Impact of medical technologies may be predicted using constructed graph bibliometrics.

Scientific research is driven by allocation of funding to different research projects based in part on the predicted scientific impact of the work. Data-driven algorithms can inform decision-making of scarce funding resources by identifying likely high-impact studies using bibliometrics. Compared to standardized citation-based metrics alone, we utilize a machine learning pipeline that analyzes high-dimensional relationships among a range of bibliometric features to improve the accuracy of predicting high-impact research. Random forest classification models were trained using 28 bibliometric features calculated from a dataset of 1,485,958 publications in medicine to retrospectively predict whether a publication would become high-impact. For each random forest model, the balanced accuracy score was above 0.95 and the area under the receiver operating characteristic curve was above 0.99. The high performance of high impact research prediction using our proposed models show that machine learning technologies are promising algorithms that can support funding decision-making for medical research.

Prevalence of Sickle Cell Trait in the Southern Suburb of Beirut, Lebanon.

OBJECTIVE: The objective of this study was to assess the prevalence, gender differences, and time trends of Sickle Cell Trait in the Southern Suburb of Beirut, Lebanon, as well as to highlight the importance of screening for Sickle Cell Trait carriers in this population. Another objective was to describe a new screening technique for Sickle Cell Trait carriers. METHODS: This was a retrospective cohort study carried out at a private laboratory in the Southern Suburb of Beirut, Lebanon between 2002 and 2014. The sickling test was carried out for each patient using two methods: the classical "sodium metabisulfite sickling test", and the new "sickling test method" used in the private lab. As a confirmatory test, hemoglobin electrophoresis was run on a random sample of 223 cases which were found to be positive using the two sickling tests. RESULTS: A total of 899 cases were found to be positive for the sickle cell trait out of 184,105 subjects screened during the 12-year period, prevalence = 0.49% (95% CI: 0.46 - 0.52). Among the total sample, females were found to have higher prevalence, where no time trend over the studied period was noted. The haemoglobin electrophoresis method confirmed the results of this new sickling test technique among the random sample of the 223 cases. CONCLUSION: We found that the prevalence of sickle cell trait is lower as compared to other Arab countries, higher in females, with no significant time trend. The sickle cell test was found to be an accurate, simple and cheap test that could be easily added as a requirement for the pre-marital testing to screen for Sickle Cell Trait carriers.