Showing 6 results for Biglarian
A Biglarian, E Hajizadeh, A Kazemnejad,
Volume 6, Issue 3 (11 2010)
Abstract
Background & Objective: Using parametric models is common approach in survival analysis. In the recent years, artificial neural network (ANN) models have increasingly used in survival prediction. The aim of this study was to predict of survival rate of patients with gastric cancer by using a parametric regression and ANN models and compare these methods.
Methods: We used the data of 436 gastric cancer patients from a cancer registry in Tehran between 2002-2007. All patients had a confirmed diagnosis. Data were randomly divided into two groups: training and testing (or validation) set. For analysis of data we used a parametric model (exponential, Weibull, normal, lognormal, logistic and log-logistic models) and a three layer ANN model. In order to compare of the prediction of two models, we used the area under receiver operating characteristic (AUROC) curve, classification table and concordance index.
Results: The prediction accuracy of the ANN and the parametric (Weibull) models were 79.45% and 73.97% respectively. The AUROC for the ANN and the Weibull models were 0.815 and 0.748 respectively.
Conclusions: The ANN had a better predictions than the Weibull model. Thus it is suggested to use of the ANN model survival prediction in field of cancer.
S Zare Delavar , E Bakhshi, F Soleimani, A Biglarian,
Volume 10, Issue 2 (Vol 10, No 2 2014)
Abstract
Background & Objectives : The identification of risk factors and their interactions is important in medical studies. The aim of this study was to identify the interaction of risk factors of cerebral palsy in 1-6 years-old children with classification regression methods.
Methods : The data of this cross-sectional study which was conducted on 225 children aged 1-6 years was collected during 2008- 2009. Classification regression methods (classification and regression tree (CART), adapting boosting (AdaBoost), bagging, and C4.5 algorithm) were used to identify interactions between risk factors. Data analysis was carried out with R3.0.1 software.
Results : The identified interactions of the factors by a) the AdaBoost method were (consanguinity: sex, previous pregnancies: vaginal delivery, consanguinity: sex: preterm, history of the disease: preterm: asphyxia, consanguinity: sex: asphyxia, history of the disease: sex: small size relative to gestational age, neonatal infection: asphyxia: small size relative to gestational age, history of the disease: sex: asphyxia, preterm: asphyxia: vaginal delivery) by b) the bagging method were (consanguinity: asphyxia, consanguinity: preterm: asphyxia), by c) the C4.5 algorithm were (asphyxia: preterm, asphyxia: consanguinity: history of the disease: preterm), and by d) the CART method were (asphyxia: consanguinity). The sensitivity and specificity of the AdaBoost method was better than other methods (0.941±0.029 and 0.951±0.030, respectively).
Conclusion : The AdaBoost method could better recognize and model potential interactions between risk factors of cerebral palsy.
S Masoudi, F Pourdanesh, A Biglarian, M Rahgozar,
Volume 11, Issue 4 (Vol 11, No.4, Winter 2016 2016)
Abstract
Background and Objectives: The aim of this study was to analyze the risks of local recurrence, second primary tumor, and metastasis in oral squamous cell carcinoma (OSCC) patients and to present their prognosis after treatment.
Methods: In this retrospective cohort study, 147 patients with oral squamous cell carcinoma (OSCC) who were older than 40 years were included using the data of 1973–2010 Surveillance, Epidemiology, and End Results (SEER) Program in the United States. The variables included gender, race, stage, histologic grade, tumor site, treatment modalities, and dates of diagnosis and death. Markov Multistate model was used for analysis.
Results: At a median follow-up of 33 months, local recurrence, second primary tumor, and distant metastasis rates were 34.01%, 85.03%, and 17.01% respectively and 40.13% of the patients died. Patients with cervical lymph nodes were at risk of second primary tumor 1.37 (1.05-2.05) times higher than early stage patients and were 2.33 (1.29-4.18) times more likely to die. After one year, the risk of death for patients with local recurrence or second primary tumor was almost similar but after 5 years, the risk of death was higher for local recurrence than second primary tumor.
Conclusion: Awareness of the next state and its time with respect to the patient’s clinical status can be one of the appropriate methods for timely diagnosis and treatment to reduce the mortality rate of OSCC patients.
R Ali Akbari Khoei, E Bakhshi, A Azarkeivan, A Biglarian,
Volume 12, Issue 3 (Vol 12, No 3 2016)
Abstract
Background and Objectives: A small sample size can influence the results of statistical analysis. A reduction in the sample size may happen due to different reasons, such as loss of information, i.e. existing missing value in some variables. This study aimed to apply bootstrap and jackknife resampling methods in survival analysis of thalassemia major patients.
Methods: In this historical cohort study, the data of 296 patients with thalassemia major who were visited at Zafar Clinic, Tehran, from 1994 to 2013 were used. Parametric survival models were used to analyze the data. The log – normal survival model was selected as the best model and then the bootstrap and jackknife resampling algorithms were used for this model. Data analysis was carried out with the STATA 12.0 software.
Results: The results of the resampling methods showed that standard errors decreased and confidence intervals were shortened. In addition, the result of the bootstrap and jackknife resampling methods showed that age group and the relationship of the parents (P<0.001) were significant compared with the log-normal model (P>0.900).
Conclusion: Comparison of the confidence intervals suggests that the jackknife resampling method can be used when the sample size is small.
Y Salimi, T Paykani, S Ahmadi, M Shirazikhah, A Almasi, A Biglarian, N Rajabi Gilan, Z Jorjoran Shushtari ,
Volume 16, Issue 5 (Vol 16, Special Issue 2021)
Abstract
Background and Objectives: Vaccine acceptance could seriously affect global efforts to control the Covid-19 pandemic. The aim of this study was to estimate the Covid-19 vaccine acceptance and its related factors in Tehran and Kermanshah.
Methods: A population-based cross-sectional study was conducted on 850 participants in Tehran and Kermanshah using the random digit dialing method. Multiple logistic regression was used to estimate the adjusted odds ratio of factors related to vaccine acceptance.
Results: The frequency of the Covid-19 vaccine acceptance was 66.47% (95% confidence interval: 69.57%, 63.21%). Moreover, 86.02% of the participants stated that they would use any type of (Iranian / foreign) vaccine approved by the Iranian Ministry of Health. However, 13.98% of the participants stated that they only preferred foreign approved vaccines (if available). The variables of age, fatalism, and socioeconomic status had significant associations with the Covid-19 vaccine acceptance.
Conclusion: Based on the results of this study, the Covid-19 vaccine acceptance was moderate. In order to achieve herd immunity by vaccination faster in our society, the strategy of prioritizing vaccination can be planned based on the related variables such as religious beliefs and fatalism, younger age groups, and people with higher socio-economic status that are willing to receive the vaccine.
Ramin Farrokhi, Samaneh Hosseinzadeh, Abbas Habibelahi, Akbar Biglarian,
Volume 20, Issue 1 (Vol.20, No.1, Spring 2024)
Abstract
Background and Objectives: Identifying pregnant women who are at risk of premature birth and determining its risk factors is essential because it affects their health. This study aimed to use an interpretable machine-learning model to predict premature birth.
Methods: In this study, data from 149,350 births in Tehran in 2019 were utilized from the Iranian Mothers and Babies Network (IMaN) dataset. Various factors related to the mother and the fetus, such as the mother's demographic variables and health status, medical history, pregnancy conditions, childbirth, and associated risks, were considered. The machine learning models, including multilayer neural networks, random forest, and XGBoost, were employed to predict the occurrence of preterm birth after data preprocessing. The models were evaluated based on accuracy, sensitivity, specificity, and area under the ROC curve. The Python programming language version 3.10.0 was applied to analyze the data.
Results: About 8.67% of births were premature. The XGBoost algorithm achieved the highest prediction accuracy (90%). According to the model output, multiple births, which account for 46% of pregnant women's births, had the highest importance score. Delivery risk factors had a score of 41%, and other variables, including neurological and mental illness, preeclampsia, and cardiovascular disease, were subsequently ranked in order of importance for this particular individual.
Conclusion: Using an interpretable machine learning method could predict the occurrence of premature birth. Based on risk factors, the interpretable machine learning method can provide personalized preventive recommendations for every pregnant woman, aiming to reduce the risk of preterm birth.
