Accuracy and agreement of national spine register data for 474 patients compared to corresponding electronic patient records

This is the authors' abstract. We don't add key points for this paper.

Purpose Data quality is essential for all types of research, including health registers. However, data quality is rarely reported. We aimed to assess the accuracy of data in a national spine register (NORspine) and its agreement with corresponding data in electronic patient records (EPR). Methods We compared data in NORspine registry against data in (EPR) for 474 patients operated for spinal stenosis in 2015 and 2016 at four public hospitals, using EPR as the gold standard. We assessed accuracy using the proportion correctly classified (PCC) and sensitivity. Agreement was quantified using Kappa statistics or interaclass correlation coefficient (ICC). Results The mean age (SD) was 66 (11) years, and 54% were females. Compared to EPR, surgeon-reported perioperative complications displayed weak agreement (kappa (95% CI) = 0.51 (0.33–0.69)), PCC of 96%, and a sensitivity (95% CI) of 40% (23–58%). ASA classification had a moderate agreement (kappa (95%CI) = 0.73 (0.66–0.80)). Comorbidities were underreported in NORspine. Perioperative details had strong to excellent agreements (kappa (95% CI) ranging from 0.76 ( 0.68–0.84) to 0.98 (0.95–1.00)), PCCs between 93% and 99% and sensitivities (95% CI) between 92% (0.84–1.00%) and 99% (0.98–1.00%). Patient-reported variables (height, weight, smoking) had excellent agreements (kappa (95% CI) between 0.93 (0.89–0.97) and 0.99 (0.98–0.99)). Conclusion Compared to electronic patient records, NORspine displayed weak agreement for perioperative complications, moderate agreement for ASA classification, strong agreement for perioperative details, and excellent agreement for height, weight, and smoking. NORspine underreported perioperative complications and comorbidities when compared to EPRs. Patient-recorded data were more accurate and should be preferred when available.

Caution warranted with surgeon-reported complications in spine registries; leaves open optimal data sources for outcomes research.