Applying a Text-Search Algorithm to Radiology Reports Can Find More Patients With Pulmonary Nodules Than Radiology Coding Alone
Introduction: Chest imaging often incidentally finds indeterminate nodules that need to be monitored to ensure early detection of lung cancers. Health care systems need effective approaches for identifying these lung nodules. We compared the diagnostic performance of 2 approaches for identifying patients with lung nodules on imaging studies (chest/abdomen): (1) relying on radiologists to code imaging studies with lung nodules; and (2) applying a text search algorithm to identify references to lung nodules in radiology reports.
Methods: We assessed all radiology studies performed between January 1, 2016 and November 30, 2016 in a single Veterans Health Administration hospital. We first identified imaging reports with a diagnostic code for a pulmonary nodule. We then applied a text search algorithm to identify imaging reports with key words associated with lung nodules. We reviewed medical records for all patients with a suspicious radiology report based on either search strategy to confirm the presence of a lung nodule. We calculated the yield and the positive predictive value (PPV) of each search strategy for finding pulmonary nodules.
Results: We identified 12,983 imaging studies with a potential lung nodule. Chart review confirmed 8,516 imaging studies with lung nodules, representing 2,912 unique patients. The text search algorithm identified all the patients with lung nodules identified by the radiology coding (n = 1,251) as well as an additional 1,661 patients. The PPV of the text search was 72% (2,912/4,071) and the PPV of the radiology code was 92% (1,251/1,363). Among the patients with nodules missed by radiology coding but identified by the text search algorithm, 130 had lung nodules > 8 mm in diameter.
Conclusions: The text search algorithm can identify additional patients with lung nodules compared to the radiology coding; however, this strategy requires substantial clinical review time to confirm nodules. Health care systems adopting nodule-tracking approaches should recognize that relying only on radiology coding might miss clinically important nodules.
The VHA system should have an effective strategy for identifying incidental lung nodules during routine radiology examinations. Relying only on radiologists to identify and code pulmonary nodules can lead to missing a significant number of patients with lung nodules and some patients with early stage lung cancer who could receive curative therapy.12,14-16 The use of a standardized algorithm, like a text search strategy, might decrease the risk of variation in the execution and result in a more sensitive detection of patients with lung nodules. The text search strategy might be easily implemented and shared with other hospitals both within and outside the VHA.
Limitations
This study was performed in a single VHA hospital and the findings may not be generalizable to other settings of care. Second, our study design is susceptible to work-up bias because the results of a diagnostic test (eg, chest or abdomen imaging) affected whether the chart review was used to verify the test result. It was not feasible to review the patient records of all radiology studies done at the facility during the study period, consequently complete 2 × 2 tables could not be created to calculate sensitivity, specificity, and negative predictive value.
Conclusion
A text search algorithm of radiology reports increased the detection of patients with lung nodules when compared with radiology diagnostic coding alone. However, the improved detection was associated with a higher rate of false positives, which requires manually reviewing a larger number of patient’s chart reports. Future research and quality improvement should focus on standardizing the radiology reporting process and improving the efficiency and reliability of follow up and tracking of incidental lung nodules.
Acknowledgments
The work reported here was supported by a grant from the Office of Rural Health (N32-FY16Q1-S1-P01577), US Department of Veterans Affairs, Veterans Health Administration. We also had the support from the Veterans Rural Health Resource Center-Iowa City, and the Health Services Research and Development (HSR&D) Service through the Comprehensive Access and Delivery Research and Evaluation (CADRE) Center (REA 09-220).
