Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review

Prediction of the functional outcome of intensive inpatient rehabilitation after stroke using machine learning methods

An accurate and reliable functional prognosis is vital to stroke patients addressing rehabilitation, to their families, and healthcare providers. This study aimed at developing and validating externally patient-wise prognostic models of the global functional outcome at discharge from intensive inpatient post-acute rehabilitation after stroke, based on a standardized comprehensive multidimensional assessment performed at admission to rehabilitation. Patients addressing intensive inpatient rehabilitation pathways within 30 days from stroke were prospectively enrolled in two consecutive multisite studies. Demographics, description of the event, clinical/functional, and psycho-social data were collected. The outcome of interest was disability in basic daily living activities at discharge, measured by the modified Barthel Index (mBI). Machine learning-based prognostic models were developed, internally cross-validated, and externally validated. Interpretability techniques were applied for the analysis of predictors. 385 patients were considered, 220 (165) for training (external test) sets. A 50.9% (55.8%) of women, 79.5% (80.0%) of ischemic, and a median [interquartile range- IQR] age of 80.0[15.0] (79.0[17.0]) were registered. The Support Vector Machine obtained the best validation performances and a median absolute error [IQR] on discharge mBI estimation of 11.5[15.0] and 9.2[13.0] points on the internal and external testing, respectively. The baseline variables providing the main contributions to the predictions were mBI, motor upper-limb score, age, and cognitive screening score. We achieved a solution to support the formulation of a functional prognosis at intensive rehabilitation admission. The interpretability analysis confirms the relevance of easily collected motor and cognitive dataat admission and of the patient's age.Trial registration: Prospectively registered on ClinicalTrials.gov (registration numbers RIPS NCT03866057, STRATEGY NCT05389878).

Closed-loop rehabilitation of upper-limb dyskinesia after stroke: from natural motion to neuronal microfluidics

This review proposes an innovative closed-loop rehabilitation strategy that integrates multiple subdomains of stroke science to address the global challenge of upper-limb dyskinesia post-stroke. Despite advancements in neural remodeling and rehabilitation research, the compartmentalization of subdomains has limited the effectiveness of current rehabilitation strategies. Our approach unites key areas-including the post-stroke brain, upper-limb rehabilitation robotics, motion sensing, metrics, neural microfluidics, and neuroelectronics-into a cohesive framework designed to enhance upper-limb motion rehabilitation outcomes. By leveraging cutting-edge technologies such as lightweight rehabilitation robotics, advanced motion sensing, and neural microfluidic models, this strategy enables real-time monitoring, adaptive interventions, and personalized rehabilitation plans. Furthermore, we explore the potential of closed-loop systems to drive neural plasticity and functional recovery, offering a transformative perspective on stroke rehabilitation. Finally, we discuss future directions, emphasizing the integration of emerging technologies and interdisciplinary collaboration to advance the field. This review highlights the promise of closed-loop strategies in achieving unprecedented integration of subdomains and improving post-stroke upper-limb rehabilitation outcomes.

Artificial intelligence in stroke rehabilitation: From acute care to long-term recovery

Stroke is a leading cause of disability worldwide, driving the need for advanced rehabilitation strategies. The integration of Artificial Intelligence (AI) into stroke rehabilitation presents significant advancements across the continuum of care, from acute diagnosis to long-term recovery. This review explores AI's role in stroke rehabilitation, highlighting its impact on early diagnosis, motor recovery, and cognitive rehabilitation. AI-driven imaging techniques, such as deep learning applied to CT and MRI scans, improve early diagnosis and identify ischemic penumbra, enabling timely, personalized interventions. AI-assisted decision support systems optimize acute stroke treatment, including thrombolysis and endovascular therapy. In motor rehabilitation, AI-powered robotics and exoskeletons provide precise, adaptive assistance, while AI-augmented Virtual and Augmented Reality environments offer immersive, tailored recovery experiences. Brain-Computer Interfaces utilize AI for neurorehabilitation through neural signal processing, supporting motor recovery. Machine learning models predict functional recovery outcomes and dynamically adjust therapy intensities. Wearable technologies equipped with AI enable continuous monitoring and real-time feedback, facilitating home-based rehabilitation. AI-driven tele-rehabilitation platforms overcome geographic barriers by enabling remote assessment and intervention. The review also addresses the ethical, legal, and regulatory challenges associated with AI implementation, including data privacy and technical integration. Future research directions emphasize the transformative potential of AI in stroke rehabilitation, with case studies and clinical trials illustrating the practical benefits and efficacy of AI technologies in improving patient recovery.

A Comprehensive Understanding of Postural Tone Biomechanics: Intrinsic Stiffness, Functional Stiffness, Antagonist Coactivation, and COP Dynamics in Post-Stroke Adults

OBJECTIVE

To analyse the relationship between traditional stiffness and muscle antagonist coactivation in both stroke and healthy participants, using linear and non-linear measures of coactivation and COP during standing, stand-to-sit, and gait initiation.

METHODS

Participants were evaluated through a cross-sectional design. Electromyography, isokinetic dynamometer, and force plate were used to calculate coactivation, intrinsic and functional stiffness, and COP displacement, with both linear and non-linear metrics. Spearman's correlations and Mann-Whitney tests were applied (p < 0.05).

RESULTS

Post-stroke participants showed higher contralesional intrinsic stiffness (p = 0.041) and higher functional stiffness (p = 0.047). Coactivation was higher on the ipsilesional side during standing (p = 0.012) and reduced on the contralesional side during standing and transitions (p < 0.01). Moderate correlations were found between intrinsic and functional stiffness (p = 0.030) and between coactivation and intrinsic stiffness (standing and stand-to-sit: p = 0.048) and functional stiffness (gait initiation: p = 0.045). COP displacement was reduced in post-stroke participants during standing (p < 0.001) and increased during gait initiation (p = 0.001). Post-stroke participants exhibited increased gastrocnemius/tibialis anterior coactivation during gait initiation (p = 0.038) and higher entropy and stability across tasks (p < 0.001).

CONCLUSION

Post-stroke participants showed higher contralesional intrinsic and functional stiffness, reduced coactivation in static tasks, and increased coactivation in dynamic tasks. COP and coactivation analyses revealed impaired stability and random control, highlighting the importance of multidimensional evaluations of postural tone.

Dynamic, Interpretable, Machine Learning-Based Outcome Prediction as a New Emerging Opportunity in Acute Ischemic Stroke Patient Care: A Proof-of-Concept Study

Introduction: While the machine learning (ML) model's black-box nature presents a significant barrier to effective clinical application, the dynamic nature of stroke patients' recovery further undermines the reliability of established predictive scores and models, making them less suitable for accurate prediction and appropriate patient care. This research is aimed at building and evaluating an interpretable ML-based model, which would perform outcome prediction at different time points of patients' recovery, giving more secure and understandable output through interpretable packages. Materials and Methods: A retrospective analysis was conducted on acute ischemic stroke (AIS) patients treated with alteplase at the Neurology Clinic of the University Clinical Center of Vojvodina (Novi Sad, Serbia), for 14 years. Clinical data were grouped into four categories based on collection time-baseline, 2-h, 24-h, and discharge features-serving as inputs for three different classifiers-support vector machine (SVM), logistic regression (LR), and random forest (RF). The 90-day modified Rankin scale (mRS) was used as the outcome measure, distinguishing between favorable (mRS ≤ 2) and unfavorable outcomes (mRS ≥ 3). Results: The sample was described with 49 features and included 355 patients, with a median age of 67 years (interquartile range (IQR) 60-74 years), 66% being male. The models achieved strong discrimination in the testing set, with area under the curve (AUC) values ranging from 0.80 to 0.96. Additionally, they were compared with a model based on the DRAGON score, which showed an AUC of 0.760 (95% confidence interval (CI), 0.640-0.862). The decision-making process was more thoroughly understood using interpretable packages: Shapley additive explanation (SHAP) and local interpretable model-agnostic explanation (LIME). They revealed the most significant features at both the group and individual patient levels. Conclusions and Clinical Implications: This study demonstrated the moderate to strong efficacy of interpretable ML-based models in predicting the functional outcomes of alteplase-treated AIS patients. In all constructed models, age, onset-to-treatment time, and platelet count were recognized as the important predictors, followed by clinical parameters measured at different time points, such as the National Institutes of Health Stroke Scale (NIHSS) and systolic and diastolic blood pressure values. The dynamic approach, coupled with interpretable models, can aid in providing insights into the potential factors that could be modified and thus contribute to a better outcome.

Clinical and neurophysiological predictors of the functional outcome in right-hemisphere stroke

OBJECTIVE

The aim of the present study is to examine the relationship between EEG measures and functional recovery in right-hemisphere stroke patients.

METHODS

Participants with stroke (PS) and neurologically unimpaired controls (UC) were enrolled. At enrolment, all participants were assessed for motor and cognitive functioning with specific scales (motricity index, trunk control test, Level of Cognitive Functioning, and Functional Independence Measure (FIM). Moreover, EEG data were recorded. At discharge, participants were re-tested with the FIM RESULTS: Powers in the delta, theta, alpha, and beta bands and connectivity within the fronto-parietal network were compared between groups. Then, the between-group discriminative EEG measures and the motor/cognitive scales were used to feed a machine learning algorithm to predict FIM scores at discharge and the length of hospitalization (LoH). Higher delta, theta, and beta and impaired connectivity were found in PS compared to UC. Moreover, motor/cognitive functioning, beta power, and fronto-parietal connectivity predicted the FIM score at discharge and the LoH (accuracy=73.2 % and 85.2 % respectively).

CONCLUSIONS

Results show that the integration of motor/cognitive scales and EEG measures can reveal the rehabilitative potentials of PS predicting their functional outcome and LoH.

SIGNIFICANCE

Synergistic clinical and electrophysiological models can support rehabilitative decision-making.

Artificial intelligence in stroke risk assessment and management via retinal imaging

Retinal imaging, used for assessing stroke-related retinal changes, is a non-invasive and cost-effective method that can be enhanced by machine learning and deep learning algorithms, showing promise in early disease detection, severity grading, and prognostic evaluation in stroke patients. This review explores the role of artificial intelligence (AI) in stroke patient care, focusing on retinal imaging integration into clinical workflows. Retinal imaging has revealed several microvascular changes, including a decrease in the central retinal artery diameter and an increase in the central retinal vein diameter, both of which are associated with lacunar stroke and intracranial hemorrhage. Additionally, microvascular changes, such as arteriovenous nicking, increased vessel tortuosity, enhanced arteriolar light reflex, decreased retinal fractals, and thinning of retinal nerve fiber layer are also reported to be associated with higher stroke risk. AI models, such as Xception and EfficientNet, have demonstrated accuracy comparable to traditional stroke risk scoring systems in predicting stroke risk. For stroke diagnosis, models like Inception, ResNet, and VGG, alongside machine learning classifiers, have shown high efficacy in distinguishing stroke patients from healthy individuals using retinal imaging. Moreover, a random forest model effectively distinguished between ischemic and hemorrhagic stroke subtypes based on retinal features, showing superior predictive performance compared to traditional clinical characteristics. Additionally, a support vector machine model has achieved high classification accuracy in assessing pial collateral status. Despite this advancements, challenges such as the lack of standardized protocols for imaging modalities, hesitance in trusting AI-generated predictions, insufficient integration of retinal imaging data with electronic health records, the need for validation across diverse populations, and ethical and regulatory concerns persist. Future efforts must focus on validating AI models across diverse populations, ensuring algorithm transparency, and addressing ethical and regulatory issues to enable broader implementation. Overcoming these barriers will be essential for translating this technology into personalized stroke care and improving patient outcomes.

Machine Learning- and Deep Learning-Based Myoelectric Control System for Upper Limb Rehabilitation Utilizing EEG and EMG Signals: A Systematic Review

Upper limb disabilities, often caused by conditions such as stroke or neurological disorders, severely limit an individual's ability to perform essential daily tasks, leading to a significant reduction in quality of life. The development of effective rehabilitation technologies is crucial to restoring motor function and improving patient outcomes. This systematic review examines the application of machine learning and deep learning techniques in myoelectric-controlled systems for upper limb rehabilitation, focusing on the use of electroencephalography and electromyography signals. By integrating non-invasive signal acquisition methods with advanced computational models, the review highlights how these technologies can enhance the accuracy and efficiency of rehabilitation devices. A comprehensive search of literature published between January 2015 and July 2024 led to the selection of fourteen studies that met the inclusion criteria. These studies showcase various approaches in decoding motor intentions and controlling assistive devices, with models such as Long Short-Term Memory Networks, Support Vector Machines, and Convolutional Neural Networks showing notable improvements in control precision. However, challenges remain in terms of model robustness, computational complexity, and real-time applicability. This systematic review aims to provide researchers with a deeper understanding of the current advancements and challenges in this field, guiding future research efforts to overcome these barriers and facilitate the transition of these technologies from experimental settings to practical, real-world applications.

The Significance of a Cerebrovascular Accident Outcome Prediction Model for Patients, Family Members, and Health Care Professionals: Qualitative Evaluation Study

BACKGROUND

Patients with cerebrovascular accident (CVA) should be involved in setting their rehabilitation goals. A personalized prediction of CVA outcomes would allow care professionals to better inform patients and informal caregivers. Several accurate prediction models have been created, but acceptance and proper implementation of the models are prerequisites for model adoption.

OBJECTIVE

This study aimed to assess the added value of a prediction model for long-term outcomes of rehabilitation after CVA and evaluate how it can best be displayed, implemented, and integrated into the care process.

METHODS

We designed a mock-up version, including visualizations, based on our recently developed prediction model. We conducted focus groups with CVA patients and informal caregivers, and separate focus groups with health care professionals (HCPs). Their opinions on the current information management and the model were analyzed using a thematic analysis approach. Lastly, a Measurement Instrument for Determinants of Innovations (MIDI) questionnaire was used to collect insights into the prediction model and visualizations with HCPs.

RESULTS

The analysis of 6 focus groups, with 9 patients, 4 informal caregivers, and 8 HCPs, resulted in 10 themes in 3 categories: evaluation of the current care process (information absorption, expectations of rehabilitation, prediction of outcomes, and decision aid), content of the prediction model (reliability, relevance, and influence on the care process), and accessibility of the model (ease of understanding, model type preference, and moment of use). We extracted recommendations for the prediction model and visualizations. The results of the questionnaire survey (9 responses, 56% response rate) underscored the themes of the focus groups.

CONCLUSIONS

There is a need for the use of a prediction model to assess CVA outcomes, as indicated by the general approval of participants in both the focus groups and the questionnaire survey. We recommend that the prediction model be geared toward HCPs, as they can provide the context necessary for patients and informal caregivers. Good reliability and relevance of the prediction model will be essential for its wide adoption.

GAPPA: Enhancing prognosis prediction in primary aldosteronism post-adrenalectomy using graph-based modeling

BACKGROUND AND OBJECTIVE

Predicting postoperative prognosis is vital for clinical decision making in patients undergoing adrenalectomy (ADX). This study introduced GAPPA, a novel GNN-based approach, to predict post-ADX outcomes in patients with unilateral primary aldosteronism (UPA). The objective was to leverage the intricate dependencies between clinico-biochemical features and clinical outcomes using GNNs integrated into a bipartite graph structure to enhance prognostic prediction accuracy.

METHODS

We conceptualized prognostic prediction as a link prediction task on a bipartite graph, with nodes representing patients, clinico-biochemical features, and clinical outcomes, and edges denoting the connections between them. GAPPA utilizes GNNs to capture these dependencies and seamlessly integrates the outcome predictions into a graph structure. This approach was evaluated using a dataset of 640 patients with UPA who underwent unilateral ADX (uADX) between 1990 and 2022. We conducted a comparative analysis using repeated stratified five-fold cross-validation and paired t-tests to evaluate the performance of GAPPA against conventional machine learning methods and previous studies across various metrics.

RESULTS

GAPPA significantly outperformed conventional machine learning methods and previous studies (p < 0.05) across various metrics. It achieved F1-score, accuracy, sensitivity, and specificity of 71.3 % ± 3.1 %, 71.1 % ± 3.4 %, 69.9 % ± 4.3 %, and 72.4 % ± 7.2 %, respectively, with an AUC of 0.775 ± 0.030. We also investigated the impact of different initialization schemes on GAPPA outcome-edge embeddings, highlighting their robustness and stability.

CONCLUSION

GAPPA aids in preoperative prognosis assessment and facilitates patient counseling, contributing to prognostic prediction and advancing the applications of GNNs in the biomedical domain.

Advancing ischemic stroke diagnosis and clinical outcome prediction using improved ensemble techniques in DSC-PWI radiomics

Ischemic stroke is a leading global cause of death and disability and is expected to rise in the future. The present diagnostic techniques, like CT and MRI, have some limitations in distinguishing acute from chronic ischemia and in early ischemia detection. This study investigates the function of ensemble models based on the dynamic radiomics features (DRF) from the dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) ischemic stroke diagnosis, neurological impairment assessment, and modified Rankin Scale (mRS) outcome prediction). DRF is extracted from the 3D images, features are selected, and dimensionality is reduced. After that, ensemble models are applied. Two model structures were developed: a voting classifier with 6 bagging classifiers and a stacking classifier based on 4 bagging classifiers. The ensemble models were evaluated on three core tasks. The Stacking_ens_LR model performed best for ischemic stroke detection, the LR Bagging model for NIH Stroke Scale (NIHSS) prediction, and the NB Bagging model for outcome prediction. These outcomes illustrate the strength of ensemble models. The work showcases the role of ensemble models and DRF in the stroke management process.

Multiple imputation integrated to machine learning: predicting post-stroke recovery of ambulation after intensive inpatient rehabilitation

Good data quality is vital for personalising plans in rehabilitation. Machine learning (ML) improves prognostics but integrating it with Multiple Imputation (MImp) for dealing missingness is an unexplored field. This work aims to provide post-stroke ambulation prognosis, integrating MImp with ML, and identify the prognostic influential factors. Stroke survivors in intensive rehabilitation were enrolled. Data on demographics, events, clinical, physiotherapy, and psycho-social assessment were collected. An independent ambulation at discharge, using the Functional Ambulation Category scale, was the outcome. After handling missingness using MImp, ML models were optimised, cross-validated, and tested. Interpretability techniques analysed predictor contributions. Pre-MImp, the dataset included 54.1% women, 79.2% ischaemic patients, median age 80.0 (interquartile range: 15.0). Post-MImp, 368 non-ambulatory patients on 10 imputed datasets were used for training, 80 for testing. The random forest (the validation best-performing algorithm) obtained 75.5% aggregated balanced accuracy on the test set. The main predictors included modified Barthel index, Fugl-Meyer assessment/motricity index, short physical performance battery, age, Charlson comorbidity index/cumulative illness rating scale, and trunk control test. This is among the first studies applying ML, together with MImp, to predict ambulation recovery in post-stroke rehabilitation. This pipeline reliably exploits the potential of incomplete datasets for healthcare prognosis, identifying relevant predictors.

Towards Transforming Neurorehabilitation: The Impact of Artificial Intelligence on Diagnosis and Treatment of Neurological Disorders

Background and Objectives: Neurological disorders like stroke, spinal cord injury (SCI), and Parkinson's disease (PD) significantly affect global health, requiring accurate diagnosis and long-term neurorehabilitation. Artificial intelligence (AI), such as machine learning (ML), may enhance early diagnosis, personalize treatment, and optimize rehabilitation through predictive analytics, robotic systems, and brain-computer interfaces, improving outcomes for patients. This systematic review examines how AI and ML systems influence diagnosis and treatment in neurorehabilitation among neurological disorders. Materials and Methods: Studies were identified from an online search of PubMed, Web of Science, and Scopus databases with a search time range from 2014 to 2024. This review has been registered on Open OSF (n) EH9PT. Results: Recent advancements in AI and ML are revolutionizing motor rehabilitation and diagnosis for conditions like stroke, SCI, and PD, offering new opportunities for personalized care and improved outcomes. These technologies enhance clinical assessments, therapy personalization, and remote monitoring, providing more precise interventions and better long-term management. Conclusions: AI is revolutionizing neurorehabilitation, offering personalized, data-driven treatments that enhance recovery in neurological disorders. Future efforts should focus on large-scale validation, ethical considerations, and expanding access to advanced, home-based care.

Predicting stroke occurrences: a stacked machine learning approach with feature selection and data preprocessing

Stroke prediction remains a critical area of research in healthcare, aiming to enhance early intervention and patient care strategies. This study investigates the efficacy of machine learning techniques, particularly principal component analysis (PCA) and a stacking ensemble method, for predicting stroke occurrences based on demographic, clinical, and lifestyle factors. We systematically varied PCA components and implemented a stacking model comprising random forest, decision tree, and K-nearest neighbors (KNN).Our findings demonstrate that setting PCA components to 16 optimally enhanced predictive accuracy, achieving a remarkable 98.6% accuracy in stroke prediction. Evaluation metrics underscored the robustness of our approach in handling class imbalance and improving model performance, also comparative analyses against traditional machine learning algorithms such as SVM, logistic regression, and Naive Bayes highlighted the superiority of our proposed method.

AI Applications in Adult Stroke Recovery and Rehabilitation: A Scoping Review Using AI

Stroke is a leading cause of long-term disability worldwide. With the advancements in sensor technologies and data availability, artificial intelligence (AI) holds the promise of improving the amount, quality and efficiency of care and enhancing the precision of stroke rehabilitation. We aimed to identify and characterize the existing research on AI applications in stroke recovery and rehabilitation of adults, including categories of application and progression of technologies over time. Data were collected from peer-reviewed articles across various electronic databases up to January 2024. Insights were extracted using AI-enhanced multi-method, data-driven techniques, including clustering of themes and topics. This scoping review summarizes outcomes from 704 studies. Four common themes (impairment, assisted intervention, prediction and imaging, and neuroscience) were identified, in which time-linked patterns emerged. The impairment theme revealed a focus on motor function, gait and mobility, while the assisted intervention theme included applications of robotic and brain-computer interface (BCI) techniques. AI applications progressed over time, starting from conceptualization and then expanding to a broader range of techniques in supervised learning, artificial neural networks (ANN), natural language processing (NLP) and more. Applications focused on upper limb rehabilitation were reviewed in more detail, with machine learning (ML), deep learning techniques and sensors such as inertial measurement units (IMU) used for upper limb and functional movement analysis. AI applications have potential to facilitate tailored therapeutic delivery, thereby contributing to the optimization of rehabilitation outcomes and promoting sustained recovery from rehabilitation to real-world settings.

Classifying Residual Stroke Severity Using Robotics-Assisted Stroke Rehabilitation: Machine Learning Approach

BACKGROUND

Stroke therapy is essential to reduce impairments and improve motor movements by engaging autogenous neuroplasticity. Traditionally, stroke rehabilitation occurs in inpatient and outpatient rehabilitation facilities. However, recent literature increasingly explores moving the recovery process into the home and integrating technology-based interventions. This study advances this goal by promoting in-home, autonomous recovery for patients who experienced a stroke through robotics-assisted rehabilitation and classifying stroke residual severity using machine learning methods.

OBJECTIVE

Our main objective is to use kinematics data collected during in-home, self-guided therapy sessions to develop supervised machine learning methods, to address a clinician's autonomous classification of stroke residual severity-labeled data toward improving in-home, robotics-assisted stroke rehabilitation.

METHODS

In total, 33 patients who experienced a stroke participated in in-home therapy sessions using Motus Nova robotics rehabilitation technology to capture upper and lower body motion. During each therapy session, the Motus Hand and Motus Foot devices collected movement data, assistance data, and activity-specific data. We then synthesized, processed, and summarized these data. Next, the therapy session data were paired with clinician-informed, discrete stroke residual severity labels: "no range of motion (ROM)," "low ROM," and "high ROM." Afterward, an 80%:20% split was performed to divide the dataset into a training set and a holdout test set. We used 4 machine learning algorithms to classify stroke residual severity: light gradient boosting (LGB), extra trees classifier, deep feed-forward neural network, and classical logistic regression. We selected models based on 10-fold cross-validation and measured their performance on a holdout test dataset using F1-score to identify which model maximizes stroke residual severity classification accuracy.

RESULTS

We demonstrated that the LGB method provides the most reliable autonomous detection of stroke severity. The trained model is a consensus model that consists of 139 decision trees with up to 115 leaves each. This LGB model boasts a 96.70% F1-score compared to logistic regression (55.82%), extra trees classifier (94.81%), and deep feed-forward neural network (70.11%).

CONCLUSIONS

We showed how objectively measured rehabilitation training paired with machine learning methods can be used to identify the residual stroke severity class, with efforts to enhance in-home self-guided, individualized stroke rehabilitation. The model we trained relies only on session summary statistics, meaning it can potentially be integrated into similar settings for real-time classification, such as outpatient rehabilitation facilities.

Leveraging Ensemble Models and Follow-up Data for Accurate Prediction of mRS Scores from Radiomic Features of DSC-PWI Images

Predicting long-term clinical outcomes based on the early DSC PWI MRI scan is valuable for prognostication, resource management, clinical trials, and patient expectations. Current methods require subjective decisions about which imaging features to assess and may require time-consuming postprocessing. This study's goal was to predict multilabel 90-day modified Rankin Scale (mRS) score in acute ischemic stroke patients by combining ensemble models and different configurations of radiomic features generated from Dynamic susceptibility contrast perfusion-weighted imaging. In Follow-up studies, a total of 70 acute ischemic stroke (AIS) patients underwent magnetic resonance imaging within 24 hours poststroke and had a follow-up scan. In the single study, 150 DSC PWI Image scans for AIS patients. The DRF are extracted from DSC-PWI Scans. Then Lasso algorithm is applied for feature selection, then new features are generated from initial and follow-up scans. Then we applied different ensemble models to classify between three classes normal outcome (0, 1 mRS score), moderate outcome (2,3,4 mRS score), and severe outcome (5,6 mRS score). ANOVA and post-hoc Tukey HSD tests confirmed significant differences in model style performance across various studies and classification techniques. Stacking models consistently on average outperformed others, achieving an Accuracy of 0.68 ± 0.15, Precision of 0.68 ± 0.17, Recall of 0.65 ± 0.14, and F1 score of 0.63 ± 0.15 in the follow-up time study. Techniques like Bo_Smote showed significantly higher recall and F1 scores, highlighting their robustness and effectiveness in handling imbalanced data. Ensemble models, particularly Bagging and Stacking, demonstrated superior performance, achieving nearly 0.93 in Accuracy, 0.95 in Precision, 0.94 in Recall, and 0.94 in F1 metrics in follow-up conditions, significantly outperforming single models. Ensemble models based on radiomics generated from combining Initial and follow-up scans can be used to predict multilabel 90-day stroke outcomes with reduced subjectivity and user burden.

Effectiveness of Two Models of Telerehabilitation in Improving Recovery from Subacute Upper Limb Disability after Stroke: Robotic vs. Non-Robotic

BACKGROUND/OBJECTIVES

Finding innovative digital solutions is fundamental to ensure prompt and continuous care for patients with chronic neurological disorders, whose demand for rehabilitation also in home-based settings is steadily increasing. The aim is to verify the safety and the effectiveness of two telerehabilitation (TR) models in improving recovery from subacute upper limb (UL) disability after stroke, with and without a robotic device.

METHODS

One hundred nineteen subjects with subacute post-stroke UL disability were assessed for eligibility. Of them, 30 patients were enrolled in the study and randomly assigned to either the Robotic Group (RG), undergoing a 20-session TR program, using a robotic device, or the Non-Robotic Group (NRG), undergoing a 20-session TR program without robotics. Clinical evaluations were measured at baseline (T0) and post-intervention (T1, 5 weeks after baseline), and included assessments of quality of life, motor skills, and clinical/functional status. The primary outcome measure was the World Health Organization Disability Assessment Schedule 2.0, evaluating the change in perceived disability.

RESULTS

Statistical analysis shows that patients of both groups improved significantly over time in all domains analyzed (mean decrease from baseline in the WHODAS 2.0 of 6.09 ± 2.62% for the NRG, and of 0.76 ± 2.21% for the RG), with a greater improvement of patients in the NRG in motor (Fugl-Meyer Assessment Upper Extremity-motor function, Box and Block Test) and cognitive skills (Trail Making Test-A).

CONCLUSIONS

This study highlights the potential of TR programs to transform stroke rehabilitation by enhancing accessibility and patient-centered care, promoting autonomy, improving adherence, and leading to better outcomes and quality of life for stroke survivors.

Prediction of poststroke independent walking using machine learning: a retrospective study

BACKGROUND

Accurately predicting the walking independence of stroke patients is important. Our objective was to determine and compare the performance of logistic regression (LR) and three machine learning models (eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and Random Forest (RF)) in predicting walking independence at discharge in stroke patients, as well as to explore the variables that predict prognosis.

METHODS

778 (80% for the training set and 20% for the test set) stroke patients admitted to China Rehabilitation Research Center between February 2020 and January 2023 were retrospectively included. The training set was used for training models. The test set was used to validate and compare the performance of the four models in terms of area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.

RESULTS

Among the three ML models, the AUC of the XGBoost model is significantly higher than that of the SVM and RF models (P < 0.001, P = 0.024, respectively). There was no significant difference in the AUCs between the XGBoost model and the LR model (0.891 vs. 0.880, P = 0.560). The XGBoost model demonstrated superior accuracy (87.82% vs. 86.54%), sensitivity (50.00% vs. 39.39%), PPV (73.68% vs. 73.33%), NPV (89.78% vs. 87.94%), and F1 score (59.57% vs. 51.16%), with only slightly lower specificity (96.09% vs. 96.88%). Together, the XGBoost model and the stepwise LR model identified age, FMA-LE at admission, FAC at admission, and lower limb spasticity as key factors influencing independent walking.

CONCLUSION

Overall, the XGBoost model performed best in predicting independent walking after stroke. The XGBoost and LR models together confirm that age, admission FMA-LE, admission FAC, and lower extremity spasticity are the key factors influencing independent walking in stroke patients at hospital discharge.

TRIAL REGISTRATION

Not applicable.

A novel prediction score determining individual clinical outcome 3 months after juvenile stroke (PREDICT-score)

BACKGROUND

Juvenile strokes (< 55 years) account for about 15% of all ischemic strokes. Structured data on clinical outcome in those patients are sparse. Here, we aimed to fill this gap by systematically collecting relevant data and modeling a juvenile stroke prediction score for the 3-month functional outcome.

METHODS

We retrospectively integrated and analyzed clinical and outcome data of juvenile stroke and TIA patients treated at the LMU University Hospital, LMU Munich, Munich. Good outcome was defined as a modified Rankin Scale of 0-2 or return to baseline of function. We analyzed candidate predictors and developed a predictive model. Predictive abilities were inspected using Area Under the ROC curve (AUROC) and visual representation of the calibration. The model was validated internally.

RESULTS

346 patients were included in the analysis. We observed a good outcome in n = 293 patients (84.7%). The prediction model for an unfavourable outcome had an AUROC of 89.1% (95% CI 83.3-93.1%). The model includes age NIHSS, ASPECTS, blood glucose and type of vessel occlusion as predictors for the individual patient outcome.

CONCLUSIONS

Here, we introduce the highly accurate PREDICT-score for the 3-month outcome after juvenile stroke derived from clinical routine data. The PREDICT-score might be helpful in guiding individual patient decisions and designing future studies but needs further prospective validation which is already planned. Trial registration The study has been registered at https://drks.de (DRKS00024407) on March 31, 2022.

Predictors of In-Hospital Mortality after Thrombectomy in Anterior Circulation Large Vessel Occlusion: A Retrospective, Machine Learning Study

BACKGROUND

Despite the increased use of mechanical thrombectomy (MT) in recent years, there remains a lack of research on in-hospital mortality rates following the procedure, the primary factors influencing these rates, and the potential for predicting them. This study aimed to utilize interpretable machine learning (ML) to help clarify these uncertainties.

METHODS

This retrospective study involved patients with anterior circulation large vessel occlusion (LVO)-related ischemic stroke who underwent MT. The patient division was made into two groups: (I) the in-hospital death group, referred to as miserable outcome, and (II) the in-hospital survival group, or favorable outcome. Python 3.10.9 was utilized to develop the machine learning models, which consisted of two types based on input features: (I) the Pre-MT model, incorporating baseline features, and (II) the Post-MT model, which included both baseline and MT-related features. After a feature selection process, the models were trained, internally evaluated, and tested, after which interpretation frameworks were employed to clarify the decision-making processes.

RESULTS

This study included 602 patients with a median age of 76 years (interquartile range (IQR) 65-83), out of which 54% (n = 328) were female, and 22% (n = 133) had miserable outcomes. Selected baseline features were age, baseline National Institutes of Health Stroke Scale (NIHSS) value, neutrophil-to-lymphocyte ratio (NLR), international normalized ratio (INR), the type of the affected vessel ('Vessel type'), peripheral arterial disease (PAD), baseline glycemia, and premorbid modified Rankin scale (pre-mRS). The highest odds ratio of 4.504 was observed with the presence of peripheral arterial disease (95% confidence interval (CI), 2.120-9.569). The Pre-MT model achieved an area under the curve (AUC) value of around 79% utilizing these features, and the interpretable framework discovered the baseline NIHSS value as the most influential factor. In the second data set, selected features were the same, excluding pre-mRS and including puncture-to-procedure-end time (PET) and onset-to-puncture time (OPT). The AUC value of the Post-MT model was around 84% with age being the highest-ranked feature.

CONCLUSIONS

This study demonstrates the moderate to strong effectiveness of interpretable machine learning models in predicting in-hospital mortality following mechanical thrombectomy for ischemic stroke, with AUCs of 0.792 for the Pre-MT model and 0.837 for the Post-MT model. Key predictors included patient age, baseline NIHSS, NLR, INR, occluded vessel type, PAD, baseline glycemia, pre-mRS, PET, and OPT. These findings provide valuable insights into risk factors and could improve post-procedural patient management.

Development and validation of outcome prediction model for reperfusion therapy in acute ischemic stroke using nomogram and machine learning

OBJECTIVE

To develop logistic regression nomogram and machine learning (ML)-based models to predict 3-month unfavorable functional outcome for acute ischemic stroke (AIS) patients undergoing reperfusion therapy.

METHODS

Patients undergoing reperfusion therapy (intravenous thrombolysis and/or endovascular treatment) were prospectively recruited. Unfavorable outcome was defined as 3-month modified Rankin Scale (mRS) score 3-6. The independent risk factors associated with unfavorable outcome were obtained by regression analysis and included in the prediction model. The performance of nomogram was assessed by the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). ML models were compared with nomogram using AUC; the generalizability of all models was ascertained in an external cohort.

RESULTS

A total of 505 patients were enrolled, with 256 in the model construction, and 249 in the external validation. Five variables were identified as prognostic factors: baseline NIHSS, D-dimer level, random blood glucose (RBG), blood urea nitrogen (BUN), and systolic blood pressure (SBP) before reperfusion. The AUC values of nomogram were 0.865, 0.818, and 0.779 in the training set, test set, and external validation, respectively. The calibration curve and DCA indicated appreciable reliability and good net benefits. The best three ML models were extra trees (ET), CatBoost, and random forest (RF) models; all of them showed favorable discrimination in the training cohort, and confirmed in the test and external sets.

CONCLUSION

Baseline NIHSS, D-dimer, RBG, BUN, and SBP before reperfusion were independent predictors for 3-month unfavorable outcome after reperfusion therapy in AIS patients. Both nomogram and ML models showed good discrimination and generalizability.

Conventional and machine learning-based risk scores for patients with early-stage hepatocellular carcinoma

BACKGROUND/AIMS

The performance of machine learning (ML) in predicting the outcomes of patients with hepatocellular carcinoma (HCC) remains uncertain. We aimed to develop risk scores using conventional methods and ML to categorize early-stage HCC patients into distinct prognostic groups.

METHODS

The study retrospectively enrolled 1,411 consecutive treatment-naïve patients with the Barcelona Clinic Liver Cancer (BCLC) stage 0 to A HCC from 2012 to 2021. The patients were randomly divided into a training cohort (n=988) and validation cohort (n=423). Two risk scores (CATS-IF and CATS-INF) were developed to predict overall survival (OS) in the training cohort using the conventional methods (Cox proportional hazards model) and ML-based methods (LASSO Cox regression), respectively. They were then validated and compared in the validation cohort.

RESULTS

In the training cohort, factors for the CATS-IF score were selected by the conventional method, including age, curative treatment, single large HCC, serum creatinine and alpha-fetoprotein levels, fibrosis-4 score, lymphocyte-tomonocyte ratio, and albumin-bilirubin grade. The CATS-INF score, determined by ML-based methods, included the above factors and two additional ones (aspartate aminotransferase and prognostic nutritional index). In the validation cohort, both CATS-IF score and CATS-INF score outperformed other modern prognostic scores in predicting OS, with the CATSINF score having the lowest Akaike information criterion value. A calibration plot exhibited good correlation between predicted and observed outcomes for both scores.

CONCLUSION

Both the conventional Cox-based CATS-IF score and ML-based CATS-INF score effectively stratified patients with early-stage HCC into distinct prognostic groups, with the CATS-INF score showing slightly superior performance.

Clinical phenotypes of patients with acute stroke: a secondary analysis

INTRODUCTION

Stroke is a leading cause of mortality worldwide and a major cause of disability having a high burden on patients, society, and caregiving systems. This study was conducted to investigate the presence of clusters of in-hospital patients with acute stroke based on demographic and clinical data. Cluster analysis reveals patterns in patient characteristics without requiring knowledge of a predefined patient category or assumptions about likely groupings within the data.

METHODS

We performed a secondary analysis of open-access anonymized data from patients with acute stroke admitted to a hospital between December 2019 to June 2021. In total, 216 patients (78; 36.1% men) were included in the analytical dataset with a mean (SD) age of 60.3 (14.4). Many demographic and clinical features were included in the analysis and the Barthel Index on discharge was used for comparing the functional recovery of the identified clusters.

RESULTS

Hierarchical clustering based on the principal components identified two clusters of 109 and 107 patients. The clusters were different in the Barthel Index scores on discharge with the mean (SD) of 39.3 (29.3) versus 62.6 (29.4); t (213.87) = -5.818, P <0.001, Cohen's d (95%CI) = -0.80 (-1.07, -0.52). A logistic model showed that age, systolic blood pressure, pulse rate, D-dimer blood level, low-density lipoprotein, hemoglobin, creatinine concentration, the National Institute of Health Stroke Scale value, and the Barthel Index scores on admission were significant predictors of cluster profiles (all P ≤0.029).

CONCLUSION

There are two clusters in hospitalized patients with acute stroke with significantly different functional recovery. This allows prognostic grouping of hospitalized acute stroke patients for prioritization of care or resource allocation. The clusters can be recognized using easily measured demographic and clinical features.

Machine learning-based survival analysis approaches for predicting the risk of pneumonia post-stroke discharge

BACKGROUND

Post-stroke pneumonia (PSP) is common among stroke patients. PSP occurring after hospital discharge continues to increase the risk of poor functional outcomes and death among stroke survivors. Currently, there is no prediction model specifically designed to predict the occurrence of PSP beyond the acute stage of stroke. This study aimed to explore the use of machine learning (ML) methods in predicting the risk of PSP after hospital discharge.

METHODS

This study analyzed data from 5,754 hospitalized stroke patients. The dataset was randomly divided into a training set and a holdout test set, with a ratio of 80:20. Several clinical and laboratory variables were utilized as predictors and different ML algorithms were employed to model time-to-event data. The ML model's predictive performance was compared to existing risk-scoring systems. A model-agnostic method based on Shapley additive explanations was utilized to interpret the ML model.

RESULTS

The study found that 5.7% of the study patients experienced pneumonia within one year after discharge. Based on repeated 5-fold cross-validation on the training set, the random survival forest (RSF) model had the highest C-index among the various ML algorithms and traditional Cox regression analysis. The final RSF model achieved a C-index of 0.787 (95% confidence interval: 0.737-0.840) on the holdout test set, outperforming five existing risk-scoring systems. The top three important predictors were the Glasgow Coma Scale score, age, and length of hospital stay.

CONCLUSIONS

The RSF model demonstrated superior discriminative ability compared to other ML algorithms and traditional Cox regression analysis, suggesting a non-linear relationship between predictors and outcomes. The developed ML model can be integrated into the hospital information system to provide personalized risk assessments.

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 of delayed cerebral ischemia followed aneurysmal subarachnoid hemorrhage. A machine-learning based study

INTRODUCTION

Delayed Cerebral Ischemia (DCI) is a significant complication following aneurysmal subarachnoid hemorrhage (aSAH) that can lead to poor outcomes. Machine learning techniques have shown promise in predicting DCI and improving risk stratification.

METHODS

In this study, we aimed to develop machine learning models to predict the occurrence of DCI in patients with aSAH. Patient data, including various clinical variables and co-factors, were collected. Six different machine learning models, including logistic regression, multilayer perceptron, decision tree, random forest, gradient boosting machine, and extreme gradient boosting (XGB), were trained and evaluated using performance metrics such as accuracy, area under the curve (AUC), precision, recall, and F1 score.

RESULTS

After data augmentation, the random forest model demonstrated the best performance, with an AUC of 0.85. The multilayer perceptron neural network model achieved an accuracy of 0.93 and an F1 score of 0.85, making it the best performing model. The presence of positive clinical vasospasm was identified as the most important feature for predicting DCI.

CONCLUSIONS

Our study highlights the potential of machine learning models in predicting the occurrence of DCI in patients with aSAH. The multilayer perceptron model showed excellent performance, indicating its utility in risk stratification and clinical decision-making. However, further validation and refinement of the models are necessary to ensure their generalizability and applicability in real-world settings. Machine learning techniques have the potential to enhance patient care and improve outcomes in aSAH, but their implementation should be accompanied by careful evaluation and validation.

Unlocking stroke prediction: Harnessing projection-based statistical feature extraction with ML algorithms

Non-communicable diseases, such as cardiovascular disease, cancer, chronic respiratory diseases, and diabetes, are responsible for approximately 71% of all deaths worldwide. Stroke, a cerebrovascular disorder, is one of the leading contributors to this burden among the top three causes of death. Early recognition of symptoms can encourage a balanced lifestyle and provide essential information for stroke prediction. To identify a stroke patient and risk factors, machine learning (ML) is a key tool for physicians. Due to different data measurement scales and their probability distributional assumptions, ML-based algorithms struggle to detect risk factors. Furthermore, when dealing with risk factors with high-dimensional features, learning algorithms struggle with complexity. In this study, rigorous statistical tests are used to identify risk factors, and PCA-FA (Integration of Principal Components and Factors) and FPCA (Factor Based PCA) approaches are proposed for projecting suitable feature representations for improving learning algorithm performances. The study dataset consists of different clinical, lifestyle, and genetic attributes, allowing for a comprehensive analysis of potential risk factors associated with stroke, which contains 5110 patient records. Using significant test (P-value <0.05), chi-square and independent sample t-test identified age, heart_disease, hypertension, work_type, ever_married, bmi, and smoking_status as risk factors for stroke. To develop the predicting model with proposed feature extraction techniques, random forests approach provides the best results when utilizing the PCA-FA method. The best accuracy rate for this approach is 92.55%, while the AUC score is 98.15%. The prediction accuracy has increased from 2.19% to 19.03% compared to the existing work. Additionally, the prediction results is robustified and reproducible with a stacking ensemble-based classification algorithm. We also developed a web-based application to help doctors diagnose stroke risk based on the findings of this study, which could be used as an additional tool to help doctors diagnose.

NSF DARE-transforming modeling in neurorehabilitation: a patient-in-the-loop framework

In 2023, the National Science Foundation (NSF) and the National Institute of Health (NIH) brought together engineers, scientists, and clinicians by sponsoring a conference on computational modelling in neurorehabiilitation. To facilitate multidisciplinary collaborations and improve patient care, in this perspective piece we identify where and how computational modelling can support neurorehabilitation. To address the where, we developed a patient-in-the-loop framework that uses multiple and/or continual measurements to update diagnostic and treatment model parameters, treatment type, and treatment prescription, with the goal of maximizing clinically-relevant functional outcomes. This patient-in-the-loop framework has several key features: (i) it includes diagnostic and treatment models, (ii) it is clinically-grounded with the International Classification of Functioning, Disability and Health (ICF) and patient involvement, (iii) it uses multiple or continual data measurements over time, and (iv) it is applicable to a range of neurological and neurodevelopmental conditions. To address the how, we identify state-of-the-art and highlight promising avenues of future research across the realms of sensorimotor adaptation, neuroplasticity, musculoskeletal, and sensory & pain computational modelling. We also discuss both the importance of and how to perform model validation, as well as challenges to overcome when implementing computational models within a clinical setting. The patient-in-the-loop approach offers a unifying framework to guide multidisciplinary collaboration between computational and clinical stakeholders in the field of neurorehabilitation.

Knowledge structure and global trends of machine learning in stroke over the past decade: A scientometric analysis

Objective

Machine learning (ML) models have been widely applied in stroke prediction, diagnosis, treatment, and prognosis assessment. We aimed to conduct a comprehensive scientometrics analysis of studies related to ML in stroke and reveal its current status, knowledge structure, and global trends.

Methods

All documents related to ML in stroke were retrieved from the Web of Science database on March 15, 2023. We refined the documents by including only original articles and reviews in the English language. The literature published over the past decade was imported into scientometrics software for influence detection and collaborative network analysis.

Results

2389 related publications were included. The annual publication outputs demonstrated explosive growth, with an average growth rate of 63.99 %. Among the 90 countries/regions involved, the United States (729 articles) and China (636 articles) were the most productive countries. Frontiers in Neurology was the most prolific journal with 94 articles. 234 highly cited articles, each with more than 31 citations, were detected. Keyword analysis revealed a total of 5333 keywords, with a predominant focus on the application of ML models in the early diagnosis, classification, and prediction of "acute ischemic stroke" and "atrial fibrillation-related stroke". The keyword "classification" had the first and longest burst, spanning from 2013 to 2018. 'Upport vector machine' got the strongest burst strength with 6.2. Keywords such as 'mechanical thrombectomy', 'expression', and 'prognosis' experienced bursts in 2022 and have continued to be prominent.

Conclusion

The applications of ML in stroke are increasingly diverse and extensive, with researchers showing growing interest over the past decade. However, the clinical application of ML in stroke is still in its early stages, and several limitations and challenges need to be addressed for its widespread adoption in clinical practice.

Development and Validation of a Decision Tree Analysis Model for Predicting Home Discharge in a Convalescent Ward: A Single Institution Study

OBJECTIVES

Accurately predicting the likelihood of inpatients' home discharge in a convalescent ward is crucial for assisting patients and families in decision-making. While logistic regression analysis has been commonly used, its complexity limits practicality in clinical settings. We focused on decision tree analysis, which is visually straightforward. This study aimed to develop and validate the accuracy of a prediction model for home discharge for inpatients in a convalescent ward using a decision tree analysis.

METHODS

The cohort consisted of 651 patients admitted to our convalescent ward from 2018 to 2020. We collected data from medical records, including disease classification, sex, age, duration of acute hospitalization, discharge destination (home or nonhome), and Functional Independence Measure (FIM) subitems at admission. We divided the cohort data into training and validation sets and developed a prediction model using decision tree analysis with discharge destination as the target and other variables as predictors. The model's accuracy was validated using the validation data set.

RESULTS

The decision tree model identified FIM grooming as the first single discriminator of home discharge, diverging at four points and identifying subsequent branching for the duration of acute hospitalization. The model's accuracy was 86.7%, with a sensitivity of 0.96, specificity of 0.52, positive predictive accuracy of 0.88, and negative predictive accuracy of 0.80. The area under the receiver operating characteristic curve was 0.75.

CONCLUSION

The predictive model demonstrated more than moderate predictive accuracy, suggesting its utility in clinical practice. Grooming emerged as a variable with the highest explanatory power for determining home discharge.

Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke

Ischemic stroke is a serious disease posing significant threats to human health and life, with the highest absolute and relative risks of a poor prognosis following the first occurrence, and more than 90% of strokes are attributable to modifiable risk factors. Currently, machine learning (ML) is widely used for the prediction of ischemic stroke outcomes. By identifying risk factors, predicting the risk of poor prognosis and thus developing personalized treatment plans, it effectively reduces the probability of poor prognosis, leading to more effective secondary prevention. This review includes 41 studies since 2018 that used ML algorithms to build prognostic prediction models for ischemic stroke, transient ischemic attack (TIA), and acute ischemic stroke (AIS). We analyzed in detail the risk factors used in these studies, the sources and processing methods of the required data, the model building and validation, and their application in different prediction time windows. The results indicate that among the included studies, the top five risk factors in terms of frequency were cardiovascular diseases, age, sex, national institutes of health stroke scale (NIHSS) score, and diabetes. Furthermore, 64% of the studies used single-center data, 65% of studies using imbalanced data did not perform data balancing, 88% of the studies did not utilize external validation datasets for model validation, and 72% of the studies did not provide explanations for their models. Addressing these issues is crucial for enhancing the credibility and effectiveness of the research, consequently improving the development and implementation of secondary prevention measures.

Machine learning-driven predictions and interventions for cardiovascular occlusions

BACKGROUND

Cardiovascular diseases remain a leading cause of global morbidity and mortality, with heart attacks and strokes representing significant health challenges. The accurate, early diagnosis and management of these conditions are paramount in improving patient outcomes. The specific disease, cardiovascular occlusions, has been chosen for the study due to the significant impact it has on public health. Cardiovascular diseases are a leading cause of mortality globally, and occlusions, which are blockages in the blood vessels, are a critical factor contributing to these conditions.

OBJECTIVE

By focusing on cardiovascular occlusions, the study aims to leverage machine learning to improve the prediction and management of these events, potentially helping to reduce the incidence of heart attacks, strokes, and other related health issues. The use of machine learning in this context offers the promise of developing more accurate and timely interventions, thus improving patient outcomes.

METHODS

We analyze diverse datasets to assess the efficacy of various machine learning algorithms in predicting heart attacks and strokes, comparing their performance to pinpoint the most accurate and reliable models. Additionally, we classify individuals by their predicted risk levels and examine key features that correlate with the incidence of cardiovascular events. The PyCaret machine learning library's Classification Module was key in developing predictive models which were evaluated with stratified cross-validation for reliable performance estimates.

RESULTS

Our findings suggest that machine learning can significantly improve the prediction accuracy for heart attacks and strokes, facilitating earlier and more precise interventions. We also discuss the integration of machine learning models into clinical practice, addressing potential challenges and the need for healthcare professionals to interpret and apply these predictions effectively.

CONCLUSIONS

The use of machine learning for risk stratification and the identification of modifiable factors may empower preemptive approaches to cardiovascular care, ultimately aiming to reduce the occurrence of life-threatening events and improve long-term patient health trajectories.

The Value of Applying Machine Learning in Predicting the Time of Symptom Onset in Stroke Patients: Systematic Review and Meta-Analysis

BACKGROUND

Machine learning is a potentially effective method for identifying and predicting the time of the onset of stroke. However, the value of applying machine learning in this field remains controversial and debatable.

OBJECTIVE

We aimed to assess the value of applying machine learning in predicting the time of stroke onset.

METHODS

PubMed, Web of Science, Embase, and Cochrane were comprehensively searched. The C index and sensitivity with 95% CI were used as effect sizes. The risk of bias was evaluated using PROBAST (Prediction Model Risk of Bias Assessment Tool), and meta-analysis was conducted using R (version 4.2.0; R Core Team).

RESULTS

Thirteen eligible studies were included in the meta-analysis involving 55 machine learning models with 41 models in the training set and 14 in the validation set. The overall C index was 0.800 (95% CI 0.773-0.826) in the training set and 0.781 (95% CI 0.709-0.852) in the validation set. The sensitivity and specificity were 0.76 (95% CI 0.73-0.80) and 0.79 (95% CI 0.74-0.82) in the training set and 0.81 (95% CI 0.68-0.90) and 0.83 (95% CI 0.73-0.89) in the validation set, respectively. Subgroup analysis revealed that the accuracy of machine learning in predicting the time of stroke onset within 4.5 hours was optimal (training: 0.80, 95% CI 0.77-0.83; validation: 0.79, 95% CI 0.71-0.86).

CONCLUSIONS

Machine learning has ideal performance in identifying the time of stroke onset. More reasonable image segmentation and texture extraction methods in radiomics should be used to promote the value of applying machine learning in diverse ethnic backgrounds.

TRIAL REGISTRATION

PROSPERO CRD42022358898; https://www.crd.york.ac.uk/Prospero/display_record.php?RecordID=358898.

From Admission to Discharge: Predicting National Institutes of Health Stroke Scale Progression in Stroke Patients Using Biomarkers and Explainable Machine Learning

As a result of social progress and improved living conditions, which have contributed to a prolonged life expectancy, the prevalence of strokes has increased and has become a significant phenomenon. Despite the available stroke treatment options, patients frequently suffer from significant disability after a stroke. Initial stroke severity is a significant predictor of functional dependence and mortality following an acute stroke. The current study aims to collect and analyze data from the hyperacute and acute phases of stroke, as well as from the medical history of the patients, in order to develop an explainable machine learning model for predicting stroke-related neurological deficits at discharge, as measured by the National Institutes of Health Stroke Scale (NIHSS). More specifically, we approached the data as a binary task problem: improvement of NIHSS progression vs. worsening of NIHSS progression at discharge, using baseline data within the first 72 h. For feature selection, a genetic algorithm was applied. Using various classifiers, we found that the best scores were achieved from the Random Forest (RF) classifier at the 15 most informative biomarkers and parameters for the binary task of the prediction of NIHSS score progression. RF achieved 91.13% accuracy, 91.13% recall, 90.89% precision, 91.00% f1-score, 8.87% FNrate and 4.59% FPrate. Those biomarkers are: age, gender, NIHSS upon admission, intubation, history of hypertension and smoking, the initial diagnosis of hypertension, diabetes, dyslipidemia and atrial fibrillation, high-density lipoprotein (HDL) levels, stroke localization, systolic blood pressure levels, as well as erythrocyte sedimentation rate (ESR) levels upon admission and the onset of respiratory infection. The SHapley Additive exPlanations (SHAP) model interpreted the impact of the selected features on the model output. Our findings suggest that the aforementioned variables may play a significant role in determining stroke patients' NIHSS progression from the time of admission until their discharge.

Profiling Somatosensory Impairment after Stroke: Characterizing Common "Fingerprints" of Impairment Using Unsupervised Machine Learning-Based Cluster Analysis of Quantitative Measures of the Upper Limb

Altered somatosensory function is common among stroke survivors, yet is often poorly characterized. Methods of profiling somatosensation that illustrate the variability in impairment within and across different modalities remain limited. We aimed to characterize post-stroke somatosensation profiles ("fingerprints") of the upper limb using an unsupervised machine learning cluster analysis to capture hidden relationships between measures of touch, proprioception, and haptic object recognition. Raw data were pooled from six studies where multiple quantitative measures of upper limb somatosensation were collected from stroke survivors (n = 207) using the Tactile Discrimination Test (TDT), Wrist Position Sense Test (WPST) and functional Tactile Object Recognition Test (fTORT) on the contralesional and ipsilesional upper limbs. The Growing Self Organizing Map (GSOM) unsupervised machine learning algorithm was used to generate a topology-preserving two-dimensional mapping of the pooled data and then separate it into clusters. Signature profiles of somatosensory impairment across two modalities (TDT and WPST; n = 203) and three modalities (TDT, WPST, and fTORT; n = 141) were characterized for both hands. Distinct impairment subgroups were identified. The influence of background and clinical variables was also modelled. The study provided evidence of the utility of unsupervised cluster analysis that can profile stroke survivor signatures of somatosensory impairment, which may inform improved diagnosis and characterization of impairment patterns.

ICTs and interventions in telerehabilitation and their effects on stroke recovery

Telerehabilitation (TR) is a new model to provide rehabilitation services to stroke survivors. It is a promising approach to deliver mainstream interventions for movement, cognitive, speech and language, and other disorders. TR has two major components: information and communication technologies (ICTs) and stroke interventions. ICTs provide a platform on which interventions are delivered and subsequently result in stroke recovery. In this mini-review, we went over features of ICTs that facilitate TR, as well as stroke interventions that can be delivered via TR platforms. Then, we reviewed the effects of TR on various stroke disorders. In most studies, TR is a feasible and effective solution in delivering interventions to patients. It is not inferior to usual care and in-clinic therapy with matching dose and intensity. With new technologies, TR may result in better outcomes than usual care for some disorders. One the other hand, TR also have many limitations that could lead to worse outcomes than traditional rehabilitation. In the end, we discussed major concerns and possible solutions related to TR, and also discussed potential directions for TR development.

A Novel Model to Generate Heterogeneous and Realistic Time-Series Data for Post-Stroke Rehabilitation Assessment

The application of machine learning-based tele-rehabilitation faces the challenge of limited availability of data. To overcome this challenge, data augmentation techniques are commonly employed to generate synthetic data that reflect the configurations of real data. One such promising data augmentation technique is the Generative Adversarial Network (GAN). However, GANs have been found to suffer from mode collapse, a common issue where the generated data fails to capture all the relevant information from the original dataset. In this paper, we aim to address the problem of mode collapse in GAN-based data augmentation techniques for post-stroke assessment. We applied the GAN to generate synthetic data for two post-stroke rehabilitation datasets and observed that the original GAN suffered from mode collapse, as expected. To address this issue, we propose a Time Series Siamese GAN (TS-SGAN) that incorporates a Siamese network and an additional discriminator. Our analysis, using the longest common sub-sequence (LCSS), demonstrates that TS-SGAN generates data uniformly for all elements of two testing datasets, in contrast to the original GAN. To further evaluate the effectiveness of TS-SGAN, we encode the generated dataset into images using Gramian Angular Field and classify them using ResNet-18. Our results show that TS-SGAN achieves a significant accuracy increase of classification accuracy (35.2%-42.07%) for both selected datasets. This represents a substantial improvement over the original GAN.

Machine learning prediction of motor function in chronic stroke patients: a systematic review and meta-analysis

Background

Recent studies have reported that machine learning (ML), with a relatively strong capacity for processing non-linear data and adaptive ability, could improve the accuracy and efficiency of prediction. The article summarizes the published studies on ML models that predict motor function 3-6 months post-stroke.

Methods

A systematic literature search was conducted in PubMed, Embase, Cochorane and Web of Science as of April 3, 2023 for studies on ML prediction of motor function in stroke patients. The quality of the literature was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). A random-effects model was preferred for meta-analysis using R4.2.0 because of the different variables and parameters.

Results

A total of 44 studies were included in this meta-analysis, involving 72,368 patients and 136 models. Models were categorized into subgroups according to the predicted outcome Modified Rankin Scale cut-off value and whether they were constructed based on radiomics. C-statistics, sensitivity, and specificity were calculated. The random-effects model showed that the C-statistics of all models were 0.81 (95% CI: 0.79; 0.83) in the training set and 0.82 (95% CI: 0.80; 0.85) in the validation set. According to different Modified Rankin Scale cut-off values, C-statistics of ML models predicting Modified Rankin Scale>2(used most widely) in stroke patients were 0.81 (95% CI: 0.78; 0.84) in the training set, and 0.84 (95% CI: 0.81; 0.87) in the validation set. C-statistics of radiomics-based ML models in the training set and validation set were 0.81 (95% CI: 0.78; 0.84) and 0.87 (95% CI: 0.83; 0.90), respectively.

Conclusion

ML can be used as an assessment tool for predicting the motor function in patients with 3-6 months of post-stroke. Additionally, the study found that ML models with radiomics as a predictive variable were also demonstrated to have good predictive capabilities. This systematic review provides valuable guidance for the future optimization of ML prediction systems that predict poor motor outcomes in stroke patients.

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022335260, identifier: CRD42022335260.

Artificial Intelligence and Machine Learning in the Diagnosis and Management of Stroke: A Narrative Review of United States Food and Drug Administration-Approved Technologies

Stroke is an emergency in which delays in treatment can lead to significant loss of neurological function and be fatal. Technologies that increase the speed and accuracy of stroke diagnosis or assist in post-stroke rehabilitation can improve patient outcomes. No resource exists that comprehensively assesses artificial intelligence/machine learning (AI/ML)-enabled technologies indicated for the management of ischemic and hemorrhagic stroke. We queried a United States Food and Drug Administration (FDA) database, along with PubMed and private company websites, to identify the recent literature assessing the clinical performance of FDA-approved AI/ML-enabled technologies. The FDA has approved 22 AI/ML-enabled technologies that triage brain imaging for more immediate diagnosis or promote post-stroke neurological/functional recovery. Technologies that assist with diagnosis predominantly use convolutional neural networks to identify abnormal brain images (e.g., CT perfusion). These technologies perform comparably to neuroradiologists, improve clinical workflows (e.g., time from scan acquisition to reading), and improve patient outcomes (e.g., days spent in the neurological ICU). Two devices are indicated for post-stroke rehabilitation by leveraging neuromodulation techniques. Multiple FDA-approved technologies exist that can help clinicians better diagnose and manage stroke. This review summarizes the most up-to-date literature regarding the functionality, performance, and utility of these technologies so clinicians can make informed decisions when using them in practice.

Automated machine learning to predict the difficulty for endoscopic resection of gastric gastrointestinal stromal tumor

Background

Accurate preoperative assessment of surgical difficulty is crucial to the success of the surgery and patient safety. This study aimed to evaluate the difficulty for endoscopic resection (ER) of gastric gastrointestinal stromal tumors (gGISTs) using multiple machine learning (ML) algorithms.

Methods

From December 2010 to December 2022, 555 patients with gGISTs in multi-centers were retrospectively studied and assigned to a training, validation, and test cohort. A difficult case was defined as meeting one of the following criteria: an operative time ≥ 90 min, severe intraoperative bleeding, or conversion to laparoscopic resection. Five types of algorithms were employed in building models, including traditional logistic regression (LR) and automated machine learning (AutoML) analysis (gradient boost machine (GBM), deep neural net (DL), generalized linear model (GLM), and default random forest (DRF)). We assessed the performance of the models using the areas under the receiver operating characteristic curves (AUC), the calibration curve, and the decision curve analysis (DCA) based on LR, as well as feature importance, SHapley Additive exPlanation (SHAP) Plots and Local Interpretable Model Agnostic Explanation (LIME) based on AutoML.

Results

The GBM model outperformed other models with an AUC of 0.894 in the validation and 0.791 in the test cohorts. Furthermore, the GBM model achieved the highest accuracy among these AutoML models, with 0.935 and 0.911 in the validation and test cohorts, respectively. In addition, it was found that tumor size and endoscopists' experience were the most prominent features that significantly impacted the AutoML model's performance in predicting the difficulty for ER of gGISTs.

Conclusion

The AutoML model based on the GBM algorithm can accurately predict the difficulty for ER of gGISTs before surgery.

Evaluation of Blood Biomarkers and Parameters for the Prediction of Stroke Survivors' Functional Outcome upon Discharge Utilizing Explainable Machine Learning

Despite therapeutic advancements, stroke remains a leading cause of death and long-term disability. The quality of current stroke prognostic models varies considerably, whereas prediction models of post-stroke disability and mortality are restricted by the sample size, the range of clinical and risk factors and the clinical applicability in general. Accurate prognostication can ease post-stroke discharge planning and help healthcare practitioners individualize aggressive treatment or palliative care, based on projected life expectancy and clinical course. In this study, we aimed to develop an explainable machine learning methodology to predict functional outcomes of stroke patients at discharge, using the Modified Rankin Scale (mRS) as a binary classification problem. We identified 35 parameters from the admission, the first 72 h, as well as the medical history of stroke patients, and used them to train the model. We divided the patients into two classes in two approaches: "Independent" vs. "Non-Independent" and "Non-Disability" vs. "Disability". Using various classifiers, we found that the best models in both approaches had an upward trend, with respect to the selected biomarkers, and achieved a maximum accuracy of 88.57% and 89.29%, respectively. The common features in both approaches included: age, hemispheric stroke localization, stroke localization based on blood supply, development of respiratory infection, National Institutes of Health Stroke Scale (NIHSS) upon admission and systolic blood pressure levels upon admission. Intubation and C-reactive protein (CRP) levels upon admission are additional features for the first approach and Erythrocyte Sedimentation Rate (ESR) levels upon admission for the second. Our results suggest that the said factors may be important predictors of functional outcomes in stroke patients.

Connectomics underlying motor functional outcomes in the acute period following stroke

Objective

Stroke remains the number one cause of morbidity in many developing countries, and while effective neurorehabilitation strategies exist, it remains difficult to predict the individual trajectories of patients in the acute period, making personalized therapies difficult. Sophisticated and data-driven methods are necessary to identify markers of functional outcomes.

Methods

Baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI (rsfMRI), and diffusion weighted scans were obtained from 79 patients following stroke. Sixteen models were constructed to predict performance across six tests of motor impairment, spasticity, and activities of daily living, using either whole-brain structural or functional connectivity. Feature importance analysis was also performed to identify brain regions and networks associated with performance in each test.

Results

The area under the receiver operating characteristic curve ranged from 0.650 to 0.868. Models utilizing functional connectivity tended to have better performance than those utilizing structural connectivity. The Dorsal and Ventral Attention Networks were among the top three features in several structural and functional models, while the Language and Accessory Language Networks were most commonly implicated in structural models.

Conclusions

Our study highlights the potential of machine learning methods combined with connectivity analysis in predicting outcomes in neurorehabilitation and disentangling the neural correlates of functional impairments, though further longitudinal studies are necessary.

Supervised Myoelectrical Hand Gesture Recognition in Post-Acute Stroke Patients with Upper Limb Paresis on Affected and Non-Affected Sides

In clinical practice, acute post-stroke paresis of the extremities fundamentally complicates timely rehabilitation of motor functions; however, recently, residual and distorted musculoskeletal signals have been used to initiate feedback-driven solutions for establishing motor rehabilitation. Here, we investigate the possibilities of basic hand gesture recognition in acute stroke patients with hand paresis using a novel, acute stroke, four-component multidomain feature set (ASF-4) with feature vector weight additions (ASF-14NP, ASF-24P) and supervised learning algorithms trained only by surface electromyography (sEMG). A total of 19 (65.9 ± 12.4 years old; 12 men, seven women) acute stroke survivors (12.4 ± 6.3 days since onset) with hand paresis (Brunnstrom stage 4 ± 1/4 ± 1, SIAS 3 ± 1/3 ± 2, FMA-UE 40 ± 20) performed 10 repetitive hand movements reflecting basic activities of daily living (ADLs): rest, fist, pinch, wrist flexion, wrist extension, finger spread, and thumb up. Signals were recorded using an eight-channel, portable sEMG device with electrode placement on the forearms and thenar areas of both limbs (four sensors on each extremity). Using data preprocessing, semi-automatic segmentation, and a set of extracted feature vectors, support vector machine (SVM), linear discriminant analysis (LDA), and k-nearest neighbors (k-NN) classifiers for statistical comparison and validity (paired t-tests, p-value < 0.05), we were able to discriminate myoelectrical patterns for each gesture on both paretic and non-paretic sides. Despite any post-stroke conditions, the evaluated total accuracy rate by the 10-fold cross-validation using SVM among four-, five-, six-, and seven-gesture models were 96.62%, 94.20%, 94.45%, and 95.57% for non-paretic and 90.37%, 88.48%, 88.60%, and 89.75% for paretic limbs, respectively. LDA had competitive results using PCA whereas k-NN was a less efficient classifier in gesture prediction. Thus, we demonstrate partial efficacy of the combination of sEMG and supervised learning for upper-limb rehabilitation procedures for early acute stroke motor recovery and various treatment applications.

Design and implementation of a Stroke Rehabilitation Registry for the systematic assessment of processes and outcomes and the development of data-driven prediction models: The STRATEGY study protocol

BACKGROUND

Stroke represents the second preventable cause of death after cardiovascular disease and the third global cause of disability. In countries where national registries of the clinical quality of stroke care have been established, the publication and sharing of the collected data have led to an improvement in the quality of care and survival of patients. However, information on rehabilitation processes and outcomes is often lacking, and predictors of functional outcomes remain poorly explored. This paper describes a multicenter study protocol to implement a Stroke rehabilitation Registry, mainly based on a multidimensional assessment proposed by the Italian Society of Physical and Rehabilitation Medicine (PMIC2020), in a pilot Italian cohort of stroke survivors undergoing post-acute inpatient rehabilitation, to provide a systematic assessment of processes and outcomes and develop data-driven prediction models of functional outcomes.

METHODS

All patients with a diagnosis of ischemic or haemorrhagic stroke confirmed by clinical assessment, admitted to intensive rehabilitation units within 30 days from the acute event, aged 18+, and providing informed consent will be enrolled. Measures will be taken at admission (T0), at discharge (T1), and at follow-up, 3 months (T2) and 6 months (T3) after the stroke. Assessment variables include anamnestic data, clinical and nursing complexity information and measures of body structures and function, activity and participation (PMIC2020), rehabilitation interventions, adverse events and discharge data. The modified Barthel Index will be our primary outcome. In addition to classical biostatistical analysis, learning algorithms will be cross-validated to achieve data-driven prognosis prediction models.

CONCLUSIONS

This study will test the feasibility of a stroke rehabilitation registry in the Italian health context and provide a systematic assessment of processes and outcomes for quality assessment and benchmarking. By the development of data-driven prediction models in stroke rehabilitation, this study will pave the way for the development of decision support tools for patient-oriented therapy planning and rehabilitation outcomes maximization.

CLINICAL TIAL REGISTRATION

The registration on ClinicalTrials.gov is ongoing and under review. The identification number will be provided when the review process will be completed.

Cross-validation of predictive models for functional recovery after post-stroke rehabilitation

Background

Rehabilitation treatments and services are essential for the recovery of post-stroke patients’ functions; however, the increasing number of available therapies and the lack of consensus among outcome measures compromises the possibility to determine an appropriate level of evidence. Machine learning techniques for prognostic applications offer accurate and interpretable predictions, supporting the clinical decision for personalised treatment. The aim of this study is to develop and cross-validate predictive models for the functional prognosis of patients, highlighting the contributions of each predictor.

Methods

A dataset of 278 post-stroke patients was used for the prediction of the class transition, obtained from the modified Barthel Index. Four classification algorithms were cross-validated and compared. On the best performing model on the validation set, an analysis of predictors contribution was conducted.

Results

The Random Forest obtained the best overall results on the accuracy (76.2%), balanced accuracy (74.3%), sensitivity (0.80), and specificity (0.68). The combination of all the classification results on the test set, by weighted voting, reached 80.2% accuracy. The predictors analysis applied on the Support Vector Machine, showed that a good trunk control and communication level, and the absence of bedsores retain the major contribution in the prediction of a good functional outcome.

Conclusions

Despite a more comprehensive assessment of the patients is needed, this work paves the way for the implementation of solutions for clinical decision support in the rehabilitation of post-stroke patients. Indeed, offering good prognostic accuracies for class transition and patient-wise view of the predictors contributions, it might help in a personalised optimisation of the patients’ rehabilitation path.