PubMed Health⌕ Search

Biomedical subjects

Gary Yen

Publications and source records attributed to Gary Yen.

2 recordsLinked to original sources

Prevention of group B streptococcal disease in the newborn.

Group B streptococcus (GBS) is a leading cause of morbidity and mortality among newborns. Universal screening for GBS among women at 35 to 37 weeks of gestation is more effective than administration of intrapartum antibiotics based on risk factors. Lower vaginal and rectal cultures for GBS are collected at 35 to 37 weeks of gestation, and routine dindamycin and erythromycin susceptibility testing is performed in women allergic to penicillin. Women with GBS bacteriuria in the current pregnancy and those who previously delivered a GBS-septic newborn are not screened but automatically receive intrapartum antibiotics. Intrapartum chemoprophylaxis is selected based on maternal allergy history and susceptibility of GBS isolates. Intravenous penicillin G is the preferred antibiotic, with ampicillin as an alternative. Penicillin G should be administered at least four hours before delivery for maximum effectiveness. Cefazolin is recommended in women allergic to penicillin who are at low risk of anaphylaxis. Clindamycin and erythromycin are options for women at high risk for anaphylaxis, and vancomycin should be used in women allergic to penicillin and whose cultures indicate resistance to clindamycin and erytbromycin or when susceptibility is unknown. Asymptomatic neonates born to GBS-colonized mothers should be observed for at least 24 hours for signs of sepsis. Newborns who appear septic should have diagnostic work-up including blood culture followed by initiation of ampicillin and gentamicin. Studies indicate that intrapartum prophylaxis of GBS carriers and selective administration of antibiotics to newborns reduce neonatal GBS sepsis by as much as 80 to 95 percent.

Antibiotic Prophylaxis↗

Hierarchical genetic algorithm for near optimal feedforward neural network design.

In this paper, we propose a genetic algorithm based design procedure for a multi layer feed forward neural network. A hierarchical genetic algorithm is used to evolve both the neural networks topology and weighting parameters. Compared with traditional genetic algorithm based designs for neural networks, the hierarchical approach addresses several deficiencies, including a feasibility check highlighted in literature. A multi objective cost function is used herein to optimize the performance and topology of the evolved neural network simultaneously. In the prediction of Mackey Glass chaotic time series, the networks designed by the proposed approach prove to be competitive, or even superior, to traditional learning algorithms for the multi layer Perceptron networks and radial basis function networks. Based upon the chosen cost function, a linear weight combination decision making approach has been applied to derive an approximated Pareto optimal solution set. Therefore, designing a set of neural networks can be considered as solving a two objective optimization problem.

Algorithms↗