TY - JOUR
T1 - Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke
AU - Tozlu, Ceren
AU - Edwards, Dylan
AU - Boes, Aaron
AU - Fisher, Stanley
AU - Tsagaris, K. Zoe
AU - Silverstein, Joshua
AU - Pepper Lane, Heather
AU - Sabuncu, Mert R.
AU - Liu, Charles
AU - Kuceyeski, Amy
N1 - Publisher Copyright:
© The Author(s) 2020.
PY - 2020/5/1
Y1 - 2020/5/1
N2 - 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 (Formula presented.) 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.
AB - 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 (Formula presented.) 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.
KW - chronic stroke
KW - Fugl-Meyer Assessment
KW - machine learning
KW - predictive models
KW - white matter disconnectivity
UR - http://www.scopus.com/inward/record.url?scp=85082187427&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082187427&partnerID=8YFLogxK
U2 - 10.1177/1545968320909796
DO - 10.1177/1545968320909796
M3 - Article
C2 - 32193984
AN - SCOPUS:85082187427
SN - 1545-9683
VL - 34
SP - 428
EP - 439
JO - Neurorehabilitation and Neural Repair
JF - Neurorehabilitation and Neural Repair
IS - 5
ER -