Identification of dementia and MCI cases in health information systems: An Italian validation study

Abstract

Introduction: The identification of dementia cases through routinely collected health data represents an easily accessible and inexpensive method to estimate the prevalence of dementia. In Italy, a project aimed at the validation of an algorithm was conducted.

Methods: The project included cases (patients with dementia or mild cognitive impairment [MCI]) recruited in centers for cognitive disorders and dementias and controls recruited in outpatient units of geriatrics and neurology. The algorithm based on pharmaceutical prescriptions, hospital discharge records, residential long-term care records, and information on exemption from health-care co-payment, was applied to the validation population.

Results: The main analysis was conducted on 1110 cases and 1114 controls. The sensitivity, specificity, and positive and negative predictive values in discerning cases of dementia were 74.5%, 96.0%, 94.9%, and 79.1%, respectively, whereas in detecting cases of MCI these values were 29.7%, 97.5%, 92.2%, and 58.1%, respectively. The variables associated with misclassification of cases were also identified.

Discussion: This study provided a validated algorithm, based on administrative data, which can be used to identify cases with dementia and, with lower sensitivity, also early onset dementia but not cases with MCI.

Keywords: Dementia; algorithm; early onset dementia; health electronic data; mild cognitive impairment; prevalence; validation.

FIGURE 1

Contribution of data sources to dementia/MCI cases identification: Venn diagram. HD, hospital discharge; DP, drug prescription; ER, exemption registry; LTCF, residents in long‐term care facilities. The percentage of cases captured by long‐term care (LCT) was 6.2%, if excluding cases from Latium for which this source of data was not available