Related Experiment Video
Updated: Oct 21, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Identifying medication-related readmissions: Two students using tools vs a multidisciplinary panel
Tristan Coppes1, Jozien van der Kloes1, Olivia Dalleur2
1Department of Clinical Pharmacy, OLVG, Amsterdam, The Netherlands.
Background:
Polypharmacy may result in medication-related readmissions (MRRs). Identifying MRRs is time consuming. Screening of readmissions by students could increase efficiency for healthcare professionals. Recently, two screening tools have been published: the Assessment Tool for identifying Hospital Admissions Related to Medications (AT-HARM10) tool and the Drug-Related Admission (DRA) adjudication guide. It is unknown whether pharmacy students could identify MRRs with these tools.
Objective:
To compare the agreement between two pharmacy students applying the AT-HARM10 tool and DRA adjudication guide in identifying MRRs vs a multidisciplinary panel.
Methods:
A retrospective study was conducted from February to July 2020 at OLVG hospital. Readmissions within 30 days after discharge from seven departments were reviewed by a multidisciplinary panel (pharmacists and physicians). MRRs were defined as readmission where medication was the main cause or medication significantly contributed to the readmission. Two 5th year pharmacy-students volunteered to blindly apply both tools individually on all MRRs and a random sample of non-MRRs. The consensus results of the students and the multidisciplinary panel were compared and displayed as a percentage and Cohen's kappa (κ).
Results:
Three hundred sixty-six readmission cases were selected in total, consisting of 181 MRRs and 185 non-MRRs. The agreement between the students using the AT-HARM10 tool vs the multidisciplinary panel was moderate (80%, κ = 0.60 (95% confidence interval (CI): 0.52-0.68)). The DRA adjudication guide had a moderate agreement (81%, κ = 0.62 (CI: 0.54-0.70)). Students misclassified MRRs mainly because the multidisciplinary panel found disease progression more profound than a contribution of medication.
Conclusions:
Two students have an overall agreement of 80% in comparison with the multidisciplinary panel with a moderate Cohen's kappa. Students are more often overestimated, but they may be a good option to preselect potential MRRs to save time for healthcare professionals. However, some MRRs will be missed.
More Related Videos
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
11:02Identification and Quantification of Deranged Metabolites in Critically Ill Patients Using NMR-Based Metabolomics
Published on: November 29, 2024
Related Concept Videos
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...
Comparing the Survival Analysis of Two or More Groups
Drug Dosing: Geriatric Patients
Drug Therapy
Antianxiety Medications
Blind Procedures