Machine learning model identifies genetic predictors of cisplatin-induced ototoxicity in CERS6 and TLR4.

Background: Cisplatin-induced ototoxicity remains a significant concern in pediatric cancer treatment due to its permanent impact on quality of life. Previously, genetic association analyses have been performed to detect genetic variants associated with this adverse reaction.

Methods: In this study, a combination of interpretable neural networks and Generative Adversarial Networks (GANs) was employed to identify genetic markers associated with cisplatin-induced ototoxicity.

Identifying Synergistic Components of Botanical Fungicide Formulations Using Interpretable Graph Neural Networks.

Botanical formulations are promising candidates for developing new biopesticides that can protect crops from pests and diseases while reducing harm to the environment. These biopesticides can be combined with permeation enhancer compounds to boost their efficacy against pests and fungal diseases. However, finding synergistic combinations of these compounds is challenging due to the large and complex chemical space.

Perspectives on Ease of Use and Value of a Self-Monitoring Application to Support Physical Activity Maintenance among Individuals Living with and beyond Cancer.

Background: Physical activity (PA) can improve the physical and psychosocial health of individuals with cancer, yet PA levels remain low. Technology may address PA maintenance barriers in oncology, though the intervention effectiveness to date remains mixed. Qualitative research can reveal the nuances of using technology-based PA maintenance tools.

Phenotype prediction from single-cell RNA-seq data using attention-based neural networks.

Motivation: A patient's disease phenotype can be driven and determined by specific groups of cells whose marker genes are either unknown or can only be detected at late-stage using conventional bulk assays such as RNA-Seq technology. Recent advances in single-cell RNA sequencing (scRNA-seq) enable gene expression profiling in cell-level resolution, and therefore have the potential to identify those cells driving the disease phenotype even while the number of these cells is small. However, most existing methods rely heavily on accurate cell type detection, and the number of available annotated samples is usually too small for training deep learning predictive models.

Effectiveness of a Self-Monitoring App in Supporting Physical Activity Maintenance Among Rural Canadians With Cancer After an Exercise Oncology Program: Cluster Randomized Controlled Trial.

Background: Despite the benefits of physical activity (PA) for individuals with cancer, most remain insufficiently active. Exercise oncology interventions can improve PA levels. Individuals struggle to maintain PA levels after interventions because of persistent psychological and environmental PA barriers.

The online delivery of exercise oncology classes supported with health coaching: a parallel pilot randomized controlled trial.

Purpose: The primary objective was to investigate the feasibility of a synchronous, online-delivered, group-based, supervised, exercise oncology maintenance program supported with health coaching.

Methods: Participants had previously completed a 12-week group-based exercise program. All participants received synchronous online delivered exercise maintenance classes, and half were block randomized to receive additional weekly health coaching calls.

First-Year Implementation of the EXercise for Cancer to Enhance Living Well (EXCEL) Study: Building Networks to Support Rural and Remote Community Access to Exercise Oncology Resources.

Barriers to exercise-oncology programs remain for those living with and beyond cancer in rural and remote communities, including geographic isolation and access to programs. The EXercise for Cancer to Enhance Living Well (EXCEL) study was designed to support exercise-oncology implementation in rural and remote communities across Canada. The purpose of this analysis was to evaluate the first-year reach, adoption, and implementation of the EXCEL study.

Implementing an exercise oncology model to reach rural and remote individuals living with and beyond cancer: a hybrid effectiveness-implementation protocol for project EXCEL (EXercise for Cancer to Enhance Living Well).

Introduction: Individuals living with and beyond cancer from rural and remote areas lack accessibility to supportive cancer care resources compared with those in urban areas. Exercise is an evidence-based intervention that is a safe and effective supportive cancer care resource, improving physical fitness and function, well-being and quality of life. Thus, it is imperative that exercise oncology programs are accessible for all individuals living with cancer, regardless of geographical location.

Multi-treatment Effect Estimation from Biomedical Data.

Several biomedical applications contain multiple treatments from which we want to estimate the causal effect on a given outcome. Most existing Causal Inference methods, however, focus on single treatments. In this work, we propose a neural network that adopts a multi-task learning approach to estimate the effect of multiple treatments.

Dignity in the care of people with advanced illness in emergency services from the perspective of family members: A qualitative study.

Background And Aim: Patients with advanced illness frequently attend emergency services, accompanied by their relatives. The objective of this study was to explore and describe the experiences of relatives, related to loss and preservation of dignity in end-of-life care in the emergency department.

Materials And Methods: Descriptive qualitative study.

Ligand Binding Prediction Using Protein Structure Graphs and Residual Graph Attention Networks.

Computational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures.

Results From a Physical Activity Intervention Feasibility Study With Kidney Inpatients.

Background: Individuals with end-stage kidney disease requiring dialysis are often physically inactive, resulting in reduced physical functioning, increased frailty, and reduced quality of life. Furthermore, extended hospital stays and frequent readmissions are common, exacerbating health care costs. Physical activity may improve physical functioning, disability, and frailty but is not part of standard care of patients requiring dialysis.

Aristotle: stratified causal discovery for omics data.

Background: There has been a simultaneous increase in demand and accessibility across genomics, transcriptomics, proteomics and metabolomics data, known as omics data. This has encouraged widespread application of omics data in life sciences, from personalized medicine to the discovery of underlying pathophysiology of diseases. Causal analysis of omics data may provide important insight into the underlying biological mechanisms.

Healthy memory aging - the benefits of regular daily activities increase with age.

As the number of older adults increases, so does the pressure on health care systems due to age-related disorders. Attempts to reduce cognitive decline have focused on individual interventions such as exercise or diet, with limited success. This study adopted a different approach by investigating the impact of combined daily activities on memory decline.

Current Evidence and Directions for Future Research in eHealth Physical Activity Interventions for Adults Affected by Cancer: Systematic Review.

Background: Physical activity (PA) interventions can increase PA and improve well-being among adults affected by cancer; however, most adults do not meet cancer-specific PA recommendations. Lack of time, facility access, and travel distances are barriers to participation in PA interventions. eHealth technologies may address some of these barriers, serving as a viable way to promote PA behavior change in this population.

Moderate-Intensity Physical Activity, Music and Art Activities Preserved Cognitive Health in Older Adults: An Argument for Social Prescribing Solution.

Rates of dementia are projected to increase over the coming years as global populations age. Without a treatment to slow the progression of dementia, many health policies are focusing on preventing dementia by slowing the rate of cognitive decline with age. However, it is unclear which lifestyle changes in old age meaningfully reduce the rate of cognitive decline associated with aging.

A survey of technology literacy and use in cancer survivors from the Alberta Cancer Exercise program.

Background: Supervised physical activity interventions can improve cancer survivor quality of life. However, they are resource intensive and may not support physical activity maintenance. Therefore, most cancer survivors remain inactive.

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

The goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines.

Physical Activity for Individuals Living with Advanced Cancer: Evidence and Recommendations.

Objectives: To provide health and fitness professionals with screening, triage, prescription, and physical activity recommendations to better serve individuals living with advanced cancer. A call to action regarding next steps to improve research and knowledge translation is also outlined, ensuring the growing number of those with advanced cancers are supported in their efforts to adopt and adhere to active lifestyles.

Data Sources: Sources include published literature, physical activity guidelines, and expert opinion from physical medicine and rehabilitation physicians, exercise physiologists, and health and exercise psychology researchers.

Protocol: A cluster randomized controlled trial of a mobile application to support physical activity maintenance after an exercise oncology program.

Objectives/purpose: Increasing physical activity (PA) among adults living with cancer is a public health priority, especially for those in remote/rural locations who have worse health outcomes and lower PA than urban populations. Mobile health technology may overcome barriers to PA participation and change PA behavior. However, few mobile health interventions have focused on sustaining PA long-term in remote/rural adults living with cancer.

ParKCa: Causal Inference with Partially Known Causes.

Methods for causal inference from observational data are an alternative for scenarios where collecting counterfactual data or realizing a randomized experiment is not possible. Our proposed method ParKCA combines the results of several causal inference methods to learn new causes in applications with some known causes and many potential causes. We validate ParKCA in two Genome-wide association studies, one real-world and one simulated dataset.

Feasibility of a multimodal exercise, nutrition, and palliative care intervention in advanced lung cancer.

Background: Advanced lung cancer patients face significant physical and psychological burden leading to reduced physical function and quality of life. Separately, physical activity, nutrition, and palliative symptom management interventions have been shown to improve functioning in this population, however no study has combined all three in a multimodal intervention. Therefore, we assessed the feasibility of a multimodal physical activity, nutrition, and palliative symptom management intervention in advanced lung cancer.

A Physical Activity Intervention Feasibility Study for Kidney Inpatients: A Basic Research Protocol.

Background: Low physical activity levels and poor physical functioning are strongly associated with poor clinical outcomes and mortality in adult kidney failure patients, regardless of treatment modality. Compared with the general population, individuals with chronic kidney disease are physically inactive, have reduced physical abilities and difficulties performing routine daily tasks, lower health-related quality of life, and higher cardiovascular morbidity and mortality. In addition, frail kidney failure patients have higher hospitalization and mortality rates as compared with other kidney failure patients.

Development and Testing of an Ultrasound-Compatible Cardiac Phantom for Interventional Procedure Simulation Using Direct Three-Dimensional Printing.

Organ phantoms are widely used for evaluating medical technologies, training clinical practitioners, as well as surgical planning. In the context of cardiovascular disease, a patient-specific cardiac phantom can play an important role for interventional cardiology procedures. However, phantoms with complicated structures are difficult to fabricate by conventional manufacturing methods.

Identification of differentially expressed gene modules in heterogeneous diseases.

Motivation: Identification of differentially expressed genes is necessary for unraveling disease pathogenesis. This task is complicated by the fact that many diseases are heterogeneous at the molecular level and samples representing distinct disease subtypes may demonstrate different patterns of dysregulation. Biclustering methods are capable of identifying genes that follow a similar expression pattern only in a subset of samples and hence can consider disease heterogeneity.