Showing 7 results for Classification
A Kabirzadeh, A Zamani Kiasari , Mr Habbibi , B Mohseni Saravi , M Khademlo, T Hakimi Moghadam ,
Volume 5, Issue 2 (9-2009)
Abstract
Background and Objectives: Making an accurate clinical diagnosis can be a great challenge with pediatricians. We aimed to compare the initial diagnosis and final diagnosis for hospitalized children in one teaching hospital in Iran.
Methods: In this cross-sectional study, patients’ clinical files were used. The relationship between variables was assessed by ANOVA and X2 statistical tests. The agreement rate between final and primary diagnosis was evaluated by Kappa coefficient.
Results: A total of 1310 patients’ hospital files were reviewed. There were 1244 (94.9%) cases with complete agreement, 12 (0.9%) with relatively agreement and 54 (4.2%) cases without agreement. The overall Kappa coefficient for primary and final diagnosis was 0.88.
Conclusions: The agreement rate between primary and secondary diagnosis in this teaching hospital was high. This might be due to academic atmosphere in teaching children hospital
S Zare Delavar , E Bakhshi, F Soleimani, A Biglarian,
Volume 10, Issue 2 (9-2014)
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.
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 Zayeri, Sh Seyedagha, H Aghamolaie, F Boroumand, P Yavari,
Volume 12, Issue 2 (8-2016)
Abstract
Background and Objectives: Breast cancer is one of the most common malignancies in women which accounts for the highest number of deaths after lung cancer. The aim of the current study was to compare the logistic regression and classification tree models in determining the risk factors and prediction of breast cancer.
Methods: We used from the data of a case-control study conducted on 303 patients with breast cancer and 303 controls. In the first step, we included 16 potential risk factors of breast cancer in both the logistic regression and classification tree models. Then, the area under the ROC curve (AUC), sensitivity, and specificity indexes were used for comparing these models.
Results: From 16 variables included in the models, 5 variables were statistically significant in both models. Sensitivity, specificity, and AUC was 71%, 69%, and 74.7% for the logistic regression and 63.3%, 68.8%, and 71.1% for the classification tree, respectively.
Conclusion: The obtained results suggest that the classification tree has more power for separating patients from healthy people. Menopausal status, number of breast cancer cases in the family, and maternal age at the first live birth were significant indicators in both models.
F Ebrahimzadeh, E Hajizadeh, M Birjandi, S Feli, Sh Ghazi,
Volume 14, Issue 3 (12-2018)
Abstract
Background and Objectives: Academic failure is of paramount importance for medical students because it might lead to a decline in scientific level of the community of physicians in the future. This study was conducted to investigate the predictors of academic failure in medical students of Lorestan University of Medical Sciences using classification tree.
Methods: In this cohort study, academic records of all medical students of Lorestan University of Medical Sciences during the academic years of 1999-2008 were selected by census and were followed up until September 2016. Academic failure was defined as having at least one of the components of appropriate grade point average, prolonged graduation, academic probation, dropout, expulsion, and any failure in ccomprehensive exams and the CART classification tree was adopted using the SPSS 22 software to predict it.
Results: The cumulative incidence of academic failure was 26.4% and the most prevalent components were prolonged graduation (21.7%) and academic probation (15.0%). The probability of academic failure was 0.449 in subjects taking guest courses, 0.220 in subjects with no history of guest courses admitted to courses with less than 40 students and admission quotas of zone 1 or 3, and 0.456 in subjects with no history of guest courses admitted to courses with more than 40 students and males.
Conclusion: With respect to identifying the predictors of academic failure, it is suggested that these students be referred to consulting centers of the university or educational supervisors’ moreover, the regulations of taking guest courses in other universities should be revised.
M Gholamhoseinzadeh, L Ghadirian Marnani, E Ehsani-Chimeh, F Rajabi,
Volume 18, Issue 1 (5-2022)
Abstract
Background and Objectives: The distribution of causes of death indicates the distribution of risk factors for death, and is a basis of planning and intervention to reduce risk factors. The quality of the registered information has problems due to the weakness of the processes of completing and issuing the death certificate or the coding method. The purpose of this study was to explain the challenges of death registration and to provide a solution in this regard.
Methods: This qualitative study was conducted in the second half of 2019 in Guilan University of Medical Sciences. The target population was the directors and experts of the death registration program. Sampling was done purposefully by counting. Data was collected through in-depth interviews using a questionnaire and simultaneous contractual content analysis to identify key themes. To ensure the validity and acceptability of the data, the participants and two research colleagues reviewed the data frequently.
Results: According to the content analysis of 24 interviews, the main challenges of death registration included manpower, organizing the death registration system in the country, and death registration software system and its implementation. These themes were abstracted from 45 subcategories and 13 main categories.
Conclusion: Considering the challenges described by death registration managers and experts, the main proposed interventions to improve the death registration system include recruiting appropriate staff, empowering and motivating various human resources departments, developing internal and external cooperation, increasing public participation, monitoring and continuous assessment to identify the strengths and weaknesses of the death registration system and adressing them, attention to the development of death registration software and its required infrastructure such as Internet access and equipment, attention to the multiplicity of systems, and efforts to integrate them.
Mahdieh Shojaei Baghini, Tahereh Naseribooriabadi, Mansooreh Rastgoo, Mahdieh Poornakhaei, Ali Mohammadpour,
Volume 18, Issue 2 (9-2022)
Abstract
Background and Objectives: Poisoning is one of the most common causes of hospitalization. The external causes of poisoning and toxic agents differ in age, gender, and occupational groups. It is essential to understand the epidemiological pattern of poisoning in each region to prevent it. This study was conducted to determine the epidemiological characteristics of poisoning in patients referred to the Kerman University of Medical Sciences teaching hospital.
Methods: This descriptive cross-sectional study was performed retrospectively. Medical records of poisoning patients were reviewed from October 2016 to October 2017. Data was gathered using a researcher-made checklist based on the minimum data elements needed to record the diagnostic expression of poisoning accurately. Data analysis was performed using descriptive and inferential statistics using SPSS software 24.
Results: Poisoning was higher in males (52.1%), the 20-30 years-old age group (28.5%), single (52.8%), urban regions (80.6%), and self-employed (29.8%). The mean age of the subjects was 26.9±17.21. The external causes of poisoning were associated with marital status, age, gender, occupation, addiction, season, a personal history of suicide attempts, a family history of suicide attempts, and a personal history of poisoning. The toxic agent was also associated with age, gender, occupation, location, and external poisoning causes.
Conclusion: According to the result, poisoning often happens intentionally, so providing a suitable and stress-free family environment might be useful to reduce the amount of intentional poisoning. Educating parents with young children more about child care and how to store chemicals is also necessary.
