Process improvement for follow-up radiology report recommendations of lung nodules

Abstract

In the modern healthcare system, there are still wide gaps of communication of imaging results to physician and patient stakeholders and tracking of whether follow-up has occurred. Patients are also unaware of the significance of findings in radiology reports. With the increase in use of cross-sectional imaging such as CT, patients are not only being diagnosed with primary urgent findings but also with incidental findings such as lung nodules; however, they are not being told of their imaging findings nor what actions to take to mitigate their risks. In addition, patients at high risk for developing lung cancer often obtain serial CT scans, but tracking these patients is challenging for the clinician.In order to advance quality improvement goals and improve patient outcomes, we developed a custom application and business process for radiology practitioners that mines available healthcare data, identifies patients with lung nodules in need of follow-up imaging, notifies the patient and the primary care physician via mail, and measures process efficacy via executed follow-up screenings and captured patient condition.This integrated analytics and communication process increased our average rate of patient follow-ups for lung nodules from 26.50 in 2015 to 59.72% in 2017. 17.18% of these patients had new lung nodules or worsening severity of lung findings detected at follow-up. This new process has added missing quality and care coordination to an at-risk patient population.ProblemCommunication of imaging results and follow-up recommendations to patients and primary care providers (PCPs) is a challenge for healthcare systems. In addition, tracking whether a patient’s follow-up has been completed is another significant gap in care coordination. Patients are often unaware of or cannot even understand the significance of radiology findings or follow-up recommendations reported after imaging procedures. In addition, patients may not have a primary physician listed at time of imaging if the first encounter is in the emergency room (ER) or if their primary care physician or specialist works in a different electronic health record platform. Communication of imaging results to different healthcare providers is challenging with the myriad of existing electronic health record systems that often lack interoperability with other clinical entities.Description of lung nodules in radiology reports can vary widely if a standardised lexicon is not used. Moreover, follow-up recommendations by radiologists can be varied for certain size lung nodules because an individual’s risk factors to develop lung cancer may not be known at the time of dictation.Approximately 500 000 radiology imaging procedures are interpreted and performed annually by a single private group of 33 radiologists located at a 665-bed regional referral centre and at a 140-bed acute care community hospital, both located in the suburbs of a major metropolitan city. Management of this volume of patients in the health system can be overwhelming to nurse navigators, and there is usually no system in place for primary care physicians to follow-up lung nodules found unexpectedly on inpatient images. The goal of this project was to develop a better automated tracking method and communication tool to reduce the likelihood that needed follow-up studies are missed by patients and clinicians.

Natural Language Processing for the Identification of Incidental Lung Nodules in Computed Tomography Reports: A Quality Control Tool

“… 20 Also, few reports have analyzed the use of NLP tools to aid proper nodule management. 13 , 22 To our knowledge, only Kang et al 13 used NLP to specifically identify ILN, reporting a high sensitivity similar to that found in our study (91.1%; 95% CI, 83.8 to 95.6) and slightly smaller specificity (82.2%; 95% CI, 77.8 to 86.1). This difference in specificity from our algorithm could be explained by their tool including descriptions related to benign nodules, such as inflammatory ground glass opacity within both upper lobes and stable small nonspecific nodules.…”

“…This difference in specificity from our algorithm could be explained by their tool including descriptions related to benign nodules, such as inflammatory ground glass opacity within both upper lobes and stable small nonspecific nodules. 13 Lim et al 22 significantly improved lung nodule follow-up by developing an analytical algorithm, mining data from radiology reports, and linking the identified patients and primary care physicians to close the loop with follow-up communication. However, that study included previously known or definitively benign nodules and did not analyze separately ILN.…”

Adherence to Follow-up Testing Recommendations in US Veterans Screened for Lung Cancer, 2015-2019

“…2 Although the US Preventive Services Task Force has recommended LCS for high-risk individuals since 2013, 3 there has been limited evidence on follow-up after initial LCS in real-world settings, with selected institutions reporting adherence ranging from 37% to 86%. [4][5][6][7][8][9] Barriers to adherence exist at the patient level (eg, reduced access to preventive health care among smokers), [10][11][12] clinician level (eg, insufficient knowledge of LCS and pulmonary nodule evaluation), [13][14][15] and system level (eg, insufficient resources to track and ensure appropriate evaluation). 7,16 Veterans are at increased risk of lung cancer, given high rates of tobacco use, with a large population of veterans eligible for LCS.…”

Incidental pulmonary nodules may lead to a high proportion of early-stage lung cancer: but it requires more than a high CT volume to achieve this

“…Therefore, it is crucial to establish clear management protocols for each hospital. In a previous study, a multifaceted communication system was implemented to ensure nodule follow-up, resulting in a significant increase in follow-up rates from 26.5% to 59.7% [ 28 ]. In another study, the hospital implemented a system using standardized language (tracker phrases) recommending time-based follow-up in chest CT reports, coupled with a computerized registry.…”