Natural Language Processing to Estimate Clinical Competency Committee Ratings.

OBJECTIVE: Residency program faculty participate in clinical competency committee (CCC) meetings, which are designed to evaluate residents' performance and aid in the development of individualized learning plans. In preparation for the CCC meetings, faculty members synthesize performance information from a variety of sources. Natural language processing (NLP), a form of artificial intelligence, might facilitate these complex holistic reviews. However, there is little research involving the application of this technology to resident performance assessments. With this study, we examine whether NLP can be used to estimate CCC ratings. DESIGN: We analyzed end-of-rotation assessments and CCC assessments for all surgical residents who trained at one institution between 2014 and 2018. We created models of end-of-rotation assessment ratings and text to predict dichotomized CCC assessment ratings for 16 Accreditation Council for Graduate Medical Education (ACGME) Milestones. We compared the performance of models with and without predictors derived from NLP of end-of-rotation assessment text. RESULTS: We analyzed 594 end-of-rotation assessments and 97 CCC assessments for 24 general surgery residents. The mean (standard deviation) for area under the receiver operating characteristic curve (AUC) was 0.84 (0.05) for models with only non-NLP predictors, 0.83 (0.06) for models with only NLP predictors, and 0.87 (0.05) for models with both NLP and non-NLP predictors. CONCLUSIONS: NLP can identify language correlated with specific ACGME Milestone ratings. In preparation for CCC meetings, faculty could use information automatically extracted from text to focus attention on residents who might benefit from additional support and guide the development of educational interventions.

Reoperative lymph node dissection for recurrent papillary thyroid cancer and effect on serum thyroglobulin.

BACKGROUND: Papillary thyroid cancer (PTC) has an excellent prognosis with current treatment methods. However, the rates of locoregional recurrence after initial surgical management remain significant. This study evaluates the effect of reoperative neck dissection for locoregional recurrence of PTC after initial total thyroidectomy and radioiodine therapy on the incidence of cervical recurrence and postoperative serum thyroglobulin (Tg) levels. METHODS: This is a retrospective cohort study conducted in a single academic medical center of patients with recurrent or persistent PTC isolated to the neck after previous total thyroidectomy with or without lymph node dissection and adjuvant I(131) therapy who were treated with reoperative lymph node dissection. Outcomes including operative complications, pathologic findings, and effect of surgery on Tg levels and rates of recurrent disease were analyzed. RESULTS: From 2001 to 2010, a total of 61 patients had reoperative neck dissections for recurrent cervical PTC with a complication rate of 5 %. Seventy-two percent of patients were clinically free of detectable disease, and 28 % of patients had recurrent, persistent, or newly metastatic disease detected during the follow-up period. All patients had significant decreases in Tg levels, with a median 98 % reduction in preoperative levels. However, only 21 % of patients had an undetectable stimulated Tg (<0.5 ng/mL) during the follow-up period of 15.5 months. CONCLUSIONS: Reoperative treatment of recurrent or persistent PTC can be performed with low complication rates, and Tg levels greatly decrease in most patients; however, few achieve undetectable stimulated Tg.

The role of radiologic studies in the evaluation and management of primary hyperaldosteronism.

BACKGROUND: Surgical treatment of primary hyperaldosteronism (PHA) requires demonstration of unilateral adrenal hypersecretion. Optimal methods for interpretation of imaging and invasive testing are still in development. METHODS: A retrospective review from 1996-2007 of 106 patients with PHA was undertaken. Patient demographics, biochemical studies, radiologic imaging, operative reports, and pathology were reviewed and comparisons made. Optimal ratios for adrenal vein sampling were tested with regard to sensitivity and specificity. Preoperative and postoperative medication requirements and blood pressures were compared among different treatment groups. RESULTS: Seventy-eight patients (62 surgically treated) met criteria for inclusion. Median arterial blood pressure at diagnosis was 150/86 mm Hg while taking 3 antihypertensive medications. 69.2% required potassium supplementation. Median aldosterone:renin ratio was 107.0. Forty-two AVS procedures changed the management of 15 patients (35.7%) when compared to CT results. AVS accuracy was 96.6 vs 88.9% for NP-59 scintigraphy. Operative patients remained on fewer antihypertensive medications (1 vs 3), and mean systolic pressure was lower (130 vs 146 mm Hg) compared with medically managed patients. CONCLUSION: When used together, pre-ACTH aldosterone ratios, normalized A/C:A/C ratios, ratios to define contralateral suppression, and post-ACTH stimulated values allowed for capture of episodically secreting tumors and subtle unilateral or bilateral hyperaldosteronism.