Showing 4 results for Prediction
Azra Kenarkoohi, Hoorieh Soleimanjahi, Shahab Falahi, Hossein Riahi Madvar, S Zahra Meshkat,
Volume 13, Issue 4 (1-2011)
Abstract
Background: Based on the severity and prognostic condition of respective cancers caused by them, papilloma viruses are classified into high, medium, and low risk groups using E6 and E7 viral proteins. Nowadays, different methods of modeling in clinical medicine are used for diagnosis of diseases and evaluation of their molecular characteristics. Among the new methods of modeling, fuzzy systems are of particular importance in various fields of science. The aim of this study was to use a new intelligent Adaptive Nero Fuzzy Inference System (ANFIS) for predicting human papilloma virus oncogenicity based on a number of biochemical properties of E7 protein. Materials and Methods: In this study, using ANFIS model, a new model was developed for predicting oncogenicity of papilloma virus isolated from patients. The process of training and testing was performed using a set of available published filed data and several statistical and graphical criteria. Accordingly, through provision of needed biochemical and biophysical data on E7 gens from the existing data, this model was developed. The results of this model were, then, validated by the authentic published data. Results: Based on the results, the developed model is capable of predicting papilloma virus oncogenicity efficiently. R2 and RMSE values in training stage were 0.99 and 101.18, respectively. In the testing stage, however, they stood at 0.94 and 173.8, respectively. Conclusion: Based on the findings, the use of ANFIS model significantly improves the accuracy of estimating virus oncogenicity phenomenon. The methodology presented in this study is a new approach in estimating viral oncogenicity and can successfully be combined with other mathematical models for model updating in real conditions.
Ahmadreza Baghestani, Mahmood Reza Gohari, Arezoo Orooji, Mohamad Amin Purhosseigholi,
Volume 18, Issue 1 (4-2015)
Abstract
Background: Colorectal cancer is the most common gastrointestinal cancer. Investigating the factors that predict survival time for these patients is important.The purpose of this study was comparison of parametric models by estimating the prediction error and also identifying the effective factors on predicted survival time of patients with colorectal cancer.
Materials and Methods: This cohort study was conducted with 600 patients who were suffered from colorectal cancer in Taleghani Hospital of Tehran between 2001 to 2005 and they were followed up for at least 5 years. For identifying the effective factors on survival time, of the patients we analyzed the data by some parametric models such as Weibull, Exponential and Log logistic and compared these models with the estimation of prediction error by apparent loss method.
Results: Among 600 patients there was 344 men (57.3%) and 256 wemon (47.7%). Of total, 151 patients were died that 62.3% of them were men. Univariate analysis showed that the effect of BMI, sex, staging of tumor, tumor site were significant but in multivariate model staging of tumor and BMI were significant. By the estimation of prediction error, the best model was Log logistic.
Conclusion: With respect to the importance of survival time prediction, we found that we can use the prediction error to compare the parametric models. In addition, because of effectiveness of tumor stages and BMI in the patients’ survival time, survival time could be increased by an on-time diagnosis and an appropriate controled diet.
Morteza Gharibi, Simin Najafgholian, Fatemeh Rafiee, Ali Nazemi, Esmaeil Mansourizadeh,
Volume 22, Issue 5 (11-2019)
Abstract
Background and Aim American College Of Emergency Medicine (ACEM) guideline has a recommendation for early diagnosis of head injuries following mild trauma. In this study we examined the prediction power, sensitivity, and specificity of this clinical guideline in the need for computed tomography (CT) scan
Methods & Materials This cross-sectional study was performed for 6 months on patients over 18 years old referred to the emergency department of Vali-e-Asr Hospital in Arak who met ACEM criteria for head CT scan for suspected mild trauma. Demographic characteristics, clinical symptoms, trauma mechanism, physical injuries caused by head trauma, and history of drug abuse were recorded. The consciousness level (Glasgow Coma Scale) was checked every two hours. Patients underwent treatment if there was a pathology in CT images, and those with no clear pathology were discharged after 6 hours and, followed up by phone for two weeks, and in case of any abnormality in the level of consciousness, they were re-examined by CT scanning.
Ethical Considerations This study has an ethical approval obtained from Arak University of Medical sciences (code: IR.ARAKMU.REC.1396.227).
Results 500 patients, 335 male (67%) and 165 females (33%) with the mean age of 46.39± 2.01 years were studied; the sensitivity the ACEM guideline for predicting the need for CT scan in patients with mild head trauma were 100% with a specificity of 3.46% (for the second recommendation, the sensitivity was 100% with a specificity of 6.7%) which indicated that the test was highly sensitive to diagnosing the patients, but its specificity was low.
Conclusion The ACEM guideline had high sensitivity to predicting the need for CT in patients with mild head trauma, but had very low specificity which makes it an unacceptable criterion for rejecting or performing CT scan in these patients.
Mr Mohsen Shamsi, Mr Ali Kulivand, Mr Mohammadjavad Ghannadzadeh, Ms Mahboobeh Khorsandi, Mr Seyedhamed Mirhosseini, Mr Amir Almasi-Hashiani, Mr Behrooz Karimi, Mr Seyednadali Alavi Bakhtiarvand, Ms Masoume Naderi Noreyni,
Volume 25, Issue 4 (9-2022)
Abstract
Introduction: Today, with the increase in population, the per capita production of waste materials and the subsequent threat and destruction of the environment is an increasing process, and waste management by the people of a society can play an essential role in reducing this problem. Therefore, the aim of this study was determine of predicting the waste management behaviors of households in Arak city in 2022.
Methods: This is a cross-sectional and analytical study that was carried out on 600 mothers of households in Arak city, who were selected by multi-stage sampling. The data collection tool was a valid and reliable researcher-made questionnaire that included demographic characteristics, knowledge, attitude and behavior of households in the field of waste management. Data were analyzed using SPSS software and t-test, chi-square and regression tests. This study was approved by the research ethics committee of Arak University of Medical Sciences (Code: IR.ARAKMU.REC.1401.040).
Results: The average age of the studied was 39±11 years and the number of family members was 3.6. In terms of type of housing, most of them lived in apartments (44%) and a smaller number lived in complexes (14%). 65 percent of the people had not received the training on the waste separation plan from the source, and among the effective training methods, the majority (38 percent) of the people had overestimated the effectiveness of the training through the Internet. The mean and standard deviation of knowledge was 66±19, attitude was 84±11 and performance was 73±18. The majority of the people studied had a good level of awareness and attitude. The regression analysis model showed that the greatest impact on the waste management behavior of the samples was the age of the people, their knowledge and attitude, which predicted a total of 33% of the waste management behavior.
Conclusions: Considering the favorable state of awareness and attitude of households in Arak city, it seems that for better waste management, other environmental factors should be emphasized, including sources of waste production at the source. Also, based on the prediction model, it is still important to inform and change the attitude of households in Arak city for better performance at younger ages.
