Machine Learning for Predicting Motor Improvement After Acute Subcortical Infarction Using Baseline Whole Brain Volumes

Application of Isokinetic Dynamometry Data in Predicting Gait Deviation Index Using Machine Learning in Stroke Patients: A Cross-Sectional Study

BACKGROUND

Three-dimensional gait analysis, supported by advanced sensor systems, is a crucial component in the rehabilitation assessment of post-stroke hemiplegic patients. However, the sensor data generated from such analyses are often complex and challenging to interpret in clinical practice, requiring significant time and complicated procedures. The Gait Deviation Index (GDI) serves as a simplified metric for quantifying the severity of pathological gait. Although isokinetic dynamometry, utilizing sophisticated sensors, is widely employed in muscle function assessment and rehabilitation, its application in gait analysis remains underexplored.

OBJECTIVE

This study aims to investigate the use of sensor-acquired isokinetic muscle strength data, combined with machine learning techniques, to predict the GDI in hemiplegic patients. This study utilizes data captured from sensors embedded in the Biodex dynamometry system and the Vicon 3D motion capture system, highlighting the integration of sensor technology in clinical gait analysis.

METHODS

This study was a cross-sectional, observational study that included a cohort of 150 post-stroke hemiplegic patients. The sensor data included measurements such as peak torque, peak torque/body weight, maximum work of repeated actions, coefficient of variation, average power, total work, acceleration time, deceleration time, range of motion, and average peak torque for both flexor and extensor muscles on the affected side at three angular velocities (60°/s, 90°/s, and 120°/s) using the Biodex System 4 Pro. The GDI was calculated using data from a Vicon 3D motion capture system. This study employed four machine learning models-Lasso Regression, Random Forest (RF), Support Vector regression (SVR), and BP Neural Network-to model and validate the sensor data. Model performance was evaluated using mean squared error (MSE), the coefficient of determination (R2), and mean absolute error (MAE). SHapley Additive exPlanations (SHAP) analysis was used to enhance model interpretability.

RESULTS

The RF model outperformed others in predicting GDI, with an MSE of 16.18, an R2 of 0.89, and an MAE of 2.99. In contrast, the Lasso Regression model yielded an MSE of 22.29, an R2 of 0.85, and an MAE of 3.71. The SVR model had an MSE of 31.58, an R2 of 0.82, and an MAE of 7.68, while the BP Neural Network model exhibited the poorest performance with an MSE of 50.38, an R2 of 0.79, and an MAE of 9.59. SHAP analysis identified the maximum work of repeated actions of the extensor muscles at 60°/s and 120°/s as the most critical sensor-derived features for predicting GDI, underscoring the importance of muscle strength metrics at varying speeds in rehabilitation assessments.

CONCLUSIONS

This study highlights the potential of integrating advanced sensor technology with machine learning techniques in the analysis of complex clinical data. The developed GDI prediction model, based on sensor-acquired isokinetic dynamometry data, offers a novel, streamlined, and effective tool for assessing rehabilitation progress in post-stroke hemiplegic patients, with promising implications for broader clinical application.

Explainable Deep-Learning Prediction for Brain-Computer Interfaces Supported Lower Extremity Motor Gains Based on Multistate Fusion

Predicting the potential for recovery of motor function in stroke patients who undergo specific rehabilitation treatments is an important and major challenge. Recently, electroencephalography (EEG) has shown potential in helping to determine the relationship between cortical neural activity and motor recovery. EEG recorded in different states could more accurately predict motor recovery than single-state recordings. Here, we design a multi-state (combining eyes closed, EC, and eyes open, EO) fusion neural network for predicting the motor recovery of patients with stroke after EEG-brain-computer-interface (BCI) rehabilitation training and use an explainable deep learning method to identify the most important features of EEG power spectral density and functional connectivity contributing to prediction. The prediction accuracy of the multi-states fusion network was 82%, significantly improved compared with a single-state model. The neural network explanation result demonstrated the important region and frequency oscillation bands. Specifically, in those two states, power spectral density and functional connectivity were shown as the regions and bands related to motor recovery in frontal, central, and occipital. Moreover, the motor recovery relation in bands, the power spectrum density shows the bands at delta and alpha bands. The functional connectivity shows the delta, theta, and alpha bands in the EC state; delta, theta, and beta mid at the EO state are related to motor recovery. Multi-state fusion neural networks, which combine multiple states of EEG signals into a single network, can increase the accuracy of predicting motor recovery after BCI training, and reveal the underlying mechanisms of motor recovery in brain activity.

Prediction Model for Unfavorable Outcome in Spontaneous Intracerebral Hemorrhage Based on Machine Learning

OBJECTIVE

The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML).

METHODS

Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR).

RESULTS

We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables.

CONCLUSION

The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

Recovery of Patients With Upper Limb Paralysis Due to Stroke Who Underwent Intervention Using Low-Frequency Repetitive Transcranial Magnetic Stimulation Combined With Occupational Therapy: A Retrospective Cohort Study

OBJECTIVES

The combination of repetitive transcranial magnetic stimulation (rTMS) and motor practice is based on the theory of neuromodulation and use-dependent plasticity. Predictive planning of occupational therapy (OT) is important for patients with rTMS conditioning. Recovery characteristics based on the severity of pretreatment upper extremity paralysis can guide the patient's practice plan for using the paretic hand. Therefore, we evaluated the recovery of patients with upper limb paralysis due to stroke who underwent a novel intervention of rTMS combined with OT (NEURO) according to the severity of upper limb paralysis based on the scores of the Fugl-Meyer assessment for upper extremity (FMA-UE) with recovery in proximal upper extremity, wrist, hand, and coordination.

MATERIALS AND METHODS

In this multicenter retrospective cohort study, the recovery of 1397 patients with upper limb paralysis was analyzed by severity at six hospitals that were accredited by the Japanese Stimulation Therapy Society for treatment. The delta values of the FMA-UE scores before and after NEURO were compared among the groups with severe, moderate, and mild paralysis using the generalized linear model.

RESULTS

NEURO significantly improved the FMA-UE total score according to the severity of paralysis (severe = 5.3, moderate = 6.0, and mild = 2.9). However, when the FMA-UE subscores were analyzed separately, the results indicated specific improvements in shoulder/elbow, wrist, fingers, and coordination movements, depending on the severity.

CONCLUSIONS

This study had enough patients who were divided according to severity and stratified by lesion location and handedness parameters. Our results suggest that independently of these factors, the extent of recovery of upper limb motor parts after NEURO varies according to the severity of paralysis.

Performance Comparison of Different Neuroimaging Methods for Predicting Upper Limb Motor Outcomes in Patients after Stroke

Several neuroimaging methods have been proposed to assess the integrity of the corticospinal tract (CST) for predicting recovery of motor function after stroke, including conventional structural magnetic resonance imaging (sMRI) and diffusion tensor imaging (DTI). In this study, we aimed to compare the predicative performance of these methods using different neuroimaging modalities and optimize the prediction protocol for upper limb motor function after stroke in a clinical environment. We assessed 28 first-ever stroke patients with upper limb motor impairment. We used the upper extremity module of the Fugl-Meyer assessment (UE-FM) within 1 month of onset (baseline) and again 3 months poststroke. sMRI (T1- and T2-based) was used to measure CST-weighted lesion load (CST-wLL), and DTI was used to measure the fractional anisotropy asymmetry index (FAAI) and the ratio of fractional anisotropy (rFA). The CST-wLL within 1 month poststroke was closely correlated with upper limb motor outcomes and recovery potential. CST‐wLL ≥ 2.068 cc indicated serious CST damage and a poor outcome (100%). CST‐wLL < 1.799 cc was correlated with a considerable rate (>70%) of upper limb motor function recovery. CST-wLL showed a comparable area under the curve (AUC) to that of the CST-FAAI (p = 0.71). Inclusion of extra-CST-FAAI did not significantly increase the AUC (p = 0.58). Our findings suggest that sMRI-derived CST-wLL is a precise predictor of upper limb motor outcomes 3 months poststroke. We recommend this parameter as a predictive imaging biomarker for classifying patients' recovery prognosis in clinical practice. Conversely, including DTI appeared to induce no significant benefits.