , Comorbidity , Cough/epidemiology , Cross-Sectional Studies , Data Collection , Female , Fever/epidemiology , Geography , Humans , Incidence , Male , Middle Aged , Models, Statistical , Regression Analysis , Risk , Risk Factors , SARS-CoV-2 , Young Adult
8.
PLoS One ; 16(10): e0257421, 2021.
Article in English | MEDLINE | ID: covidwho-1468157

ABSTRACT

Coronavirus Disease-2019 (COVID-19) quickly surged the whole world and affected people's physical, mental, and social health thereby upsetting their quality of life. Therefore, we aimed to investigate the quality of life (QoL) of COVID-19 positive patients after recovery in Bangladesh. This was a study of adult (aged ≥18 years) COVID-19 individuals from eight divisions of Bangladesh diagnosed and confirmed by Reverse Transcription-Polymerase Chain Reaction (RT-PCR) from June 2020 to November 2020. Given a response rate of 60% in a pilot study, a random list of 6400 COVID-19 patients was generated to recruit approximately 3200 patients from eight divisions of Bangladesh and finally a total of 3244 participants could be recruited for the current study. The validated Bangla version of the World Health Organization Quality of Life Brief (WHOQOL-BREF) questionnaire was used to assess the QoL. Data were analyzed by STATA (Version 16.1) and R (Version 4.0.0). All the procedures were conducted following ethical approval and in accordance with the Declaration of Helsinki. The mean scores of QoL were highest for the physical domain (68.25±14.45) followed by social (65.10±15.78), psychological (63.28±15.48), and environmental domain (62.77±13.07). Psychological and physical domain scores among females were significantly lower than the males (p<0.001). The overall quality of life was lower in persons having a chronic disease. Participants over 45 years of age were 52% less likely to enjoy good physical health than the participants aged below 26 years (AOR: 0.48, CI: 0.28-0.82). The quality of life of employed participants was found 1.8 times higher than the unemployed (AOR: 1.80, CI: 1.11-2.91). Those who were admitted to hospitals during infection had a low QoL score in physical, psychological, and socials domains. However, QoL improved in all aspect except the psychological domain for each day passed after the diagnosis. These findings call for a focus on the quality of life of the COVID-19 affected population, with special emphasis given to females, older adults, unemployed, and people with comorbidities.


Subject(s)
COVID-19/psychology , Quality of Life , Adult , Area Under Curve , Bangladesh , COVID-19/pathology , COVID-19/virology , Comorbidity , Female , Humans , Logistic Models , Male , Middle Aged , ROC Curve , SARS-CoV-2/isolation & purification , Smoking , Surveys and Questionnaires
9.
Dis Markers ; 2021: 2571912, 2021.
Article in English | MEDLINE | ID: covidwho-1463050

ABSTRACT

Background: Coronavirus disease 2019 (COVID-19) is highly contagious and continues to spread rapidly. However, there are no simple and timely laboratory techniques to determine the severity of COVID-19. In this meta-analysis, we assessed the potential of the neutrophil-lymphocyte ratio (NLR) as an indicator of severe versus nonsevere COVID-19 cases. Methods: A search for studies on the NLR in severe and nonsevere COVID-19 cases published from January 1, 2020, to July 1, 2021, was conducted on the PubMed, EMBASE, and Cochrane Library databases. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio (DOR), and area under the curve (AUC) analyses were done on Stata 14.0 and Meta-disc 1.4 to assess the performance of the NLR. Results: Thirty studies, including 5570 patients, were analyzed. Of these, 1603 and 3967 patients had severe and nonsevere COVID-19, respectively. The overall sensitivity and specificity were 0.82 (95% confidence interval (CI), 0.77-0.87) and 0.77 (95% CI, 0.70-0.83), respectively; positive and negative correlation ratios were 3.6 (95% CI, 2.7-4.7) and 0.23 (95% CI, 0.17-0.30), respectively; DOR was 16 (95% CI, 10-24), and the AUC was 0.87 (95% CI, 0.84-0.90). Conclusion: The NLR could accurately determine the severity of COVID-19 and can be used to identify patients with severe disease to guide clinical decision-making.


Subject(s)
COVID-19/immunology , Lymphocytes/immunology , Neutrophils/immunology , SARS-CoV-2 , Area Under Curve , Biomarkers/blood , COVID-19/blood , Confidence Intervals , Humans , Leukocyte Count , Likelihood Functions , Odds Ratio , Sensitivity and Specificity , Severity of Illness Index
10.
JAMA Netw Open ; 4(10): e2124946, 2021 10 01.
Article in English | MEDLINE | ID: covidwho-1460117

ABSTRACT

Importance: Machine learning could be used to predict the likelihood of diagnosis and severity of illness. Lack of COVID-19 patient data has hindered the data science community in developing models to aid in the response to the pandemic. Objectives: To describe the rapid development and evaluation of clinical algorithms to predict COVID-19 diagnosis and hospitalization using patient data by citizen scientists, provide an unbiased assessment of model performance, and benchmark model performance on subgroups. Design, Setting, and Participants: This diagnostic and prognostic study operated a continuous, crowdsourced challenge using a model-to-data approach to securely enable the use of regularly updated COVID-19 patient data from the University of Washington by participants from May 6 to December 23, 2020. A postchallenge analysis was conducted from December 24, 2020, to April 7, 2021, to assess the generalizability of models on the cumulative data set as well as subgroups stratified by age, sex, race, and time of COVID-19 test. By December 23, 2020, this challenge engaged 482 participants from 90 teams and 7 countries. Main Outcomes and Measures: Machine learning algorithms used patient data and output a score that represented the probability of patients receiving a positive COVID-19 test result or being hospitalized within 21 days after receiving a positive COVID-19 test result. Algorithms were evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC) scores. Ensemble models aggregating models from the top challenge teams were developed and evaluated. Results: In the analysis using the cumulative data set, the best performance for COVID-19 diagnosis prediction was an AUROC of 0.776 (95% CI, 0.775-0.777) and an AUPRC of 0.297, and for hospitalization prediction, an AUROC of 0.796 (95% CI, 0.794-0.798) and an AUPRC of 0.188. Analysis on top models submitting to the challenge showed consistently better model performance on the female group than the male group. Among all age groups, the best performance was obtained for the 25- to 49-year age group, and the worst performance was obtained for the group aged 17 years or younger. Conclusions and Relevance: In this diagnostic and prognostic study, models submitted by citizen scientists achieved high performance for the prediction of COVID-19 testing and hospitalization outcomes. Evaluation of challenge models on demographic subgroups and prospective data revealed performance discrepancies, providing insights into the potential bias and limitations in the models.


Subject(s)
Algorithms , Benchmarking , COVID-19/diagnosis , Clinical Decision Rules , Crowdsourcing , Hospitalization/statistics & numerical data , Machine Learning , Adolescent , Adult , Aged , Aged, 80 and over , Area Under Curve , COVID-19/epidemiology , COVID-19/therapy , COVID-19 Testing , Child , Child, Preschool , Female , Humans , Infant , Infant, Newborn , Male , Middle Aged , Models, Statistical , Prognosis , ROC Curve , Severity of Illness Index , Washington/epidemiology , Young Adult
11.
BMC Med Res Methodol ; 21(1): 96, 2021 05 06.
Article in English | MEDLINE | ID: covidwho-1455917

ABSTRACT

BACKGROUND: Advances in machine learning (ML) provide great opportunities in the prediction of hospital readmission. This review synthesizes the literature on ML methods and their performance for predicting hospital readmission in the US. METHODS: This review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) Statement. The extraction of items was also guided by the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS). Electronic databases PUBMED, MEDLINE, and EMBASE were systematically searched from January 1, 2015, through December 10, 2019. The articles were imported into COVIDENCE online software for title/abstract screening and full-text eligibility. Observational studies using ML techniques for hospital readmissions among US patients were eligible for inclusion. Articles without a full text available in the English language were excluded. A qualitative synthesis included study characteristics, ML algorithms utilized, and model validation, and quantitative analysis assessed model performance. Model performances in terms of Area Under the Curve (AUC) were analyzed using R software. Quality in Prognosis Studies (QUIPS) tool was used to assess the quality of the reviewed studies. RESULTS: Of 522 citations reviewed, 43 studies met the inclusion criteria. A majority of the studies used electronic health records (24, 56%), followed by population-based data sources (15, 35%) and administrative claims data (4, 9%). The most common algorithms were tree-based methods (23, 53%), neural network (NN) (14, 33%), regularized logistic regression (12, 28%), and support vector machine (SVM) (10, 23%). Most of these studies (37, 85%) were of high quality. A majority of these studies (28, 65%) reported ML algorithms with an AUC above 0.70. There was a range of variability within AUC reported by these studies with a median of 0.68 (IQR: 0.64-0.76; range: 0.50-0.90). CONCLUSIONS: The ML algorithms involving tree-based methods, NN, regularized logistic regression, and SVM are commonly used to predict hospital readmission in the US. Further research is needed to compare the performance of ML algorithms for hospital readmission prediction.


Subject(s)
Machine Learning , Patient Readmission , Algorithms , Area Under Curve , Humans , Logistic Models
12.
Sci Rep ; 11(1): 19713, 2021 10 05.
Article in English | MEDLINE | ID: covidwho-1454811

ABSTRACT

The novel coronavirus disease 2019 (COVID-19) presents with non-specific clinical features. This may result in misdiagnosis or delayed diagnosis, and lead to further transmission in the community. We aimed to derive early predictors to differentiate COVID-19 from influenza and dengue. The study comprised 126 patients with COVID-19, 171 with influenza and 180 with dengue, who presented within 5 days of symptom onset. All cases were confirmed by reverse transcriptase polymerase chain reaction tests. We used logistic regression models to identify demographics, clinical characteristics and laboratory markers in classifying COVID-19 versus influenza, and COVID-19 versus dengue. The performance of each model was evaluated using receiver operating characteristic (ROC) curves. Shortness of breath was the strongest predictor in the models for differentiating between COVID-19 and influenza, followed by diarrhoea. Higher lymphocyte count was predictive of COVID-19 versus influenza and versus dengue. In the model for differentiating between COVID-19 and dengue, patients with cough and higher platelet count were at increased odds of COVID-19, while headache, joint pain, skin rash and vomiting/nausea were indicative of dengue. The cross-validated area under the ROC curve for all four models was above 0.85. Clinical features and simple laboratory markers for differentiating COVID-19 from influenza and dengue are identified in this study which can be used by primary care physicians in resource limited settings to determine if further investigations or referrals would be required.


Subject(s)
COVID-19/pathology , Dengue/pathology , Influenza, Human/pathology , Adult , Area Under Curve , COVID-19/complications , COVID-19/virology , Cohort Studies , Dengue/complications , Dengue/virology , Diagnosis, Differential , Diarrhea/etiology , Female , Fever/etiology , Humans , Influenza, Human/complications , Influenza, Human/virology , Lymphocyte Count , Male , Middle Aged , Platelet Count , RNA, Viral/analysis , RNA, Viral/metabolism , ROC Curve , SARS-CoV-2/genetics , SARS-CoV-2/isolation & purification , Vomiting/etiology , Young Adult
13.
Sci Rep ; 11(1): 19795, 2021 10 05.
Article in English | MEDLINE | ID: covidwho-1454809

ABSTRACT

We are concerned with the issue of detecting changes and their signs from a data stream. For example, when given time series of COVID-19 cases in a region, we may raise early warning signals of an epidemic by detecting signs of changes in the data. We propose a novel methodology to address this issue. The key idea is to employ a new information-theoretic notion, which we call the differential minimum description length change statistics (D-MDL), for measuring the scores of change sign. We first give a fundamental theory for D-MDL. We then demonstrate its effectiveness using synthetic datasets. We apply it to detecting early warning signals of the COVID-19 epidemic using time series of the cases for individual countries. We empirically demonstrate that D-MDL is able to raise early warning signals of events such as significant increase/decrease of cases. Remarkably, for about [Formula: see text] of the events of significant increase of cases in studied countries, our method can detect warning signals as early as nearly six days on average before the events, buying considerably long time for making responses. We further relate the warning signals to the dynamics of the basic reproduction number R0 and the timing of social distancing. The results show that our method is a promising approach to the epidemic analysis from a data science viewpoint.


Subject(s)
Algorithms , COVID-19/epidemiology , Area Under Curve , Basic Reproduction Number , COVID-19/virology , Humans , Models, Statistical , Pandemics , ROC Curve , SARS-CoV-2/isolation & purification
14.
Crit Care Med ; 49(10): 1664-1673, 2021 10 01.
Article in English | MEDLINE | ID: covidwho-1452743

ABSTRACT

OBJECTIVES: The rapid diagnosis of acute infections and sepsis remains a serious challenge. As a result of limitations in current diagnostics, guidelines recommend early antimicrobials for suspected sepsis patients to improve outcomes at a cost to antimicrobial stewardship. We aimed to develop and prospectively validate a new, 29-messenger RNA blood-based host-response classifier Inflammatix Bacterial Viral Non-Infected version 2 (IMX-BVN-2) to determine the likelihood of bacterial and viral infections. DESIGN: Prospective observational study. SETTING: Emergency Department, Campus Benjamin Franklin, Charité-Universitätsmedizin Berlin, Germany. PATIENTS: Three hundred twelve adult patients presenting to the emergency department with suspected acute infections or sepsis with at least one vital sign change. INTERVENTIONS: None (observational study only). MEASUREMENTS AND MAIN RESULTS: Gene expression levels from extracted whole blood RNA was quantified on a NanoString nCounter SPRINT (NanoString Technologies, Seattle, WA). Two predicted probability scores for the presence of bacterial and viral infection were calculated using the IMX-BVN-2 neural network classifier, which was trained on an independent development set. The IMX-BVN-2 bacterial score showed an area under the receiver operating curve for adjudicated bacterial versus ruled out bacterial infection of 0.90 (95% CI, 0.85-0.95) compared with 0.89 (95% CI, 0.84-0.94) for procalcitonin with procalcitonin being used in the adjudication. The IMX-BVN-2 viral score area under the receiver operating curve for adjudicated versus ruled out viral infection was 0.83 (95% CI, 0.77-0.89). CONCLUSIONS: IMX-BVN-2 demonstrated accuracy for detecting both viral infections and bacterial infections. This shows the potential of host-response tests as a novel and practical approach for determining the causes of infections, which could improve patient outcomes while upholding antimicrobial stewardship.


Subject(s)
Bacterial Infections/diagnosis , RNA, Messenger/analysis , Virus Diseases/diagnosis , Aged , Aged, 80 and over , Area Under Curve , Bacterial Infections/blood , Bacterial Infections/physiopathology , Berlin , Biomarkers/analysis , Biomarkers/blood , Emergency Service, Hospital/organization & administration , Emergency Service, Hospital/statistics & numerical data , Female , Humans , Male , Middle Aged , Prospective Studies , RNA, Messenger/blood , ROC Curve , Virus Diseases/blood , Virus Diseases/physiopathology
15.
Clin Appl Thromb Hemost ; 27: 10760296211045902, 2021.
Article in English | MEDLINE | ID: covidwho-1443743

ABSTRACT

INTRODUCTION: Diabetes is the most common of comorbidity in patients with SARS-COV-2 pneumonia. Coagulation abnormalities with D-dimer levels are increased in this disease. OBJECTIFS: We aimed to compare the levels of D-dimer in diabetic and non-diabetic patients with COVID 19. A link between D-dimer and mortality has also been established. MATERIALS: A retrospective study was carried out at the University Hospital Center of Oujda (Morocco) from November 01st to December 01st, 2020. Our study population was divided into two groups: a diabetic group and a second group without diabetes to compare clinical and biological characteristics between the two groups. In addition, the receiver operator characteristic curve was used to assess the optimal D-dimer cut-off point for predicting mortality in diabetics. RESULTS: 201 confirmed-COVID-19-patients were included in the final analysis. The median age was 64 (IQR 56-73), and 56% were male. Our study found that D-dimer levels were statistically higher in diabetic patients compared to non-diabetic patients. (1745 vs 845 respectively, P = 0001). D-dimer level > 2885 ng/mL was a significant predictor of mortality in diabetic patients with a sensitivity of 71,4% and a specificity of 70,7%. CONCLUSION: Our study found that diabetics with COVID-19 are likely to develop hypercoagulation with a poor prognosis.


Subject(s)
COVID-19/blood , Diabetes Mellitus/blood , Fibrin Fibrinogen Degradation Products/analysis , SARS-CoV-2 , Thrombophilia/blood , Aged , Area Under Curve , Biomarkers , C-Reactive Protein/analysis , COVID-19/complications , COVID-19/epidemiology , Comorbidity , Diabetes Complications/blood , Diabetes Complications/epidemiology , Diabetes Mellitus/epidemiology , Female , Hospital Mortality , Humans , Hypertension/epidemiology , Inflammation/immunology , Kaplan-Meier Estimate , Male , Middle Aged , Oxidative Stress , Prognosis , ROC Curve , Retrospective Studies , Risk Factors , Thrombophilia/etiology , Thrombophilia/immunology
16.
JAMA Netw Open ; 4(9): e2128534, 2021 09 01.
Article in English | MEDLINE | ID: covidwho-1441922

ABSTRACT

Importance: Currently, there are no presymptomatic screening methods to identify individuals infected with a respiratory virus to prevent disease spread and to predict their trajectory for resource allocation. Objective: To evaluate the feasibility of using noninvasive, wrist-worn wearable biometric monitoring sensors to detect presymptomatic viral infection after exposure and predict infection severity in patients exposed to H1N1 influenza or human rhinovirus. Design, Setting, and Participants: The cohort H1N1 viral challenge study was conducted during 2018; data were collected from September 11, 2017, to May 4, 2018. The cohort rhinovirus challenge study was conducted during 2015; data were collected from September 14 to 21, 2015. A total of 39 adult participants were recruited for the H1N1 challenge study, and 24 adult participants were recruited for the rhinovirus challenge study. Exclusion criteria for both challenges included chronic respiratory illness and high levels of serum antibodies. Participants in the H1N1 challenge study were isolated in a clinic for a minimum of 8 days after inoculation. The rhinovirus challenge took place on a college campus, and participants were not isolated. Exposures: Participants in the H1N1 challenge study were inoculated via intranasal drops of diluted influenza A/California/03/09 (H1N1) virus with a mean count of 106 using the median tissue culture infectious dose (TCID50) assay. Participants in the rhinovirus challenge study were inoculated via intranasal drops of diluted human rhinovirus strain type 16 with a count of 100 using the TCID50 assay. Main Outcomes and Measures: The primary outcome measures included cross-validated performance metrics of random forest models to screen for presymptomatic infection and predict infection severity, including accuracy, precision, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). Results: A total of 31 participants with H1N1 (24 men [77.4%]; mean [SD] age, 34.7 [12.3] years) and 18 participants with rhinovirus (11 men [61.1%]; mean [SD] age, 21.7 [3.1] years) were included in the analysis after data preprocessing. Separate H1N1 and rhinovirus detection models, using only data on wearble devices as input, were able to distinguish between infection and noninfection with accuracies of up to 92% for H1N1 (90% precision, 90% sensitivity, 93% specificity, and 90% F1 score, 0.85 [95% CI, 0.70-1.00] AUC) and 88% for rhinovirus (100% precision, 78% sensitivity, 100% specificity, 88% F1 score, and 0.96 [95% CI, 0.85-1.00] AUC). The infection severity prediction model was able to distinguish between mild and moderate infection 24 hours prior to symptom onset with an accuracy of 90% for H1N1 (88% precision, 88% sensitivity, 92% specificity, 88% F1 score, and 0.88 [95% CI, 0.72-1.00] AUC) and 89% for rhinovirus (100% precision, 75% sensitivity, 100% specificity, 86% F1 score, and 0.95 [95% CI, 0.79-1.00] AUC). Conclusions and Relevance: This cohort study suggests that the use of a noninvasive, wrist-worn wearable device to predict an individual's response to viral exposure prior to symptoms is feasible. Harnessing this technology would support early interventions to limit presymptomatic spread of viral respiratory infections, which is timely in the era of COVID-19.


Subject(s)
Biometry/methods , Common Cold/diagnosis , Influenza A Virus, H1N1 Subtype , Influenza, Human/diagnosis , Rhinovirus , Severity of Illness Index , Wearable Electronic Devices , Adult , Area Under Curve , Biological Assay , Biometry/instrumentation , Cohort Studies , Common Cold/virology , Early Diagnosis , Feasibility Studies , Female , Humans , Influenza A Virus, H1N1 Subtype/growth & development , Influenza, Human/virology , Male , Mass Screening , Models, Biological , Rhinovirus/growth & development , Sensitivity and Specificity , Virus Shedding , Young Adult
17.
PLoS Med ; 18(9): e1003777, 2021 09.
Article in English | MEDLINE | ID: covidwho-1440982

ABSTRACT

BACKGROUND: Rapid detection, isolation, and contact tracing of community COVID-19 cases are essential measures to limit the community spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). We aimed to identify a parsimonious set of symptoms that jointly predict COVID-19 and investigated whether predictive symptoms differ between the B.1.1.7 (Alpha) lineage (predominating as of April 2021 in the US, UK, and elsewhere) and wild type. METHODS AND FINDINGS: We obtained throat and nose swabs with valid SARS-CoV-2 PCR test results from 1,147,370 volunteers aged 5 years and above (6,450 positive cases) in the REal-time Assessment of Community Transmission-1 (REACT-1) study. This study involved repeated community-based random surveys of prevalence in England (study rounds 2 to 8, June 2020 to January 2021, response rates 22%-27%). Participants were asked about symptoms occurring in the week prior to testing. Viral genome sequencing was carried out for PCR-positive samples with N-gene cycle threshold value < 34 (N = 1,079) in round 8 (January 2021). In univariate analysis, all 26 surveyed symptoms were associated with PCR positivity compared with non-symptomatic people. Stability selection (1,000 penalized logistic regression models with 50% subsampling) among people reporting at least 1 symptom identified 7 symptoms as jointly and positively predictive of PCR positivity in rounds 2-7 (June to December 2020): loss or change of sense of smell, loss or change of sense of taste, fever, new persistent cough, chills, appetite loss, and muscle aches. The resulting model (rounds 2-7) predicted PCR positivity in round 8 with area under the curve (AUC) of 0.77. The same 7 symptoms were selected as jointly predictive of B.1.1.7 infection in round 8, although when comparing B.1.1.7 with wild type, new persistent cough and sore throat were more predictive of B.1.1.7 infection while loss or change of sense of smell was more predictive of the wild type. The main limitations of our study are (i) potential participation bias despite random sampling of named individuals from the National Health Service register and weighting designed to achieve a representative sample of the population of England and (ii) the necessary reliance on self-reported symptoms, which may be prone to recall bias and may therefore lead to biased estimates of symptom prevalence in England. CONCLUSIONS: Where testing capacity is limited, it is important to use tests in the most efficient way possible. We identified a set of 7 symptoms that, when considered together, maximize detection of COVID-19 in the community, including infection with the B.1.1.7 lineage.


Subject(s)
COVID-19/complications , COVID-19/diagnosis , Models, Biological , Ageusia/diagnosis , Ageusia/etiology , Ageusia/virology , Anosmia/diagnosis , Anosmia/etiology , Anosmia/virology , Appetite , Area Under Curve , COVID-19/virology , Chills/diagnosis , Chills/etiology , Chills/virology , Communicable Disease Control , Cough/diagnosis , Cough/etiology , Cough/virology , England , False Positive Reactions , Female , Fever/diagnosis , Fever/etiology , Fever/virology , Humans , Male , Mass Screening , Myalgia/diagnosis , Myalgia/etiology , Myalgia/virology , Pharyngitis/diagnosis , Pharyngitis/etiology , Pharyngitis/virology , Polymerase Chain Reaction , SARS-CoV-2/genetics , State Medicine
18.
Sci Rep ; 11(1): 18959, 2021 09 23.
Article in English | MEDLINE | ID: covidwho-1437695

ABSTRACT

The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.


Subject(s)
COVID-19/epidemiology , Forecasting/methods , Intensive Care Units/trends , Area Under Curve , Computational Biology/methods , Critical Care/statistics & numerical data , Critical Care/trends , Denmark/epidemiology , Hospitalization/trends , Hospitals/trends , Humans , Machine Learning , Pandemics , ROC Curve , Respiration, Artificial/statistics & numerical data , Respiration, Artificial/trends , Retrospective Studies , Risk Assessment/methods , Risk Factors , SARS-CoV-2/pathogenicity , Ventilators, Mechanical/trends
19.
Sci Rep ; 11(1): 18638, 2021 09 20.
Article in English | MEDLINE | ID: covidwho-1428897

ABSTRACT

Risk prediction scores are important tools to support clinical decision-making for patients with coronavirus disease (COVID-19). The objective of this paper was to validate the 4C mortality score, originally developed in the United Kingdom, for a Canadian population, and to examine its performance over time. We conducted an external validation study within a registry of COVID-19 positive hospital admissions in the Kitchener-Waterloo and Hamilton regions of southern Ontario between March 4, 2020 and June 13, 2021. We examined the validity of the 4C score to prognosticate in-hospital mortality using the area under the receiver operating characteristic curve (AUC) with 95% confidence intervals calculated via bootstrapping. The study included 959 individuals, of whom 224 (23.4%) died in-hospital. Median age was 72 years and 524 individuals (55%) were male. The AUC of the 4C score was 0.77, 95% confidence interval 0.79-0.87. Overall mortality rates across the pre-defined risk groups were 0% (Low), 8.0% (Intermediate), 27.2% (High), and 54.2% (Very High). Wave 1, 2 and 3 values of the AUC were 0.81 (0.76, 0.86), 0.74 (0.69, 0.80), and 0.76 (0.69, 0.83) respectively. The 4C score is a valid tool to prognosticate mortality from COVID-19 in Canadian hospitals and can be used to prioritize care and resources for patients at greatest risk of death.


Subject(s)
COVID-19/mortality , Hospitalization , Aged , Aged, 80 and over , Area Under Curve , COVID-19/diagnosis , Female , Humans , Male , Middle Aged , Ontario/epidemiology , Reproducibility of Results , Retrospective Studies
20.
Biomed Res Int ; 2021: 3893733, 2021.
Article in English | MEDLINE | ID: covidwho-1412962

ABSTRACT

Background: In emergency hospital settings, rapid diagnosis and isolation of SARS-CoV-2 patients are required. The aim of the study was to evaluate the performance of an antigen chemiluminescence enzymatic immunoassay (CLEIA) and compare it with that of Real-time Reverse transcription-Polymerase Chain Reaction (RT-qPCR), the gold standard assay, to assess its suitability as a rapid diagnostic method for managing patients in the emergency department (ED). Methods: Consecutive patients with no previous history of SARS-CoV-2 infection attending the ED of the Policlinico Hospital of Bari between 23rd October and 4th November 2020 were enrolled. Clinical and demographic data were collected for all patients. Nasopharyngeal swabs collected on admission were subjected both to molecular (RT-qPCR) and antigen (CLEIA) tests for SARS-CoV-2. The performance of the CLEIA antigen test was analyzed using R Studio software and Microsoft Excel. Receiver operating characteristics were also performed. Results: A total of 911 patients were enrolled, of whom 469 (51.5%) were male. Of the whole cohort, 23.7% tested positive for SARS-CoV-2 by RT-qPCR and 24.5% by CLEIA. The overall concordance rate was 96.8%. The sensitivity, specificity, positive predictive value, and negative predictive value of the antigen test were 94.9% (95% CI, 91.9-97.0), 97.4% (95% CI, 96.5-98.1), 91.9% (95% CI, 89.0-94.0), and 98.4% (95% CI, 97.4-99.1), respectively. The area under the curve (AUC) was 0.99. The kappa coefficient was 0.91. The overall positive and negative likelihood ratios were 37 (95% CI 23-58) and 0.05 (95% CI, 0.03-0.09), respectively. Conclusions: Data analysis demonstrated that the antigen test showed very good accuracy for discriminating SARS-CoV-2-infected patients from negative participants. The CLEIA is suitable for rapid clinical diagnosis of patients in hospital settings, particularly in EDs with a high prevalence of symptomatic patients and where a rapid turnaround time is critical. Timely and accurate testing for SARS-CoV-2 plays a crucial role in limiting the spread of the virus.


Subject(s)
COVID-19 Serological Testing/methods , Nasopharynx/virology , Adult , Aged , Antigens, Viral/analysis , Area Under Curve , COVID-19 Nucleic Acid Testing/methods , Emergency Service, Hospital , Female , Humans , Immunoassay , Italy , Luminescent Measurements , Male , Middle Aged , Sensitivity and Specificity , Tertiary Care Centers
SELECTION OF CITATIONS
SEARCH DETAIL
...