جستجوی مقالات مرتبط با کلیدواژه "‎logistic regression model" در نشریات گروه "پزشکی"

Spinal muscular atrophy is an inherited neurodegenerative disorder that typically leads to severe physical disability. The present study aimed to determine the subjective evaluation of this disorder screening and analyze its influencing factors in Iran.‎    

A cross-sectional study was performed using data from the second survey of women either pregnant or planning to become pregnant in Tehran, the capital of Iran, in 2022. The dependent variable was the willingness to pay for this disease screening test. The independent variables included sociodemographic, economic, and health characteristics, the history of this disease or other diseases of the person and family, and knowledge about this disease in the included population. Logistic regression was utilized to identify independent variables associated with the dependent variable, and the results were reported as unadjusted and adjusted odds ratios and P values with 95% CIs. A questionnaire was used as a research tool, and STATA 17 software was used for data analysis. The monetary value of spinal muscular atrophy (SMA) screening was calculated by estimating willingness to pay using the congenital valuation method.   

In total, 578 women were included. About 64.85% of respondents had a willingness to pay for SMA screening as the dependent variable, with a mean of $526. University education (P = 0.009) and pregnancy experience (P = 0.021) were associated with the dependent variable.  

Iranian women expressed their willingness to undergo screening tests, but due to financial constraints, they expected the government and nongovernmental organizations to bear most of the cost.

Background and

Evaluating the causal association effect of risk factors is essential in estimating the mortality rate among COVID-19 patients. Much research has been conducted to assess the impact of COVID-19 on death in various countries worldwide. However, few studies have addressed the effect of causal association of risk factors. This study aims to address this gap by estimating the impact of COVID-19 on death by evaluating the causal association with the risk factors. 

The research population included all inpatients with initial COVID-19 symptoms, confirmed by their PCR test results. They were admitted to hospitals affiliated with Golestan University of Medical Science, Golestan, Iran, in 2020. We employed the propensity score method, an effective statistical technique for evaluating the causal association effect of risk factors in observational studies. We also used the student and chi-squared tests to compare the differences between the two study groups.

We used the propensity score matching estimation approach and logistic regression analysis for comparison. Of 6379 inpatients, 5581 (87.5%) were discharged or recovered, and 798 (12.5%) died. The causal association between treatment results (discharged vs died) and variables of PCR test, SpO2, gender, age, and hospitalization duration in ICU were statistically significant. 

The propensity score matching estimation method revealed a high risk of death in patients with PCR+ test diagnosis. Specifically, using this approach, the above-measured risk factors increased the chance of death in patients with PCR+ to 72%. However, the traditional multiple logistic regression model estimated the risk of death at 46%, suggesting potential underestimation. This disparity might be due to better control of the effect of the above-measured risk factors by the propensity score matching. Therefore, the former estimating approach is more effective in assessing the impact of COVID-19 on death.

In clinical practices, multiple biomarkers are frequently used on the same subjects for diagnosis of an adverse outcome. This study compares two alternative multiple linear regression approaches as the logistic regression model and the discriminant function score in combing several markers.

Ten thousand simulated data sets were generated from binormal and non-binormal pairs of distributions with different sample sizes and correlation structures. Each dataset underwent a logistic regression and the discriminant analysis simultaneously. The ROC analysis was performed with each marker alone and also their combining scores. For two alternative approaches, the average of AUC and its root mean square error (RMSE) were estimated over 10000 replications trials for all configurations and sample sizes used. The practical utility of the two methods is further illustrated with a clinical example of real data as well.

The two approaches yielded identical accuracy in particular with binormal data. With non- binormal data, the logistic regression risk score produced an equal or a slightly better accuracy than the discriminate function score.

Overall, the two approaches yield rather identical results. However, adopting the logistic regression model may incorporate slightly better accuracy index than discriminant analysis with non-binormal data.

 Reducing infant mortality in the whole world is one of the millennium development goals.The aim of this study was to determine the factors related to infant mortality using data mining algorithms.

 This population-based case-control study was conducted in eight provinces of Iran. A sum of 2,386 mothers (1,076 cases and 1,310 controls) enrolled in this study. Data were extracted from health records of mothers and filled with checklists in health centers. We employed several data mining algorithms such as AdaBoost classifier, Support Vector Machine, Artificial Neural Networks, Random Forests, K-nearest neighborhood, and Naïve Bayes in order to recognize the important predictors of infant death; binary logistic regression model was used to clarify the role of each selected predictor.

 In this study, 58.7% of infant mortalities occurred in rural areas, that 55.6% of them were boys. Moreover, Naïve Bayes and Random Forest were highly capable of predicting related factors among data mining models. Also, the results showed that events during pregnancy such as dental disorders, high blood pressure, loss of parents, factors related to infants such as low birth weight, and factors related to mothers like consanguineous marriage and gap of pregnancy (< 3 years) were all risk factors while the age of pregnancy (18 - 35 year) and a high degree of education were protective factors.

 Infant mortality is the consequence of a variety of factors, including factors related to infants themselves and their mothers and events during pregnancy. Owing to the high accuracy and ability of modern modeling compared to traditional modeling, it is recommended to use machine learning tools for indicating risk factors of infant mortality.

Pakistan, a country with a 27 high burden countries of multidrug resistance tuberculosis. To predict the associated risk factors and proportion of loss to follow up among MDR-TB patients treated at PMDT sites of Punjab from 2017 to 2019.

This case control study based on the standardized reporting and recording case record forms called as Electronic Nominal Review System (ENRS) of National TB Control Program, Pakistan. A logistic regression model was used to assess risk factors of lost to follow up MDR-TB patients.

A total of 539 patients with MDR-TB were included in the final analysis. Among them, 207 patients (7.5%) had lost to follow up outcome at the end of the study. MDR-TB lost to follow up patients were more likely to report older age (AOR: 1.40, CI: 1.14-1.71, p=0.000),  history of lost to follow up from first line drugs treatment (AOR: 0.39, CI: 0.28-0.56, p=0.000), co-morbid (AOR:1.54, CI: 1.24-1.91, p=0.000), adverse reaction of second line drugs (AOR: 0.45, CI: 0.37-0.56, p=0.000), long distance between patient’s home and PMDT site (AOR: 0.68, CI: 0.52-0.89, p=0.001).

The history of lost to follow up from first line drugs treatment, co-morbid, older age and long distance were independent risk factors of MDR-TB. Proper training for PMDT sites staff, friendly follow up services and psychological counseling may help to reduce lost to follow up.