Reports From the Field

Improving Hospital Metrics Through the Implementation of a Comorbidity Capture Tool and Other Quality Initiatives


 

References

Methods

In the fall of 2019, we embarked on a multifaceted quality improvement project aimed at improving comorbidity capture for patients hospitalized at our institution. The health system includes 2 academic inpatient facilities, a 560-bed tertiary hospital and a 40-bed cancer facility. Since September 2017, we have used Epic as our EHR. In August 2019, we started working with Vizient Clinical Data Base5 to allow benchmarking with peer institutions. We assessed the impact of this initiative with a pre/post study design.

Quality Initiatives

This quality improvement project consisted of a series of 5 targeted interventions coupled with continuous monitoring and education.

1. Comorbidity coding. In October 2019, we met with the clinical documentation specialists (CDS) and the coding team to educate them on the value of coding all comorbidities that have an impact on CMI and expected mortality, not only those that optimize the DRG.

2. Physician query. In October 2019, we modified the process for physician query response, allowing physicians to answer queries in the EHR through a reply tool incorporated into the query and accept answers in the body of the Epic message as an active part of the EHR.

3. EHR logic. In August 2020, we developed an EHR smart logic to automatically capture fluid and electrolyte disturbances and renal dysfunction, based on the most recent laboratory values. The logic automatically populated potentially appropriate diagnoses in the assessment and plan of provider notes, which require provider acknowledgment and which providers are able to modify (eFigure 1).

tables and figures for JCOM

4. Comorbidity capture tool. In November 2020, we developed a standardized tool to allow providers to easily capture Elixhauser comorbidities (eFigure 2). The Elixhauser index is a method for measuring comorbidities based on International Classification of Diseases, Ninth Revision, Clinical Modification and International Classification of Disease, Tenth Revision diagnosis codes found in administrative data1-6 and is used by US News & World Report and Vizient to assess comorbidity burden. Our tool automatically captures diagnoses recorded in previous documentation and allows providers to easily provide the management plan for each; this information is automatically pulled into the provider note.

tables and figures for JCOM

The development of this tool used an existing functionality within the Epic EHR called SmartForms, SmartData Elements, and SmartLinks. The only cost of tool development was the time invested—124 hours inclusive of 4 hours of staff education. Specifically, a panel of experts (including physicians of different specialties, an analyst, and representatives from the quality office) met weekly for 30 minutes per week over 5 weeks to agree on specific clinical criteria and guide the EHR build analyst. Individual panel members confirmed and validated design requirements (in 15 hours over 5 weeks). Our senior clinical analyst II dedicated 80 hours to actual build time, 15 hours to design time, and 25 hours to tailor the function to our institution’s workflow. This tool was introduced in November 2020; completion was optional at the time of hospital admission but mandatory at discharge to ensure compliance.

5. Quality team. The CDI functionality was transitioned to be under the direction of the institution’s quality team/chief medical officer office. This was a paradigm shift for physician engagement. We started speaking and customizing queries and technology focusing on severity of illness and speaking “physician language.” Providers received education on a regular basis, with scheduled meetings with departments and divisions, residents, and advanced practice providers, and on an individual basis as needed to fill gaps in knowledge about the documentation process or occasional requests. Last, extensive review of the medical record was conducted regularly by the quality team and physician champions. The focus of those reviews was on hospital-acquired conditions and patient safety indicators that were validated to ensure that the conditions were present on admission, or if the condition was not clearly documented, that the team request additional clarification by the provider when indicated. Mortality reviews were performed, with special focus on those with mortality well below expected, to ensure that all relevant and impactful codes were included.

Pages

Recommended Reading

Comparison of Fractional Flow Reserve–Guided PCI and Coronary Bypass Surgery in 3-Vessel Disease
Journal of Clinical Outcomes Management
Intervention in Acute Hospital Unit Reduces Delirium Incidence for Older Adults, Has No Effect on Length of Stay, Other Complications
Journal of Clinical Outcomes Management
Structural Ableism: Defining Standards of Care Amid Crisis and Inequity
Journal of Clinical Outcomes Management
Role and Experience of a Subintensive Care Unit in Caring for Patients With COVID-19 in Italy: The CO-RESP Study
Journal of Clinical Outcomes Management
Differences in COVID-19 Outcomes Among Patients With Type 1 Diabetes: First vs Later Surges
Journal of Clinical Outcomes Management
Early Hospital Discharge Following PCI for Patients With STEMI
Journal of Clinical Outcomes Management
Using a Real-Time Prediction Algorithm to Improve Sleep in the Hospital
Journal of Clinical Outcomes Management
Oxygen Therapies and Clinical Outcomes for Patients Hospitalized With COVID-19: First Surge vs Second Surge
Journal of Clinical Outcomes Management
Acute STEMI During the COVID-19 Pandemic at a Regional Hospital: Incidence, Clinical Characteristics, and Outcomes
Journal of Clinical Outcomes Management
A Practical and Cost-Effective Approach to the Diagnosis of Heparin-Induced Thrombocytopenia: A Single-Center Quality Improvement Study
Journal of Clinical Outcomes Management