Modelling length bias in a longitudinally‐linked record system of HIV cases

Abstract

We compare numbers of hospital admissions for intravenous drug using (IVDU) HIV patients and other HIV patients in acute-care facilities in New York State. Data consist of routinely collected hospital-discharge reports from New York's Statewide Planning and Research Cooperative System, linked into longitudinal case histories. Because recognition of an IVDU depends on an opioid diagnosis on any record in the case history, the observed distribution of the number of admissions per case for recognized IVDU's is biased towards greater numbers of admissions. We develop and apply a model to overcome this biasing. Our findings reveal that the mean numbers of admissions for the two groups differ significantly, but less so than without recognition of the length biasing.

Decision Analysis for the Assessment of a Record Linkage Procedure

“…Record linkage is of minor concerni n countries in whichu nique reliable identi-fiers(common in North Americansystems, such as health maintenanceo rganizations) are availablebut mayberatherchallenging if the amount andquality of the data available forp ersonali dentification is limited [1]. Ar eviewo fr ecentr eports [3] has pointed out record linkage efforts in many countries (Canada,U SA, Italy,S weden, Finland,D enmark,T he Netherlands)f or a variety of purposes including cancer registration [4][5][6][7]; heartdisease (8,9) or HIV [10,11] survey;a nd post-marketing drug surveillance [12,13]. This reviewshowedthat the difficultiesi nm atching information concerning agiven individual were not the samei na ll countries.These differences in the identification proceduresa re relatedt o significant variations in legislation, regulations andguidelines for privacy protection of personal health information among countries ando rganizations [ 14].…”

The Feasibility and Accuracy of Anonymized Record Linkage to Estimate Shared Clientele among Three Health and Social Service Agencies

“…A review of recent reports shows record-linkage efforts in many countries (Canada, the USA, Italy, Sweden, Finland, Denmark, The Netherlands) for a variety of purposes: studies of cancer [7][8][9][10][11][12][13][14][15], including occupational cancers [16][17][18][19]; heart disease [20][21][22][23]; HIV [24,25]; and post-marketing drug surveillance [26][27][28][29], among others [30][31][32][33][34][35][36][37][38][39][40][41][42][43][44].…”