The Need for Practical and Accurate Measures of Value for Radiology

Health Systems Science - A Primer for Radiologists

Health systems science (HSS) is an educational framework designed to promote improved care through enhanced citizenship and the training of systems-fluent individuals trained in the science of health care delivery.  HSS education in residency builds upon foundations established during medical school, emphasizing practical skills development, and fostering a growth mindset among trainees.  The HSS framework organizes elements of system-based practice for radiology trainees, promoting practice-readiness for providing safe, timely, effective, efficient, equitable and patient centered radiological care. This paper serves as a primer for radiologists to understand and apply the HSS framework. Additionally, we highlight radiology-specific curricular elements aligned with the HSS framework, and provide teaching resources both for classroom education and for resident self-study.

Patient communication in radiology: Moving up the agenda

Optimised communication between patients and the imaging team is an essential component of providing patient-centred and value-based care. Communication with patients can be challenging in the setting of busy radiology departments where there is a focus on efficient and accurate diagnosis. Traditionally, most results are provided directly to the referring clinician. However, the importance of direct communication between the radiologist and patient is increasingly relevant, particularly in the context of face-to-face settings such as rapid assessment and ultrasound clinics, and interventional radiology, as well as in written form through electronic patient portals. Artificial intelligence tools may improve efficiency, allowing more time for radiologists to communicate directly with patients. There is a need for dedicated training in communication skills for imaging professionals. This review considers the topic of patient communication in the setting of imaging departments and discusses the ways that communication skills may be improved through training and through harnessing emerging digital technologies that may enhance the quality of communication.

Machine Learning and Improved Quality Metrics in Acute Intracranial Hemorrhage by Noncontrast Computed Tomography

OBJECTIVE

The timely reporting of critical results in radiology is paramount to improved patient outcomes. Artificial intelligence has the ability to improve quality by optimizing clinical radiology workflows. We sought to determine the impact of a United States Food and Drug Administration-approved machine learning (ML) algorithm, meant to mark computed tomography (CT) head examinations pending interpretation as higher probability for intracranial hemorrhage (ICH), on metrics across our healthcare system. We hypothesized that ML is associated with a reduction in report turnaround time (RTAT) and length of stay (LOS) in emergency department (ED) and inpatient populations.

MATERIALS AND METHODS

An ML algorithm was incorporated across CT scanners at imaging sites in January 2018. RTAT and LOS were derived for reports and patients between July 2017 and December 2017 prior to implementation of ML and compared to those between January 2018 and June 2018 after implementation of ML. A total of 25,658 and 24,996 ED and inpatient cases were evaluated across the entire healthcare system before and after ML, respectively.

RESULTS

RTAT decreased from 75 to 69 minutes (P <0.001) at all facilities in the healthcare system. At the level 1 trauma center specifically, RTAT decreased from 67 to 59 minutes (P <0.001). ED LOS decreased from 471 to 425 minutes (P <0.001) for patients without ICH, and from 527 to 491 minutes for those with ICH (P = 0.456). Inpatient LOS decreased from 18.4 to 15.8 days for those without ICH (P = 0.001) and 18.1 to 15.8 days for those with ICH (P = 0.02).

CONCLUSION

We demonstrated that utilization of ML was associated with a statistically significant decrease in RTAT. There was also a significant decrease in LOS for ED patients without ICH, but not for ED patients with ICH. Further evaluation of the impact of such tools on patient care and outcomes is needed.

Unread Second-Opinion Radiology Reports: A Potential Waste of Health Care Resources

OBJECTIVE. The purpose of this study was to investigate how frequently second-opinion radiology reports are not read by clinicians and to identify reasons why reports are not read. MATERIALS AND METHODS. This retrospective study included 4696 consecutive second-opinion reports of external imaging examinations that were authorized by subspecialty radiologists at a tertiary care institution over a 1-year period. RESULTS. Of 4696 second-opinion reports, 537 were not read by a clinician, corresponding to a frequency of 11.4% (95% CI, 10.6-12.3%). On multivariate logistic regression analysis, five variables were significantly and independently associated with the second-opinion report not being read: inpatient status (odds ratio [OR], 163.26; p < 0.001), sonography as the imaging modality (OR, 5.07; p = 0.014), surgery (OR, 0.18; p < 0.001) or neurology (OR, 2.82; p < 0.001) as the requesting clinician's specialty, and interventional radiology as the subspecialty of the radiologist who authorized the second-opinion report (OR, 3.52; p = 0.047). We found no significant independent associations between the clinician not reading the second-opinion report and patient age, patient sex, or time between submission of the second-opinion request and finalization of the report. CONCLUSION. A considerable proportion of second-opinion reports are not read by clinicians, which represents an appreciable but potentially reversible waste of health care resources. The reasons why clinicians do not read reports need to be investigated in future studies. If subspecialty radiologists and clinicians take the proven determinants into account, the amount of second-opinion readings with limited additional clinical value may be reduced.