scholarly journals Value of laboratory tests in COVID-19 hospitalized patients for clinical decision-makers: a predictive model, using data mining approach

2020 ◽  
Author(s):  
Atefeh Mousavi ◽  
Soheyla Rezaei ◽  
Jamshid Salamzadeh ◽  
Ali Mirzazadeh ◽  
Farzad Peiravian ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Service Providers ◽  
Laboratory Data ◽  
Clinical Decision ◽  
Hospitalized Patients ◽  
Decision Makers ◽  
Adult Patients ◽  
Data Mining Approach ◽  
Logistic Regression Method ◽  
Using Data

Abstract Purpose: Because of the rapid increase in confirmed cases of COVID-19, in particular those with severe or critical status, overwhelming of health systems is a worldwide concern. Therefore, identifying high-risk COVID-19 patients, can help service providers for priority setting and hospital resource allocation. Methods: 4542 adult patients with confirmed COVID-19 admitted in 15 hospitals in Tehran, Iran, from Feb 20 to April 18, 2020 were included in this retrospective cohort study with final outcomes of survived and died patients. Demographic features including age and sex, and laboratory data measured at admission were extracted and compared between recovered and died patients. Data analysis was performed applying SPSS modeler software using a logistic regression method.Results: Of 4542 hospitalized adult patients, 822 patients (18.09%) died during hospitalization, and 3720 (81.90%) recovered and discharged. Based on logistic regression model, older age, 40-49 (RR= 1.80, CI: 1.13-2.87), 50-59 (RR=2.63, CI: 1.71-4.02), 60-69 (RR= 4.40, CI: 2.92-6.63), 70-79 (RR=7.49, CI: 5.01-11.19), Above 80 (RR=13.85, CI: 9.23-2.77), ALT ≥ 55 IU/ (RR=2.20, CI: 1.69-2.86), AST ≥ 100 IU/L (RR=5.93, CI: 4.75-7.39), ALP ≥ 200 IU/L (RR=2.46, CI: 1.80-3.37), sodium < 135 mEq/l (RR=1.69, CI: 1.35-2.11) or more than 145 mEq/l (RR=7.24, CI: 5.07-10.33), potassium > 5.50 mEq/l (RR=7.53, CI: 4.15-13.64), and calcium < 8.50 mEq/l (RR=3.39, CI: 2.81-4.09), CPK between 307-600 IU/L (RR=2.73, CI: 2.12-3.53) and above 600 IU/L (RR=4.41, CI: 3.40-5.71) in men, and 192-400 IU/L (RR=2.73, CI: 2.12-3.53), and above 400 (RR=4.41, CI: 3.40-5.71) in women, CRP > 3 mg/l (RR=3.22, CI: 1.99-5.20), and creatinine > 1.5 mg/l (RR=6.37, CI: 5.30-7.66) were significantly associated with COVID-19 mortality. Conclusion: Our findings suggested less than one in five hospitalized patients with COVID-19 die mostly due to electrolyte disbalance, liver, and renal dysfunctions. Better supportive care is needed to improve outcomes for patients with COVID-19.

scholarly journals 60. New Prognostic Markers for COVID-19 Disease

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S161-S162
Author(s):  
Amr Ramahi ◽  
Kok Hoe Chan ◽  
Laxminarayan Prabhakar ◽  
Iyad Farouji ◽  
Divya Thimmareddygari ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Cohort Study ◽  
Prognostic Markers ◽  
Univariate Analysis ◽  
Laboratory Data ◽  
Hospitalized Patients ◽  
Prognostic Indicators ◽  
Blood Profile ◽  
New Model ◽  
D Dimer

Abstract Background A few COVID-19 related retrospective studies have established that older age, elevated neutrophil-lymphocyte ratio (NLR), and decreased lymphocyte-CRP ratio (LCR) were associated with worse outcome. Herein, we aim to identify new prognostic markers associated with mortality. Methods We conducted a retrospective hospital cohort study on patients ≥ 18 years old with confirmed COVID-19, who were admitted to our hospital between 03/15/2020 and 05/25/2020. Study individuals were recruited if they had a complete CBC profile and inflammatory markers such as CRP, ferritin, D-dimer and LDH, as well as a well-defined clinical outcomes (discharged alive or expired). Demographic, clinical and laboratory data were reviewed and retrieved. Univariate and multivariate logistic regression methods were employed to identify prognostic markers associated with mortality. Results Out of the 344 confirmed COVID-19 hospitalized patients during the study period, 31 who did not have a complete blood profile were excluded; 303 patients were included in the study, 89 (29%) expired, and 214 (71%) were discharged alive. Demographic analysis was tabulated in Table 1. The univariate analysis showed a significant association of death with absolute neutrophil count (ANC, p=0.022), NLR (p=002), neutrophil-monocyte ratio (NMR, p=&lt; 0.0001), LCR (p=0.007), lymphocyte-LDH ratio (LLR, p=&lt; 0.0001), lymphocyte-D-dimer ratio (LDR, p=&lt; 0.0001), lymphocyte-ferritin ratio (LFR, p=&lt; 0.0001), and platelets (p=0.037) with mortality. With multivariable logistic regression analysis, the only values that had an odds of survival were high LDR (odds ratio [OR] 1.763; 95% confidence interval [CI], 1.20–2.69), and a high LFR (OR 1.136, CI 1.01–1.34). We further build up a model which can predict &gt;85% mortality in our cohorts with the utilization of D-dimer (&gt;500 ng/ml), Ferritin (&gt;200 ng/ml), LDR (&lt; 1.6), LFR (&lt; 4) and ANC (&gt;2.5). This new model has a ROC of 0.68 (p&lt; 0.0001). Conclusion This retrospective cohort study of hospitalized patients with COVID-19 suggests LDR and LFR as potential independent prognostic indicators. A new model with combination of D-dimer, Ferritin, LDR, LFR and ANC, was able to predict &gt;85% mortality in our cohort with ROC of 0.68, it will need to be validated in a prospective cohort study. Disclosures Jihad Slim, MD, Abbvie (Speaker’s Bureau)Gilead (Speaker’s Bureau)Jansen (Speaker’s Bureau)Merck (Speaker’s Bureau)ViiV (Speaker’s Bureau)

scholarly journals Predictors of hospital mortality among patients with COVID-19 in Tehran, Iran

2021 ◽  
Vol 9 ◽  
pp. 205031212110515
Author(s):  
Fatemeh Esfahanian ◽  
SeyedAhmad SeyedAlinaghi ◽  
Nazanin Janfaza ◽  
Marcarious M. Tantuoyir
Keyword(s):  
Logistic Regression ◽  
Confidence Interval ◽  
Odds Ratio ◽  
Adjusted Odds Ratio ◽  
Laboratory Data ◽  
Hospitalized Patients ◽  
Multivariate Logistic Regression ◽  
Predictors Of Mortality ◽  
Laboratory Test Results ◽  
History Of

Objective: The coronavirus disease 2019 (COVID-19) has become a global pandemic. Timely and effective predictors of survival and death rates are crucial for improving the management of COVID-19 patients. In this study, we evaluated the predictors of mortality based on the demographics, comorbidities, clinical characteristics, laboratory findings, and vital signs of 500 patients with COVID-19 admitted at Imam Khomeini Hospital Complex, the biggest hospital in Tehran, Iran. Methods: Five hundred hospitalized laboratory-confirmed COVID-19 patients were included in this study. Subsequently, electronic medical records, including patient demographics, clinical manifestation, comorbidities, and laboratory test results were collected and analyzed. They were divided into two groups: expired and discharged. Demographics, clinical, and laboratory data were compared among the two groups. The related factors with death in the patients were determined using univariate and multivariate logistic regression approaches. Results: Among the 500 hospitalized patients, most patients were male (66.4% versus 33.6%). The expired group had more patients ⩾70 years of age compared with the discharged group (32.9% versus 16.3%, respectively). Almost 66% of the expired patients were hospitalized for ⩾5 days which was higher than the discharge group (26.9%). Patients with a history of opium use in the expired group were significantly higher compared to the discharged group (14.8% versus 8.6%, p = 0.04) as well as a history of cancer (15.5% versus 4.7%, p < 0.001). Out of the 500 patients with COVID-19, four patients (2.6%) were HIV positive, all of whom expired. Dyspnea (76.4%), fever (56.6%), myalgia (59.9%), and dry cough (67%) were the most common chief complaints of hospitalized patients. Age ⩾70 years (adjusted odds ratio = 2.49; 95% confidence interval, 1.02–6.04), being female (adjusted odds ratio = 2.06; 95% confidence interval, 1.25–3.41), days of hospitalization (adjusted odds ratio = 5.73; 95% confidence interval, 3.49–9.41), and having cancer (adjusted odds ratio = 3.23; 95% confidence interval, 1.42–7.39) were identified as independent predictors of mortality among COVID-19 patients. Conclusion: Discharged and expired COVID-19 patients had distinct clinical and laboratory characteristics, which were separated by principal component analysis. The mortality risk factors for severe patients identified in this study using a multivariate logistic regression model included elderly age (⩾70 years), being female, days of hospitalization, and having cancer.

scholarly journals 1438. Prevalence and Risk Factors for Extended Spectrum Betalactamases Among Hospitalized Patients with Community Acquired Pyelonephritis in Colombia

2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S801-S801
Author(s):  
Mariana Franco Rodríguez ◽  
Jorge Cortes
Keyword(s):  
Risk Factors ◽  
Escherichia Coli ◽  
Logistic Regression ◽  
Hospitalized Patients ◽  
Adult Patients ◽  
Charlson Score ◽  
Esbl Production ◽  
E Coli ◽  
Extended Spectrum ◽  
Tract Infections

Abstract Background Urinary tract infections (UTI) are the most frequent bacterial infection in hospitalized patients. Extented spectrum betalactamases (ESBL) producing bacteria causing UTI have become more prevalent. Escherichia coli (E. coli) is the most frequent ESBL producing bacteria isolated in UTI. This drug resistant organisms are associated with poorer outcomes for patients. In low income countries, approaching to and treating ESBL E. coli, represent a major challenge for health care centers. Methods A retrospective cohort of adult patients with community acquired pyelonephritis caused by Escherichia coli was identified in a tertiary hospital in Colombia. Susceptibility was performed with Vitek (BioMerieux, France); extended spectrum beta lactamase (ESBL) production was defined phenotypically. Inclusion criteria were adult patients hospitalized with a positive urine culture for E. coli. Demographic and clinical characteristics were searched in electronic records. Risk factors associated with ESBL production were identified by using a multivariate logistic regression analysis. Results During 7 years 817 patients with pyelonephritis caused by E. coli were identified. 79 (9.7%) of them were caused by ESBL producers. Women were 66% and 408 (74.8% of them) had menopause. Mean age was 64.2 years (standard deviation of 19.1). Of the cohort, 481 (561.1%) had at least some comorbidity and was frequent to find diabetes (18.5%), immunosuppression due to oncologic disease or medications (18.4%), urolithiasis or previous surgical procedures (17%). After logistic regression, risk factors identified to predict ESBL production, were: being a man (aOR 5.4, 2.1-18.2), a woman with menopause (aOR 2.9, 1.3 -9.9), and the Charlson score (aOR 0.83, 0.73 – 0.96). Previous antibiotic use was not related to ESBL infection. Conclusion In this relatively large cohort of patients with pyelonephritis caused by E. coli, ESBL production risk factors were not clearly identified other than sex and menopause. Curiously, Charlson score predicted a lower risk of resistance. Other factors (food consumptions and others) might be driving the resistance in the community in E. coli. Disclosures Jorge Cortes, MD, Pfizer (Research Grant or Support)

scholarly journals Models of Forecasting in Financial Analysis of Non-Financial Corporations

2018 ◽  
Author(s):  
Eva Litavcová ◽  
Sylvia Jenčová ◽  
Róbert Štefko
Keyword(s):  
Logistic Regression ◽  
Regression Models ◽  
Financial Analysis ◽  
Slovak Republic ◽  
Regression Method ◽  
Decision Makers ◽  
Logistic Regression Models ◽  
Financial Metrics ◽  
Logistic Regression Method ◽  
Probability Of Bankruptcy

Corporate Diagnosis is now recognized as an important tool by decision makers to predict and correct burgeoning problems that a corporation may face. Methods based on this model stem from the use of mathematics and are increasingly being applied in the analysis of production processes. The goal of this paper is to use a logistic regression to design a scoring model for non-financial corporations in industry. Based on the data obtained from the Registry of the Slovak Republic for 738 non-financial corporations, according to SK NACE 26, SK NACE 27, the proportional financial metrics, using the logistic regression method, were calculated. By applying these methods, two logistic regression models were found to reliably estimate the probability of bankruptcy for a firm.

scholarly journals The Classification of Customers’ Sentiment using Data Mining Approaches

2019 ◽  
Vol IV (IV) ◽  
pp. 146-156
Author(s):  
Dost Muhammad Khan ◽  
Tariq Aziz Rao ◽  
Faisal Shahzad
Keyword(s):  
Data Mining ◽  
Service Providers ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
Decision Makers ◽  
Supervised Machine Learning ◽  
Market Trends ◽  
Using Data

Data mining is a procedure of extracting the requisite information from unprocessed records by using certain methodologies and techniques. Data having sentiments of customers is of utmost importance for managers and decision-makers who intend to monitor the progress, to maintain the quality of their products or services and to observe the latest market trends for business support. Billions of customers are using micro-blogging websites and social media for sharing their opinions about different topics on daily basis. Therefore, it has become a source of acquiring information but to identify a particular feature of a product is still an issue as the information retrieves from varied sources. We proposed a framework for data acquisition, preprocessing, feature extraction and used three supervised machine-learning algorithms for classification of customers’ sentiments. The proposed framework also tested to evaluate the system’s performance. Our proposed methodology will be helpful for researchers, service providers, and decisionmakers.

Comparison of Examinees’ and Doctors’ Judgement of Health Status Using Data in an AMHTS

1984 ◽  
Vol 23 (01) ◽  
pp. 15-22
Author(s):  
Y. Sekita ◽  
T. Ohta ◽  
M. Inoue ◽  
H. Takeda
Keyword(s):  
Health Status ◽  
Discriminant Analysis ◽  
Explanatory Power ◽  
Laboratory Data ◽  
Subjective Symptom ◽  
Health Conditions ◽  
Testing System ◽  
Multiple Discriminant Analysis ◽  
Canonical Axis ◽  
Using Data

SummaryJudgements of examinees’ health status by doctors and by the examinees themselves are compared applying multiple discriminant analysis. The doctors’ judgements of the examinees’ health status are studied comparatively using laboratory data and the examinees’ subjective symptom data.This data was obtained in an Automated Multiphasic Health Testing System. We discuss the health conditions which are significant for the judgement of doctors about the examinees. The results show that the explanatory power, when using subjective symptom data, is fair in the case of the doctors’ judgement. We found common variables, such as nervousness, lack of perseverance etc., which form the first canonical axis.

scholarly journals Laboratory predictors of death from coronavirus disease 2019 (COVID-19) in the area of Valcamonica, Italy

2020 ◽  
Vol 58 (7) ◽  
pp. 1100-1105 ◽  
Author(s):  
Graziella Bonetti ◽  
Filippo Manelli ◽  
Andrea Patroni ◽  
Alessandra Bettinardi ◽  
Gianluca Borrelli ◽  
...  
Keyword(s):  
Hospital Stay ◽  
Clinical Decision Making ◽  
Troponin I ◽  
Laboratory Data ◽  
High Sensitivity ◽  
Clinical Decision ◽  
International Normalized Ratio ◽  
Serum Glucose ◽  
Hospital Death ◽  
Laboratory Findings

AbstractBackgroundComprehensive information has been published on laboratory tests which may predict worse outcome in Asian populations with coronavirus disease 2019 (COVID-19). The aim of this study is to describe laboratory findings in a group of Italian COVID-19 patients in the area of Valcamonica, and correlate abnormalities with disease severity.MethodsThe final study population consisted of 144 patients diagnosed with COVID-19 (70 who died during hospital stay and 74 who survived and could be discharged) between March 1 and 30, 2020, in Valcamonica Hospital. Demographical, clinical and laboratory data were collected upon hospital admission and were then correlated with outcome (i.e. in-hospital death vs. discharge).ResultsCompared to patients who could be finally discharged, those who died during hospital stay displayed significantly higher values of serum glucose, aspartate aminotransferase (AST), creatine kinase (CK), lactate dehydrogenase (LDH), urea, creatinine, high-sensitivity cardiac troponin I (hscTnI), prothrombin time/international normalized ratio (PT/INR), activated partial thromboplastin time (APTT), D-dimer, C reactive protein (CRP), ferritin and leukocytes (especially neutrophils), whilst values of albumin, hemoglobin and lymphocytes were significantly decreased. In multiple regression analysis, LDH, CRP, neutrophils, lymphocytes, albumin, APTT and age remained significant predictors of in-hospital death. A regression model incorporating these variables explained 80% of overall variance of in-hospital death.ConclusionsThe most important laboratory abnormalities described here in a subset of European COVID-19 patients residing in Valcamonica are highly predictive of in-hospital death and may be useful for guiding risk assessment and clinical decision-making.

scholarly journals 22. Description of Hospitalized Patients with Influenza Vaccine Failure

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S35-S35
Author(s):  
Joanna Kimball ◽  
Yuwei Zhu ◽  
Dayna Wyatt ◽  
Helen Talbot
Keyword(s):  
Logistic Regression ◽  
Influenza Vaccine ◽  
Influenza Vaccination ◽  
Older Patients ◽  
Influenza A ◽  
Influenza Season ◽  
Hospitalized Patients ◽  
Vaccine Failure ◽  
Increased Risk ◽  
Immunosuppressed Patients

Abstract Background Despite influenza vaccination, some patients develop illness and require hospitalization. Many factors contribute to vaccine failure, including mismatch of the vaccine and circulating strains, waning immunity, timing of influenza season, age and patient comorbidities such as immune function. This study compared vaccinated, hospitalized patients with and without influenza. Methods This study used 2015–2019 Tennessee data from the US Hospitalized Adult Influenza Vaccine Effectiveness Network database. Enrolled patients were ≥ 18 years vaccinated for the current influenza season and admitted with an acute respiratory illness. Patient or surrogate interviews and medical chart abstractions were performed, and influenza vaccinations were confirmed by vaccine providers. Influenza PCR testing was performed in a research lab. Statistical analyses were performed with STATA and R using Pearson’s chi-squared, Kruskal-Wallis and Wilcoxon rank-sum tests and multivariate logistic regression. Results 1236 patients met study criteria, and 235 (19%) tested positive for influenza. Demographics, vaccines and comorbidities were similar between the two groups (Table 1) except for morbid obesity, which was more common in influenza negative patients (13% vs 8%, p = 0.04), and immunosuppression, which was more common in the influenza positive (63% vs 54%, p = 0.01). Logistic regression analysis demonstrated older patients (OR 1.47, 95% CI 1.03–2.10) and immunosuppressed patients (OR 1.56, 1.15–2.12) were at increased risk for influenza (Table 2 and Figure 1). Immunosuppression also increased the risk for influenza A/H3N2 (OR 1.86, 95% CI 1.25–2.75). A sensitivity analysis was performed on patients who self-reported influenza vaccination for the current season without vaccine verification and demonstrated increased risk of influenza in older adults (OR 1.66, 95% CI 1.16–2.39). Table 1: Demographics of influenza positive versus influenza negative patients in influenza vaccinated, hospitalized patients. Table 2: Logistic regression analyses of vaccinated, hospitalized influenza positive patients; vaccinated, hospitalized patients with influenza A subtypes and self-reported vaccinated, hospitalized influenza positive patients. Figure 1: Predicted Probability of Hospitalization with Influenza, Influenza A/H1N1 and Influenza A/H3N2 in Vaccinated Patients by Age. Conclusion Our study demonstrated an increased risk of influenza vaccine failure in older patients and immunosuppressed patients. These groups are also at increased risk for influenza complications. To improve protection of these patients against future influenza illnesses, more effective vaccines are needed, and more research on ring vaccination should be pursued. Disclosures All Authors: No reported disclosures

Sign in / Sign up

Export Citation Format

Share Document