Algorithmic Prediction of Delayed Radiology Turn-Around-Time during Non-Business Hours.

RATIONALE AND OBJECTIVES: Radiology turnaround time is an important quality measure that can impact hospital workflow and patient outcomes. We aimed to develop a machine learning model to predict delayed turnaround time during non-business hours and identify factors that contribute to this delay. MATERIALS AND METHODS: This retrospective study consisted of 15,117 CT cases from May 2018 to May 2019 during non-business hours at two hospital campuses after applying exclusion criteria. Of these 15,177 cases, 7,532 were inpatient cases and 7,585 were emergency cases. Order time, scan time, first communication by radiologist, free-text indications, and other clinical metadata were extracted. A combined XGBoost classifier and Random Forest natural language processing model was trained with 85% of the data and tested with 15% of the data. The model predicted two measures of delay: when the exam was ordered to first communication (total time) and when the scan was completed to first communication (interpretation time). The model was analyzed with the area under the curve (AUC) of receiver operating characteristic (ROC) and feature importance. Source code: https://bit.ly/2UrLiVJ RESULTS: The algorithm reached an AUC of 0.85, with a 95% confidence interval [0.83, 0.87], when predicting delays greater than 245 minutes for "total time" and 0.71, with a 95% confidence interval [0.68, 0.73], when predicting delays greater than 57 minutes for "interpretation time". At our institution, CT scan description (e.g. "CTA chest pulmonary embolism protocol"), time of day, and year in training were more predictive features compared to body part, inpatient status, and hospital campus for both interpretation and total time delay. CONCLUSION: This algorithm can be applied clinically when a physician is ordering the scan to reasonably predict delayed turnaround time. Such a model can be leveraged to identify factors associated with delays and emphasize areas for improvement to patient outcomes.

Follow-up of incidental pulmonary nodules and association with mortality in a safety-net cohort.

Background Though incidental pulmonary nodules are common, rates of guideline-recommended surveillance and associations between surveillance and mortality are unclear. In this study, we describe adherence (categorized as complete, partial, late and none) to guideline-recommended surveillance among patients with incidental 5-8 mm pulmonary nodules and assess associations between adherence and mortality. Methods This was a retrospective cohort study of 551 patients (≥35 years) with incidental pulmonary nodules conducted from September 1, 2008 to December 31, 2016, in an integrated safety-net health network. Results Of the 551 patients, 156 (28%) had complete, 87 (16%) had partial, 93 (17%) had late and 215 (39%) had no documented surveillance. Patients were followed for a median of 5.2 years [interquartile range (IQR), 3.6-6.7 years] and 82 (15%) died during follow-up. Adjusted all-cause mortality rates ranged from 2.24 [95% confidence interval (CI), 1.24-3.25] deaths per 100 person-years for complete follow-up to 3.30 (95% CI, 2.36-4.23) for no follow-up. In multivariable models, there were no statistically significant associations between the levels of surveillance and mortality (p > 0.16 for each comparison with complete surveillance). Compared with complete surveillance, adjusted mortality rates were non-significantly increased by 0.45 deaths per 100 person-years (95% CI, -1.10 to 2.01) for partial, 0.55 (95% CI, -1.08 to 2.17) for late and 1.05 (95% CI, -0.35 to 2.45) for no surveillance. Conclusions Although guideline-recommended surveillance of small incidental pulmonary nodules was incomplete or absent in most patients, gaps in surveillance were not associated with statistically significant increases in mortality in a safety-net population.

Displaying radiation exposure and cost information at order entry for outpatient diagnostic imaging: a strategy to inform clinician ordering.

BACKGROUND: Displaying radiation exposure and cost information at electronic order entry may encourage clinicians to consider the value of diagnostic imaging. METHODS: An urban safety-net health system displayed radiation exposure information for CT and cost information for CT, MRI and ultrasound on an electronic referral system for outpatient ordering. We assessed whether there were differences in numbers of outpatient CT scans and MRIs per month relative to ultrasounds before and after the intervention, and evaluated primary care clinicians' responses to the intervention. RESULTS: There were 23 171 outpatient CTs, 15 052 MRIs and 43 266 ultrasounds from 2011 to 2014. The ratio of CTs to ultrasounds decreased by 15% (95% CI 9% to 21%), from 58.2 to 49.6 CTs per 100 ultrasounds; the ratio of MRIs to ultrasounds declined by 13% (95% CI 7% to 19%), from 37.5 to 32.5 per 100. Of 300 invited, 190 (63%) completed the web-based survey in 17 clinics. 154 (81%) noticed the radiation exposure information and 158 (83.2%) noticed the cost information. Clinicians believed radiation exposure information was more influential than cost information: when unsure clinically about ordering a test (radiation=69.7%; cost=46.4%), when a patient wanted a test not clinically indicated (radiation=77.5%; cost=54.8%), when they had a choice between imaging modalities (radiation=77.9%; cost=66.6%), in patient care discussions (radiation=71.9%; cost=43.2%) and in trainee discussions (radiation=56.5%; cost=53.7%). Resident physicians and nurse practitioners were more likely to report that the cost information influenced them (p<0.05). CONCLUSIONS: Displaying radiation exposure and cost information at order entry may improve clinician awareness about diagnostic imaging safety risks and costs. More clinicians reported the radiation information influenced their clinical practice.

Clinicians' views on displaying cost information to increase clinician cost-consciousness.

OBJECTIVES: To evaluate 1) clinician attitudes towards incorporating cost information into decision making when ordering imaging studies; and 2) clinician reactions to the display of Medicare reimbursement information for imaging studies at clinician electronic order entry. STUDY DESIGN: Focus group study with inductive thematic analysis. METHODS: We conducted focus groups of primary care clinicians and subspecialty physicians (nephrology, pulmonary, and neurology) (N = 50) who deliver outpatient care in 12 hospital-based clinics and community health centers in an urban safety net health system. We analyzed focus group transcripts using an inductive framework to identify emergent themes and illustrative quotations. RESULTS: Clinicians believed that their knowledge of healthcare costs was low and wanted access to relevant cost information for reference. However, many clinicians believed it was inappropriate and unethical to consider costs in individual patient care decisions. Among clinicians' negative reactions toward displaying costs at order entry, 4 underlying themes emerged: 1) belief that ordering is already limited to clinically necessary tests; 2) importance of prioritizing responsibility to patients above that to the healthcare system; 3) concern about worsening healthcare disparities; and 4) perceived lack of accountability for healthcare costs in the system. CONCLUSIONS: Although clinicians want relevant cost information, many voiced concerns about displaying cost information at clinician order entry in safety net health systems. Alternative approaches to increasing cost-consciousness may be more acceptable to clinicians.

Clinician perspectives on considering radiation exposure to patients when ordering imaging tests: a qualitative study.

BACKGROUND AND OBJECTIVES: Increased computer tomography (CT) scan use has contributed to a rise in medically-associated radiation exposure. The extent to which clinicians consider radiation exposure when ordering imaging tests is unknown. We examined (1) outpatient clinician attitudes towards considering radiation exposure when ordering CT scans; and (2) clinician reactions to displaying radiation exposure information for CT scans at clinician electronic order entry. METHODS: We conducted nine focus groups with primary care clinicians and subspecialty physicians (nephrology, pulmonary and neurology) (n=50) who deliver outpatient care across 12 hospital-based clinics and community health centres in an urban safety-net health system, which use a common electronic order entry system. We analysed focus group transcripts using an inductive framework to identify emergent themes and illustrative quotations. FINDINGS: Clinicians felt they had limited knowledge of the clinical implications of radiation exposure. Many believed clinically relevant information such as the increased risk of malignancy from CT scans would be useful to inform decision-making and patient-clinician discussions. Clinicians noted that patient vulnerability and long wait times for tests with less radiation exposure (such as MRI or ultrasound) often acted as barriers to minimise patient radiation exposure from CT scans. Clinicians suggested providing patients' cumulative radiation exposure or formal decision aids to improve the usefulness of the radiation exposure information. CONCLUSIONS: Displaying clinically relevant radiation exposure information at order entry may improve clinician knowledge and inform patient-clinician discussions regarding risks and benefits of imaging. However, limited access to tests with lower radiation exposure in safety-net settings may trump efforts to minimise patient radiation exposure.