Inpatient diagnostic assessments: 2. Interrater reliability and outcomes of structured vs. unstructured interviews

Abstract

A preceding study found that structured interviews (SCID-CV, Computer Assisted Diagnostic Interview [CADI]) were significantly more accurate than the unstructured Traditional Diagnostic Assessment (TDA) for making inpatient diagnoses, using Consensus Diagnosis as the standard. This study measured interrater reliability for diagnoses between the Emergency Room (ER) and the Inpatient Unit (IU), as achieved by TDA vs. CADI. It selected subjects from consecutive admissions to the ER who were transferred to the IU. Group 1 had 33 subjects evaluated with TDA, leading to interrater agreement=45.5% (15/33) and kappa=0.24 ('poor'). Group 2 had 39 subjects evaluated with CADI, leading to interrater agreement=79.5% (31/39) and kappa=0.75 ('excellent'). Group 3 had 33 subjects, again evaluated with TDA, leading to interrater agreement=54.5% (18/33) and kappa=0.43 ('fair'). The test-retest-test (TDA-CADI-TDA) format demonstrated that CADI had better interrater reliability than TDA. How diagnostic reliability might correlate with parameters like timing of treatment choices and length of stay are also measured and discussed.