Dataset Information

Development of stroke identification algorithm for claims data using the multicenter stroke registry database.

ABSTRACT: BACKGROUND:Identifying acute ischemic stroke (AIS) among potential stroke cases is crucial for stroke research based on claims data. However, the accuracy of using the diagnostic codes of the International Classification of Diseases 10th revision was less than expected. METHODS:From the National Health Insurance Service (NHIS) claims data, stroke cases admitted to the hospitals participating in the multicenter stroke registry (Clinical Research Collaboration for Stroke in Korea, CRCS-K) during the study period with principal or additional diagnosis codes of I60-I64 on the 10th revision of International Classification of Diseases were extracted. The datasets were randomly divided into development and validation sets with a ratio of 7:3. A stroke identification algorithm using the claims data was developed and validated through the linkage between the extracted datasets and the registry database. RESULTS:Altogether, 40,443 potential cases were extracted from the NHIS claims data, of which 31.7% were certified as AIS through linkage with the CRCS-K database. We selected 17 key identifiers from the claims data and developed 37 conditions through combinations of those key identifiers. The key identifiers comprised brain CT, MRI, use of tissue plasminogen activator, endovascular treatment, carotid endarterectomy or stenting, antithrombotics, anticoagulants, etc. The sensitivity, specificity, and diagnostic accuracy of the algorithm were 81.2%, 82.9%, and 82.4% in the development set, and 80.2%, 82.0%, and 81.4% in the validation set, respectively. CONCLUSIONS:Our stroke identification algorithm may be useful to grasp stroke burden in Korea. However, further efforts to refine the algorithm are necessary.

SUBMITTER: Kim JY

PROVIDER: S-EPMC7021298 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of stroke identification algorithm for claims data using the multicenter stroke registry database.

Kim Jun Yup JY Lee Keon-Joo KJ Kang Jihoon J Kim Beom Joon BJ Han Moon-Ku MK Kim Seong-Eun SE Lee Heeyoung H Park Jong-Moo JM Kang Kyusik K Lee Soo Joo SJ Kim Jae Guk JG Cha Jae-Kwan JK Kim Dae-Hyun DH Park Tai Hwan TH Park Moo-Seok MS Park Sang-Soon SS Lee Kyung Bok KB Park Hong-Kyun HK Cho Yong-Jin YJ Hong Keun-Sik KS Choi Kang-Ho KH Kim Joon-Tae JT Kim Dong-Eog DE Ryu Wi-Sun WS Choi Jay Chol JC Oh Mi-Sun MS Yu Kyung-Ho KH Lee Byung-Chul BC Park Kwang-Yeol KY Lee Ji Sung JS Jang Sujung S Chae Jae Eun JE Lee Juneyoung J Bae Hee-Joon HJ

PloS one 20200214 2

<h4>Background</h4>Identifying acute ischemic stroke (AIS) among potential stroke cases is crucial for stroke research based on claims data. However, the accuracy of using the diagnostic codes of the International Classification of Diseases 10th revision was less than expected.<h4>Methods</h4>From the National Health Insurance Service (NHIS) claims data, stroke cases admitted to the hospitals participating in the multicenter stroke registry (Clinical Research Collaboration for Stroke in Korea, C ...[more]

PMID: 32059039

Similar Datasets

Project description:BackgroundThe linkage of registries to Medicare claims data can help extend follow-up for patients receiving medical devices. In the present study, we tested and validated an algorithm that does not require patient identifiers to link data from a national vascular registry and Medicare claims data.MethodsWe used data from the Vascular Quality Initiative (VQI), a registry capturing data from >600 centers for several different vascular procedures, and Medicare claims from 2003 to 2018. We restricted the study to patients aged ≥65 years who had fee-for-service entitlement at their procedure. We performed an indirect linkage to combine the VQI and Medicare data at the patient level using a sequential algorithm based on the patient's date of birth, sex, zip code, procedure date, and procedure facility. We compared the indirectly linked cohort against a reference standard of a cohort directly linked using Social Security numbers. We calculated the matching rate and accuracy overall and before and after October 2015 when the International Classification of Diseases, 10th revision (ICD-10) system was adopted in the United States.ResultsA total of 144,045 VQI-Medicare-linked patients were in the reference standard cohort. Using the indirect linking algorithm, we matched 133,966 of the 144,045 VQI patients to their Medicare claims with a matching rate of 93.0%. Of the 133,966 patients, 133,104 were correctly matched (matching accuracy, 99.4%). The matching rate was higher when the indirect linkage was implemented using the ICD-10 coded data than using the ICD-9 coded data (94.0% vs 92.2%). The accuracy of the indirect linkage remained high for all procedure modules after the ICD-10 coding change (overall, 99.4%; range, 99.0%-99.7%).ConclusionsIn the present study, we successfully used indirect identifiers to link the VQI data to Medicare claims with >90% success and >99% accuracy. When direct linkage of the registry claims data using Social Security numbers is not possible because of availability or confidentiality, or both, our algorithm for indirect linkage provides a suitable alternative. The matching rate and accuracy will help ensure the accuracy of long-term follow-up and the completeness and representativeness of linked databases for relevant research and quality improvement initiatives.

Project description:Pregnancy is a condition of broad interest across many medical and health services research domains, but one not easily identified in healthcare claims data. Our objective was to establish an algorithm to identify pregnant women and their pregnancies in claims data. We identified pregnancy-related diagnosis, procedure, and diagnosis-related group codes, accounting for the transition to International Statistical Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) diagnosis and procedure codes, in health encounter reporting on 10/1/2015. We selected women in Merative MarketScan commercial databases aged 15-49 years with pregnancy-related claims, and their infants, during 2008-2019. Pregnancies, pregnancy outcomes, and gestational ages were assigned using the constellation of service dates, code types, pregnancy outcomes, and linkage to infant records. We describe pregnancy outcomes and gestational ages, as well as maternal age, census region, and health plan type. In a sensitivity analysis, we compared our algorithm-assigned date of last menstrual period (LMP) to fertility procedure-based LMP (date of procedure + 14 days) among women with embryo transfer or insemination procedures. Among 5,812,699 identified pregnancies, most (77.9%) were livebirths, followed by spontaneous abortions (16.2%); 3,274,353 (72.2%) livebirths could be linked to infants. Most pregnancies were among women 25-34 years (59.1%), living in the South (39.1%) and Midwest (22.4%), with large employer-sponsored insurance (52.0%). Outcome distributions were similar across ICD-9 and ICD-10 eras, with some variation in gestational age distribution observed. Sensitivity analyses supported our algorithm's framework; algorithm- and fertility procedure-derived LMP estimates were within a week of each other (mean difference: -4 days [IQR: -13 to 6 days]; n = 107,870). We have developed an algorithm to identify pregnancies, their gestational age, and outcomes, across ICD-9 and ICD-10 eras using administrative data. This algorithm may be useful to reproductive health researchers investigating a broad range of pregnancy and infant outcomes.

Project description:IntroductionNontraumatic intracranial hemorrhage (ICH) is a neurological emergency of research interest; however, unlike ischemic stroke, has not been well studied in large datasets due to the lack of an established administrative claims-based definition. We aimed to evaluate both explicit diagnosis codes and machine learning methods to create a claims-based definition for this clinical phenotype.MethodsWe examined all patients admitted to our tertiary medical center with a primary or secondary International Classification of Disease version 9 (ICD-9) or 10 (ICD-10) code for ICH in claims from any portion of the hospitalization in 2014-2015. As a gold standard, we defined the nontraumatic ICH phenotype based on manual chart review. We tested explicit definitions based on ICD-9 and ICD-10 that had been previously published in the literature as well as four machine learning classifiers including support vector machine (SVM), logistic regression with LASSO, random forest and xgboost. We report five standard measures of model performance for each approach.ResultsA total of 1830 patients with 2145 unique ICD-10 codes were included in the initial dataset, of which 437 (24%) were true positive based on manual review. The explicit ICD-10 definition performed best (Sensitivity = 0.89 (95% CI 0.85-0.92), Specificity = 0.83 (0.81-0.85), F-score = 0.73 (0.69-0.77)) and improves on an explicit ICD-9 definition (Sensitivity = 0.87 (0.83-0.90), Specificity = 0.77 (0.74-0.79), F-score = 0.67 (0.63-0.71). Among machine learning classifiers, SVM performed best (Sensitivity = 0.78 (0.75-0.82), Specificity = 0.84 (0.81-0.87), AUC = 0.89 (0.87-0.92), F-score = 0.66 (0.62-0.69)).ConclusionsAn explicit ICD-10 definition can be used to accurately identify patients with a nontraumatic ICH phenotype with substantially better performance than ICD-9. An explicit ICD-10 based definition is easier to implement and quantitatively not appreciably improved with the additional application of machine learning classifiers. Future research utilizing large datasets should utilize this definition to address important research gaps.

Dataset Information

Development of stroke identification algorithm for claims data using the multicenter stroke registry database.

Publications

Development of stroke identification algorithm for claims data using the multicenter stroke registry database.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets