Hasil untuk "Nutritional diseases. Deficiency diseases"

T. Rantanen, S. Volpato, MD Luigi Ferrucci et al.

Lynn Lieberman Lawry, Jessica Korona-Bailey, Tiffany E. Hamm et al.

Abstract Background Ukraine’s Ministry of Health formally recognized rehabilitation as an essential component of universal health coverage in 2020. However, services remain fragmented and under-resourced, particularly following the full-scale invasion by the Russian Federation in February 2022. Widespread injuries due to trench warfare, drones, and large-scale ground combat have placed unprecedented strain on the Ukrainian trauma and rehabilitation systems, which continue to lack a cohesive national strategy. This study aimed to (1) assess the trauma and rehabilitation system in Ukraine during the ongoing conflict; (2) identify current needs, gaps, and opportunities for strengthening rehabilitation services; and (3) inform national and international stakeholders—including the United States and NATO—about urgent priorities to support Ukraine’s rehabilitation infrastructure, reintegration pathways, and gender-sensitive care delivery. Methods We conducted 36 qualitative key informant interviews across all NATO levels of care using an adapted Global Trauma System Evaluation Tool. Thematic analysis focused on rehabilitation-related domains. Results Respondents highlighted shortages in staff, equipment, and mental health integration. Rehabilitation remains unevenly implemented, with better access for military versus civilian patients. Care for survivors of conflict-related sexual violence and support for women’s equitable access were consistently cited gaps. Conclusions Ukraine’s growing burden of war-related injuries necessitates urgent investment in a coordinated national rehabilitation strategy. Priorities include workforce development, equipment supply, mental health integration, and inclusive care models that address the needs of women and conflict related sexual violence survivors. Evidence-based rehabilitation, supported by validated training for clinicians, is essential for long-term recovery, societal reintegration, and national resilience.

Danyang Zhang, Haitao Shi, Chongcao Wei et al.

Abstract Background Metabolic syndrome (MetS) is a conglomerate of metabolic abnormalities including hypertension, obesity, hyperglycemia, hypertriglyceridemia, and low levels of high-density lipoprotein cholesterol (HDL-C). The relationship between MetS and Inflammatory Bowel Disease (IBD) has received a lot of attention lately. Epidemiological investigation has yet to determine if the two illnesses are causally related. To investigate the causal link between IBD and MetS levels, we screened publically available genome-wide association study (GWAS) data using Mendelian randomization (MR) analysis. The study aimed to comprehensively analyze the causal association of each component of MetS, including fasting blood glucose(FBG), HDL-C, triglyceride(TG), waist circumference(WC), and hypertension, on the risk of IBD and its subtypes via univariate, two-way, and multivariate MR (MVMR) methods. Methods We selected independent genetic variants of MetS and IBD as instrumental variables (IVs) from published data from the IEU OpenGWAS project and IIBDGC (International Inflammatory Bowel Disease Genetic Consortium), used MR to infer potential causal effects between them, and used a variety of methods (random effect inverse variance weighting (IVW), weighted median, MR-Egger regression, etc.) to ensure the robustness of causal effects. Results Univariate two-sample MR (TSMR) revealed that WC was significantly linked to the risk of Crohn’s disease (CD) (OR = 1.659; 95% CI: 1.144–2.405; p = 0.008) and IBD (OR = 1.383; 95% CI: 1.050–1.822; p = 0.021). However, MVMR did not support this finding. In MVMR analysis, hypertension was predicted to be positively associated with the risk of IBD (OR = 2.322516, 95% CI: 1.097713–4.91392, p = 0.0275365), whereas FBG was confirmed to reduce the risk of CD in MVMR studies (OR = 0.4346427, 95% CI: 0.2685399–0.7034868, p = 0.0006948939). Other elements of the MetS did not significantly correlate with IBD. Conclusion Although confounding factors cannot be completely ruled out, certain metabolic components, such as WC, may impact the risk of IBD. In addition to highlighting the need for more research to understand the underlying mechanisms and potential indirect effects between MetS components and IBD, this research offers insight into therapeutic treatment decisions for patients with IBD and MetS.

Susan M Rattigan, Ibrahim Ngoumboute Mbouombouo, Mohamed Antar Abdou Tahirou et al.

Background: A novel ready-to-use microbiome-directed food (MDF) has been developed for the management of acute malnutrition using ingredients that promote repair of the gut microbiota of undernourished children. Objectives: This study aims to assess the acceptability of MDF compared with standard nutritional care among children with acute malnutrition. Methods: Two randomized crossover trials consisting of 2 14-d periods of at-home consumption were conducted. Children aged 6 to <24 mo with severe acute malnutrition (SAM) or moderate acute malnutrition (MAM) were individually randomized in a 1:1 ratio to the sequence of receiving MDF then standard nutritional care, or vice versa. Standard nutritional care consisted of ready-to-use therapeutic food for SAM and ready-to-use supplementary food for MAM. The primary outcome was at-home acceptability, defined as the return of ≥75% of sachets empty after the 14-d at-home consumption period. The primary analysis was a noninferiority analysis, in which MDF was considered noninferior if the lower bound of the 95% confidence interval (CI) of the difference in at-home acceptability comparing MDF with standard nutritional care was within −20 percentage points. Secondary outcomes included caregiver’s perception of the child’s liking, as well as caregiver willingness to use in the future and preference between the 2 foods. Results: In all, 128 children with SAM and 146 children with MAM were randomized. MDF was noninferior to standard nutritional care in terms of at-home acceptability among children with SAM (risk difference: −7.0; 95% CI lower bound: −11.6%) and among children with MAM (risk difference: −2.3%; 95% CI lower bound: −6.1%). There were no differences in caregiver willingness to use either food in future. Conclusions: MDF is acceptable for the management of acute malnutrition in children aged 6 to <24 mo in Niger and should be further tested in other populations with a high prevalence of acute malnutrition. Effectiveness of the novel food will be assessed in forthcoming trials. Trial registration number: This trial was registered at clinicaltrials.gov as NCT05551819.

Jie Song, Mengqiao He, Shumin Ren et al.

Many rare genetic diseases exhibit recognizable facial phenotypes, which are often used as diagnostic clues. However, current facial phenotype diagnostic models, which are trained on image datasets, have high accuracy but often suffer from an inability to explain their predictions, which reduces physicians' confidence in the model output.In this paper, we constructed a dataset, called FGDD, which was collected from 509 publications and contains 1147 data records, in which each data record represents a patient group and contains patient information, variation information, and facial phenotype information. To verify the availability of the dataset, we evaluated the performance of commonly used classification algorithms on the dataset and analyzed the explainability from global and local perspectives. FGDD aims to support the training of disease diagnostic models, provide explainable results, and increase physicians' confidence with solid evidence. It also allows us to explore the complex relationship between genes, diseases, and facial phenotypes, to gain a deeper understanding of the pathogenesis and clinical manifestations of rare genetic diseases.

Rani H. Singh, Marie-Hélène Bourdages, Angela Kurtz et al.

Abstract Background The autosomal recessive disorder N-acetylglutamate synthase (NAGS) deficiency is the rarest defect of the urea cycle, with an incidence of less than one in 2,000,000 live births. Hyperammonemic crises can be avoided in individuals with NAGS deficiency by the administration of carbamylglutamate (also known as carglumic acid), which activates carbamoyl phosphatase synthetase 1 (CPS1). The aim of this case series was to introduce additional cases of NAGS deficiency to the literature as well as to assess the role of nutrition management in conjunction with carbamylglutamate therapy across new and existing cases. Methods We conducted retrospective chart reviews of seven cases of NAGS deficiency in the US and Canada, focusing on presentation, diagnosis, medication management, nutrition management, and outcomes. Results Five new and two previously published cases were included. Presenting symptoms were consistent with previous reports. Diagnostic confirmation via molecular testing varied in protocol across cases, with consecutive single gene tests leading to long delays in diagnosis in some cases. All patients responded well to carbamylglutamate therapy, as indicated by normalization of plasma ammonia and citrulline, as well as urine orotic acid in patients with abnormal levels at baseline. Although protein restriction was not prescribed in any cases after carbamylglutamate initiation, two patients continued to self-restrict protein intake. One patient experienced two episodes of hyperammonemia that resulted in poor long-term outcomes. Both episodes occurred after a disruption in access to carbamylglutamate, once due to insurance prior authorization requirements and language barriers and once due to seizure activity limiting the family’s ability to administer carbamylglutamate. Conclusions Follow-up of patients with NAGS deficiency should include plans for illness and for disruption of carbamylglutamate access, including nutrition management strategies such as protein restriction. Carbamylglutamate can help patients with NAGS deficiency to liberalize their diets, but the maximum safe level of protein intake to prevent hyperammonemia is not yet known. Patients using this medication should still monitor their diet closely and be prepared for any disruptions in medication access, which might require immediate dietary adjustments or medical intervention to prevent hyperammonemia.

Minjeong Jeong, Jinhyun Kim, Dahye Han et al.

Objectives A campus-based intervention to enhance food literacy (FL) and establish exercise habits among college students was developed and the program’s effectiveness was evaluated. Methods The 13-session program was developed based on the transtheoretical model and social cognitive theory. Junior and senior students majoring in food and nutrition and physical education were asked to participate as mentors, with freshmen and sophomores from varied majors as mentees. The program encompassed food, nutrition, and exercise lessons including cooking sessions. Data were collected via pre- and post-program surveys using a questionnaire consisting of items on FL and nutrition behaviors and physical fitness measurements. Results Among 39 participants (35.9% male, 64.1% female), the overall FL score increased significantly from 64.1 to 70.6 post-program (P = 0.001). Significant increases were observed in the nutrition and safety (P < 0.001), cultural and relational (P = 0.023), and socio-ecological (P = 0.001) domains, as well as knowledge (P = 0.001), self-efficacy (P = 0.013), attitude (P < 0.001), and behavior (P = 0.005) items in three domains of FL. Additionally, meal duration increased significantly (P = 0.007) and sit-up performance among female showed a meaningful change (P = 0.046). Changes in dietary behaviors significantly progressed (P = 0.015) while that in exercise habits approached a marginal significance (P = 0.053) after the intervention. Conclusion The results reveal positive changes in FL and some modifications in eating habits, although the program had limited effects on physical activity and fitness measurements. These findings suggest that strategic approaches to foster exercise behavior changes in college students are required. This pilot program can serve as foundational data for improving and expanding multicomponent health promotion programs for this population.

Qin Pei, Yuwei Song, Zhongwei Huang et al.

Abstract Background There is insufficient research on how gender-affirming hormone therapy (GAHT) affects body fat modifications in transwomen from China. It is unclear whether hormone therapy affects the prevalence of obesity and blood lipid levels within this population. The current research aimed to assess how GAHT and treatment duration had an impact on the change in and redistribution of body fat in Chinese transwomen. Methods This study included 40 transwomen who had not received GAHT and 59 who had. Body fat, blood lipid, and blood glucose levels were measured. GAHT is mainly a pharmacologic (estrogen and anti-androgen) treatment. The study also stratified participants based on the duration of GAHT to assess its impact on body fat distribution. The duration of GAHT was within one year, one to two years, two to three years, or more than three years. Results After receiving GAHT, total body fat increased by 19.65%, and the percentage of body fat increased by 17.63%. The arm, corrected leg, and leg regions showed significant increases in fat content (+ 24.02%, + 50.69%, and + 41.47%, respectively) and percentage (+ 25.19%, + 34.90%, and + 30.39%, respectively). The total visceral fat content decreased (-37.49%). Based on the diagnostic standards for a body mass index ≥ 28 or total body fat percentage ≥ 25% or 30%, the chance of developing obesity did not change significantly. Blood glucose levels significantly increased (+ 12.31%). Total cholesterol levels (-10.45%) decreased significantly. Fat changes in those who received GAHT for one to two years were significantly different from those who did not receive GAHT. Conclusion After receiving GAHT, total body fat and regional fat increased in Chinese transwomen, and the body fat distribution changed from masculine to feminine, especially during the first two years. However, neither the increase in total body fat percentage nor the decrease in visceral fat content didn’t bring about significant changes in the incidence of obesity, nor did triglycerides or low-density lipoprotein-cholesterol.

Kimberley Szeto, John Arnold, Carol Maher

Abstract Increasing physical activity in patients offers dual benefits, fostering improved patient health and recovery, while also bolstering healthcare system efficiency by minimizing costs related to extended hospital stays, complications, and readmissions. Wearable activity trackers offer valuable opportunities to enhance physical activity across various healthcare settings and among different patient groups. However, their integration into healthcare faces multiple implementation challenges related to the devices themselves, patients, clinicians, and systemic factors. This article presents the Wearable Activity Tracker Checklist for Healthcare (WATCH), which was recently developed through an international Delphi study. The WATCH provides a comprehensive framework for implementation and evaluation of wearable activity trackers in healthcare. It covers the purpose and setting for usage; patient, provider, and support personnel roles; selection of relevant metrics; device specifications; procedural steps for issuance and maintenance; data management; timelines; necessary adaptations for specific scenarios; and essential resources (such as education and training) for effective implementation. The WATCH is designed to support the implementation of wearable activity trackers across a wide range of healthcare populations and settings, and in those with varied levels of experience. The overarching goal is to support broader, sustained, and systematic use of wearable activity trackers in healthcare, therefore fostering enhanced physical activity promotion and improved patient outcomes.

Catarina Botelho, Alberto Abad, Tanja Schultz et al.

Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients' lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines "reference speech" and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer's and Parkinson's disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.

Allen Yang, Edward Yang

According to PBS, nearly one-third of Americans lack access to primary care services, and another forty percent delay going to avoid medical costs. As a result, many diseases are left undiagnosed and untreated, even if the disease shows many physical symptoms on the skin. With the rise of AI, self-diagnosis and improved disease recognition have become more promising than ever; in spite of that, existing methods suffer from a lack of large-scale patient databases and outdated methods of study, resulting in studies being limited to only a few diseases or modalities. This study incorporates readily available and easily accessible patient information via image and text for skin disease classification on a new dataset of 26 skin disease types that includes both skin disease images (37K) and associated patient narratives. Using this dataset, baselines for various image models were established that outperform existing methods. Initially, the Resnet-50 model was only able to achieve an accuracy of 70% but, after various optimization techniques, the accuracy was improved to 80%. In addition, this study proposes a novel fine-tuning strategy for sequence classification Large Language Models (LLMs), Chain of Options, which breaks down a complex reasoning task into intermediate steps at training time instead of inference. With Chain of Options and preliminary disease recommendations from the image model, this method achieves state of the art accuracy 91% in diagnosing patient skin disease given just an image of the afflicted area as well as a patient description of the symptoms (such as itchiness or dizziness). Through this research, an earlier diagnosis of skin diseases can occur, and clinicians can work with deep learning models to give a more accurate diagnosis, improving quality of life and saving lives.

Y. Ogawa, M. Kinoshita, S. Shimada et al.

The skin is the third most zinc (Zn)-abundant tissue in the body. The skin consists of the epidermis, dermis, and subcutaneous tissue, and each fraction is composed of various types of cells. Firstly, we review the physiological functions of Zn and Zn transporters in these cells. Several human disorders accompanied with skin manifestations are caused by mutations or dysregulation in Zn transporters; acrodermatitis enteropathica (Zrt-, Irt-like protein (ZIP)4 in the intestinal epithelium and possibly epidermal basal keratinocytes), the spondylocheiro dysplastic form of Ehlers-Danlos syndrome (ZIP13 in the dermal fibroblasts), transient neonatal Zn deficiency (Zn transporter (ZnT)2 in the secretory vesicles of mammary glands), and epidermodysplasia verruciformis (ZnT1 in the epidermal keratinocytes). Additionally, acquired Zn deficiency is deeply involved in the development of some diseases related to nutritional deficiencies (acquired acrodermatitis enteropathica, necrolytic migratory erythema, pellagra, and biotin deficiency), alopecia, and delayed wound healing. Therefore, it is important to associate the existence of mutations or dysregulation in Zn transporters and Zn deficiency with skin manifestations.

Maoping Duan, Tianxu Li, Bo Liu et al.

Abstract As the second most abundant trace element in the human body, zinc nutrition is constantly a hot topic. More than one-third population is suffering zinc deficiency, which results in various types of diseases or nutritional deficiencies. Traditional ways of zinc supplementation seem with low absorption rates and significant side effects. Zinc supplements with dietary components are easily accessible and improve zinc utilization rate significantly. Also, mechanisms of maintaining zinc homeostasis are of broad interest. The present review focuses on zinc nutrition in human health in inductive methods. Mainly elaborate on different diseases relating to zinc disorder, highlighting the impact on the immune system and the recent COVID-19. Then raise food-derived zinc-binding compounds, including protein, peptide, polysaccharide, and polyphenol, and also analyze their possibilities to serve as zinc complementary. Finally, illustrate the way to maintain zinc homeostasis and the corresponding mechanisms. The review provides data information for maintaining zinc homeostasis with the food-derived matrix.

Hsin-Fu Lee, Chi Chuang, Pei-Ru Li et al.

Abstract Aims The effectiveness and limb safety of sodium glucose co-transporter 2 inhibitors (SGLT2i) for patients with type-2 diabetes (T2D) who have received peripheral artery disease (PAD) revascularization are unknown. Methods and results In this nationwide retrospective cohort study, we identified a total of 2,455 and 8,695 patients with T2D who had undergone PAD revascularization and received first prescriptions for SGLT2i and dipeptidyl peptidase-4 inhibitors (DPP4i), respectively, between May 1, 2016, and December 31, 2019. We used 1:1 propensity score matching (PSM) to balance covariates between the two study groups. Patients were followed up from the drug index date until the occurrence of specified outcomes, death, discontinuation of the index drug, or the end of the study period, whichever occurred first. After PSM, we observed that compared with DPP4i, SGLT2i were associated with comparable risks of ischemic stroke, acute myocardial infarction, and heart failure hospitalization but were associated with a lower risk of cardiac death (hazard ratio [HR]: 0.60; 95% confidence interval [CI]: 0.40–0.90]; p = 0.0126). Regarding major limb outcomes, SGLT2i were associated with comparable risks of repeated revascularization and lower limb amputation compared with DPP4i. SGLT2i were associated with a lower risk of composite renal outcomes (HR: 0.40; 95% CI: 0.27–0.59; p < 0.0001) compared with DPP4i. Conclusion In a real-world study of patients with T2D who had undergone PAD revascularization, SGLT2i were associated with lower risks of cardiac death and composite renal outcomes but not associated with increased risks of adverse limb events compared with DPP4i.

Arianna Maiorana, Francesco Tagliaferri, Carlo Dionisi-Vici

Glycogen storage type Ib (GSDIb) is a rare inborn error of metabolism caused by glucose-6-phosphate transporter (G6PT, SLC37A4) deficiency. G6PT defect results in excessive accumulation of glycogen and fat in the liver, kidney, and intestinal mucosa and into both glycogenolysis and gluconeogenesis impairment. Clinical features include hepatomegaly, hypoglycemia, lactic acidemia, hyperuricemia, hyperlipidemia, and growth retardation. Long-term complications are liver adenoma, hepatocarcinoma, nephropathy and osteoporosis. The hallmark of GSDIb is neutropenia, with impaired neutrophil function, recurrent infections and inflammatory bowel disease. Alongside classical nutritional therapy with carbohydrates supplementation and immunological therapy with granulocyte colony-stimulating factor, the emerging role of 1,5-anhydroglucitol in the pathogenesis of neutrophil dysfunction led to repurpose empagliflozin, an inhibitor of the renal glucose transporter SGLT2: the current literature of its off-label use in GSDIb patients reports beneficial effects on neutrophil dysfunction and its clinical consequences. Surprisingly, this glucose-lowering drug ameliorated the glycemic and metabolic control in GSDIb patients. Furthermore, numerous studies from big cohorts of type 2 diabetes patients showed the efficacy of empagliflozin in reducing the cardiovascular risk, the progression of kidney disease, the NAFLD and the metabolic syndrome. Beneficial effects have also been described on peripheral neuropathy in a prediabetic rat model. Increasing evidences highlight the role of empagliflozin in regulating the cellular energy sensors SIRT1/AMPK and Akt/mTOR, which leads to improvement of mitochondrial structure and function, stimulation of autophagy, decrease of oxidative stress and suppression of inflammation. Modulation of these pathways shift the oxidative metabolism from carbohydrates to lipids oxidation and results crucial in reducing insulin levels, insulin resistance, glucotoxicity and lipotoxicity. For its pleiotropic effects, empagliflozin appears to be a good candidate for drug repurposing also in other metabolic diseases presenting with hypoglycemia, organ damage, mitochondrial dysfunction and defective autophagy.

Saurav Sagar, Mohammed Javed, David S Doermann

The agricultural sector plays an essential role in the economic growth of a country. Specifically, in an Indian context, it is the critical source of livelihood for millions of people living in rural areas. Plant Disease is one of the significant factors affecting the agricultural sector. Plants get infected with diseases for various reasons, including synthetic fertilizers, archaic practices, environmental conditions, etc., which impact the farm yield and subsequently hinder the economy. To address this issue, researchers have explored many applications based on AI and Machine Learning techniques to detect plant diseases. This research survey provides a comprehensive understanding of common plant leaf diseases, evaluates traditional and deep learning techniques for disease detection, and summarizes available datasets. It also explores Explainable AI (XAI) to enhance the interpretability of deep learning models' decisions for end-users. By consolidating this knowledge, the survey offers valuable insights to researchers, practitioners, and stakeholders in the agricultural sector, fostering the development of efficient and transparent solutions for combating plant diseases and promoting sustainable agricultural practices.

Wentao Zhang, Yujun Huang, Tong Zhang et al.

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. To address the catastrophic forgetting issue, an Adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases at each round (or task) of continual learning, without changing the shared feature extractor. The learnable lightweight task-specific adapter(s) can be flexibly designed (e.g., two convolutional layers) and then added to the pretrained and fixed feature extractor. Together with a specially designed task-specific head which absorbs all previously learned old diseases as a single "out-of-distribution" category, task-specific adapter(s) can help the pretrained feature extractor more effectively extract discriminative features between diseases. In addition, a simple yet effective fine-tuning is applied to collaboratively fine-tune multiple task-specific heads such that outputs from different heads are comparable and consequently the appropriate classifier head can be more accurately selected during model inference. Extensive empirical evaluations on three image datasets demonstrate the superior performance of ACL in continual learning of new diseases. The source code is available at https://github.com/GiantJun/CL_Pytorch.

Achyut Tiwari, Aryan Chugh, Aman Sharma

Heart disease is the major cause of non-communicable and silent death worldwide. Heart diseases or cardiovascular diseases are classified into four types: coronary heart disease, heart failure, congenital heart disease, and cardiomyopathy. It is vital to diagnose heart disease early and accurately in order to avoid further injury and save patients' lives. As a result, we need a system that can predict cardiovascular disease before it becomes a critical situation. Machine learning has piqued the interest of researchers in the field of medical sciences. For heart disease prediction, researchers implement a variety of machine learning methods and approaches. In this work, to the best of our knowledge, we have used the dataset from IEEE Data Port which is one of the online available largest datasets for cardiovascular diseases individuals. The dataset isa combination of Hungarian, Cleveland, Long Beach VA, Switzerland & Statlog datasets with important features such as Maximum Heart Rate Achieved, Serum Cholesterol, Chest Pain Type, Fasting blood sugar, and so on. To assess the efficacy and strength of the developed model, several performance measures are used, such as ROC, AUC curve, specificity, F1-score, sensitivity, MCC, and accuracy. In this study, we have proposed a framework with a stacked ensemble classifier using several machine learning algorithms including ExtraTrees Classifier, Random Forest, XGBoost, and so on. Our proposed framework attained an accuracy of 92.34% which is higher than the existing literature.

Jihen Amara, Birgitta König-Ries, Sheeba Samuel

Plant diseases remain a considerable threat to food security and agricultural sustainability. Rapid and early identification of these diseases has become a significant concern motivating several studies to rely on the increasing global digitalization and the recent advances in computer vision based on deep learning. In fact, plant disease classification based on deep convolutional neural networks has shown impressive performance. However, these methods have yet to be adopted globally due to concerns regarding their robustness, transparency, and the lack of explainability compared with their human experts counterparts. Methods such as saliency-based approaches associating the network output to perturbations of the input pixels have been proposed to give insights into these algorithms. Still, they are not easily comprehensible and not intuitive for human users and are threatened by bias. In this work, we deploy a method called Testing with Concept Activation Vectors (TCAV) that shifts the focus from pixels to user-defined concepts. To the best of our knowledge, our paper is the first to employ this method in the field of plant disease classification. Important concepts such as color, texture and disease related concepts were analyzed. The results suggest that concept-based explanation methods can significantly benefit automated plant disease identification.

S. Baldermann, L. Blagojevic, Katja Frede et al.

ABSTRACT Malnutrition, poor health, hunger, and even starvation are still the world's greatest challenges. Malnutrition is defined as deficiency of nutrition due to not ingesting the proper amounts of nutrients by simply not eating enough food and/or by consuming nutrient-poor food in respect to the daily nutritional requirements. Moreover, malnutrition and disease are closely associated and incidences of such diet-related diseases increase particularly in low- and middle-income states. While foods of animal origin are often unaffordable to low-income families, various neglected crops can offer an alternative source of micronutrients, vitamins, as well as health-promoting secondary plant metabolites. Therefore, agricultural and horticultural research should develop strategies not only to produce more food, but also to improve access to more nutritious food. In this context, one promising approach is to promote biodiversity in the dietary pattern of low-income people by getting access to nutritional as well as affordable food and providing recommendations for food selection and preparation. Worldwide, a multitude of various plant species are assigned to be consumed as grains, vegetables, and fruits, but only a limited number of these species are used as commercial cash crops. Consequently, numerous neglected and underutilized species offer the potential to diversify not only the human diet, but also increase food production levels, and, thus, enable more sustainable and resilient agro- and horti-food systems. To exploit the potential of neglected plant (NP) species, coordinated approaches on the local, regional, and international level have to be integrated that consequently demand the involvement of numerous multi-stakeholders. Thus, the objective of the present review is to evaluate whether NP species are important as “Future Food” for improving the nutritional status of humans as well as increasing resilience of agro- and horti-food systems.