Related Experiment Video
Updated: Sep 10, 2025

Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
Published on: June 10, 2025
Incorporating the Present-on-Admission Indicator to Predict In-hospital Mortality Through Elixhauser Measures: A
Jianfang Liu1, Ani Bilazarian2, Madeline M Pollifrone1
1Columbia University School of Nursing, New York, NY.
Background:
In 2021, the Agency for Health Care Research and Quality (AHRQ) updated its guidelines for using the Present-on-Admission (POA) indicator in the Elixhauser comorbidity index. This update helps distinguish pre-existing comorbidities from complications that arise after hospital admission, improving the validity of hospital performance assessments and more accurately measuring patients' severity of illness upon admission.
Objective:
To evaluate differences in comorbidity prevalence and the predictive performance of the Elixhauser Comorbidity Index for in-hospital mortality at admission under 3 comorbidity coding guidelines, including one that ignores the POA indicator.
Research Design:
A retrospective analysis of inpatient administrative data on Medicare beneficiaries.
Subjects:
The dataset included 1,810,106 adult Medicare inpatient admissions across 6 U.S. states between 2017 and 2019.
Methods:
Elastic net models were applied to predict in-hospital mortality using 3 approaches to coding comorbidities: (1) No-POA (including all conditions as admission comorbidities), (2) Full-POA (including only POA conditions as comorbidities), and (3) the 2021 AHRQ Partial-POA (applying POA to a subset of conditions to code comorbidities). Results: C-statistics were 0.800 (0.797-0.804), 0.768 (0.763-0.771), and 0.786 (0.781-0.790) for No-POA, full-POA, and 2021 AHRQ partial-POA guidelines, respectively.
Conclusion:
Ignoring the POA inflated model performance by misclassifying complications as admission comorbidities. The 2021 Partial-POA guidelines achieved intermediate C-statistics while ensuring internal validity by accurately measuring illness severity at admission. This supports improved hospital evaluations, care quality, resource allocation, tailored intervention, and reimbursement. The elastic net model shows promise as a standard for predicting in-hospital mortality with the Elixhauser comorbidity measure.
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
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Related Concept Videos
Kaplan-Meier Approach
Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Comparing the Survival Analysis of Two or More Groups
Healthcare Associated Infections II: Preventive Measures
The best practices for preventing healthcare-associated infections include hand hygiene, patient risk...
Cancer Survival Analysis
Introduction To Survival Analysis
The primary goal of survival analysis is to estimate survival time—the time...