Search

Abstract The purpose of the study was to detect Hard Exudates (HE) and classify Disorganization of Retinal Inner Layers (DRIL) implementing a Deep Learning (DL) system on optical coherence tomography (OCT) images of eyes with diabetic macular edema (DME). We collected a dataset composed of 442 OCT images on which we annotated 6847 HE and the presence of DRIL. A complex operational pipeline was defined to implement data cleaning and image transformations, and train two DL models. The state-of-the-art neural network architectures (Yolov7, ConvNeXt, RegNetX) and advanced techniques were exploited to aggregate the results (Ensemble learning, Edge detection) and obtain a final model. The DL approach reached good performance in detecting HE and classifying DRIL. Regarding HE detection the model got an AP@0.5 score equal to 34.4% with Precision of 48.7% and Recall of 43.1%; while for DRIL classification an Accuracy of 91.1% with Sensitivity and Specificity both of 91.1% and AUC and AUPR values equal to 91% were obtained. The P-value was lower than 0.05 and the Kappa coefficient was 0.82. The DL models proved to be able to identify HE and DRIL in eyes with DME with a very good accuracy and all the metrics calculated confirmed the system performance. Our DL approach demonstrated to be a good candidate as a supporting tool for ophthalmologists in OCT images analysis.

The treatment of older patients with cancer is challenging owing to frailty and the presence of comorbidities, which complicate treatment decisions by impacting tolerance to therapeutic interventions, as well as poor representation of this patient population in clinical trials, leading to a lack of evidence-based data, especially in later lines of therapy. There is an urgent need for predictive models that could provide diagnostic and prognostic information relevant to older patients with cancer. Organoid technology has emerged as a promising frontier in cancer treatment, offering a versatile platform for personalized medicine and drug development. By recapitulating the three-dimensional (3D) architecture, cell-matrix interactions and tissue heterogeneity, organoid cultures provide an accurate representation of individual tumor properties, thus enabling the precise modeling of tumor behavior. Clinical trials have demonstrated a high predictive value and statistically significant correlation between the patient’s clinical response and tumor organoid response in different cancer types. The first ongoing Swiss registry study aims to apply organoid-based drug screening technology to identify optimal treatments in older cancer patients in the second or later therapy line setting. This study will help to identify optimal personalized treatment strategies while reducing unnecessary treatment-related toxicity and improving patient outcomes in this patient population. PEER REVIEWED ARTICLE **Peer reviewers:** Dr Andreas Hochstrasser, Hospital Thun, Thun, Switzerland Dr Bich Doan Nguyen-Sträuli, University Hospital Basel, Basel, Switzerland Received on April 22, 2024; accepted after peer review on October 23, 2024; published online on October 30, 2024.

Abstract Background The current paradigm of competency-based medical education and learner-centredness requires learners to take an active role in their training. However, deliberate and planned continual assessment and performance improvement is hindered by the fragmented nature of many medical training programs. Attempts to bridge this continuity gap between supervision and feedback through learner handover have been controversial. Learning plans are an alternate educational tool that helps trainees identify their learning needs and facilitate longitudinal assessment by providing supervisors with a roadmap of their goals. Informed by self-regulated learning theory, learning plans may be the answer to track trainees’ progress along their learning trajectory. The purpose of this study is to summarise the literature regarding learning plan use specifically in undergraduate medical education and explore the student’s role in all stages of learning plan development and implementation. Methods Following Arksey and O’Malley’s framework, a scoping review will be conducted to explore the use of learning plans in undergraduate medical education. Literature searches will be conducted using multiple databases by a librarian with expertise in scoping reviews. Through an iterative process, inclusion and exclusion criteria will be developed and a data extraction form refined. Data will be analysed using quantitative and qualitative content analyses. Discussion By summarising the literature on learning plan use in undergraduate medical education, this study aims to better understand how to support self-regulated learning in undergraduate medical education. The results from this project will inform future scholarly work in competency-based medical education at the undergraduate level and have implications for improving feedback and supporting learners at all levels of competence. Scoping review registration: Open Science Framework osf.io/wvzbx.

Abstract Since the collapse of the Soviet Union and transition to a new forest inventory system, Russia has reported almost no change in growing stock (+ 1.8%) and biomass (+ 0.6%). Yet remote sensing products indicate increased vegetation productivity, tree cover and above-ground biomass. Here, we challenge these statistics with a combination of recent National Forest Inventory and remote sensing data to provide an alternative estimate of the growing stock of Russian forests and to assess the relative changes in post-Soviet Russia. Our estimate for the year 2014 is 111 ± 1.3 × 109 m3, or 39% higher than the value in the State Forest Register. Using the last Soviet Union report as a reference, Russian forests have accumulated 1163 × 106 m3 yr-1 of growing stock between 1988–2014, which balances the net forest stock losses in tropical countries. Our estimate of the growing stock of managed forests is 94.2 × 109 m3, which corresponds to sequestration of 354 Tg C yr-1 in live biomass over 1988–2014, or 47% higher than reported in the National Greenhouse Gases Inventory.

The research objective was to study the association of the AGT rs699 missense SNP with arterial hypertension (AH) and metabolic risk factors among indigenous people of the Arctic territory of Yakutia. The obtained data show that representatives of indigenous people of the Arctic territory of Yakutia with the homozygous GG genotype for the AGT SNP rs699 are characterized by high levels of systolic blood pressure. The carriage of the GG genotype in AH patients is associated with a high frequency of hypo-HDL cholesterolemia. The carriage of GG genotype in AH patients, compared to subjects without AH, is characterized by higher blood levels of total cholesterol, LDL-C, and triglycerides and is associated with a high frequency of abdominal obesity. Thus, the AGT rs699 missense SNP was found to be associated with metabolic risk factors in indigenous AH persons of the Arctic territory of Yakutia.