Logistic regression analysis and machine learning for predicting post-stroke gait independence: a retrospective study.

This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms-specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893-0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable.

Comparing the contribution of each clinical indicator in predictive models trained on 980 subacute stroke patients: a retrospective study.

Post-stroke disability affects patients' lifestyles after discharge, and it is essential to predict functional recovery early in hospitalization to allow time for appropriate decisions. Previous studies reported important clinical indicators, but only a few clinical indicators were analyzed due to insufficient numbers of cases. Although review articles can exhaustively identify many prognostic factors, it remains impossible to compare the contribution of each predictor. This study aimed to determine which clinical indicators contribute more to predicting the functional independence measure (FIM) at discharge by comparing standardized coefficients. In this study, 980 participants were enrolled to build predictive models with 32 clinical indicators, including the stroke impairment assessment set (SIAS). Trunk function had the most significant standardized coefficient of 0.221. The predictive models also identified easy FIM sub-items, SIAS, and grip strength on the unaffected side as having positive standardized coefficients. As for the predictive accuracy of this model, R2 was 0.741. This is the first report that included FIM sub-items separately in post-stroke predictive models with other clinical indicators. Trunk function and easy FIM sub-items were included in the predictive model with larger positive standardized coefficients. This predictive model may predict prognosis with high accuracy, fewer clinical indicators, and less effort to predict.

Improvement of predictive accuracies of functional outcomes after subacute stroke inpatient rehabilitation by machine learning models.

OBJECTIVES: Stepwise linear regression (SLR) is the most common approach to predicting activities of daily living at discharge with the Functional Independence Measure (FIM) in stroke patients, but noisy nonlinear clinical data decrease the predictive accuracies of SLR. Machine learning is gaining attention in the medical field for such nonlinear data. Previous studies reported that machine learning models, regression tree (RT), ensemble learning (EL), artificial neural networks (ANNs), support vector regression (SVR), and Gaussian process regression (GPR), are robust to such data and increase predictive accuracies. This study aimed to compare the predictive accuracies of SLR and these machine learning models for FIM scores in stroke patients. METHODS: Subacute stroke patients (N = 1,046) who underwent inpatient rehabilitation participated in this study. Only patients' background characteristics and FIM scores at admission were used to build each predictive model of SLR, RT, EL, ANN, SVR, and GPR with 10-fold cross-validation. The coefficient of determination (R2) and root mean square error (RMSE) values were compared between the actual and predicted discharge FIM scores and FIM gain. RESULTS: Machine learning models (R2 of RT = 0.75, EL = 0.78, ANN = 0.81, SVR = 0.80, GPR = 0.81) outperformed SLR (0.70) to predict discharge FIM motor scores. The predictive accuracies of machine learning methods for FIM total gain (R2 of RT = 0.48, EL = 0.51, ANN = 0.50, SVR = 0.51, GPR = 0.54) were also better than of SLR (0.22). CONCLUSIONS: This study suggested that the machine learning models outperformed SLR for predicting FIM prognosis. The machine learning models used only patients' background characteristics and FIM scores at admission and more accurately predicted FIM gain than previous studies. ANN, SVR, and GPR outperformed RT and EL. GPR could have the best predictive accuracy for FIM prognosis.

Effects of the COVID-19 Pandemic on Physical Function of Community-Dwelling People with Disabilities in Japan.

In 2020, COVID-19 spread throughout the world, and international measures such as travel bans, quarantines, and increased social distancing were implemented. In Japan, the number of infected people increased, and a state of emergency was declared from 16 April to 25 May 2020. Such a change in physical activity could lead to a decline in physical function in people with disabilities. A retrospective study was conducted to determine the impact of the pandemic on the physical function of disabled persons living in the community. Data were collected at four points in time: two points before the declaration of the state of emergency was issued and two points after the declaration period had ended. Time series data of physical function at four points in time were compared for 241 people with disabilities. The mean age was 72.39 years; 157 had stroke, 59 musculoskeletal disease, and 26 other diseases. Overall, there was a long-term decrease in walking speed (p < 0.001) and a worsening of the Timed Up-and-Go (TUG) score (p < 0.001) after the period of the state of emergency. The TUG score worsened only in the group with a walking speed of 1.0 m/s or less before the state of emergency (p = 0.064), suggesting that this group was more susceptible.

Determinants of Step-through Gait Pattern Acquisition in Subacute Stroke Patients.

Objectives: Stroke patients may have a step-to gait pattern during the early stages of gait reacquisition. This gait provides stability, but it is slow and inefficient. Therefore, acquiring step-through gait is desirable for better efficiency as ability improves. This study aimed to examine the relevant factors affecting the acquisition of step-through gait pattern in subacute stroke patients based on assessments of physical function at admission. Methods: This was a retrospective cohort study. A total of 91 patients with hemiplegic stroke, Functional Independence Measure (FIM) gait item of 4 or less on admission, and FIM gait item of 5 or greater on discharge were included. Factors necessary for the acquisition of step-through gait pattern were examined based on the motor function assessed by Stroke Impairment Assessment Set (SIAS) at the time of admission. Gait pattern was defined by the gait step length of the Tinetti Performance-Oriented Mobility Assessment at discharge. Results: Knee-joint extension function on the paralyzed side was determined as a factor associated with the acquisition of step-through gait pattern at discharge [odds ratio 2.24, 95% confidence interval (CI) 1.44‒3.50, P<0.001]. The area under the receiver operating characteristic curve for predicting the step-through gait pattern at discharge was 0.786 (95% CI 0.676-0.896, P<0.001) for the SIAS knee joint score at admission; the optimal cut-off score being 2 or greater (sensitivity 81%, specificity 61%). Conclusions: Knee function on the paralyzed side in subacute stroke patients is an independent predictor for the acquisition of step-through gait pattern.

Comparison of the after-effects of transcranial direct current stimulation over the motor cortex in patients with stroke and healthy volunteers.

It is known that weak transcranial direct current stimulation (tDCS) induces persistent excitability changes in the cerebral cortex. There are, however, few studies that compare the after-effects of anodal versus cathodal tDCS in patients with stroke. This study assessed the after-effects of tDCS over the motor cortex in patients with hemiparetic stroke and healthy volunteers. Seven stroke patients and nine healthy volunteers were recruited. Ten minutes of anodal and cathodal tDCS (1 mA) and sham stimulation were applied to the affected primary motor cortex (M1) on different days. In healthy subjects, tDCS was applied to the right M1. Before and after tDCS, motor-evoked potentials (MEPs) in the first dorsal interosseous (FDI) muscle and silent period were measured. Anodal tDCS increased the MEPs of the affected FDI in patients with stroke as well as in healthy subjects. Cathodal tDCS increased the MEPs of the affected FDI in patients with stroke. In healthy subjects, however, cathodal tDCS decreased the MEPs. We found no significant change in the duration of the silent period after anodal or cathodal tDCS. We found that both anodal and cathodal tDCS increased the affected M1 excitability in patients with stroke. It is thought that the after-effects of tDCS are different in patients with stroke compared with healthy subjects.

Clinical neurophysiology in the diagnosis of peroneal nerve palsy.

Peroneal neuropathy is one of the common focal mononeuropathies in the lower extremities occurring in both adults and children. Foot drop due to weakness of ankle dorsiflexion is the most common presentation of a peroneal neuropathy. It may also result from other causes involving the upper or lower motor neurons. Disorders that must be distinguished from peroneal neuropathy include sciatic mononeuropathy, lumbosacral plexopathy, motor neuron disease, polyneuropathy, and an L5 radiculopathy. To establish a diagnosis, electrodiagnostic studies have been used to localize the level of the abnormality and to establish prognosis. The most common site of injury is the fibular head, but focal neuropathies have also been reported at the level of the calf, ankle, and foot. In this article, we overviewed the peroneal nerve palsy, and its diagnosis by neurophysiologic evaluation, conduction study and needle EMG. The neurophysiologic information gives us the underlying pathophysiology and its prognosis. Therefore the neurophysiologic evaluation must be performed not only for the differential diagnosis, but also for planning the treatment strategy.