METHODS: We first tested ten traditional machine learning algorithms, and then the three-best performing algorithms (three types of SVM) were used in the rest of the study. To improve the performance of these algorithms, a data preprocessing with normalization was carried out. Moreover, a genetic algorithm and particle swarm optimization, coupled with stratified 10-fold cross-validation, were used twice: for optimization of classifier parameters and for parallel selection of features.
RESULTS: The presented approach enhanced the performance of all traditional machine learning algorithms used in this study. We also introduced a new optimization technique called N2Genetic optimizer (a new genetic training). Our experiments demonstrated that N2Genetic-nuSVM provided the accuracy of 93.08% and F1-score of 91.51% when predicting CAD outcomes among the patients included in a well-known Z-Alizadeh Sani dataset. These results are competitive and comparable to the best results in the field.
CONCLUSIONS: We showed that machine-learning techniques optimized by the proposed approach, can lead to highly accurate models intended for both clinical and research use.
METHODS: A parallel, cluster, randomized controlled, interventional trial is being conducted for 18 months in Damansara Damai, Selangor, Malaysia, to determine the efficacy of using gravid oviposition sticky (GOS) trap and dengue non-structural 1 (NS1) antigen test for early surveillance of dengue among Aedes mosquitoes to reduce dengue outbreaks. Eight residential apartments were randomly assigned into intervention and control arms. GOS traps are set at the apartments to collect Aedes weekly, following which dengue NS1 antigen is detected in these mosquitoes. When a dengue-positive mosquito is detected, the community will be advised to execute vector search-and-destroy and protective measures. The primary outcome concerns the the percentage change in the (i) number of dengue cases and (ii) durations of dengue outbreaks. Whereas other outcome measures include the change in density threshold of Aedes and changes in dengue-related knowledge, attitude and practice among cluster inhabitants.
DISCUSSION: This is a proactive and early dengue surveillance in the mosquito vector that does not rely on notification of dengue cases. Surveillance using the GOS traps should be able to efficiently provide sufficient coverage for multistorey dwellings where population per unit area is likely to be higher. Furthermore, trapping dengue-infected mosquitoes using the GOS trap, helps to halt the dengue transmission carried by the mosquito. It is envisaged that the results of this randomized controlled trial will provide a new proactive, cheap and targeted surveillance tool for the prevention and control of dengue outbreaks.
TRIAL REGISTRATION: This is a parallel-cluster, randomized controlled, interventional trial, registered at ClinicalTrials.gov (ID: NCT03799237), on 8th January 2019 (retrospectively registered).
DESIGN: An analysis of the English Longitudinal Study of Ageing (ELSA) cohort.
SETTING: United Kingdom community-based.
PARTICIPANTS: 5197 community-dwelling older adults recruited to a prospective longitudinal cohort study.
MEASUREMENTS: Data on the occurrence of falls and number of falls, which occurred during a 12-month follow-up period, were assessed against the specific cognitive domains of memory, numeracy skills, and executive function. Binomial logistic regression was performed to evaluate the association between each cognitive domain and the dichotomous outcome of falls in the preceding 12 months using unadjusted and adjusted models.
RESULTS: Of the 5197 participants included in the analysis, 1308 (25%) reported a fall in the preceding 12 months. There was no significant association between the occurrence of a fall and specific forms of cognitive dysfunction after adjusting for self-reported hearing, self-reported eyesight, and functional performance. After adjustment, only orientation (odds ratio [OR]: 0.80; 95% confidence intervals [CI]: 0.65-0.98, p = 0.03) and verbal fluency (adjusted OR: 0.98; 95% CI: 0.96-1.00; p = 0.05) remained significant for predicting recurrent falls.
CONCLUSIONS: The cognitive phenotype rather than cognitive impairment per se may predict future falls in those presenting with more than one fall.
Methods: The assay system utilized a known NS2B/NS3 peptide substrate, a recombinant of NS2B/NS3 protease with proprietary StrepTactin® donor and nickel chelate acceptor beads in 384-well format.
Results: The optimized assay to screen for NS2B/NS3 protease inhibitors was demonstrated to be potentially useful with reasonable z' factor, coefficient variance and signal to background ratio. However, screening of synthesized thioguanine derivatives using the optimized AlphaScreen® assay revealed weak NS2B/NS3 inhibition activities.
Conclusion: The AlphaScreen® assay to screen for NS2B/NS3 protease inhibitors is potentially applicable for high throughput screening.
METHODS: This was an open-label, prospective, multicentre, randomized trial. Three hospitals where the current protocol was to administer prophylactic amoxycillin-clavulanic acid served as the sites of recruitment. Women who delivered vaginally beyond 24+ 0 weeks of gestation with ragged membranes were invited to participate in the trial and randomized into prophylaxis or expectant management with medical advice by blocks of 10, at a 1:1 ratio. A medication adherence diary was provided and patients followed up at 2 weeks and 6 weeks postpartum.
RESULTS: A total of 6569 women gave birth vaginally in three centres during the trial period, of which 10.9% had ragged membranes. The incidence of endometritis was not significantly raised in women with or without prophylaxis (0.90% vs 0.29%; p = 0.60). All cases of endometritis presented within the first 2 weeks and preventive use of antibiotics did not ameliorate the severity of endometritis since rates of ICU admission, surgical evacuation and transfusion were comparable.
CONCLUSION: Preventive use of antibiotics after vaginal delivery in women with ragged placental membranes did not result in a reduction of endometritis. Educating women on the signs and symptoms of endometritis would suffice. Based on the reported incidence of ragged membranes, a change in practice would result in 1500 less prescriptions of antibiotics per annum in these three centres.
TRIAL REGISTRATION: NCT03459599 (Retrospectively registered on 9 March 2018).