RESUMEN
Methods for assessing the loss of hand function post-stroke examine limited aspects of motor performance and are not sensitive to subtle changes that can cause deficits in everyday object manipulation tasks. Efficiently lifting an object entails a prediction of required forces based on intrinsic features of the object (sensorimotor integration), short-term updates in the forces required to lift objects that are poorly predicted (sensorimotor memory), as well as the ability to modulate distal fingertip forces, which are not measured by existing assessment tools used in clinics for both diagnostic and rehabilitative purposes. The presented research examined these three components of skilled object manipulation in 60 chronic, unilateral middle cerebral artery stroke participants. Performance was compared to age-matched control participants, and linear regressions were used to predict performance based on clinical scores. Most post-stroke participants performed below control levels in at least one of the tasks. Post-stroke participants presented with combinations of deficits in each of the tasks performed, regardless of the hemisphere damaged by the stroke. Surprisingly, the ability to modulate distal forces was impaired in those patients with damage ipsilateral (right hemisphere) to the hand being used. Sensorimotor integration was also impaired in patients with right hemisphere damage, though they performed at control levels in later lifts, whereas left-hemisphere-damaged patients did not. Lastly, during a task requiring sensorimotor memory, neither patient group performed outside of control ranges on initial lifts, with patients with right hemisphere damage showing impaired performance in later lifts suggesting they were unable to learn the mapping novel mapping of color and mass of the objects. The presented research demonstrates unilateral MCA stroke patients can have deficits in one or more components required for the successful manipulation of hand-held objects and that skillful object lifting requires intact bilateral systems. Further, this information may be used in future studies to aid efforts that target rehabilitation regimens to a stroke survivor's specific pattern of deficits.
Asunto(s)
Infarto de la Arteria Cerebral Media , Accidente Cerebrovascular , Humanos , Infarto de la Arteria Cerebral Media/complicaciones , Infarto de la Arteria Cerebral Media/diagnóstico por imagen , Desempeño Psicomotor , Arteria Cerebral Media/diagnóstico por imagen , Fuerza de la Mano , Lateralidad Funcional , Accidente Cerebrovascular/complicaciones , Accidente Cerebrovascular/diagnóstico por imagenRESUMEN
While many business intelligence methods have been applied to predict movie box office revenue, the studies using an ensemble approach to predict box office revenue are almost nonexistent. In this study, we propose decision trees, k-nearest-neighbors (k-NN), and linear regression using ensemble methods and the prediction performance of decision trees based on random forests, bagging and boosting are compared with that of k-NN and linear regression based on bagging and boosting using the sample of 1439 movies. The results indicate that ensemble methods based on decision trees (random forests, bagging, boosting) outperform ensemble methods based on k-NN (bagging, boosting) in predicting box office at week 1, 2, 3 after release. Decision trees using ensemble methods provide better prediction performance than ensemble methods based on linear regression analysis in the box office at week 1 after release. This is explained by the results that after comparing the prediction performance between ensemble methods and non-ensemble methods. For decision tree methods, unlike the other methods, the prediction performance of ensemble methods is greater than that of non-ensemble methods. This shows that decision trees using ensemble methods provide better application effectiveness of ensemble methods than k-NN and linear regression analysis.