Interrupted time series design to evaluate the effect of the ICD-9-CM to ICD-10-CM coding transition on injury hospitalization trends

Abstract

BackgroundImplementation of the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) in the U.S. on October 1, 2015 was a significant policy change with the potential to affect established injury morbidity trends. This study used data from a single state to demonstrate 1) the use of a statistical method to estimate the effect of this coding transition on injury hospitalization trends, and 2) interpretation of significant changes in injury trends in the context of the structural and conceptual differences between ICD-9-CM and ICD-10-CM, the new ICD-10-CM-specific coding guidelines, and proposed ICD-10-CM-based framework for reporting of injuries by intent and mechanism. Segmented regression analysis was used for statistical modeling of interrupted time series monthly data to evaluate the effect of the transition to ICD-10-CM on Kentucky hospitalizations’ external-cause-of-injury completeness (percentage of records with principal injury diagnoses supplemented with external-cause-of-injury codes), as well as injury hospitalization trends by intent or mechanism, January 2012–December 2017.ResultsThe segmented regression analysis showed an immediate significant drop in external-cause-of-injury completeness during the transition month, but returned to its pre-transition levels in November 2015. There was a significant immediate change in the percentage of injury hospitalizations coded for unintentional (3.34%) and undetermined intent (− 3.39%). There were immediate significant changes in the level of injury hospitalization rates due to poisoning, suffocation, struck by/against, other transportation, unspecified mechanism, and other specified not elsewhere classifiable mechanism. Significant change in slope after the transition (without immediate level change) was identified for assault, firearm, cut/pierce, and motor vehicle traffic injury rates. The observed trend changes reflected structural and conceptual features of ICD-10-CM coding (e.g., poisoning and suffocations are now captured via diagnosis codes only), new coding guidelines (e.g., requiring coding of injury intent as “accidental” if it is unknown or unspecified), and CDC proposed external-cause-of-injury code groupings by injury intent and mechanism. Researchers can replicate this methodology assessing trends in injuries or other ICD-10-CM-coded conditions using administrative billing data sets.ConclusionsThe CDC ‘s Proposed Framework for Presenting Injury Data Using ICD-10-CM External Cause of Injury Codes provided a logical transition from the ICD-9-CM-based matrix on injury hospitalization trends by intent and mechanism. Our findings are intended to raise awareness that changes in the ICD-10-CM coding system must be understood to assure accurate interpretation of injury trends.Electronic supplementary materialThe online version of this article (10.1186/s40621-018-0165-8) contains supplementary material, which is available to authorized users.

Signal of increased opioid overdose during COVID-19 from emergency medical services data

“…Segmented regression analysis for interrupted time series ( Bernal et al, 2017 ; Wagner et al, 2002 ) with autoregressive error model ( SAS, 2020 ; Slavova et al, 2018 ) was used to model the daily EMS OOR linear trends in the two segments of the study period, before and after March 6, 2020, the day of the state emergency declaration. The analysis estimated the changes in both the intercept and the slope for before and during COVID-19 study periods.…”

Social Distancing Has Merely Stabilized COVID-19 in the US

“…In particular, ITS analysis has been used to evaluate health care quality improvement using population-level longitudinal data [20]. Existing work has also used ITS analysis to examine the effectiveness of the transition from ICD-9-CM to ICD-10-CM coding on injury hospitalization [21].…”

Mapping from the International Classification of Diseases (ICD) 9th to 10th Revision for Research in Biologics and Biosimilars Using Administrative Healthcare Data

“…30 There were also segmented regression analyses to evaluate the effect of ICD-10 implementation, and quantifications of the overall impact of mapped ICD-10 codes on study associations and outcome estimations compared with ICD-9 codes. 13,15,16,25,28,43,44 Besides the challenges in determining the performance of ICD-10 versus ICD-9 codes, our study has limitations. First, for broader use, we did not implement specific algorithms that combine pharmacy dispensing data or codes from multiple time points.…”