Background: Breast cancer (BC) is one of the most common malignancies in women. Early diagnosis of BC and metastasis among the patients based on an accurate system can increase survival of the patients to > 86%. This study aimed to compare the performance of six machine learning techniques two traditional methods for the prediction of BC survival and metastasis. Methods: We used a dataset that include the records of 550 breast cancer patients. Naive Bayes (NB), Random Forest (RF), AdaBoost, Support Vector Machine (SVM), Least-square SVM (LSSVM) and Adabag, Logistic Regression (LR) and Linear Discriminant Analysis were used for the prediction of breast cancer survival and metastasis. The performance of the used techniques was evaluated with sensitivity, specificity, likelihood ratio and total accuracy. Results: Out of 550 patients, 83.4% were alive and 85% did not experience metastasis. In prediction of survival, the average specificity of all techniques was ≥94% and the SVM and LDA have greater sensitivity (73%) in comparison to other techniques. The greater total accuracy (93%) belonged to the SVM and LDA. For metastasis prediction, the RF had the highest specificity (98%), the NB had highest sensitivity (36%) and the LR and LDA had the highest total accuracy (86%). Conclusions: Our finding showed that the SVM outperformed other machine learning methods in prediction of survival of the patients in terms of several criteria. Nevertheless, the LDA technique as a classical method showed similar performance.

To assess the prevalence of soft tissue calcifications and their panoramic radiographic characteristics. Material and Methods: This descriptive retrospective study evaluated 2027 panoramic radiographs. The type and location of calcifications and the age and gender of patients were evaluated by two radiologists. Data were analyzed via SPSS and the Chi-square, Fisher's exact and Kappa tests were used to compare the categorical demographic variables among the groups. The confidence interval was set to 95% and p<0.05 was considered statistically significant. Results: The prevalence of calcified stylohyoid ligament was 11.24%. This value was 3.99% for tonsillolith, 1.33% for calcified carotid plaque, 0.69% for antrolith, 0.39% for calcified lymph node, 0.29% for phleboliths, and 0.19% for sialoliths. The prevalence of these conditions had no significant association with gender or age (p=0.102). The prevalence of bilateral calcified stylohyoid ligament, tonsillolith, and a calcified carotid plaque was significantly higher (p<0.001). The most prevalent type of calcified stylohyoid ligament, according to O'Carroll's classification, belonged to types 1, 4, 3 and 2 (p<0.001). The most commonly observed radiographic pattern was multiple, well-defined tonsilloliths (75.3%, p<0.001). Conclusion: The prevalence of soft tissue calcifications on panoramic radiographs was relatively low in this Iranian population. The most calcifications were respectively calcified stylohyoid ligament, tonsillolith, calcified carotid plaque, antrolith, calcified lymph node, phleboliths and sialoliths. Calcified stylohyoid ligament, tonsillolith and calcified carotid plaque were more bilaterally. Thereby panoramic imaging can help in primary assessment, epidemiologic and screening evaluation of these calcifications.

Background Curing of colorectal cancer (CRC) occurs at the time of resection, but it is not immediately observable. If the cancer is not completely eliminated, the patient will not be cured of cancer and will experience a recurrence as the tumor has regrown to a detectable size. The main proposes of the present study was to assess the effects of different covariates on the probability of being cured as well as the time to recurrence, time to death, and time to death after recurrence in CRC patients by using multi-state cure model.Methods In the present study, the information of 283 patients with adenocarcinoma CRC, who underwent resection, from 1992 to 2015 in Imam Khomeini Hospital of Hamadan, Iran, were analyzed. A multi-state cure model is used to joint modeling the recurrence and death in patients with CRC when a fraction of patients was apparently cured after resection.Results The results revealed that females, patients diagnosed at stage IV and whom underwent radiotherapy were less likely to be apparently cured. Also, more than 50% of not cured patients recurred later. Moreover, the survival time of patients was affected by the stage of disease, age at diagnosis and receiving radiation therapy. In addition, sex had a significant effect on the time-to-recurrence.Conclusions The multi-state cure model provided a flexible framework to study and compare the effects of prognostic factors simultaneously on the transition between different health states and the probability of being apparently cured of CRC.

OBJECTIVES:With a gradual decline in maternal mortality in recent years in Iran, this study was conducted to identify the remaining risk factors for maternal death.METHODS:This 8-year nested case-control study was conducted in Hamadan Province, in the west of Iran, from April 2006 to March 2014. It included 185 women (37 cases and 148 controls). All maternal deaths that occurred during the study period were considered cases. For every case, four women with a live birth were selected as controls from the same area and date. Conditional logistic regression analysis was performed and the odds ratio (OR) and its 95% confidence interval (CI) were obtained for each risk factor.RESULTS:The majority of cases were aged 20-34 years, died in hospital, and lived in urban areas. The most common causes of death were bleeding, systemic disease, infection, and pre-eclampsia. The OR estimate of maternal death was 8.48 (95% CI=1.26-56.99) for advanced maternal age (≥35 years); 2.10 (95% CI=0.07-65.43) for underweight and 10.99 (95% CI=1.65-73.22) for overweight or obese women compared to those with normal weight; 1.56 (95% CI=1.08-2.25) for every unit increase in gravidity compared to those with one gravidity; 1.73 (95% CI=0.34-8.88) for preterm labors compared to term labors; and 17.54 (95% CI= 2.71-113.42) for women with systemic diseases.CONCLUSIONS:According to our results, advanced maternal age, abnormal body mass index, multiple gravidity, preterm labor, and systemic disease were the main risk factors for maternal death. However, more evidence based on large cohort studies in different settings is required to confirm our results.

Curing of colorectal cancer (CRC) occurs at the time of resection but it is not immediately observable. If the cancer is not completely eliminated, the patient will not be cured of cancer and will experience recurrence as the tumor has regrown to a detectable size. The main propose of the present study was to assess the effects of different covariates on the probability of being cured as well as the time-to-recurrence, and time-to-death in CRC patients by using multi-state cure model. The information of 283 patients with CRC, who underwent resection, from 2000 to 2015 in Imam Khomeini Hospital of Hamadan, Iran, were analyzed. The results of multi-state cure model reveal that females and who experience metastasis were more likely to be apparently cured. It has been shown that sex has a significant effect on the time-to-recurrence given patient was in the not cured group. The survival time of patients of the not cured group was affected by the stage of disease. However, the survival of the apparently cured patients were affected by age at diagnosis and metastasis status. The multi-state cure model provided a flexible framework to study the effects of prognostic factors simultaneously on the transition between different states and the probability of being apparently cured of CRC.