JMIR Publications

ABSTRACT

Background:

Clinical decision support systems (CDSS) have been developed to address anemia, significant morbidity, mortality, and cost in patients with end-stage kidney disease (ESKD) undergoing hemodialysis. However, whether physician compliance with CDSS affects treatment response is yet unclarified.

Objective:

This study investigated the physician compliance with CDSS.

Methods:

We extracted the electronic health records of ESKD patients on hemodialysis at the Far Eastern Memorial Hospital Hemodialysis Center from 2016 to 2020 to evaluate CDSS performance using random intercept models.

Results:

We included 717 eligible hemodialysis patients (mean age, 62.9 +/- 11.6 years; male, 59.9%) with 36,091 hemoglobin measurements (average hemoglobin and on-target [Hb 10-12 g/dL] rate was 11.1 +/- 1.4 g/dL and 59.9%, respectively). On-target rate decreased from 61.3% (pre-CDSS) to 56.2% (post-CDSS) owing to a high hemoglobin percentage of >12 g/dL (pre, 21.5%; post, 29.0%). The failure rate (hemoglobin <10 g/dL) decreased from 17.2 (pre-CDSS) to 14.8% (post-CDSS). The average weekly erythropoietin-stimulating agent (ESA) use of 5,848 ± 4,211 units/week did not differ between phases. The overall concordance between CDSS recommendations and physician prescriptions was 62.3%. The CDSS concordance increased from 56.2% to 78.6% between phases. In the adjusted random intercept model, post-CDSS phase compared with pre-CDSS phase showed increased hemoglobin by 0.17 (95% confidence interval [CI] 0.14-.21) g/dL; weekly ESA by 264 (95% CI 158-371) units/week; and 3.4-fold increased concordance rate (95% CI 3.1-3.6) whereas, on-target rate (29% [odds ratio: OR 0.71, 95%CI 0.66-0.75]) and failure rate (16% [OR 0.84, 95%CI 0.76-0.92]) reduced. After additional adjustments for concordance in the full models, increased hemoglobin and decreased on-target rate tended towards attenuation (from 0.17 to 0.13 g/dL and 0.71 to 0.73, respectively). Increased ESA and decreased failure rate were completely mediated by CDSS concordance (from 264 to 50 units and 0.84 to 0.97, respectively).

Conclusions:

CDSS reduced the failure rate of anemia management, and physician compliance with CDSS was a complete intermediate factor accounting for CDSS effects. Further studies are warranted to address factors influencing physician compliance, to improve patient outcomes.