Development of a Berg Balance Scale Short-Form Using a Machine Learning Approach in Patients With Stroke

Abstract

Background and Purpose: The Berg Balance Scale (BBS) is frequently used in routine clinical care and research settings and has good psychometric properties. This study was conducted to develop a short form of the BBS using a machine learning approach (BBS-ML). Methods: Data of 408 individuals poststroke were extracted from a published database. The initial (ie, 4-, 5-, 6-, 7-, and 8-item) versions were constructed by selecting top-ranked items based on the feature selection algorithm in the artificial neural network model. The final version of the BBS-ML was chosen by selecting the short form that used a smaller number of items to achieve a higher predictive power R 2 , a lower 95% limit of agreement (LoA), and an adequate possible scoring point (PSP). An independent sample of 226 persons with stroke was used for external validation.

Developing a Short-Form Buss–Warren Aggression Questionnaire Based on Machine Learning

“…Previous studies have used regression algorithms to develop a shortened version of the scale without a cutoff (or call it a threshold) [22,[24][25][26], making it difficult for teachers and clinicians to categorize participants as positive or negative cases based on the shortened version of the scale alone. In contrast, the BWAQ-ML is a shortened version of the BWAQ that has been developed based on machine learning classification algorithms with an explicit cutoff, and the results that can be derived from its use are easier to understand and interpret.…”

“…An increasing number of studies have used machine learning techniques to simplify psychometric instruments, but they are mainly focused on clinical psychological assessment [21]. Wang reduced the Berg Balance Scale from 14 to 6 items based on machine learning techniques, with a 57% reduction in the number of items [22]. The R 2 of the short version of the questionnaire was more significant than 0.96, and the LoAs were less than 95%, indicating good recognition performance.…”