Search

Background Stroke is a leading cause of disability, injury, and death in elderly people and represents a major public health problem with substantial medical and economic consequences. The incidence of stroke rapidly increases with age, doubling for each decade after age 55 years. Gait impairment is one of the most important problems after stroke, and improving walking function is often a key component of any rehabilitation program. To achieve this goal, a robotic gait trainer seems to be promising. In fact, some studies underline the efficacy of robotic gait training based on end-effector technology, for different diseases, in particular in stroke patients. In this randomized controlled trial, we verify the efficacy of the robotic treatment in terms of improving the gait and reducing the risk of falling and its long-term effects. Methods In this single-blind randomized controlled trial, we will include 152 elderly subacute stroke patients divided in two groups to receive a traditional rehabilitation program or a robotic rehabilitation using G-EO system, an end-effector device for the gait rehabilitation, in addition to the traditional therapy. Twenty treatment sessions will be conducted, divided into 3 training sessions per week, for 7 weeks. The control group will perform traditional therapy sessions lasting 50 min. The technological intervention group, using the G-EO system, will carry out 30 min of traditional therapy and 20 min of treatment with a robotic system. The primary outcome of the study is the evaluation of the falling risk. Secondary outcomes are the assessment of the gait improvements and the fear of falling. Further evaluations, such as length and asymmetry of the step, walking and functional status, and acceptance of the technology, will be carried. Discussion The final goal of the present study is to propose a new approach and an innovative therapeutic plan in the post-stroke rehabilitation, focused on the use of a robotic device, in order to obtain the beneficial effects of this treatment. Trial registration ClinicalTrials.gov NCT04087083. Registered on September 12, 2019

Background Serial electrocardiography aims to contribute to electrocardiogram (ECG) diagnosis by comparing the ECG under consideration with a previously made ECG in the same individual. Here, we present a novel algorithm to construct dedicated deep-learning neural networks (NNs) that are specialized in detecting newly emerging or aggravating existing cardiac pathology in serial ECGs. Methods We developed a novel deep-learning method for serial ECG analysis and tested its performance in detection of heart failure in post-infarction patients, and in the detection of ischemia in patients who underwent elective percutaneous coronary intervention. Core of the method is the repeated structuring and learning procedure that, when fed with 13 serial ECG difference features (intra-individual differences in: QRS duration; QT interval; QRS maximum; T-wave maximum; QRS integral; T-wave integral; QRS complexity; T-wave complexity; ventricular gradient; QRS-T spatial angle; heart rate; J-point amplitude; and T-wave symmetry), dynamically creates a NN of at most three hidden layers. An optimization process reduces the possibility of obtaining an inefficient NN due to adverse initialization. Results Application of our method to the two clinical ECG databases yielded 3-layer NN architectures, both showing high testing performances (areas under the receiver operating curves were 84% and 83%, respectively). Conclusions Our method was successful in two different clinical serial ECG applications. Further studies will investigate if other problem-specific NNs can successfully be constructed, and even if it will be possible to construct a universal NN to detect any pathologic ECG change. Electronic supplementary material The online version of this article (10.1186/s12938-019-0630-9) contains supplementary material, which is available to authorized users.