Learning from errors: Implementation of a resident-oriented radiology morbidity and mortality conference as an educational tool.

PURPOSE: Our diagnostic radiology (DR) program lacked a formalized, structured process for residents to learn from errors. Prior DR residency Accreditation Council for Graduate Medical Education (ACGME) survey results additionally demonstrated opportunity for improvement in resident evaluation, resources, and patient safety/teamwork. Our project's purpose was to implement and evaluate a new resident-oriented radiology morbidity and mortality (M&M) conference to enhance resident education. METHODS: All DR residents (n = 48) were surveyed regarding a new didactic M&M consisting of quarterly resident-led and faculty-moderated M&Ms. Cases for potential review were collected and stored in a REDCap database via an anonymous survey, from which resident-selected faculty curators would select 4-6 for presentation. Residents presented these cases and the group discussed applicable improvements. An anonymous survey of residents followed each conference. Relevant questions from ACGME survey data were extracted from the two years preceding the didactic M&M and the pilot year. RESULTS: Before implementation, 86% of responding residents (n = 29; 60% of resident complement) supported the program, 90% expressed willingness to share their own mistakes, and 79% preferred faculty involvement. Respondents favored careful selection of faculty to promote education. At one year, 100% of respondents (n = 17; 35% of resident complement) approved of adding the didactic M&M and endorsed program continuance. All respondents expressed a willingness to share their own mistakes. There was also coincident improvement in ACGME survey data in the domains of evaluation, resources, and patient safety/teamwork. CONCLUSION: We designed and implemented a resident-oriented M&M conference that resulted in increased resident confidence and impacted ACGME survey results in evaluation, resources, and patient safety/teamwork. PRECIS: Implementation of a structured, resident-oriented radiology M&M conference can increase resident confidence and impact ACGME survey results in the domains of evaluation, resources, and patient safety/teamwork.

Management of Incidental Thyroid Nodules on Chest CT: Using Natural Language Processing to Assess White Paper Adherence and Track Patient Outcomes.

OBJECTIVE: The purpose of this study was to develop a natural language processing (NLP) pipeline to identify incidental thyroid nodules (ITNs) meeting criteria for sonographic follow-up and to assess both adherence rates to white paper recommendations and downstream outcomes related to these incidental findings. METHODS: 21583 non-contrast chest CT reports from 2017 and 2018 were retrospectively evaluated to identify reports which included either an explicit recommendation for thyroid ultrasound, a description of a nodule ≥ 1.5 cm, or description of a nodule with suspicious features. Reports from 2018 were used to train an NLP algorithm called fastText for automated identification of such reports. Algorithm performance was then evaluated on the 2017 reports. Next, any patient from 2017 with a report meeting criteria for ultrasound follow-up was further evaluated with manual chart review to determine follow-up adherence rates and nodule-related outcomes. RESULTS: NLP identified reports with ITNs meeting criteria for sonographic follow-up with an accuracy of 96.5% (95% CI 96.2-96.7) and sensitivity of 92.1% (95% CI 89.8-94.3). In 10006 chest CTs from 2017, ITN follow-up ultrasound was indicated according to white paper criteria in 81 patients (0.8%), explicitly recommended in 46.9% (38/81) of patients, and obtained in less than half of patients in which it was appropriately recommended (17/35, 48.6%). DISCUSSION: NLP accurately identified chest CT reports meeting criteria for ITN ultrasound follow-up. Radiologist adherence to white paper guidelines and subsequent referrer adherence to radiologist recommendations showed room for improvement.