Automated Severity Classification of AIDS Hospitalizations
Frank W. Stitt, Ying Lü, Gordon M. Dickinson, Nancy G. Klimas · Medical Decision Making · 1991
To validate an automated AIDS severity-of-illness prognostic algorithm, 2,113 discharge summaries of HIV-infected patients were merged with the Problem-Oriented Medical Synopsis (POMS) and an HIV risk registry. The combination of a medically derived classification and staging algorithm with multivariate statistical techniques was used for automated severity-of-illness disease staging and prognostic assignment. The model correctly predicted the outcomes of 82% of all cases (death, survivorship) at discharge, and 66% of deaths.