Calculation of the minimal clinically important difference in operated patients with adult spine deformity: advantages of the ROC method and significance of prevalence in threshold selection.

Abstract

The Minimal Clinically Important Difference (MCID) is crucial to evaluate management outcomes, but different thresholds have been obtained in different works. Part of this variability is due to measurement error and influence of the database, both essential for calculating the MCID. The aim of this study was to introduce the association of the ROC method in the anchor-based MCID calculation for ODI, SRS-22r, and SF-36, to objectively set the threshold for the anchor-based MCID in an adult spine deformity (ASD) population. Multicentric study based on a prospective database of consecutively operated ASD patients. An anchor question was used to assess patients' quality of life after surgery. Different approaches were used to calculate the MCID and then compared: SEM (Standard Error of Measurement), MDC (Minimal Detectable Change), and anchor-based MCID with ROC method. 516 patients were included. Those who responded with 6 and 7 to the anchor question were considered improved. The MCID ranges obtained with the ROC method exhibited the lowest variability. Prediction error rates ranged from 31% (SRS-22r) to 41% (SF-36 MCS). The MCID ranges spanned between 12 and 15 for ODI, 0.6 and 0.73 for SRS-22r, 6.62 and 7.41 for SF-36 PCS, and between 2.69 and 5.63 for SF-36 MCS. The ROC method proposes an MCID range with error rate, and can objectively determine the threshold for distinguishing improved and non-improved patients. As the MCID correlates with the utilized database and error of measurement, each study should compute its own MCID for each PROM to allow comparison among different publications. II.