The evaluation and management of macronutrient deficiency dermatoses.

In industrialized countries, nutritional dermatoses are likely underdiagnosed and result in increased disease morbidity and utilization of hospital resources. These findings underscore the need for physicians to be able to correctly identify these deficiencies. Nutritional dermatoses may be split into micronutrient deficiencies and macronutrient deficiencies. This article is intended to serve as a supplement to a 2-part review of micronutrient deficiency dermatoses and highlights cutaneous findings in patients with protein-energy malnutrition and essential fatty acid deficiency. This article reviews the evaluation, cutaneous manifestations, and management of macronutrient deficiencies.

The epidemiology, impact, and diagnosis of micronutrient nutritional dermatoses part 1: Zinc, selenium, copper, vitamin A, and vitamin C.

Dermatologists play a critical role in diagnosing and managing nutritional deficiencies as they often present with cutaneous findings. Traditionally, nutritional dermatoses are taught in the context of developing countries, famine, population displacement, and poor health care access; however, in the United States, common risk factors include chronic liver disease, alcoholism, psychiatric disease, bariatric surgery, inflammatory bowel disease, and hemodialysis. Additionally, nutritional dermatoses may be underdiagnosed in the United States and result in increased morbidity and utilization of hospital resources. There is a need for providers in developed nations to identify these deficiencies, and this review aims to meet that practice gap and provide relevant context to these diseases for dermatologists. This 2-part review series will focus on the epidemiology, impact, appearance, and diagnostic modalities for micronutrient deficiencies, including zinc, selenium, copper, and vitamins A and C in part 1. The companion review will focus on the B-complex vitamins.

High performance in risk stratification of intraductal papillary mucinous neoplasms by confocal laser endomicroscopy image analysis with convolutional neural networks (with video).

BACKGROUND AND AIMS: EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs. METHODS: A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines. RESULTS: Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs. CONCLUSION: EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation.

Predictors of Pancreatic Cancer-Associated Weight Loss and Nutritional Interventions.

OBJECTIVES: Pancreatic ductal adenocarcinoma (PDAC) is often accompanied by weight loss. We sought to characterize factors associated with weight loss and observed nutritional interventions, as well as define the effect of weight loss on survival. METHODS: Consecutive subjects diagnosed with PDAC (N = 123) were retrospectively evaluated. Univariate analysis was used to compare subjects with and without substantial (>5%) weight loss. Multivariate logistic regression was performed to identify factors associated with weight loss, and survival analyses were performed using Kaplan-Meier curves and Cox survival models. RESULTS: Substantial weight loss at diagnosis was present in 71.5% of subjects and was independently associated with higher baseline body mass index, longer symptom duration, and increased tumor size. Recommendations for nutrition consultation and pancreatic enzyme replacement therapy occurred in 27.6% and 36.9% of subjects, respectively. Weight loss (>5%) was not associated with worse survival on multivariate analysis (hazard ratio, 1.32; 95% confidence interval, 0.76-2.30), unless a higher threshold (>10%) was used (hazard ratio, 1.77; 95% confidence interval, 1.09-2.87). CONCLUSIONS: Despite the high prevalence of weight loss at PDAC diagnosis, there are low observed rates of nutritional interventions. Weight loss based on current criteria for cancer cachexia is not associated with poor survival in PDAC.