No abstract

This study presents a feature selection method that uses genetic algorithms to create two artificial neural network-based models that provide a sequential forecast of accident duration from the time of accident notification to the accident site clearance. These two models can provide the estimated duration time by plugging in relevant traffic data as soon as an accident is notified. To select data feature, the genetic algorithm is designed to decrease the number of model inputs while preserving the relevant traffic characteristics. Using the proposed feature selection method, the mean absolute percentage error for forecasting accident duration at each time point is mostly under 29%, which indicates that these models have a reasonable forecasting ability. Thanks to this model, travelers and traffic management units can better understand the impact of accidents. This study shows that the proposed models are feasible in the Intelligent Transportation Systems context.

There are minimal data regarding chronic management of single-ventricle ventricular assist device (VAD) patients. This study aims to describe our center's multidisciplinary team management of single-ventricle patients supported long term with the Berlin Heart EXCOR Pediatric VAD. Patient #1 was a 4-year-old with double-outlet right ventricle with aortic atresia, L-looped ventricles, and heart block who developed heart failure 1 year after Fontan. She initially required extracorporeal membrane oxygenation support and was transitioned to Berlin Heart systemic VAD. She was supported for 363 days (cardiac intensive care unit [CICU] 335 days, floor 28 days). The postoperative course was complicated by intermittent infection including methicillin-resistant Staphylococcus aureus, intermittent hepatic and renal insufficiencies, and transient antithrombin, protein C, and protein S deficiencies resulting in multiple thrombi. She had a total of five pump changes over 10 months. Long-term medical management included anticoagulation with enoxaparin, platelet inhibition with aspirin and dipyridamole, and antibiotic prophylaxis using trimethoprim/sulfamethoxazole. She developed sepsis of unknown etiology and subsequently died from multiorgan failure. Patient #2 was a 4-year-old with hypoplastic left heart syndrome who developed heart failure 2 years after bidirectional Glenn shunt. At systemic VAD implantation, he was intubated with renal insufficiency. Post-VAD implantation, his renal insufficiency resolved, and he was successfully extubated to daytime nasal cannula and biphasic positive airway pressure at night. He was supported for 270 days (CICU 143 days, floor 127 days). The pump was upsized to a 50-mL pump in May 2011 for increased central venous pressures (29 mm Hg). Long-term medical management included anticoagulation with warfarin and single-agent platelet inhibition using dipyridamole due to aspirin resistance. He developed increased work of breathing requiring intubation, significant anasarca, and bleeding from the endotracheal tube. The family elected to withdraw support. Although both patients died prior to heart transplantation, a consistent specialized multidisciplinary team approach to the medical care of our VAD patients, consisting of cardiothoracic surgeons, heart transplant team, hematologists, pharmacists, infectious disease physicians, psychiatrists, specialty trained bedside nursing, and nurse practitioners, allowed us to manage these patients long term while awaiting heart transplantation.

Dopamine is a key neurotransmitter in reinforcement learning and action control. Recent findings suggest that these components are inherently entangled. Here, we tested if increases in dopamine tone by administration of L-DOPA upregulate deliberative "model-based" control of behavior or reflexive "model-free" control as predicted by dual-control reinforcement-learning models. Alternatively, L-DOPA may impair learning as suggested by "value" or "thrift" theories of dopamine. To this end, we employed a two-stage Markov decision-task to investigate the effect of L-DOPA (randomized cross-over) on behavioral control while brain activation was measured using fMRI. L-DOPA led to attenuated modelfree control of behavior as indicated by the reduced impact of reward on choice and increased stochasticity of model-free choices. Correspondingly, in the brain, L-DOPA decreased the effect of reward while prediction-error signals were unaffected. Taken together, our results suggest that L-DOPA reduces model-free control of behavior by attenuating the transfer of value to action..