Objectives This systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs). Design A systematic review was performed. Setting The databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool. Participants Admitted patients to the ED. Main outcome measure In-hospital mortality. Results Fifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction. Conclusion This review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.

Oral cancer stands among the 10 top causes of cancer death in the world. Considering the role of epidemiologic information on planning and effective interventions, the present study aimed to investigate the epidemiology of oral cancer in Iran. The required information for this systematic review study was obtained from PubMed, Google Scholar, CINAHL,SID, Medlib, Magiran and Iranmedex databases, using key words "cancer", "oral cancer", "squamous cell carcinoma", "oral cavity carcinoma" and their Persian equivalents in combination with keywords of epidemiology, prevalence, etiology, frequency, and Iran from 1990 to 2014. From 1,065 related studies found, finally 25 were included to the study. The mean age of 8,248 patients in 25 studies was 54.0±15.1 years. The male/female ratio for oral cancer was 1.91. Tongue with average percentage of 29.9 was the most involved site. Regarding microscopic grade, 65.7% of cases were grade 1. SCCs, accounting for an average of 70.0%, was the most common among all types of oral cancer. In the majority of studies, smoking including cigarette, hookah, and tobacco consumption was found to be a risk factor. The epidemiological pattern of oral cancer in Iran is somewhat similar to that of other countries. Yet the information on hand in this field is limited and considering the role of epidemiological data we suggest conducting more accurate studies to catch data that is required for effective programs and interventions.

Breast cancer prognosis is steadily improving due to early detection of primary cancer in screening programs and revolutionizing treatment development. In the metastatic setting, therapy improvements render breast cancer a chronic disease. Although FDG-PET/CT has emerged as a highly accurate method for staging metastatic breast cancer, there has been no change in response evaluation methods for decades. FDG-PET/CT has proven high prognostic values in patients with metastatic breast cancer when using quantitative PET methods. It has also shown a higher predictive value than conventional CT when applying the respective response evaluation criteria, RECIST and PERCIST. Response categorization using FDG-PET/CT is more sensitive in detecting progressive and regressive disease, while conventional imaging such as CT and bone scintigraphy deem stable disease more often. These findings reflect the higher accuracy of FDG-PET/CT for response evaluation in this patient group. But does the higher accuracy of FDG-PET/CT translate into a patient benefit when implementing it for monitoring response to palliative treatment? We have evidence of survival benefit from a retrospective study indicating the superiority of using FDG-PET/CT compared with conventional imaging for response evaluation in metastatic breast cancer patients. The survival benefit seems to result from earlier detection of progression with FDG-PET/CT than conventional imaging, leading to an earlier change in treatment with potentially better efficacy of the subsequent treatment line. FDG-PET/CT can be used semiquantitatively as suggested in PERCIST. However, we still need to improve clinically applicable methods based on neural network modeling to better integrate the quantitative information in a smart and standardized way, enabling relevant comparability between scans, patients, and institutions. Such innovation is warranted to support imaging specialists in diagnostic response assessment. Prospective multicenter studies analyzing patients' survival, quality of life, societal and patient costs of replacing conventional imaging with FDG-PET/CT are needed before firm conclusions can be drawn on which type of scan to recommend in future clinical guidelines.

Gestational Diabetes (GD) is one of the major public health issues. The purpose of the present study was to perform a systematic review and meta-analysis to assess the risk factors and prevalence rate of this disorder in Iran. This systematic review and meta- analysis article was prepared using the databases of Science Direct, Pub-Med, Scopus, Magiran, Iranmedex and SID, Google search engine, Gray Literature, reference lists check and hand searching using keywords such as “prevalence”, “gestational diabetes mellitus”, “GDM”, “risk factor*”, “Iran” and “Postpartum Diabetes”. The selected papers were fully reviewed and the required information for the systematic review was extracted and summarized using extraction table in Microsoft Office Excel software. Twenty-four of 1011 papers were quite relevant to the objectives of the review so they were included. The mean age of the participants was 29.43±4.97 yr and the prevalence of GDM was 3.41% (the highest and the lowest prevalence rates were 18.6% and 1.3% respectively). Among the influential factors mentioned in the literature, potential causes of GDM are gestational age, history of gestational diabetes, family history of diabetes, body mass index, abortions and parity, and history of macrosomia. Considering the high prevalence of postpartum diabetes and its related factors in Iran, strategic planning for disease prevention and reduction is inevitable.

SiRNA-mediated Silencing of Survivin Inhibits Proliferation and Enhances Etoposide Chemosensitivity in Acute Myeloid Leukemia Cells Survivin;siRNA;etoposide;HL-60;apoptosis; Background: Overexpression of survivin, a known inhibitor of apoptosis, is associated with tumor progression and drug resistance in numerous malignancies, including leukemias. The aim of this study was to investigate the effect of a specific survivin small interference RNA (siRNA) on proliferation and the sensitivity of HL-60 acute myeloid leukemia (AML) cells to the chemotherapeutic drug etoposide. Materials and Methods: The cells were transfected with siRNAs using Lipofectamine $^{TM}2000$ transfection reagent. Relative survivin mRNA and protein levels were measured by quantitative real-time PCR and Western blotting, respectively. Trypan blue exclusion assays were performed to monitor tumor cell proliferation after siRNA transfection. The cytotoxic effects of etoposide and survivin siRNA, alone and in combination, on leukemic cells were determined using MTT assay. Apoptosis was assessed by ELISA cell death assay. Results: Survivin siRNA markedly reduced both mRNA and protein expression levels in a time-dependent manner, leading to distinct inhibition of cell proliferation and increased spontaneous apoptosis. Surprisingly, survivin siRNA synergistically increased the cell toxic effects of etoposide. Moreover, survivin down-regulation significantly enhanced its induction of apoptosis. Conclusions: Our study suggests that down-regulation of survivin by siRNA can trigger apoptosis and overcome drug resistance of leukemia cells. Therefore, survivin siRNA may be an effective adjuvant in AML chemotherapy.

We compared lesion-based sensitivity of dual-time-point FDG-PET/CT, bone scintigraphy (BS), and low-dose CT (LDCT) for detection of various types of bone metastases in patients with metastatic breast cancer. Prospectively, we included 18 patients with recurrent breast cancer who underwent dual-time-point FDG-PET/CT with LDCT and BS within a median time interval of three days. A total of 488 bone lesions were detected on any of the modalities and were categorized by the LDCT into osteolytic, osteosclerotic, mixed morphologic, and CT-negative lesions. Lesion-based sensitivity was 98.2% (95.4–99.3) and 98.8% (96.8–99.5) for early and delayed FDG-PET/CT, respectively, compared with 79.9% (51.1–93.8) for LDCT, 76.0% (36.3–94.6) for BS, and 98.6% (95.4–99.6) for the combined BS+LDCT. BS detected only 51.2% of osteolytic lesions which was significantly lower than other metastatic types. SUVs were significantly higher for all lesion types on delayed scans than on early scans (P<0.0001). Osteolytic and mixed-type lesions had higher SUVs than osteosclerotic and CT-negative metastases at both time-points. FDG-PET/CT had significantly higher lesion-based sensitivity than LDCT and BS, while a combination of the two yielded sensitivity comparable to that of FDG-PET/CT. Therefore, FDG-PET/CT could be considered as a sensitive one-stop-shop in case of clinical suspicion of bone metastases in breast cancer patients.