Search

Diabetes affects roughly 537 million people in the world, and it is predicted to reach 783 million by 2045. Diabetic Foot Ulcer (DFU) is a major issue with diabetes that may lead to lower limb amputation. The rapid evolution of DFU demands immediate intervention to prevent the terrible consequences of amputation and related complications.This research introduces a novel approach utilizing deep neural networks and machine learning for the accurate classification of diabetic foot ulcer (DFU) images. The proposed method harnesses the cutting-edge capabilities of Convolutional Neural Networks (CNN) and Vision Image Transformers (ViT) within a Siamese Neural Network (SNN) Architecture. By employing similarity learning, the model efficiently categorizes DFU images into four distinct classes: None, Infection, Ischemia, or Both. The training process involves the use of the DFU2021 dataset, with all ethical clearances duly obtained. Notably, the model exhibits remarkable performance on both the validation and test data, indicating a significant breakthrough in the field of DFU disease image classification. The potential of this innovative model extends beyond classification; it holds promise as an integral component of a comprehensive detection tool and longitudinal treatment protocol validation for DFU disease.

In the hospitality industry, revenue management is vital for the sustainability of the business. Powering this strategic concept is the occupancy rate (OR) forecast. Predicting occupancy of the hotel is essential for managers’ decision-making process as it gives an estimate of the future business performance. However, the fast-changing marketing demands in the tourism sector, boosted by the advent of online booking, generating accurate forecast figures is nowadays a tough task - needing personnel with advance technical skills and expensive software. The aim of the Systematic Literature review is to provide an insight of the use of Deep Learning techniques for OR prediction. The latest trends in this field over five years (from 2017 to 2022) are highlighted. Through this SRL, three research questions are answered. The questions are related to the variables, deep learning algorithms for prediction and the evaluation metrics used for evaluating the models developed. The Snowballing methodology was used to carry out the SLR. 50 papers were selected for the final analysis. Five categories of variables were identified. LSTM was found to be the most popular deep learning algorithm used to build prediction models. Seven performance metrics were found and among them MAPE was the most popular. To conclude it was found that the hybrid model, CNN-LSTM, to increase accuracy and required more investigation.

It is a known fact that AI models need massive amounts of data for training. In the medical field, the data are not necessarily available at a single site but are distributed over several sites. In the field of medical data sharing, particularly among healthcare institutions, the need to maintain the confidentiality of sensitive information often restricts the comprehensive utilization of real-world data in machine learning. To address this challenge, our study experiments with an innovative approach using federated learning to enable collaborative model training without compromising data confidentiality and privacy. We present an adaptation of the federated averaging algorithm, a predominant centralized learning algorithm, to a peer-to-peer federated learning environment. This adaptation led to the development of two extended algorithms: Federated Averaging Peer-to-Peer and Federated Stochastic Gradient Descent Peer-to-Peer. These algorithms were applied to train deep neural network models for the detection and monitoring of diabetic foot ulcers, a critical health condition among diabetic patients. This study compares the performance of Federated Averaging Peer-to-Peer and Federated Stochastic Gradient Descent Peer-to-Peer with their centralized counterparts in terms of model convergence and communication costs. Additionally, we explore enhancements to these algorithms using targeted heuristics based on client identities and f1-scores for each class. The results indicate that models utilizing peer-to-peer federated averaging achieve a level of convergence that is comparable to that of models trained via conventional centralized federated learning approaches. This represents a notable progression in the field of ensuring the confidentiality and privacy of medical data for training machine learning models.

Diabetes affects roughly 537 million people, and is predicted to reach 783 million by 2045. Diabetes Foot Ulcer (DFU) is a major complication associated with diabetes and can lead to lower limb amputation. The rapid evolution of diabetic foot ulcers (DFUs) necessitates immediate intervention to prevent the severe consequences of amputation and related complications. Continuous and meticulous patient monitoring for individuals with diabetic foot ulcers (DFU) is crucial and is currently carried out by medical practitioners on a daily basis. This research article introduces DFU-Helper, a novel framework that employs a Siamese Neural Network (SNN) for accurate and objective assessment of the progression of diabetic foot ulcers (DFUs) over time. DFU-Helper provides healthcare professionals with a comprehensive visual and numerical representation in terms of the similarity distance of the disease, considering five distinct disease conditions: none, infection, ischemia, both (presence of ischemia and infection), and healthy. The SNN achieves the best Macro F1-score of 0.6455 on the test dataset when applying pseudo-labeling with a pseudo-threshold set to 0.9. The SNN is used in the process of creating anchors for each class using feature vectors. When a patient initially consults a healthcare professional, an image is transmitted to the model, which computes the distances from each class anchor point. It generates a comprehensive table with corresponding figures and a visually intuitive radar chart. In subsequent visits, another image is captured and fed into the model alongside the initial image. DFU-Helper then plots both images and presents the distances from the class anchor points. Our proposed system represents a significant advancement in the application of deep learning for the longitudinal assessment of DFU. To the best of our knowledge, no existing tool harnesses deep learning for DFU follow-up in a comparable manner.

Objective To report multicentred use of the heavy silicone oil Densiron 68 for anatomical reattachment following rhegmatogenous retinal detachment (RRD) repair and its associated complications.Methods and analysis Patients from seven vitreoretinal units within the UK that underwent RRD repair with Densiron 68 between January 2015 and December 2019 were identified. Primary outcome measures were primary and final reattachment rate, retained Densiron and failure rate. Secondary outcome measures were duration of tamponade, final visual acuity (VA) and complications of heavy silicone oil.Results 134 eyes of 134 patients were involved in the study. Primary surgical success was achieved in 48.5%, while a final reattachment rate of 73.4% was observed. The mean duration of Densiron 68 tamponade was 139.5 days. Mean final VA was 1.01 (range 0–2.9). 8 eyes (6.0%) required long-term topical steroids for anterior uveitis, whereas none of the eyes required long-term pressure-lowering treatment. Emulsification rate was 10.7% (6 eyes).Conclusion This is the largest real-world study on Densiron 68 in the UK. Densiron 68 facilitates tamponade of inferior retinal pathology and may be considered as an option for tamponade of inferior retinal pathologies.

Health literate self-management education is at stake for the prevention and management of non-communicable diseases in low resources settings and countries. Here we describe the Learning Nest in Ordinary Context (NA-CO in French, Nids d'Apprentissage en Contexte Ordinaire) aiming at the structuring of health education programs at the micro- (education sessions) and the meso-levels (adapted to context). The Learning Nest model was designed based on a combination on health literacy principles and on studies conducted with vulnerable people with non-communicable diseases. Observation of NA-CO active-learning sessions found them to be operational and relevant as they center on access, understanding, and use of health information while integrating the ordinary context of learners. The Learning Nest packages (including several adapted thematic sessions, training of trainers and development in context) were shown to be feasible and realistic in diverse locations (Reunion, Mali, Mayotte, Mauritius, Burundi). Qualitative and intervention studies have documented the potential usefulness of the Learning Nest model for context- and setting-specific health literacy interventions. [ABSTRACT FROM AUTHOR]

Background: Reporting quality of systematic reviews and meta-analyses is of critical importance in dermatology because of their key role in informing health care decisions. Objective: To assess the compliance of systematic reviews and meta-analyses in leading dermatology journals with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement guidelines. Methods: This review was carried out in accordance with PRISMA guidelines. Included studies were reviews published across 6 years in the top 4 highest-impact-factor dermatology journals of 2017. Records and full texts were screened independently. Data analysis was conducted with univariate multivariable linear regression. The primary outcome was to assess the compliance of systematic reviews and meta-analyses in leading dermatology journals with the PRISMA statement. Results: A total of 166 studies were included and mean PRISMA compliance across all articles was 73%. Compliance significantly improved over time (β = .016; P =

Heavy menstrual bleeding has a high prevalence and is well documented in adult patients with hypermobile-type Ehlers-Danlos syndrome, but there is limited research surrounding work-up and treatment for the adolescent population. Excessive menstrual blood loss can significantly interfere with emotional and physical quality of life. A provider should acquire a comprehensive medical and menstrual history and focused physical examination, as well as baseline laboratory studies, to determine the presence of anemia or underlying bleeding disorder. Use of a pictorial blood assessment chart may be considered to help quantify the amount of bleeding. Treatment to reduce heavy menstrual flow and referral to specialty care should be initiated swiftly to improve quality of life for this population. [Pediatr Ann. 2024;53(3):e104–e108.] [ABSTRACT FROM AUTHOR]

Abstract Background To report the clinical course and the multimodal retinal imaging of a spontaneous retinal pigment epithelial (RPE) tear in a type 2 choroidal neovascularization (CNV) secondary to age-related macular degeneration treated with anti-vascular endothelial growth factor (VEGF) treatment. Case presentation A 74 year-old man presented with visual acuity deterioration in the right eye. Multimodal retinal imaging showed a predominantly classic (type 2) CNV complicated by a spontaneous RPE tear. The patient received six intravitreal injections of anti-VEGF which resulted in improvement of the vision and stabilization of the neovascular lesion on optical coherence tomography (OCT). Longitudinal changes of the RPE-photoreceptors interface, including RPE splitting, are reported on OCT. Conclusion RPE tears may spontaneously occur in type 2 CNV. Anti-VEGF treatment should be aimed at promoting RPE repair and limiting the extent of the scarring. The mechanisms of RPE repair during treatment may be documented with OCT.

Inspiring New Science to Guide Healthcare in Turner Syndrome (InsighTS) Registry is a national, multicenter registry for individuals with Turner syndrome (TS) designed to collect and store validated longitudinal clinical data from a diverse cohort of patients with TS. Herein, we describe the rationale, design, and approach used to develop the InsighTS registry, as well as the demographics of the initial participants to illustrate the registry's diversity and future utility. Multiple stakeholder groups have been involved from project conceptualization through dissemination, ensuring the registry serves the priorities of the TS community. Key features of InsighTS include recruitment strategies to facilitate enrollment of participants that appropriately reflect the population of individuals with TS receiving care in the US, clarity of data ownership and sharing, and sustainability of this resource. The registry gathers clinical data on diagnosis, treatment, comorbidities, health care utilization, clinical practices, and quality of life with the goal of improving health outcomes for this population. Future directions include multiple patient‐centered clinical‐translational research projects that will use the InsighTS platform. This thorough and thoughtful planning will ensure InsighTS is a valuable and sustainable resource for the TS community for decades to come. [ABSTRACT FROM AUTHOR]