Capturing long-term outcomes from large clinical databases by use of claims data is a potential strategy for improving efficiency while reducing study costs. We sought to compare the use of Medicare data with data from the Women's Health Initiative (WHI) to determine peripheral vascular events, as defined by the WHI study design.Methods:
We studied participants from the WHI with both adjudicated outcomes and links to Medicare enrollment and utilization data through 2007. Outcomes of interest included hospitalizations for treatment of abdominal aortic aneurysm (AAA), lower extremity peripheral artery disease (LE PAD), and carotid artery stenosis (CAS). Events determined by WHI adjudication were compared with events defined by coding algorithms using diagnosis and procedure codes from Medicare data with a pilot data set and then validated with a test data set. We assessed agreement by a κ statistic and evaluated reasons for disagreement.Results:
In the pilot set, records from 50,511 participants were analyzed. Agreement between the Centers for Medicare and Medicaid Services and WHI for admissions with a diagnosis but no treatment procedures for vascular conditions was poor (κ, 0.02-0.18). On the basis of WHI outcome data collection, vascular treatment procedures occurred in 29 participants for AAA, 204 for LE PAD events, and 281 for CAS. Medicare hospital claims recorded 41 treatments for AAA, 255 for LE PAD, and 317 for CAS. For participants with a Centers for Medicare and Medicaid Services-captured vascular procedure and a record adjudicated by WHI, κ values for treatment procedures were 0.81 for AAA, 0.77 for PAD, and 0.93 for CAS. For vascular procedures identified by WHI but not by Medicare hospital data (n = 82), 55% were captured by Medicare physician claims. Conversely, for treatments identified by Medicare hospital data but not captured by WHI adjudication (n = 57), 74% had physician claims consistent with the procedure. Fifteen participants with AAA or LE PAD procedures in hospital claims had medical records available for review, and nine of these had definitive documentation of procedures that were not captured by the WHI adjudication process. Estimated positive predictive value of Medicare data was 91% to 94% for AAA, 92% to 95% for LE PAD, and 94% to 99% for CAS. Available test set data (n = 50,253) yielded generally similar results with κ of 0.77 for AAA, 0.79 for LE PAD, and 0.94 for CAS.Conclusions:
Medicare data appear useful for identifying vascular treatment procedures for WHI participants. Medicare hospital claims identify more procedures than WHI does, with high positive predictive value, but also may not capture some procedures identified in WHI.