Search

Background/Aims: Renal biopsy is the gold standard to determine the pathologic type of primary nephrotic syndrome, which is critical for diagnosis, choice of treatment and evaluation of prognosis. However, in some cases, renal biopsy cannot be performed. Methods: To explore the possibility of predicting the histology type of primary nephrotic syndrome without the need for biopsy, we trained and validated a machine learning algorithm using data from 222 patients with biopsy-confirmed primary nephrotic syndrome treated at our hospital between May 2008 and January 2016. The model was then tested prospectively on another sample of 63 patients with biopsy-confirmed primary nephrotic syndrome. Results: Overall accuracy of prediction from the retrospective set of 222 patients was 62.2% across all types of nephrotic syndrome. The accuracy of model prediction for the prospectively collected dataset of 63 patients was 61.9%. The algorithm identified 17 of 33 variables as contributing strongly to type of renal pathology. Conclusion: To our knowledge, this is the first such application of machine learning to predict the pathologic type of primary nephrotic syndrome, which may be clinically useful by itself as well as helpful for guiding future efforts at machine learning-based prediction in other disease contexts.

Objective The purpose of this study was to describe the ultrasonographic findings of angioleiomyoma based on pathological subtypes. Materials and methods Thirty-nine patients with subcutaneous angioleiomyomas in the extremities were retrospectively reviewed by two radiologists and a pathologist. Sonographic images were analyzed to evaluate each tumor's anatomic location, size, shape, margin, heterogeneity, echogenicity, associated findings, and vascularity. Results Angioleiomyomas were divided into 3 subtypes: capillary (n = 16), venous (n = 22), and cavernous (n = 1). The one cavernous angioleiomyoma was a hypoechoic mass with rich vascularity. Hypoechogenicity was more frequently observed for venous tumors (77.3%) than for capillary tumors (43.8%), and isoechogenicity was more frequently observed for capillary tumors (56.2%) than for venous tumors (22.7%). Moderate vascularity was more frequently observed for venous tumors (59.1%) than for capillary tumors (12.5%), and little vascularity was more frequently observed for capillary tumors (62.5%) than for venous tumors (13.6%). The aforementioned findings including echogenicity (p = 0.034) and vascularity (p = 0.003) were statistically significant. Conclusion Awareness of sonographic findings of angioleiomyomas based on pathologic subtypes could be helpful for diagnosing angioleiomyoma and could increase diagnostic accuracy for superficial soft-tissue masses in our practice.

BACKGROUND: Breast cancer is the most common cancer among women worldwide. Based on the latest Iranian national cancer department report, the total number of women registered with breast cancer was 6976 cases during 2007. Five year survival is one of the indicators used for evaluation of the quality for care to different types of malignancies including breast cancer. OBJECTIVES: The aim of this study was to estimate survival rate of breast cancer in 6147 Iranian patients at a national level in different geographic regions. MATERIALS AND METHODS: 6147 cases of breast cancer, which had telephone number and were diagnosed between 2001-2006, were called to obtain information about their life status. Survival estimates were calculated using the Kaplan-Meier method, and the survival probability was calculated for the overall cohort and in different categories of gender, age and pathologic type of tumor. Hazard ratios (HR) according to demographic and risk variables were calculated by Cox's proportional hazard model. RESULTS: The overall 5-year survival rate was 71.0%. The mean survival time was different between men and women, which was statistically significant. The number of men involved with breast cancer was 172 (2.8%) of all cases. The 5-year survival rate for patients in age group 41-50 years was significantly higher than other age groups (P = 0.001). The likelihood of death was higher in patients with 61 years old or more years rather than those below forty years old (HR = 1.31; 95% CI: 1.12-1.55). CONCLUSIONS: THE FINDINGS OF THIS STUDY MIGHT HELP IRANIAN HEALTH MANAGERS: 1) to be more conscious about geographical and regional determinants which will affect overall survival rate. 2) To carry preventive activities such as public education particularly in Iranian men. 3) To think about screening and early detection of breast cancer.