Showing 8 results for Models
M Sedehi, Y Mehrabi, A Kazemnejad, V Joharimajd, F Hadaegh,
Volume 6, Issue 4 (3-2011)
Abstract
Background & Objective: Mixed outcomes arise when, in a multivariate model, response variables measured on different scales such as binary and continuous. Artificial neural networks (ANN) can be used for modeling in situations where classic models have restricted application when some of their assumptions are not met. In this paper, we propose a method based on ANNs for modeling mixed binary and continuous outcomes.
Methods: Univariate and bivariate models were evaluated based on two different sets of simulated data. The scaled conjugate gradient (SCG) algorithm was used for optimization. To end the algorithm and finding optimum number of iteration and learning coefficient, mean squared error (MSE) was computed. Predictive accuracy rate criterion was employed for selection of appropriate model. We also used our model in medical data for joint prediction of metabolic syndrome (binary) and HOMA-IR (continues) in Tehran Lipid and Glucose Study (TLGS). The codes were written in R 2.9.0 and MATLAB 7.6.
Results: The predictive accuracy for univariate and bivariate models based on simulated dataset Ι, where two outcomes associated with a common covariate, were shown to be approximately similar. However, in simulated dataset ΙΙ in which two outcomes associated with different covariates, predictive accuracy in bivariate models were seen to be larger than that of univariate models.
Conclusions: It is indicated that the predictive accuracy gain is higher in bivariate model, when the outcomes share a different set of covariates with higher level of correlation between the outcomes.
H Soori, A Ansarifar, F Mubasheri, A Mahmoudlou, Z Noorafkan, M Bakhtiari,
Volume 7, Issue 4 (3-2012)
Abstract
Normal
0
false
false
false
EN-US
X-NONE
AR-SA
The relationship between
two things if one is another originator or creator, called causality. Although this
concept is not specified to Medical Sciences and Epidemiology, the importance
of this issue is more highlighted in the field of epidemiology. Causation is
the most basic concepts in empirical sciences and is still under discussion
because it is dependent on the basis of any scientific laws without acceptance
something cease causality is impossible. With the increasing development of
science as well as epidemiology, causality has found a broader concept and its
application in analytical studies and logical interpretation of the results of
this type of study, has a wider dimension. Due to developing new epidemiology
courses at medical universities and increase the number of students, it is felt
to talk more about the causality concept. In this review causality concepts in
the humanities is overviewed, its history is briefly described, the causality
of Medical Epidemiology and also Islamic religion is considered, then the
causality framework, and models to interpret the conventional causality will be
discussed.
Aa Akhlaghi, M Hosseini, M Mahmoodi, M Shamsipour, E Najafi,
Volume 8, Issue 2 (9-2012)
Abstract
Background & Objectives: Peritoneal
dialysis is one of the most common types of dialysis in patients with renal
failure. However multivariate analysis such as log- rank test and Cox have
usually used to evaluate association of risk factors in survival of this group
of patients, the aim of this study was to perform of Weibull, Gamma, Lognormal and
Logistic Mixture cure models in survival analysis of these patients.
Methods: Data
of 433 patients undergoing CAPD who registered in two centers in Tehran, Iran
between 1997 to 2009 were used in this analysis. We investigated center,
gender, age, cholesterol, Low Density Lipoprotein (LDL), High density
lipoprotein (HDL), triglyceride, albumin, hemoglobin, creatinine, Fasting Blood
Sugar (FBS), calcium and phosphorous as variables effect with Kaplan-Meier and
cure model. CUREREGR module was used for survival analysis.
Results: Comparison
of AIC (Akaike Information Criterion) of Weibull, Gama, Lognormal and Logistic
Mixture cure models showed that Weibull distribution AIC is lower for almost
all variables than other distributions. Weibull distribution has better fitness
for data than others. In the multivariate Weibull model, age and albumin
variables had significant effect on long-term survival of patients (P<0.01).
Triglycerides effect on long-term survival had borderline (P = 0.065). Also
HDL, FBS and calcium were significant on short term survival (P<0.01) but
significance of LDL was borderline (P=0.088).
Conclusion: Cure models have the ability to analyze
dialysis patients' survival data and can differentiate long-term survival from short-
term survival. The interpretation of survival data with these statistical
models could be more accurate and would help to make better prediction for
patients by health care professionals.
A Saki Malehi , E Hajizadeh, K Ahmadi, P Mansouri,
Volume 10, Issue 1 (6-2014)
Abstract
Background and Objectives : The aim of this study was to assess the disease trajectory and recurrence rate of pemphigus based on the analysis of the gap time between successive recurrent events. In this regard, the most important associated factors with the risk of recurrence could be explained.
Methods: This longitudinal study was performed on 112 pemphigus patients who attended the dermatology department of Imam Khomeini Hospital, Tehran, Iran, from March 2006 to January 2013. The study duration was considered from the diagnosis of the disease to December 2013. Recurrent events were analyzed based on the gap time between successive events using the multivariate time dependent frailty model. The time between two recurrent gap times was determined monthly between two successive events.
Results : Decreasing the gap times between two successive events indicates that the subsequent event after the first recurrence occurs with shorter time intervals. So, the disease trajectory represents an increase in the recurrence rate over time. Based on the results of multivariate frailty model, IgG antibody's level was the only effective factor on the recurrence hazard rate of the patients. Also, this model proved that the frailty effects were time dependent frailties.
Conclusion: Assessing the disease trajectory and recurrence hazard rate can be achieved through analyzing the gap time between successive recurrent events. This analysis also identifies the factors that influence the risk of subsequent recurrent events.
Z Asadollahi, P Jafari, M Rezaeian,
Volume 10, Issue 1 (6-2014)
Abstract
Background & Objectives: Due to the increasing tendency to measure the quality of life in recent years and the extensive quality of life questionnaires, it is important to determine the appropriate method of analyzing data derived from these studies. The aim of the present study was to introduce ordinal logistic regression models as an appropriate method for analyzing the data of quality of life.
Methods: The data was derived from a cross-sectional study on quality of life survey of 938 students. For data analysis, two binary logistic regression models and ordinal logistic regression models were used and the results of these models were compared.
Results: The results of goodness of fit showed that all three models were fitted well. Based on the ordinal logistic regression models, the three variables out of the explanatory variables were statistically associated with the response while based on the binary logistic regression model, after combining two categories of response variable, only two variables were significant. Therefore, combining the categories of the response variable should be avoided as much as possible because it may lead to data loss due to ignoring some of the response categories.
Conclusion: It is concluded that to analyze quality of life data, due to the nature of the response variable, ordinal logistic regression models are recommended considering the fewer parameter estimates and easier interpretation of the results
H Sharifi, Aa Haghdoost,
Volume 11, Issue 1 (6-2015)
Abstract
Background & Objectives : Management of time-dependent variables is the advantages of survival analysis. This study compares time-dependent and -independent variables in survival analysis in culling of dairy cows.
Methods: In this historical cohort, 7067 dairy cows in the Province of Tehran were recruited. Cows were followed to the next calving or culling. Data on the occurrence of health disorders, calving season, parity, and milk production was obtained. Model 1 treated diseases as time-independent covariates. In models 2, up to 5 diseases were considered time-dependent covariates. For each observation, we split follow-up time in intervals each corresponding to a different lactation month using Lexis expansion of the original dataset. Model 2 assumed that an animal experienced a certain disease from the beginning of the occurrence of that disease by the end of the period. Model 3 assumed that cows were at risk from the begging of the study until the disease occurred (inverse of model 2). In models 4 and 5, an animal was assumed to experience a certain disease for 1 month if the disease occurred during this period. In Model 4 assumed diseases occurred only one time, and in model 5, multiple disease occurrences at different months were considered as different episodes.
Results : AIC in model 1 and 5 was 10809 and 10366 moreover, BIC was 10926 and 10528. According to this numbers and the shape of the Cox-Snell Residuals, model 5 with Gompertz distribution was the best model.
Conclusion : Models without time dependency tended to seriously underestimate the risk of a disease on culling.
M Teimouri , E Ebrahimi, Sm Alavinia,
Volume 11, Issue 4 (3-2016)
Abstract
Background and Objectives: Diabetic patients are always at risk of hypertension. In this paper, the main goal was to design a native cost sensitive model for the diagnosis of hypertension among diabetics considering the prior probabilities.
Methods: In this paper, we tried to design a cost sensitive model for the diagnosis of hypertension in diabetic patients, considering the distribution of the disease in the general population. Among the data mining algorithms, Decision Tree, Artificial Neural Network, K-Nearest Neighbors, Support Vector Machine, and Logistic Regression were used. The data set belonged to Azarbayjan-e-Sharqi, Iran.
Results: For people with diabetes, a systolic blood pressure more than 130 mm Hg increased the risk of hypertension. In the non-cost-sensitive scenario, Youden's index was around 68%. On the other hand, in the cost-sensitive scenario, the highest Youden's index (47.11%) was for Neural Network. However, in the cost-sensitive scenario, the value of the imposed cost was important, and Decision Tree and Logistic Regression show better performances.
Conclusion: When diagnosing a disease, the cost of miss-classifications and also prior probabilities are the most important factors rather than only minimizing the error of classification on the data set.
F Feizmanesh, Aa Safaei,
Volume 14, Issue 3 (12-2018)
Abstract
Background and Objectives: Pulmonary embolism is a potentially fatal and prevalent event that has led to a gradual increase in the number of hospitalizations in recent years. For this reason, it is one of the most challenging diseases for physicians. The main purpose of this paper was to report a research project to compare different data mining algorithms to select the most accurate model for predicting pulmonary embolism in hospitalized patients. This model would provide the knowledge needed by the medical staff fir better decision making.
Methods: In this research, we designed a prediction model using different methods of machine learning that would best predict the probability of pulmonary embolism in patients at risk. Among data mining algorithms, Bayesian network, decisions tree (J48), logistic regression (LR), and sequential minimal optimization (SMO) were used. The data used in the study included risk factors and past history of patients admitted to the Lung Department of Shariati Hospital, Tehran, Iran.
Results: The results showed that the accuracy and specificity of all prediction models were satisfactory. The Bayesian model had the highest sensitivity in predicting pulmonary embolism.
Conclusion: Although the results showed a little difference in the performance of prediction models, the Bayesian model is a more appropriate tool to predict the occurrence of pulmonary embolism in hospitalized patients in this type of data. It can be considered a supportive approach along medical decisions to improve disease prediction.
