Item Reduction of the Boston Carpal Tunnel Questionnaire Using Decision Tree Modeling

To produce an electronic decision tree version of the Boston Carpal Tunnel Questionnaire (DT-BCTQ) using the chi-squared automatic interaction detection (CHAID) algorithm to reduce questionnaire length of the Boston Carpal Tunnel Questionnaire (BCTQ) while minimizing the loss of measurement properties.

Criterion standard study. All BCTQs completed between January 2012 and September 2016 by patients who were treated for carpal tunnel syndrome (CTS) were randomly divided into a development and a validation dataset at a 3-to-1 ratio. Optimization of the CHAID algorithm was performed in the development dataset to determine the most optimal DT-BCTQ.

Private hand clinic providing both surgical and nonsurgical (orthosis and exercise therapy) treatment for hand and wrist disorders.

Patients with CTS (N=4470) completed a total of 10,055 BCTQs.

Not applicable.

The intraclass correlation coefficient (ICC) was calculated between the original BCTQ scores and the scores predicted by the DT-BCTQ in the validation dataset. Bland-Altman plots visualized the agreement between the BCTQ and the DT-BCTQ.

The DT-BCTQ reduced the number of questions needed to ask a patient from 11 to a maximum of 3 for the symptom severity scale domain and from 8 to maximum of 3 for the functional status scale domain. The ICC between the original BCTQ and DT-BCTQ was 0.94. The mean difference between the BCTQ and DT-BCTQ was 0.05 on the 0-5 scale (95% confidence interval [CI], -0.48 to 0.57) for the symptom severity scale; 0.02 (95% CI, -0.45 to 0.49) for the functional status scale; and 0.04 (95% CI, -0.31 to 0.39) for the total BCTQ score.

By creating the DT-BCTQ, we diminished the number of questions needed to ask a patient from 18 to a maximum of 6 questions (3 for each subscore) when administering the BCTQ while maintaining an ICC of 0.94 with the original BCTQ.