Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke

Oh fuck, more prediction crapola. DO YOU NOT KNOW THAT SURVIVORS DON'T CARE ABOUT PREDICTIONS, THEY WANT REHAB RESULTS? Just maybe if you talked to a few survivors before starting worthless research like this.  And they are all Ph.Ds, probably their mentors and senior researchers also. Meaning that educational achievement doesn't necessarily include common sense. 

Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke

Show all authors

Ceren Tozlu, PhD, Dylan Edwards, PhD*, Aaron Boes, MD, PhD, ...

First Published March 20, 2020 Research Article Find in PubMed

https://doi.org/10.1177/1545968320909796

Article information

Abstract

Background.
Accurate prediction of clinical impairment in upper-extremity motor function following therapy in chronic stroke patients is a difficult task for clinicians but is key in prescribing appropriate therapeutic strategies. Machine learning is a highly promising avenue with which to improve prediction accuracy in clinical practice.  
Objectives.
The objective was to evaluate the performance of 5 machine learning methods in predicting postintervention upper-extremity motor impairment in chronic stroke patients using demographic, clinical, neurophysiological, and imaging input variables.  
Methods.
A total of 102 patients (female: 31%, age 61 ± 11 years) were included. The upper-extremity Fugl-Meyer Assessment (UE-FMA) was used to assess motor impairment of the upper limb before and after intervention. Elastic net (EN), support vector machines, artificial neural networks, classification and regression trees, and random forest were used to predict postintervention UE-FMA. The performances of methods were compared using cross-validated R².  
Results.
EN performed significantly better than other methods in predicting postintervention UE-FMA using demographic and baseline clinical data (median R2EN=0.91,R2RF=0.88,R2ANN=0.83,R2SVM=0.79,R2CART=0.70;

P < .05). Preintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors. The difference in MT had greater importance than the absence or presence of a motor-evoked potential (MEP) in the affected hemisphere.  
Conclusion.
Machine learning methods may enable clinicians to accurately predict a chronic stroke patient’s postintervention UE-FMA. Interhemispheric difference in the MT is an important predictor of chronic stroke patients’ response to therapy and, therefore, could be included in prospective studies.