Logistic Regression Prediction Model for Cardiovascular Disease

2020 ◽  
Vol 7 (1) ◽  
pp. 33-38
Author(s):  
Tania Ciu ◽  
Raymond Sunardi Oetama
Keyword(s):  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Analysis Data ◽  
Research Area ◽  
Unhealthy Lifestyle ◽  
Patient Medical Record ◽  
Regression Algorithms ◽  
Main Factors ◽  
Class Labels ◽  
Logistic Regression Algorithm

— It is undeniable that cardiovascular disease is the number one cause of death in the world. Various factors such as age, cholesterol level, and unhealthy lifestyle can trigger cardiovascular disease. The symptoms of cardiovascular disease are also challenging to identify. It takes careful understanding and analysis related to patient medical record data and identification of the parameters that cause this disease. This study was conducted to predict the main factors causing cardiovascular disease. In this study, a dataset consisting of 14 attributes with class labels was used as the basis for identification as a link between factors that cause cardiovascular disease. The research area used is the area of ​​analysis data where the analyzed data are on factors that influence the presence of cardiovascular disease in the State of Cleveland. In predicting cardiovascular disease, a logistic regression algorithm will be used to see the interrelation between the dependent variable and the independent variables involved. With this research, it is expected to be able to increase readers' knowledge and insight related to how to analyze cardiovascular disease using logistic regression algorithms and the main factors that cause cardiovascular disease.

scholarly journals Study of a Privacy Preserving Logistic Regression Algorithm (PPLRA) For Data Privacy in the Context of Big Data

2021 ◽  
Vol 2083 (3) ◽  
pp. 032059
Author(s):  
Qiang Chen ◽  
Meiling Deng
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Privacy Protection ◽  
Data Privacy ◽  
Absolute Error ◽  
Average Absolute Error ◽  
Regression Algorithms ◽  
Hadoop Platform ◽  
Logistic Regression Algorithm ◽  
Computing Speed

Abstract Regression algorithms are commonly used in machine learning. Based on encryption and privacy protection methods, the current key hot technology regression algorithm and the same encryption technology are studied. This paper proposes a PPLAR based algorithm. The correlation between data items is obtained by logistic regression formula. The algorithm is distributed and parallelized on Hadoop platform to improve the computing speed of the cluster while ensuring the average absolute error of the algorithm.

scholarly journals Model for predicting heart failure using Random Forest and Logistic Regression algorithms

2021 ◽  
Vol 1208 (1) ◽  
pp. 012039
Author(s):  
Vedran Grgić ◽  
Denis Mušić ◽  
Elmir Babović
Keyword(s):  
Heart Failure ◽  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Feature Selection ◽  
Random Forest ◽  
Feature Selection Method ◽  
Selection Method ◽  
Random Forest Algorithm ◽  
Regression Algorithms ◽  
Significant Factors

Abstract The paper analyzes the cardiovascular parameters of patients with heart disease. The aim of this study was to predict death in a patient with cardiovascular disease based on 12 parameters, using Random Forest and Logistic Regression algorithms. Parameters were tuned for both algorithms to determine the best settings. The most significant factors in the process predicted were found using the FEATURE SELECTION method of both algorithms. By comparative analysis of the obtained results, the highest accuracy of 90% was obtained using the Random Forest Algorithm.

scholarly journals Google Play Content Scraping and Knowledge Engineering using Natural Language Processing Techniques with the Analysis of User Reviews

2020 ◽  
Vol 30 (1) ◽  
pp. 192-208 ◽  
Author(s):  
Hamza Aldabbas ◽  
Abdullah Bajahzar ◽  
Meshrif Alruily ◽  
Ali Adil Qureshi ◽  
Rana M. Amir Latif ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Language Processing ◽  
Mobile Application ◽  
Knowledge Engineering ◽  
Machine Learning Algorithms ◽  
Application Development ◽  
User Reviews ◽  
N Gram ◽  
Logistic Regression Algorithm ◽  
Google Play

Abstract To maintain the competitive edge and evaluating the needs of the quality app is in the mobile application market. The user’s feedback on these applications plays an essential role in the mobile application development industry. The rapid growth of web technology gave people an opportunity to interact and express their review, rate and share their feedback about applications. In this paper we have scrapped 506259 of user reviews and applications rate from Google Play Store from 14 different categories. The statistical information was measured in the results using different of common machine learning algorithms such as the Logistic Regression, Random Forest Classifier, and Multinomial Naïve Bayes. Different parameters including the accuracy, precision, recall, and F1 score were used to evaluate Bigram, Trigram, and N-gram, and the statistical result of these algorithms was compared. The analysis of each algorithm, one by one, is performed, and the result has been evaluated. It is concluded that logistic regression is the best algorithm for review analysis of the Google Play Store applications. The results have been checked scientifically, and it is found that the accuracy of the logistic regression algorithm for analyzing different reviews based on three classes, i.e., positive, negative, and neutral.

Patients Living With HIV Are Less Likely to Receive Appropriate Statin Therapy for Cardiovascular Disease Risk Reduction

2021 ◽  
pp. 089719002199979
Author(s):  
Roshni P. Emmons ◽  
Nicholas V. Hastain ◽  
Todd A. Miano ◽  
Jason J. Schafer
Keyword(s):  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Statin Therapy ◽  
Risk Reduction ◽  
Blood Cholesterol ◽  
Control Group ◽  
Atherosclerotic Cardiovascular Disease ◽  
Ascvd Risk ◽  
Living With Hiv ◽  
To Receive

Background: Recent studies suggest that statins are underprescribed in patients living with HIV (PLWH) at risk for atherosclerotic cardiovascular disease (ASCVD), but none have assessed if eligible patients receive the correct statin and intensity compared to uninfected controls. Objectives: The primary objective was to determine whether statin-eligible PLWH are less likely to receive appropriate statin therapy compared to patients without HIV. Methods: This retrospective study evaluated statin eligibility and prescribing among patients in both an HIV and internal medicine clinic at an urban, academic medical center from June-September 2018 using the American College of Cardiology/American Heart Association guideline on treating blood cholesterol to reduce ASCVD risk. Patients were assessed for eligibility and actual treatment with appropriate statin therapy. Characteristics of patients appropriately and not appropriately treated were compared with chi-square testing and predictors for receiving appropriate statin therapy were determined with logistic regression. Results: A total of 221/300 study subjects were statin-eligible. Fewer statin-eligible PLWH were receiving the correct statin intensity for their risk benefit group versus the uninfected control group (30.2% vs 67.0%, p < 0.001). In the multivariable logistic regression analysis, PLWH were significantly less likely to receive appropriate statin therapy, while those with polypharmacy were more likely to receive appropriate statin therapy. Conclusion: Our study reveals that PLWH may be at a disadvantage in receiving appropriate statin therapy for ASCVD risk reduction. This is important given the heightened risk for ASCVD in this population, and strategies that address this gap in care should be explored.

Abstract 17220: Risk Factors for Recurrent Peripartum Cardiomyopathy in 783 Women in California

Circulation ◽  
2018 ◽  
Vol 138 (Suppl_1) ◽  
Author(s):  
Punag Divanji ◽  
Gregory Nah ◽  
Ian Harris ◽  
Anu Agarwal ◽  
Nisha I Parikh
Keyword(s):  
Risk Factors ◽  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Regression Models ◽  
Subsequent Pregnancy ◽  
Peripartum Cardiomyopathy ◽  
Lv Function ◽  
Logistic Regression Models ◽  
Grand Multiparity ◽  
Adjusted Logistic Regression

Introduction: Characterized by significant left ventricular (LV) dysfunction and clinical heart failure (HF), peripartum cardiomyopathy (PPCM) has an incidence of approximately 1/2200 live births (0.04%). Prior studies estimate that approximately 25% of those with recovered LV function will have recurrent clinical PPCM during subsequent pregnancies, compared to 50% of those without recovered LV function. Specific predictors of recurrent PPCM have not been studied in cohorts with large numbers. Methods: From 2005-2011, we identified 1,872,227 pregnancies by International Classification of Diseases, 9th Revision (ICD-9) codes in the California Healthcare Cost and Utilization Project (HCUP) database, which captures over 95% of the California hospitalized population. Excluding 15,765 women with prior cardiovascular disease (myocardial infarction, coronary artery disease, stroke, HF, valve disease, or congenital heart disease), yielded n=1,856,462 women. Among women without prior cardiovascular disease, we identified index and subsequent pregnancies with PPCM to determine episodes of recurrent PPCM. We considered the following potential predictors of PPCM recurrence in both univariate and age-adjusted logistic regression models: age, race, hypertension, diabetes, smoking, obesity, chronic kidney disease, family history, pre-eclampsia, ectopic pregnancy, income, and insurance status. Results: In HCUP, n=783 women had pregnancies complicated by PPCM (mean age=30.8 years). Among these women, n=133 had a subsequent pregnancy (17%; mean age=28.1 years), with a mean follow-up of 4.34 years (±1.71 years). In this group of 133 subsequent pregnancies, n=14 (10.5%) were complicated by recurrent PPCM, with a mean time-to-event of 2.2 years (±1.89 years). Among the risk factors studied, the only univariate predictor of recurrent PPCM was grand multiparity, defined as ≥ 5 previous deliveries (odds ratio: 22; 95% confidence interval 4.43-118.22). The other predictors we studied were not significantly associated with recurrent PPCM in either univariate or multivariable models. Conclusion: In a large population database in California with 783 cases of PPCM over a 6-year period, 17% of women had a subsequent pregnancy, of which 10.5% had recurrent PPCM. In age-adjusted logistic regression models, grand multiparity was the only statistically significant predictor of recurrent PPCM.

MO120STONE COMPOSITION AND CARDIOVASCULAR DISEASE  IN PATIENTS WIITH NEPHROLITHIASIS

2021 ◽  
Vol 36 (Supplement_1) ◽  
Author(s):  
Ana Lucía Valencia ◽  
Armando Coca ◽  
Arturo Lorenzo ◽  
Veronica Fidalgo ◽  
Vicente Perez ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Chronic Kidney Disease ◽  
Logistic Regression ◽  
Uric Acid ◽  
Regression Analysis ◽  
Kidney Disease ◽  
Kidney Stone ◽  
Stone Disease ◽  
Stone Composition ◽  
Adjusted Logistic Regression

Abstract Background and Aims Kidney stone disease is widely prevalent in the general population and has been associated with multiple comorbidities including hypertension, diabetes, chronic kidney disease and cardiovascular disease. We aimed to describe the possible link between stone composition and cardiovascular disease and its differential effect among women and men. Method Retrospective review of patients with known stone composition seen in a nephrolithiasis unit in the last five years. Anthropometric and clinical data were gathered from the hospital records. Stone composition was defined as such if ≥50% of the stone was made from a single component. Cardiovascular disease included coronary artery disease, stroke and peripheral vascular disease. Unadjusted and adjusted logistic regression analysis were applied to describe the potential relationship between stone composition and cardiovascular disease. Results 337 patients were included in the study sample. Median age was 57 (IQR 47-67), 61.1% males. 58.2% suffered from recurrent stone disease and 28.5% from family history of stone formation. 32.9% of patients had hypertension, 22,4% diabetes and 13,1% chronic kidney disease. The most common kidney stone component was calcium oxalate (38.6%) followed by calcium phosphate (21.3%), uric acid (14.2%), struvite (8%) and brushite (0.9%). Only uric acid as main stone component was associated with cardiovascular disease among men but not women in our sample in univariate analysis. That relationship was lost in adjusted logistic regression analysis. Conclusion Calcium oxalate and phosphate were the most common components of kidney stones. No relationship was found between stone composition and cardiovascular disease in the study sample.

Abstract 17309: Scope and Determinants of Nonfinancial Barriers to Healthcare Access in Individuals With Atherosclerotic Cardiovascular Disease

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Isaac Acquah ◽  
Javier Valero-Elizondo ◽  
Miguel Cainzos Achirica ◽  
Rahul Singh ◽  
Karan Shah ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Low Income ◽  
Barriers To Care ◽  
Multinomial Logistic Regression ◽  
The Elderly ◽  
Atherosclerotic Cardiovascular Disease ◽  
The Us ◽  
Barriers To Healthcare ◽  
Relative Prevalence

Introduction: Barriers to healthcare - financial and nonfinancial - may result in unmet health needs and adverse outcomes. Despite this, the nonfinancial barriers to care among adults with atherosclerotic cardiovascular disease (ASCVD) is poorly defined in the US. We aimed to explore the scope and determinants of nonfinancial barriers to care among individuals with ASCVD. Methods: We analyzed data from the 2013-17 National Health Interview Survey (NHIS). We included adults with self-reported ASCVD (heart attack, angina, and/or stroke). Nine key variables in the NHIS that represent nonfinancial barriers to healthcare were assessed as absent/present, and participants were classified as having 0-1, 2, or ≥3 barriers. Multinomial logistic regression (using 0-1 nonfinancial barriers as reference) was used to evaluate the relationship between various sociodemographic factors, and an increasing number of nonfinancial barriers. Results: Of all the 15,758 adults with ASCVD (8.1% annually in the US; representing 19.6 million), 23.4% reported having at least one nonfinancial barrier to care while 4.9% reported 3 nonfinancial barriers. In a multivariable multinomial logistic regression, after stratifying by age, individuals from low-income families had an almost 2-fold relative prevalence of 3 nonfinancial barriers ( Figure) . In the elderly, however, lack of insurance was the strongest predictor (relative prevalence ratio of 6.51 [95% confidence interval; 2.25, 18.87]) of having ≥3 barriers. Conclusion: Among adults with ASCVD, the relative prevalence of ≥3 nonfinancial barriers was low (4.9%) with low-income being the only modifiable predictor of reporting ≥3 nonfinancial barriers and lack of insurance being the strongest predictor in the elderly. Addressing financial barriers to healthcare may help alleviate these nonfinancial barriers.

Study on the Optimal Use of Land from the Perspective of Soil Ecological Value

2014 ◽  
Vol 908 ◽  
pp. 366-369
Author(s):  
Yan Ling Hu ◽  
Zeng Lei Xi ◽  
Li Hong Li
Keyword(s):  
Factor Score ◽  
Factor Model ◽  
Research Area ◽  
Single Factor ◽  
Ecological Value ◽  
Soil Resources ◽  
Soil Function ◽  
Functional Value ◽  
Main Factors

In order to achieve the optimal use of soil resources,not only the soil function value in research area should be calculated scientifically,but also some practical methods and tools should be researched in planning.The article took five districts of Zhengzhou city as research area,and took functional value indexes data in factor model,then get four main factors,correlation between each other is very weak.According to the factor score,the article analysed how to use the conclusion comprehensively from two aspects: single factor and integrated factor.

Sign in / Sign up

Export Citation Format

Share Document