Controversial Trials First: Identifying Disagreement Between Clinical Guidelines and New Evidence.

Clinical guidelines integrate latest evidence to support clinical decision-making. As new research findings are published at an increasing rate, it would be helpful to detect when such results disagree with current guideline recommendations. In this work, we describe a software system for the automatic identification of disagreement between clinical guidelines and published research. A critical feature of the system is the extraction and cross-lingual normalization of information through natural language processing. The initial version focuses on the detection of cancer treatments in clinical trial reports that are not addressed in oncology guidelines. We evaluate the relevance of trials retrieved by our system retrospectively by comparison with historic guideline updates and also prospectively through manual evaluation by guideline experts. The system improves precision over state-of-the-art literature research strategies while maintaining near-total recall. Detailed error analysis highlights challenges for fine-grained clinical information extraction, in particular when extracting population definitions for tumor-agnostic therapies.

Distinct Clinicopathological and Prognostic Features of Thin Nodular Primary Melanomas: An International Study from 17 Centers.

BACKGROUND: Nodular melanoma (NM) is more likely to be fatal compared with other melanoma subtypes, an effect attributed to its greater Breslow thickness. METHODS: Clinicopathological features of NM and superficial spreading melanoma (SSM) diagnosed in 17 centers in Europe (n = 15), the United States, and Australia between 2006 and 2015, were analyzed by multivariable logistic regression analysis, with emphasis on thin (T1 ≤ 1.0 mm) melanomas. Cox analysis assessed melanoma-specific survival. All statistical tests were two sided. RESULTS: In all, 20 132 melanomas (NM: 5062, SSM: 15 070) were included. Compared with T1 SSM, T1 NM was less likely to have regression (odds ratio [OR] = 0.46, 95% confidence interval [CI] = 0.29 to 0.72) or nevus remnants histologically (OR = 0.60, 95% CI = 0.42 to 0.85), and more likely to have mitoses (OR = 1.97, 95% CI = 1.33 to 2.93) and regional metastasis (OR = 1.77, 95% CI = 1.02 to 3.05). T1 NM had a higher mitotic rate than T1 SSM (adjusted geometric mean = 2.2, 95% CI = 1.9 to 2.5 vs 1.6, 95% CI = 1.5 to 1.7 per mm2, P < .001). Cox multivariable analysis showed a higher risk for melanoma-specific death for NM compared with SSM for T1 (HR = 2.10, 95% CI = 1.24 to 3.56) and T2 melanomas (HR = 1.30, 95% CI = 1.01 to 1.68), and after accounting for center heterogeneity, the difference was statistically significant only for T1 (HR = 2.20, 95% CI = 1.28 to 3.78). The NM subtype did not confer increased risk within each stratum (among localized tumors or cases with regional metastasis). CONCLUSIONS: T1 NM (compared with T1 SSM) was associated with a constellation of aggressive characteristics that may confer a worse prognosis. Our results indicate NM is a high-risk melanoma subtype that should be considered for inclusion in future prognostic classifications of melanoma.