Search published articles
Showing 8 results for Subject: Bio-statistics
Dr Mahsa Saadati,
Volume 5, Issue 2 (10-2017)
Volume 5, Issue 2 (10-2017)
Abstract
Background & Objective: Migration, in any forms and by any motivations or outcomes, as a demographic phenomenon, has various cultural and socio-economic effects on local, regional, national and international levels. On the other hand, fertility plays an important role in health and population studies and researchers have examined its changes and trends in various aspects. The aim of this research was modeling the mean number of children ever born (CEB) for women who have left their cities or villages and migrated to Tehran city using regression tree model.
Methods: Data was obtained from 2% of raw data from the census of 2011 and analyzed by regression tree model. Tree models are nonparametric statistical techniques which do not need complicated and unreachable assumptions of traditional parametric ones and have a considerable accuracy of modeling. These models are associated with simple interpretation of results. Therefore, they have been used by researches in many fields such as social sciences.
Results: Age, educational level, job status, cause of migration, internet use for urban migrant women and age for rural migrant women were assumed as influential covariates in predicting the mean number of CEB.
Conclusion: Regression tree findings revealed that urban migrants who were in higher age groups, lower educational levels, unemployed and have not used internet have had more mean number of CEBs.
Methods: Data was obtained from 2% of raw data from the census of 2011 and analyzed by regression tree model. Tree models are nonparametric statistical techniques which do not need complicated and unreachable assumptions of traditional parametric ones and have a considerable accuracy of modeling. These models are associated with simple interpretation of results. Therefore, they have been used by researches in many fields such as social sciences.
Results: Age, educational level, job status, cause of migration, internet use for urban migrant women and age for rural migrant women were assumed as influential covariates in predicting the mean number of CEB.
Conclusion: Regression tree findings revealed that urban migrants who were in higher age groups, lower educational levels, unemployed and have not used internet have had more mean number of CEBs.
Arezou Bagheri, Mahsa Saadati,
Volume 6, Issue 2 (6-2018)
Volume 6, Issue 2 (6-2018)
Abstract
Background and objectives: Birth spacing is an important variable for identification of fertility acceleration, total fertility rate, and maternal and fetal health. Therefore, special attention has been paid to this issue by researchers in the fields of medical sciences, health, and population. In addition, proper analysis of this concept is of foremost importance. Application of classical analytical techniques with no attention to their assumptions (e.g., independence of events) is associated with inefficient results. As such, this study aimed to present frailty models as effective models for this analysis.
Methods: Frailty models consider the dependence between unobserved intervals and dispersions by exerting a random impact on the model. Different types of these models include shared, conditional, correlated and time-dependent frailty, each of which along with their applications were presented in the current research using two examples. Results: In practice, the shared frailty model is highly applied due to its simplicity. Nevertheless, since most of the unknown factors affecting the birth spacing are not common between different births, the shared frailty models must be used with caution.
Conclusion: Use of classical statistical methods, such as the Cox proportional hazards model, the important assumption of which is the dependence of events occurred, is not appropriate for the accurate analysis of birth spacing. On the other hand, frailty models consider the correlation between the intervals and are an effective method for analysis of birth spacing, use of which is recommended to researchers in fields of medicine and population.
Ali Behnampour, Akbar Biglarian, Enayatolah Bakhshi,
Volume 7, Issue 2 (7-2019)
Volume 7, Issue 2 (7-2019)
Abstract
Background and objectives: Autism spectrum disorder (ASD) is a childhood neurodevelopmental disorder and according to DSM-5 classification, its severity includes three levels: requiring support, requiring substantial support, and requiring very substantial support. This classification is unclear from a possible perspective and from a fuzzy point of view; it has a degree of uncertainty. The purpose of this study is to predict the severity of autism disorder by fuzzy logistic regression.
Methods: In this cross-sectional study, 22 children with ASD which referred to the rehabilitation centers of Gorgan in 2017 were used as a research sample. Therapist's viewpoint about the severity of the disorder that is measured by linguistic terms (low, moderate, high) was considered as fuzzy output variable. In addition, to determine the prediction model for the severity of autism, a fuzzy logistic regression model was used. In this sense parameters were estimated by least square estimations (LSE) and least absolute deviations (LAD) methods and then the two methods were compared using goodness-of-fit index.
Results: The age of children varied from 6 to 17 years old with mean of 10.44± 3.33 years. Also, the goodness-of-fit index for the model that was estimated by the LAD method was 0.0634, and this value was less than the LSE method (0.1255). The estimated model by the LAD indicates that with the constant of the values of other variables, with each unit increase in the variables of age, male gender, raw score of stereotypical movements, communication and social interaction subscales, possibilistic odds of severity of autism disorder varied about 0.67 (decrease), 0.362 (decrease), 0.098 (increase), 0.019 (increase) and 0.097 (increase) respectively.
Conclusion: The LAD method was better than LSE in parameter estimation. So, the estimated model by this method can be used to predict the severity of autism disorder for new patients who referred to rehabilitation centers and according to predicted severity of the disorder, proper treatments for children can be initiated.
Mahsa Saadati, Arezoo Bagheri,
Volume 7, Issue 3 (9-2019)
Volume 7, Issue 3 (9-2019)
Abstract
Background and objectives: Application of statistical machine learning methods such as ensemble based approaches in survival analysis has been received considerable interest over the past decades in time-to-event data sets. One of these practical methods is survival forests which have been developed in a variety of contexts due to their high precision, non-parametric and non-linear nature. This article aims to evaluate the performance of survival forests by comparing them with Cox-proportional hazards (CPH) model in studying first birth interval (FBI).
Methods: A cross sectional study in 2017 was conducted by the stratified random sampling and a structured questionnaire to gather the information of 610, 15-49-year-old married women in Tehran. Considering some influential covariates on FBI, random survival forest (RSF) and conditional inference forest (CIF) were constructed by bootstrap sampling method (1000 trees) using R-language packages. Then, the best model is used to identify important predictors of FBI by variable importance (VIMP) and minimal depth measures.
Results: According to prediction accuracy results by out-of-bag (OOB) C-index and integrated Brier score (IBS), RSF outperforms CPH and CIF in analyzing FBI (C-index of 0.754 for RSF vs 0.688 for CIF and 0.524 for CPH and IBS of 0.076 for RSF vs 0.086 for CIF and 0.107 for CPH). Woman’s age was the most important predictor on FBI.
Conclusions: Applying suitable method in analyzing FBI assures the results which be used for making policies to overcome decrement in total fertility rate.
Methods: A cross sectional study in 2017 was conducted by the stratified random sampling and a structured questionnaire to gather the information of 610, 15-49-year-old married women in Tehran. Considering some influential covariates on FBI, random survival forest (RSF) and conditional inference forest (CIF) were constructed by bootstrap sampling method (1000 trees) using R-language packages. Then, the best model is used to identify important predictors of FBI by variable importance (VIMP) and minimal depth measures.
Results: According to prediction accuracy results by out-of-bag (OOB) C-index and integrated Brier score (IBS), RSF outperforms CPH and CIF in analyzing FBI (C-index of 0.754 for RSF vs 0.688 for CIF and 0.524 for CPH and IBS of 0.076 for RSF vs 0.086 for CIF and 0.107 for CPH). Woman’s age was the most important predictor on FBI.
Conclusions: Applying suitable method in analyzing FBI assures the results which be used for making policies to overcome decrement in total fertility rate.
Sayede Shadi Nazari , Solmaz Norouzi, Mohammad Asghari Jafar-Abadi,
Volume 8, Issue 1 (3-2020)
Volume 8, Issue 1 (3-2020)
Abstract
Background and objective: Prevalence and the spread of novel Coronavirus (2019-ncov) cause significant life and financial destruction worldwide and is the cause of severe respiratory infection in humans. The present study briefly reviews the latest information on how the virus is distributed around the world. The main question of the study are: 1- In which geographic regions of the world is the Coronavirus more concentrated? 2- Is the distribution of the Coronavirus geographically stable?
Material and Methods: To answer these questions, we first began collecting and studying the available scientific resources. The required data was obtained from a daily report of confirmed, recovered, and deaths by the Coronavirus separated by state which was collected from January 22, 2020 to Jun 19, 2020. Based on analyzing available patterns in spatial statistics tool in ArcGIS and geostatistical models, we examined how the Coronavirus was distributed around the world.
Results: The spread of the disease is increasing all over the world. Using the results of Map 1, it is seen that the spread of Corona virus has a trend and starts in China and then spreads to the Middle East, Europe and the United States in a linear manner. The results also show that the prevalence of mortality is higher than that of recovery. Central mean and median for all types (Confirmed, Recovered and death) are close to each other. Death mean and median was close to Western countries and Recovered mean and median was close to Eastern countries, while confirmed mean and median was located in the center.
Conclusion: Based on spatial statistics tool in ArcGIS and geostatistical models, we examined how the Coronavirus was distributed around the world. Our results showed that the spread of Corona virus had a trend and started in China and then spread to the Middle East, Europe and the United States in a likely linear manner.
Material and Methods: To answer these questions, we first began collecting and studying the available scientific resources. The required data was obtained from a daily report of confirmed, recovered, and deaths by the Coronavirus separated by state which was collected from January 22, 2020 to Jun 19, 2020. Based on analyzing available patterns in spatial statistics tool in ArcGIS and geostatistical models, we examined how the Coronavirus was distributed around the world.
Results: The spread of the disease is increasing all over the world. Using the results of Map 1, it is seen that the spread of Corona virus has a trend and starts in China and then spreads to the Middle East, Europe and the United States in a linear manner. The results also show that the prevalence of mortality is higher than that of recovery. Central mean and median for all types (Confirmed, Recovered and death) are close to each other. Death mean and median was close to Western countries and Recovered mean and median was close to Eastern countries, while confirmed mean and median was located in the center.
Conclusion: Based on spatial statistics tool in ArcGIS and geostatistical models, we examined how the Coronavirus was distributed around the world. Our results showed that the spread of Corona virus had a trend and started in China and then spread to the Middle East, Europe and the United States in a likely linear manner.
Fatemeh Bagheri, Mohammad Jafar Tarokh, Majid Ziaratban,
Volume 8, Issue 2 (7-2020)
Volume 8, Issue 2 (7-2020)
Abstract
Background and objective: Automatic semantic segmentation of skin lesions is one of the most important medical requirements in the diagnosis and treatment of skin cancer, and scientists always try to achieve more accurate lesion segmentation systems. Developing an accurate model for lesion segmentation helps in timely diagnosis and appropriate treatment.
Material and Methods: In this study, a two-stage deep learning-based method is presented for accurate segmentation of skin lesions. At the first stage, detection stage, an approximate location of the lesion in a dermoscopy is estimated using deep Yolo v2 network. A sub-image is cropped from the input dermoscopy by considering a margin around the estimated lesion bounding box and then resized to a predetermined normal size. DeepLab convolutional neural network is used at the second stage, segmentation stage, to extract the exact lesion area from the normalized image.
Results: A standard and well-known dataset of dermoscopic images, (ISBI) 2017 dataset, is used to evaluate the proposed method and compare it with the state-of-the-art methods. Our method achieved Jaccard value of 79.05%, which is 2.55% higher than the Jaccard of the winner of the ISIC 2017 challenge.
Conclusion: Experiments demonstrated that the proposed two-stage CNN-based lesion segmentation method outperformed other state-of-the-art methods on the well-known ISIB2017 dataset. High accuracy in detection stage is of most important. Using the detection stage based on Yolov2 before segmentation stage, DeepLab3+ structure with appropriate backbone network, data augmentation, and additional modes of input images are the main reasons of the significant improvement.
Material and Methods: In this study, a two-stage deep learning-based method is presented for accurate segmentation of skin lesions. At the first stage, detection stage, an approximate location of the lesion in a dermoscopy is estimated using deep Yolo v2 network. A sub-image is cropped from the input dermoscopy by considering a margin around the estimated lesion bounding box and then resized to a predetermined normal size. DeepLab convolutional neural network is used at the second stage, segmentation stage, to extract the exact lesion area from the normalized image.
Results: A standard and well-known dataset of dermoscopic images, (ISBI) 2017 dataset, is used to evaluate the proposed method and compare it with the state-of-the-art methods. Our method achieved Jaccard value of 79.05%, which is 2.55% higher than the Jaccard of the winner of the ISIC 2017 challenge.
Conclusion: Experiments demonstrated that the proposed two-stage CNN-based lesion segmentation method outperformed other state-of-the-art methods on the well-known ISIB2017 dataset. High accuracy in detection stage is of most important. Using the detection stage based on Yolov2 before segmentation stage, DeepLab3+ structure with appropriate backbone network, data augmentation, and additional modes of input images are the main reasons of the significant improvement.
Parisa Karimi Darabi, Mohammad Jafar Tarokh,
Volume 8, Issue 3 (10-2020)
Volume 8, Issue 3 (10-2020)
Abstract
Background and Objectives: Currently, diabetes is one of the leading causes of death in the world. According to several factors diagnosis of this disease is complex and prone to human error. This study aimed to analyze the risk of having diabetes based on laboratory information, life style and, family history with the help of machine learning algorithms. When the model is trained properly, people can examine their risk of having diabetes.
Material and Methods: To classify patients, by using Python, eight different machine learning algorithms (Logistic Regression, Nearest Neighbor, Decision Tree, Random Forest, Support Vector Machine, Naive Bayesian, Neural Network and Gradient Boosting) were analysed. were evaluated by accuracy, sensitivity, specificity and ROC curve parameters.
Results: The model based on the gradient boosting algorithm showed the best performance with a prediction accuracy of %95.50.
Conclusion: In the future, this model can be used for diagnosis diabete. The basis of this study is to do more research and develop models such as other learning machine algorithms.
Material and Methods: To classify patients, by using Python, eight different machine learning algorithms (Logistic Regression, Nearest Neighbor, Decision Tree, Random Forest, Support Vector Machine, Naive Bayesian, Neural Network and Gradient Boosting) were analysed. were evaluated by accuracy, sensitivity, specificity and ROC curve parameters.
Results: The model based on the gradient boosting algorithm showed the best performance with a prediction accuracy of %95.50.
Conclusion: In the future, this model can be used for diagnosis diabete. The basis of this study is to do more research and develop models such as other learning machine algorithms.
Ahmad Pourdarvish , Reza Hashemi , Jabbar Azar , Solmaz Norouzi ,
Volume 11, Issue 3 (12-2023)
Volume 11, Issue 3 (12-2023)
Abstract
Background: In medical research and survival analysis, it is common for an individual or item's failure to be attributable to multiple causes, also known as competing risks. This article focuses on examining the competing risks model as the data increasingly becomes type II censored and randomly removed. The model assumes that the causes of failure are independent and that the lifetimes of individuals are described by the Cox model. At each failure time, the number of items or people removed follows a binomial distribution. The article derives estimators for the indefinite parameters in the model. The study presents a set of detailed data and includes a simulation study that also illustrates the results.
Methods: Different reasons, frequently known as competing risks, are frequently embroiled in an individual's or an item's failure in medical research survival analysis. The competing risks shown under sort II dynamic censoring with random removals are the subject of this research.
We get the maximum likelihood and inexact most extreme probability estimators of the obscure parameters. The asymptotic distribution of the maximum probability estimators is utilized to decide the CIs. Then, Monte Carlo simulations were applied to demonstrate the approach. The analyses were performed utilizing R 4.0.4 software.
Results: For stroke, systolic blood pressure (SBP) and hypertension status are the only significant variables. In contrast, gender, body mass index (BMI), smoking status, the logarithm of urinary albumin and creatinine ratio, and diabetes status are significant variables for coronary heart disease (CHD) and other cardiovascular diseases (CVDs). The results suggest that significant risk factors differ for different types of CVD events.
Conclusion: The outcomes of the simulation study indicate that progressively right-censored type II sampling designs outperformed the usual censored type II sampling designs. Therefore, the estimated parameters on the defined pattern setting are recommended. They can be used in many practical situations when competing risks occur, and progressive censoring could be considered.
| Page 1 from 1 |
© 2024 CC BY-NC 4.0 | Jorjani Biomedicine Journal
Designed & Developed by : Yektaweb