Creating a Comprehensive Customer Service Program to Help Convey Critical and Acute Results of Radiology Studies

Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., ML 5031, Cincinnati, OH 45229, USA.
American Journal of Roentgenology (Impact Factor: 2.73). 01/2011; 196(1):W48-51. DOI: 10.2214/AJR.10.4240
Source: PubMed


Communication of acute or critical results between the radiology department and referring clinicians has been a deficiency of many radiology departments. The failure to perform or document these communications can lead to poor patient care, patient safety issues, medical-legal issues, and complaints from referring clinicians. To mitigate these factors, a communication and documentation tool was created and incorporated into our departmental customer service program. This article will describe the implementation of a comprehensive customer service program in a hospital-based radiology department.
A comprehensive customer service program was created in the radiology department. Customer service representatives were hired to answer the telephone calls to the radiology reading rooms and to help convey radiology results. The radiologists, referring clinicians, and customer service representatives were then linked via a novel workflow management system. This workflow management system provided tools to help facilitate the communication needs of each group. The number of studies with results conveyed was recorded from the implementation of the workflow management system.
Between the implementation of the workflow management system on August 1, 2005, and June 1, 2009, 116,844 radiology results were conveyed to the referring clinicians and documented in the system. This accounts for more than 14% of the 828,516 radiology cases performed in this time frame.
We have been successful in creating a comprehensive customer service program to convey and document communication of radiology results. This program has been widely used by the ordering clinicians as well as radiologists since its inception.

20 Reads
  • Source
    • "Despite the imperative of good communication to avoid medical errors, it does not always occur. Inadequate communication of critical results is the cause of the majority of malpractice cases involving radiologists in the USA [9]. The Joint Commission reported that up to 70% of sentinel medical errors were caused by communication errors [10]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. The absence of an automated system to identify and track radiology recommendations is an important barrier to ensuring timely follow-up of patients especially with non-acute incidental findings on imaging examinations. In this paper, we present a text processing pipeline to automatically identify clinically important recommendation sentences in radiology reports. Our extraction pipeline is based on natural language processing (NLP) and supervised text classification methods. To develop and test the pipeline, we created a corpus of 800 radiology reports double annotated for recommendation sentences by a radiologist and an internist. We ran several experiments to measure the impact of different feature types and the data imbalance between positive and negative recommendation sentences. Our fully statistical approach achieved the best f-score 0.758 in identifying the critical recommendation sentences in radiology reports.
    Journal of Biomedical Informatics 01/2013; 46(2). DOI:10.1016/j.jbi.2012.12.005 · 2.19 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. When recommendations are not systematically identified and promptly communicated to referrers, poor patient outcomes can result. Using information technology can improve communication and improve patient safety. In this paper, we describe a text processing approach that uses natural language processing (NLP) and supervised text classification methods to automatically identify critical recommendation sentences in radiology reports. To increase the classification performance we enhanced the simple unigram token representation approach with lexical, semantic, knowledge-base, and structural features. We tested different combinations of those features with the Maximum Entropy (MaxEnt) classification algorithm. Classifiers were trained and tested with a gold standard corpus annotated by a domain expert. We applied 5-fold cross validation and our best performing classifier achieved 95.60% precision, 79.82% recall, 87.0% F-score, and 99.59% classification accuracy in identifying the critical recommendation sentences in radiology reports.
    AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 01/2011; 2011:1593-602.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Background and purpose: The Joint Commission has identified timely reporting of critical results as one of the National Patient Safety Goals. We surveyed directors of neuroradiology fellowships to assess and compare critical findings lists across programs. Materials and methods: A 3-question survey was e-mailed to directors of neuroradiology fellowships with the following questions: 1) Do you currently have a "critical findings" list that you abide by in your neuroradiology division? 2) How is that list distributed to your residents and fellows for implementation, if at all? and 3) Was this list vetted by neurology, neurosurgery, and otolaryngology departments? Programs with CF lists were asked for a copy of the list. Summary and comparative statistics were calculated. Results: Fifty-one of 89 (57.3%) programs responded. Twenty-one of 51 (41.2%) programs had CF lists. Lists were distributed during orientation, sent via Web sites and e-mails, and posted in work areas. Eleven of 21 lists were developed internally, and 5 of 21, with the input from other departments. The origin of 5 of 21 lists was unknown. Forty CF entities were seen in 20 submitted lists (mean, 9.1; range, 2-23). The most frequent entities were the following: cerebral hemorrhage (18 of 20 lists), acute stroke (15 of 20), spinal cord compression (15 of 20), brain herniation (12 of 20), and spinal fracture/instability (12 of 20). Programs with no CF lists called clinicians on the basis of "common sense" and "clinical judgment." Conclusions: Less than a half (41.2%) of directors of neuroradiology fellowships that responded have implemented CF lists. CF lists have variable length and content and are predominantly developed by radiology departments without external input.
    American Journal of Neuroradiology 10/2012; 34(4). DOI:10.3174/ajnr.A3300 · 3.59 Impact Factor
Show more

Similar Publications