Background: Nuts are nutrient-dense foods that contribute to healthier eating. Food image datasets enable artificial intelligence (AI) powered diet-tracking apps to help people monitor daily eating patterns. Aim: This study aimed to create an image dataset of commonly consumed nut types and use it to build an AI computer vision model to automate nut type classification tasks. Methods: iPhone 11 was used to take photos of 11 nut types—almond, brazil nut, cashew, chestnut, hazelnut, macadamia, peanut, pecan, pine nut, pistachio, and walnut. The dataset contains 2200 images, 200 per nut type. The dataset was randomly split into the training (60% or 1320 images), validation (20% or 440 images), and test sets (20% or 440 images). A neural network model was constructed and trained using transfer learning and other computer vision techniques—data augmentation, mixup, normalization, label smoothing, and learning rate optimization. Results: The trained neural network model correctly predicted 338 out of 440 images (40 per nut type) in the validation set, achieving 99.55% accuracy. Moreover, the model classified the 440 images in the test set with 100% accuracy. Conclusion: This study built a nut image dataset and used it to train a neural network model to classify images by nut type. The model achieved near-perfect accuracy on the validation and test sets, demonstrating the feasibility of automating nut type classification using smartphone photos. Being made open-source, the dataset and model can assist the development of diet-tracking apps that facilitate users’ adoption and adherence to a healthy diet.

Nuts are nutrient-dense foods and can be incorporated into a healthy diet. Artificial intelligence-powered diet-tracking apps may promote nut consumption by providing real-time, accurate nutrition information but depend on data and model availability. Our team developed a dataset comprising 1380 photographs, each in RGB color format and with a resolution of 4032 × 3024 pixels. These images feature 11 types of nuts that are commonly consumed. Each photo includes three nut types; each type consists of 2–4 nuts, so 6–9 nuts are in each image. Rectangular bounding boxes were drawn using a visual geometry group (VGG) image annotator to facilitate the identification of each nut, delineating their locations within the images. This approach renders the dataset an excellent resource for training models capable of multi-label classification and object detection, as it was meticulously divided into training, validation, and test subsets. Utilizing transfer learning in Python with the IceVision framework, deep neural network models were adeptly trained to recognize and pinpoint the nuts depicted in the photographs. The ultimate model exhibited a mean average precision of 0.7596 in identifying various nut types within the validation subset and demonstrated a 97.9% accuracy rate in determining the number and kinds of nuts present in the test subset. By integrating specific nutritional data for each type of nut, the model can precisely (with error margins ranging from 0.8 to 2.6%) calculate the combined nutritional content—encompassing total energy, proteins, carbohydrates, fats (total and saturated), fiber, vitamin E, and essential minerals like magnesium, phosphorus, copper, manganese, and selenium—of the nuts shown in a photograph. Both the dataset and the model have been made publicly available to foster data exchange and the spread of knowledge. Our research underscores the potential of leveraging photographs for automated nut calorie and nutritional content estimation, paving the way for the creation of dietary tracking applications that offer real-time, precise nutritional insights to encourage nut consumption.

Objective: This systematic review aims to describe the impact of specific antimicrobial stewardship program (ASP) strategies on implementation and stewardship-related outcomes. Design: Systematic literature review. Methods: We systematically searched multiple databases using search terms that focused on stewardship and implementation. An original search was completed on October 29, 2021, and then updated on February 26, 2025. Studies were eligible for inclusion if they were in English, reported an antimicrobial resource outcome, and using either a comparison group or a pre/post design as a minimum level of rigor. Data from articles were extracted to understand the context and design of the evaluation, the types of approaches used, and outcomes assessed. Results: Out of 2035 studies that were identified, we included 250 full-text peer-reviewed manuscripts. Of the 250 studies included, 52% were conducted in the USA. The majority (80%) of studies were conducted in inpatient settings, particularly in adult academic hospitals (29%). Programs were often implemented hospital-wide or across multiple specialties, with a focus on emergency medicine and intensive care units. Education or learning (64% of studies) and handshake stewardship (56% of studies) were by far the most common ASP strategies used. Mortality (36% of studies) and drug choice (57% of studies) were the most tracked patient and resource outcomes, respectively. Conclusions: Our review highlights the variability in approaches as part of ASPs, indicating a need for a more systematic understanding of how different approaches are implemented and their subsequent impact on antimicrobial use.

This study documented and assessed benthic macroinvertebrate communities on a section of Canyon Creek through Tensleep Preserve in Washakie County, Wyoming, USA. Data for these communities are compared with previous samples collected downstream on agricultural land, as well as upstream and downstream from two subterranean, limestone sinks on the preserve. A shift from Plecoptera, Coleoptera, and Ephemeroptera to mainly Ephemeroptera to mainly Trichoptera was observed from the uppermost to the lowermost sites; Chironomidae and Diptera dominated the previously sampled section. High proportions of scrapers in sampled communities on the preserve beginning downstream of the upstream sink system suggested a prevalence of autochthonous detritus over allochthonous detritus at these sites. Macroinvertebrate community compositions and calculated metrics indicated high water quality for sites on the preserve and lower water quality for the agriculturally impacted sites. Ten taxa recorded from samples between the subterranean sinks were not recorded elsewhere. The mayfly Ameletus validus was abundant at the exit of the upper sink system at which the substrate was lined with irregular limestone slabs, and this taxon may be limited to the interior of this sink. Neothremma is identified as a feasible indicator taxon for climate change.

Climate change is the greatest threat to global health, yet there are few foundational climate resources available for integration into medical school curricula. We describe an interactive session for equipping medical students with practical and empowering foundational climate-health competencies. We developed a 2-hour interactive lecture+ preceded by 30 minutes of required prep work. Knowledge was assessed using two-question quizzes. A postsession survey evaluated session effectiveness and self-assessed attitudes and preparedness. A total of 375 students participated; 164 completed all assessment and evaluation measures. The average knowledge quiz score after required prep was 80%. Of all students, 82% reported that more than half of the session's climate change mitigative strategies were new to them. Ratings of preparedness for five tasks linked to learning objectives significantly improved in all classes (p < .001), with 8%-58% of students before the session and 89%-100% of students after the session reporting being fairly/completely prepared. Qualitative responses also supported achievement of learning objectives. Rates of satisfaction with the required prep and lecture+ were 79% and 89%, respectively. Cited strengths included overall quality and the use of cases to highlight health care environmental impacts and opportunities for mitigation. This resource fills an urgent need for an integrable session for medical schools hoping to achieve action-oriented, foundational climate-health competencies. Key characteristics of this work include the diversity of the development team, ease and flexibility of session implementation, a focus on empowerment, and strong assessment and evaluation data supporting achievement of learning objectives.