Predictive model for acute respiratory distress syndrome events in ICU patients in China using machine learning algorithms: a secondary analysis of a cohort study.

BACKGROUND: To develop a machine learning model for predicting acute respiratory distress syndrome (ARDS) events through commonly available parameters, including baseline characteristics and clinical and laboratory parameters. METHODS: A secondary analysis of a multi-centre prospective observational cohort study from five hospitals in Beijing, China, was conducted from January 1, 2011, to August 31, 2014. A total of 296 patients at risk for developing ARDS admitted to medical intensive care units (ICUs) were included. We applied a random forest approach to identify the best set of predictors out of 42 variables measured on day 1 of admission. RESULTS: All patients were randomly divided into training (80%) and testing (20%) sets. Additionally, these patients were followed daily and assessed according to the Berlin definition. The model obtained an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.82 and yielded a predictive accuracy of 83%. For the first time, four new biomarkers were included in the model: decreased minimum haematocrit, glucose, and sodium and increased minimum white blood cell (WBC) count. CONCLUSIONS: This newly established machine learning-based model shows good predictive ability in Chinese patients with ARDS. External validation studies are necessary to confirm the generalisability of our approach across populations and treatment practices.

Effect of dominant follicle status at the time of retrieval on the clinical outcomes in natural cycle IVF combined with immature oocyte treatment.

OBJECTIVE: It is commonly believed that the oocytes from small follicles are unhealthy when a dominant follicle (DF) is recruited in the ovaries, especially when the DF is ovulated. This study aims to confirm whether the presence or ovulation of DF at the time of retrieval affects the clinical outcome of the natural cycle IVF with in vitro maturation (NC-IVF/M) treatment. METHODS: Data were collected from 446 women with regular menstrual cycle and 536 retrieval cycles using NC-IVF/M treatment. The cycles were divided into three groups based on the results of the oocyte retrieval cycle. Group A covers the collection of oocytes from the DF and small follicles; Group B incorporates failed oocyte retrieval from DF and then the oocytes are retrieved only from small follicles; and Group C includes the retrieval of oocytes only from small follicles accompanied with an ovulated DF. Furthermore, Group B and C have subgroups to include whether in vivo matured oocytes were obtained from small follicles. Following aspiration of DF and small follicles, mature oocytes were inseminated on the date of retrieval by intracytoplasmic sperm injection (ICSI) and the immature oocytes were matured in vitro. If the immature oocytes were matured in vitro, they were inseminated using ICSI, and then the embryos obtained from in vivo and in vitro matured oocytes were transferred accordingly. RESULTS: The oocytes from DF were successfully retrieved in 445 cycles (83.0%), failed to be retrieved in 54 cycles (10.1%) and ovulated in 37 cycles (6.9%). In Group A, an average of 2.0 ± 1.7 mature oocytes were retrieved, which was significantly higher than the average of Group B, with 1.3 ± 1.3 matured oocytes and Group C, with an average of 1.1 ± 1.5 matured oocytes (P < 0.01). However, the average number of immature oocytes retrieved from each group show no difference among the three groups. There was no significant difference in maturation rates of immature oocytes, fertilization rates among the three groups. The clinical pregnancy rate per transfer cycle is 34.5%, 34.6% and 25.7% in Group A, B and C, respectively. No significant differences were observed in embryonic development and implantation capacity in Group B and C in comparison to Group A. And there was no significant difference in clinical pregnancy, implantation, live birth and miscarriage rates among the three groups. No significant differences were observed in the developmental and implantation capacity according to with or without in vivo matured oocytes were retrieved in Group B and Group C. CONCLUSION: The presence or ovulation of the dominant follicle from the ovaries does not significantly influence the developmental and implantation capacity of immature oocytes retrieved from small follicles, suggesting that NC-IVF/M is a promising treatment option for women without ovarian stimulation.

MicroRNA-181 targets Yin Yang 1 expression and inhibits cervical cancer progression.

Dysregulated expression of microRNAs (miRNAs) has been observed in numerous types of human cancer, including cervical cancer (CC). The present study aimed to elucidate the expression and roles of miR­181 in cervical cancer tissues and cells. HeLa cells with a stable overexpression of miR­181 were generated and injected subcutaneously into the front legs of nude mice. Functional assays revealed a reduced rate of proliferation and an enhanced rate of apoptosis following transfection of CC cells with miR­181 mimics. In addition, miR­181 also suppressed tumor growth in the nude mice. At the molecular level, it was found that Yin Yang 1, an oncogene in several types of human cancer, was negatively regulated by miR­181. Therefore, the findings of the present study suggest that exogenous overexpression of miR­181 may be a potential approach for the treatment of CC in the future.

Importance of spondin 1 and cellular retinoic acid binding protein 1 in the clinical diagnosis of ovarian cancer.

BACKGROUND: Diagnosis of ovarian cancer is often delayed because of subtle symptoms and a lack of a specific, sensitive test useful for the general population. The majority of cases are diagnosed at late stages, after the tumor has metastasized and implanted on many other abdominal organs and cavity surfaces. A paucity of prognostic markers makes it difficult to define which tumors will act aggressively and shorten survival. Hence, it is imperative to have new screening tests for diagnosis of ovarian cancer at earlier stages, prior to metastatic progression. Diagnosis at these early stages will dramatically increase the overall survival of women with ovarian cancer. MATERIAL AND METHODS: Based on previously published literature on proposed molecular cell markers in ovarian carcinoma, we sought to validate the overexpression of two genes (cellular retinoic acid Binding Protein, CRABP-1, and spondin 1) through immunohistochemistry. RESULTS: We verified the overexpression of spondin 1 in ovarian cancer. Expression of cellular retinoic acid Binding Protein, CRABP-1 in whole ovarian cancer tissue sections was higher than in the TMA tissue cores. CONCLUSION: Our results thus demonstrate that spondin 1 is a useful marker for ovarian cancer; additionally, the high percentages of tumors that are positive for spondin 1 make it an ideal target for therapy. CRABP-1 was not expressed at high levels in any subtype of ovarian cancer, making it a poor marker.