Patricia Silveira MD, Presenter: Nothing to Disclose

Ruth M. Dunne MBBCh, Abstract Co-Author: Nothing to Disclose

Nisha Sainani MD, Abstract Co-Author: Nothing to Disclose

Stuart G. Silverman MD, Abstract Co-Author: Author, Wolters Kluwer nv

Clare M. C. Tempany-Afdhal MD, Abstract Co-Author: Research Grant, InSightec Ltd Research Consultant, Profound Medical Inc

Ramin Khorasani MD, Abstract Co-Author: Consultant, Medicalis Corp

Ronilda Lacson MD, PhD, Abstract Co-Author: Nothing to Disclose

Assess the impact of implementing a structured design and a computer-aided diagnosis (CAD) tool on the quality of prostate multiparametric MRI (mp-MRI) reports.

Institutional review board approval was obtained for this HIPAA-compliant pre-/post-interventional study performed at a 793-bed, quaternary care, academic medical center. We randomly sampled prostate mp-MRI reports finalized between August 1, 2012 and July 31, 2013. An intervention consisting of a structured design and a CAD tool integrated into PACS workstations was implemented on February 1, 2013; and was accompanied by a 1-hour targeted instructional program for radiology faculty and trainees. Primary outcome measure was quality of prostate mp-MRI reports, classified as sub-standard, standard and optimal quality using report quality metrics derived by institutional abdominal radiologists’ consensus. Following manual report review, chi-square or Student t-tests were used to compare report quality six months pre- and post-intervention. Logistic regression analysis was performed to control for confounders and determine factors associated with standard quality reports.

A total 312 prostate mp-MRI reports were analyzed. Post-intervention, optimal quality reports and standard reports increased significantly from 0/156 [0%] to 21/156 [13.5%] (p<0.001), and from 47/156 [30.1%] to 89/156 [57.1%] (p<0.001), respectively. When controlling for confounding factors, use of either structured design or CAD increased the likelihood of a standard quality report (OR=2.8; p=0.011 and OR=3.4; p=0.002, respectively).

Implementing a structured design and a CAD tool significantly improved the quality of prostate mp-MRI reports, but documentation of quality metrics on prostate mp-MRI reports still needs additional improvement. Potential next steps are automated monitoring of report content through the use of natural language processing tools, feedback to radiologists using quality dashboards, education targeting quality metrics awareness, financial incentives for adherence, and mandatory use of the new technologies.

Documentation of quality metrics might improve referring physicians’ management decision-making process and, therefore, patient care.

Silveira, P, Dunne, R, Sainani, N, Silverman, S, Tempany-Afdhal, C, Khorasani, R, Lacson, R, The Impact of a Structured Design and a Computer-aided Diagnosis Tool on the Quality of Prostate Multiparametric MRI Reports.  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14011211.html