Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon

In precision agriculture, the nitrogen level is significantly important for establishing phenotype, quality and yield of crops. It cannot be achieved in the future without appropriate nitrogen fertilizer application. Moreover, a convenient and real-time advance technology for nitrogen nutrition diagnosis of crops is a prerequisite for an efficient and reasonable nitrogen-fertilizer management system. With the development of research on plant phenotype and artificial intelligence technology in agriculture, deep learning has demonstrated a great potential in agriculture for recognizing nondestructive nitrogen nutrition diagnosis in plants by automation and high throughput at a low cost. To build a nitrogen nutrient-diagnosis model, muskmelons were cultivated under different nitrogen levels in a greenhouse. The digital images of canopy leaves and the environmental factors (light and temperature) during the growth period of muskmelons were tracked and analyzed. The nitrogen concentrations of the plants were measured, we successfully constructed and trained machine-learning- and deep-learning models based on the traditional backpropagation neural network (BPNN), the emerging convolution neural network (CNN), the deep convolution neural network (DCNN) and the long short-term memory (LSTM) for the nitrogen nutrition diagnosis of muskmelon. The adjusted determination coefficient (R2) and mean square error (MSE) between the predicted values and measured values of nitrogen concentration were adopted to evaluate the models’ accuracy. The values were R2 = 0.567 and MSE = 0.429 for BPNN model; R2 = 0.376 and MSE = 0.628 for CNN model; R2 = 0.686 and MSE = 0.355 for deep convolution neural network (DCNN) model; and R2 = 0.904 and MSE = 0.123 for the hybrid model DCNN–LSTM. Therefore, DCNN–LSTM shows the highest accuracy in predicting the nitrogen content of muskmelon. Our findings highlight a base for achieving a convenient, precise and intelligent diagnosis of nitrogen nutrition in muskmelon.

Consenso sobre a terminologia padronizada do processo de cuidado em nutrição para pacientes adultos com doença renal crônica

This consensus represents the first collaboration between three professional organizations focused on nutrition: Brazilian Association of Nutrition (ASBRAN), Brazilian Society of Nephrology (SBN) and Brazilian Society of Parenteral and Enteral Nutrition (Braspen/SBNPE), with the objective of identifying internationally standardized terminology and instruments for the nutrition care process. The focus is to facilitate the training of nutritionists who work with adult patients with chronic kidney diseases (CKD). Eleven issues related to nutrition screening, care and management of outcomes were raised. Recommendations were based on international guidelines and electronic databases such as PubMed, EMBASE™, CINHAL, Web of Science and Cochrane. From the sending of lists of internationally standardized terms, 20 nutrition specialists selected those they considered very clear and relevant for clinical practice with CKD outpatients. The content validity index (CVI) was calculated, with 80% agreement in the responses. The Grading of Recommendations, Assessment, Development and Evaluation (GRADE) was used to assign evidence strength to the recommendations. A total of 107 terms were selected for Nutrition Assessment and Reassessment, 28 for Nutrition Diagnosis, 9 for Nutrition Intervention, and 94 for Nutrition Monitoring and Evaluation in Nutrition. The list of selected terms and identification of instruments will assist in training planning and implementation of standardized nutrition terminology in Brazil for nutritionists working with CKD patients.

Current approaches to diet diagnostics and diet therapy in infants with functional gastrointestinal disorders

The incidence of functional gastrointestinal disorders (FGIDs) in infants is very high. They are not only a medical challenge, but also a social problem. The causes of FGIDs are still being discussed by researchers. Particular attention is paid to impairments in functioning of the brain-intestine axis, formation of the intestinal microbiota, as well as psychological factors. FGID is a diagnosis of exclusion; however, no clear criteria for this diagnosis have been developed so far. If a baby has regurgitation, colic and/or constipation, an active search and differential diagnosis with various diseases manifesting themselves with such symptoms are necessary. Nutrition diagnosis is an important step in the diagnosis of FGIDs, which allows timely identification or exclusion of this pathology. In this study, we have demonstrated high efficacy of Comfort baby formulas, adapted fermented milk formulas, and antireflux formulas in artificial feeding of infants with FGIDs. Key words: functional gastrointestinal disorders, regurgitation, colic, constipation, infants, diet therapy, Comfort formulas, functional components

Simulation in Learning and Using the Nutrition Care Process/Terminology: Experiences and Perceptions of Dietitians in Canada

Purpose: To investigate experiences with, and perceptions of, simulation in learning and using the Nutrition Care Process/Terminology (NCP/T) of dietitians in Canada. Methods: In February–March 2017, a convenience sample of 382 dietitians in Canada (71.8% in clinical practice) completed an online survey regarding the type(s), setting(s), and perceptions of the simulations in which they engaged in learning and using the NCP/T. Results: A majority (76.7%) of respondents had engaged in NCP/T-related simulation, most commonly case studies (85.3%) and role-play (42.0%), as part of workplace/volunteer training (51.4%) and undergraduate internship/stage/practicum (34.2%). Nearly half (49.5%) of respondents learned all 4 NCP components via simulation, with Nutrition Diagnosis being the most common individual component (57%). Over three-quarters of respondents agreed/strongly agreed that simulation helped them better understand/use the NCP/T and that NCP/T-related knowledge/skills gained through simulation are transferable to the clinical setting/dietetic practice. Conclusions: Dietitians in Canada perceive simulation to have helped them learn and use the NCP/T. Resources should be directed at further developing simulation for teaching the NCP/T in dietetics education and training. Research investigating characteristics, barriers, and facilitators of effective NCP/T-simulation, using objective (vs. perceived) learning outcome measures is needed.

Sports Nutritionists Adopt the Nutrition Care Process (NCP) Road Map to Develop Individualized Meal Planning for Athletes.

Background: It is considered that the implementation of nutrition care process (NCP) leads to more efficient and effective care, as well as enhancing the roles of dietetics and nutrition professionals in the clinical setting. However, little is known about the NCP being implemented in the sports nutrition setting to deliver nutrition care, especially in meal planning. Therefore, this study aims to identify the process that sports nutritionists (SNs) practise in meal planning to plan meals for athletes and identify the application of NCP.Methods: In-depth interviews, using semi-structured interview questions, were conducted with SNs employed at the National Sports Institute of Malaysia. Five SNs who managed different types of sports were recruited. The interviews were audio-recorded and transcribed verbatim. Data were entered into ATLAS.ti 8 and analyzed using thematic analysis.Results: The following processes were identified: (i) collecting pertinent data; (ii) analyzing the collected data; (iii) determining nutrition prescriptions; (iv) formulating goals and determining actions; (v) implementing actions and recommendations; and (vi) monitoring.Conclusions: This study identified 6 general processes practiced by sports nutritionists in meal planning that comprised of the NCP’s interrelated steps, except nutrition diagnosis statement from the Nutrition Diagnosis step of the NCP. A comprehensive process and workflow can help sports dietitians or nutritionists to develop individualized meal plans that can improve athletes’ nutritional status, adherence, health and sports performance.