Application of Triggers on VA "Big Data" may Help Identify Patients Experiencing Delays in Diagnostic Evaluation of Chest Imaging

BACKGROUND:
Wider use of electronic health records (EHRs) has created vast amounts of digitally-stored data ("big data") to track a patient's journey through the continuum of healthcare. However, the follow-up of abnormal imaging test results remains a problem despite communication facilitated by the EHR. Triggers offer one method to use big EHR data to prevent and mitigate the impact of delays in care related to missed test results. Triggers consist of computerized algorithms that can scan thousands of patient records to flag those with clues suggestive of patient safety events. This study tested the application of a trigger within VA's EHR to help identify delays in patient follow-up related to abnormal chest imaging results. Investigators focused on Veterans (n=208,633) seen at seven VAMCs in the Midwest from January through December 2012. The trigger was applied to all patient records where a chest radiograph or CT was performed during the study period. Analysis included calculating the trigger's diagnostic performance, Investigators then evaluated time to follow-up and delays. For this study, investigators chose 30 days to complete follow-up action, allowing sufficient time for clinicians to follow up with patients without significant progression of disease.

FINDINGS:

• The trigger identified delays in patient follow-up with a reasonable accuracy for use in the clinical setting, suggesting that triggers are able to identify almost all delays related to abnormal lung imaging follow-up, and cost-effectively minimize the amount of effort providers spend reviewing false-positive results.
• Among the 208,633 Veterans in this study, 40,218 chest imaging tests were performed, of which 1,847 results were suspicious for malignancy and 655 (35%) were trigger-positive (patients had a trigger-identified delay in follow-up).
• Manual review of 400 randomly selected trigger-positive patients identified 242 (65%) records where follow-up diagnostic evaluation was not performed within 30 days.

IMPLICATIONS:

• The application of triggers on big EHR data may aid in identifying patients experiencing delays in diagnostic evaluation of chest imaging results suspicious for malignancy. Future work to develop and refine similar algorithms more widely can potentially reduce delays in diagnostic evaluation and improve quality and safety of patient care.

LIMITATIONS:

• Retrospective chart reviews relied on text within the electronic record, which may not always describe actual care delivered – or the rationale for not taking action.
• This study was not designed to evaluate the clinical or economic impact of prospective triggers use on morbidity, mortality, and stage at diagnosis.

AUTHOR/FUNDING INFORMATION:
This study was partly funded by HSR&D (CRE 12-033). All authors except Dr. Sittig are part of HSR&D's Center for Innovations in Quality, Effectiveness and Safety (IQuESt) in Houston, TX.

Murphy DR, Meyer AND, Bhise V, Russo E, Sittig D, Wei L, Wu L, and Singh H. Computerized Triggers of Big Data to Detect Delays in Follow-up of Chest Imaging Results. CHEST. September 2016;150(3):613-20.