A multimodal approach using fundus images and text meta-data in a machine learning classifier with embeddings to predict years with self-reported diabetes - An exploratory analysis
CONCLUSIONS: The machine learning model had acceptable accuracy and F1 score, and correctly classified more than half of the patients according to diabetes duration. Using large foundational models to extract image and text embeddings seems a feasible and efficient approach to predict years living with self-reported diabetes.PMID:38616442 | DOI:10.1016/j.pcd.2024.04.002 (Source: Primary Care)
Source: Primary Care - April 15, 2024 Category: Primary Care Authors: Rodrigo M Carrillo-Larco Gusseppe Bravo-Rocca Manuel Castillo-Cara Xiaolin Xu Antonio Bernabe-Ortiz Source Type: research
No “cookie cutter rules”: best practice for social care staff in supporting autistic adults with relationships and sexuality
Claire Bates, Rose Matthews Advances in Autism, Vol. ahead-of-print, No. ahead-of-print, pp.- The purpose of this study is to explore the support needs surrounding intimate relationships and sexuality of autistic adults accessing funded social care in England.Semi-structured interviews with 15 autistic adults who were accessing funded social care examined their support needs surrounding intimate relationships and sexuality, with subsequent data analysis using reflexive thematic analysis.Four themes were generated: Help at hand, but not too close for comfort, No “cookie-cutter rules”: personalised, inclusive approaches...
Source: Advances in Autism - April 15, 2024 Category: Child Development Authors: Claire Bates Rose Matthews Source Type: research
Exploring the learning preferences of farmworker ‐serving community health workers
This study provides librarians, along with public health and medical professionals, with useful information about learning preferences to inform the creation of new and varied learning materials for community health workers. (Source: Health Information and Libraries Journal)
Source: Health Information and Libraries Journal - April 15, 2024 Category: Databases & Libraries Authors: Hannah Gordon,
Genesis Ramirez,
Emery L. Harwell,
Jamie E. Bloss,
Ra úl Gámez,
Catherine E. LePrevost Tags: REGULAR FEATURE ARTICLE Source Type: research
Learning-enabled data transmission with up to 32 multiplexed orbital angular momentum channels through a commercial multi-mode fiber
Multiplexing orbital angular momentum (OAM) modes enable high-capacity optical communication. However, the highly similar speckle patterns ... (Source: Optics Letters)
Source: Optics Letters - April 15, 2024 Category: Physics Authors: Jihong Tang Yaling Yin Jingwen Zhou Yong Xia Jianping Yin Source Type: research
What I'm learning … with Holly Baker‐Rand
(Source: The Obstetrician and Gynaecologist)
Source: The Obstetrician and Gynaecologist - April 15, 2024 Category: OBGYN Authors: Holly Baker ‐Rand,
Jo Morrison Tags: And finally … Source Type: research
Sarcoidosis in pregnancy
Key content:
Sarcoidosis is an uncommon multi-system disorder characterised by the presence of non-caseating granulomas. It has a peak incidence between the ages of 20 –40 years old.
The pathogenesis of sarcoidosis is uncertain; however, it is known to be associated with an exaggerated T helper 1 (TH1) immune response leading to systemic inflammation and granuloma formation.
Suppression in TH1 responses in pregnancy leads to disease remission in the majority of pregnancies. Nevertheless, the potential for decompensation in a subgroup remains, and consideration should be given to the pre-pregnancy state.
Sarcoidos...
Source: The Obstetrician and Gynaecologist - April 15, 2024 Category: OBGYN Authors: Joshua Odendaal,
Fiona L Mackie,
Sofia Tosounidou,
Swati Ghosh,
Ellen Knox Tags: Review Source Type: research
Machine-learning analysis reveals an important role for negative selection in shaping cancer aneuploidy landscapes
Aneuploidy, an abnormal number of chromosomes within a cell, is a hallmark of cancer. Patterns of aneuploidy differ across cancers, yet are similar in cancers affecting closely related tissues. The selection p... (Source: Genome Biology)
Source: Genome Biology - April 15, 2024 Category: Genetics & Stem Cells Authors: Juman Jubran, Rachel Slutsky, Nir Rozenblum, Lior Rokach, Uri Ben-David and Esti Yeger-Lotem Tags: Research Source Type: research
Ultrasound-based deep learning radiomics model for differentiating benign, borderline, and malignant ovarian tumours: a multi-class classification exploratory study
Accurate preoperative identification of ovarian tumour subtypes is imperative for patients as it enables physicians to custom-tailor precise and individualized management strategies. So, we have developed an u... (Source: BMC Medical Imaging)
Source: BMC Medical Imaging - April 15, 2024 Category: Radiology Authors: Yangchun Du, Wenwen Guo, Yanju Xiao, Haining Chen, Jinxiu Yao and Ji Wu Tags: Research Source Type: research
Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers
AbstractBreast cancer is the most prevalent cancer among women, and its diagnosis requires the accurate identification and classification of histological features for effective patient management. Artificial intelligence, particularly through deep learning, represents the next frontier in cancer diagnosis and management. Notably, the use of convolutional neural networks and emerging Vision Transformers (ViT) has been reported to automate pathologists ’ tasks, including tumor detection and classification, in addition to improving the efficiency of pathology services. Deep learning applications have also been extended to t...
Source: International Journal of Clinical Oncology - April 15, 2024 Category: Cancer & Oncology Source Type: research
TLOD: Innovative ovarian tumor detection for accurate multiclass classification and clinical application
AbstractOvarian tumors pose a major threat to women's health, mostly remaining undetected until they reach advanced stages, resulting in complex treatment and decreased survival rates. Besides, tumor heterogeneity is more responsible for poor treatment response and adverse prognosis. The purpose of this research is to identify ovarian epithelial tumors in premature stage using histopathological images. In this research, we address the need for an improved ovarian tumor detection method through the development of an innovative simple intelligent approach ‘Transfer Learning with ResNet-based Deep Learning for Ovarian Tumor...
Source: Network Modeling Analysis in Health Informatics and Bioinformatics - April 15, 2024 Category: Bioinformatics Source Type: research
An Automated Multi-scale Feature Fusion Network for Spine Fracture Segmentation Using Computed Tomography Images
AbstractSpine fractures represent a critical health concern with far-reaching implications for patient care and clinical decision-making. Accurate segmentation of spine fractures from medical images is a crucial task due to its location, shape, type, and severity. Addressing these challenges often requires the use of advanced machine learning and deep learning techniques. In this research, a novel multi-scale feature fusion deep learning model is proposed for the automated spine fracture segmentation using Computed Tomography (CT) to these challenges. The proposed model consists of six modules; Feature Fusion Module (FFM),...
Source: Journal of Digital Imaging - April 15, 2024 Category: Radiology Source Type: research
Pure Vision Transformer (CT-ViT) with Noise2Neighbors Interpolation for Low-Dose CT Image Denoising
AbstractConvolutional neural networks (CNN) have been used for a wide variety of deep learning applications, especially in computer vision. For medical image processing, researchers have identified certain challenges associated with CNNs. These challenges encompass the generation of less informative features, limitations in capturing both high and low-frequency information within feature maps, and the computational cost incurred when enhancing receptive fields by deepening the network. Transformers have emerged as an approach aiming to address and overcome these specific limitations of CNNs in the context of medical image ...
Source: Journal of Digital Imaging - April 15, 2024 Category: Radiology Source Type: research
Integration of multiomics analyses reveals unique insights into CD24-mediated immunosuppressive tumor microenvironment of breast cancer
ConclusionThis study highlights the importance of CD24+breast cancer cells in clinical prognosis and immunosuppressive microenvironment, which may provide a new direction for improving patient outcomes. (Source: Inflammation Research)
Source: Inflammation Research - April 15, 2024 Category: Research Source Type: research
Architecting the metabolic reprogramming survival risk framework in LUAD through single-cell landscape analysis: three-stage ensemble learning with genetic algorithm optimization
Recent studies have increasingly revealed the connection between metabolic reprogramming and tumor progression. However, the specific impact of metabolic reprogramming on inter-patient heterogeneity and progno... (Source: Journal of Translational Medicine)
Source: Journal of Translational Medicine - April 15, 2024 Category: Research Authors: Xinti Sun, Minyu Nong, Fei Meng, Xiaojuan Sun, Lihe Jiang, Zihao Li and Peng Zhang Tags: Research Source Type: research
A framework for identification of brain tumors from MR images using progressive segmentation
ConclusionsThe study concludes that the proposed Hybrid Watershed –Clustering framework, powered by the PS-RIM algorithm, markedly improves the detection and differentiation of brain tumors in MR images. It exhibits exceptional accuracy, resilience, and computational efficiency. These findings hold substantial potential for advancing computer vision and image an alysis in medical diagnostics, which could improve patient outcomes in managing brain tumors.Graphical abstract (Source: Health and Technology)
Source: Health and Technology - April 15, 2024 Category: Information Technology Source Type: research
