Documentation of nonroutine communications of critical or significant radiology results: a multiyear experience at a tertiary hospital

Analysis of critical report notification from musculoskeletal radiology in a tertiary academic medical institution with a regional trauma center

Purpose

We aimed to analyze the prevalence, causes, and clinical settings of 4-year critical radiologic reports (CRRs) notified from the musculoskeletal section of the radiology department. Then, we investigated the communication outcomes.

Methods

This study was approved by our institutional review board. We retrospectively included 175 musculoskeletal CRRs from our database between January 2017 and December 2020. The CRRs were analyzed by two musculoskeletal radiologists, who categorized the CRRs by clinical setting (emergency department(ED) patient, outpatient, and inpatient), body part, type of image modality, reason for CRR, incidental lesion, and clinical outcome. The clinical outcome was retrieved from the electronic medical records.

Results

The 175 musculoskeletal CRRs accounted for 5.4% of the CRRs (n = 3217) available in the study period. Most CRRs (94.9%, 166/175) corresponded to the musculoskeletal system, while the remaining ones (5.1%, 9/175) corresponded to the non-musculoskeletal system. In addition, the spine, extremities, and thoracic cage accounted for 52.6%, 40.6%, and 1.7% of the musculoskeletal CRRs, respectively. Moreover, most patients presented to the ED (50.3%, 88/175), followed by inpatients (30.9%, 54/175), and outpatients (18.9%, 33/175). The CRR reasons included missed fracture (54.3%), suspected malignancy (16%), clinical emergency (10.3%), unexpected infection/inflammation (11.4%), and others (8%). Furthermore, 11 (6.3%) incidental lesions were not related to the primary imaging purpose. Referring clinicians actively acknowledged 80% of the CRRs. The loss to follow-up action was the highest in the ED patients (35.2%, 31/88; p < 0.001), being significantly higher than that in outpatients (6.1%, 2/33) and inpatients (3.7%, 2/54).

Conclusion

Missed fractures were the most common cause of musculoskeletal CRRs. ED showed prevalence in musculoskeletal CRRs and reflected the highest loss to follow-up action. ED physicians should pay more attention to CRRs to enhance patient care.

Imaging informatics: essential tools for the delivery of imaging services

There are rapid changes occurring in the health care environment. Radiologists face new challenges but also new opportunities. The purpose of this report is to review how new informatics tools and developments can help the radiologist respond to the drive for safety, quality, and efficiency. These tools will be of assistance in conducting research and education. They not only provide greater efficiency in traditional operations but also open new pathways for the delivery of new services and imaging technologies. Our future as a specialty is dependent on integrating these informatics solutions into our daily practice.

Automated detection of critical results in radiology reports

The goal of this study was to develop and validate text-mining algorithms to automatically identify radiology reports containing critical results including tension or increasing/new large pneumothorax, acute pulmonary embolism, acute cholecystitis, acute appendicitis, ectopic pregnancy, scrotal torsion, unexplained free intraperitoneal air, new or increasing intracranial hemorrhage, and malpositioned tubes and lines. The algorithms were developed using rule-based approaches and designed to search for common words and phrases in radiology reports that indicate critical results. Certain text-mining features were utilized such as wildcards, stemming, negation detection, proximity matching, and expanded searches with applicable synonyms. To further improve accuracy, the algorithms utilized modality and exam-specific queries, searched under the "Impression" field of the radiology report, and excluded reports with a low level of diagnostic certainty. Algorithm accuracy was determined using precision, recall, and F-measure using human review as the reference standard. The overall accuracy (F-measure) of the algorithms ranged from 81% to 100%, with a mean precision and recall of 96% and 91%, respectively. These algorithms can be applied to radiology report databases for quality assurance and accreditation, integrated with existing dashboards for display and monitoring, and ported to other institutions for their own use.