Development and validation of open-source deep neural networks for comprehensive chest x-ray reading: a retrospective, multicentre study.

BACKGROUND: Artificial intelligence (AI) systems for automated chest x-ray interpretation hold promise for standardising reporting and reducing delays in health systems with shortages of trained radiologists. Yet, there are few freely accessible AI systems trained on large datasets for practitioners to use with their own data with a view to accelerating clinical deployment of AI systems in radiology. We aimed to contribute an AI system for comprehensive chest x-ray abnormality detection. METHODS: In this retrospective cohort study, we developed open-source neural networks, X-Raydar and X-Raydar-NLP, for classifying common chest x-ray findings from images and their free-text reports. Our networks were developed using data from six UK hospitals from three National Health Service (NHS) Trusts (University Hospitals Coventry and Warwickshire NHS Trust, University Hospitals Birmingham NHS Foundation Trust, and University Hospitals Leicester NHS Trust) collectively contributing 2 513 546 chest x-ray studies taken from a 13-year period (2006-19), which yielded 1 940 508 usable free-text radiological reports written by the contemporary assessing radiologist (collectively referred to as the "historic reporters") and 1 896 034 frontal images. Chest x-rays were labelled using a taxonomy of 37 findings by a custom-trained natural language processing (NLP) algorithm, X-Raydar-NLP, from the original free-text reports. X-Raydar-NLP was trained on 23 230 manually annotated reports and tested on 4551 reports from all hospitals. 1 694 921 labelled images from the training set and 89 238 from the validation set were then used to train a multi-label image classifier. Our algorithms were evaluated on three retrospective datasets: a set of exams sampled randomly from the full NHS dataset reported during clinical practice and annotated using NLP (n=103 328); a consensus set sampled from all six hospitals annotated by three expert radiologists (two independent annotators for each image and a third consultant to facilitate disagreement resolution) under research conditions (n=1427); and an independent dataset, MIMIC-CXR, consisting of NLP-annotated exams (n=252 374). FINDINGS: X-Raydar achieved a mean AUC of 0·919 (SD 0·039) on the auto-labelled set, 0·864 (0·102) on the consensus set, and 0·842 (0·074) on the MIMIC-CXR test, demonstrating similar performance to the historic clinical radiologist reporters, as assessed on the consensus set, for multiple clinically important findings, including pneumothorax, parenchymal opacification, and parenchymal mass or nodules. On the consensus set, X-Raydar outperformed historical reporter balanced accuracy with significance on 27 of 37 findings, was non-inferior on nine, and inferior on one finding, resulting in an average improvement of 13·3% (SD 13·1) to 0·763 (0·110), including a mean 5·6% (13·2) improvement in critical findings to 0·826 (0·119). INTERPRETATION: Our study shows that automated classification of chest x-rays under a comprehensive taxonomy can achieve performance levels similar to those of historical reporters and exhibit robust generalisation to external data. The open-sourced neural networks can serve as foundation models for further research and are freely available to the research community. FUNDING: Wellcome Trust.

[The benefits of reading aloud in geriatric wards and institutions]. / Les bienfaits de la lecture à voix haute dans les services et institutions de gériatrie.

The number of elderly patients hospitalized in geriatric wards and institutions on a temporary or more permanent basis is increasing. We know that thymic symptoms, such as depression, behavioral disorders and boredom, are common in these patients. We also know that the drug therapies used to treat these symptoms are sometimes a source of iatrogenesis and can be ineffective. That's why "non-drug" therapies are so useful. What if reading aloud could be part of the management of our elderly patients?

Oncological Treatment-Related Fatigue in Oncogeriatrics: A Scoping Review.

Fatigue is a highly prevalent symptom in both cancer patients and the older population, and it contributes to quality-of-life impairment. Cancer treatment-related fatigue should thus be included in the risk/benefit assessment when introducing any treatment, but tools are lacking to a priori estimate such risk. This scoping review was designed to report the current evidence regarding the frequency of fatigue for the different treatment regimens proposed for the main cancer indications, with a specific focus on age-specific data, for the following tumors: breast, ovary, prostate, urothelium, colon, lung and lymphoma. Fatigue was most frequently reported using the National Cancer Institute Common Terminology Criteria for Adverse Events (NCI CTCAE) versions 3 to 5. A total of 324 regimens were analyzed; data on fatigue were available for 217 (67%) of them, and data specific to older patients were available for 35 (11%) of them; recent pivotal trials have generally reported more fatigue grades than older studies, illustrating increasing concern over time. This scoping review presents an easy-to-understand summary that is expected to provide helpful information for shared decisions with patients regarding the anticipation and prevention of fatigue during each cancer treatment.

Exercise prehabilitation during neoadjuvant chemotherapy may enhance tumour regression in oesophageal cancer: results from a prospective non-randomised trial.

BACKGROUND: There is increasing evidence for the use of exercise in cancer patients and data supporting enhanced tumour volume reduction following chemotherapy in animal models. To date, there is no reported histopathological evidence of a similar oncological benefit in oesophageal cancer. METHODS: A prospective non-randomised trial compared a structured prehabilitation exercise intervention during neoadjuvant chemotherapy and surgery versus conventional best-practice for oesophageal cancer patients. Biochemical and body composition analyses were performed at multiple time points. Outcome measures included radiological and pathological markers of disease regression. Logistic regression calculated ORs with 95% CI for the likelihood of pathological response adjusting for chemotherapy regimen and chemotherapy delivery. RESULTS: Comparison of the Intervention (n=21) and Control (n=19) groups indicated the Intervention group had higher rates of tumour regression (Mandard TRG 1-3 Intervention n=15/20 (75%) vs Control n=7/19 (36.8%) p=0.025) including adjusted analyses (OR 6.57; 95% CI 1.52 to 28.30). Combined tumour and node downstaging (Intervention n=9 (42.9%) vs Control n=3 (15.8%) p=0.089) and Fat Free Mass index were also improved (Intervention 17.8 vs 18.7 kg/m2; Control 16.3 vs 14.7 kg/m2, p=0.026). Differences in markers of immunity (CD-3 and CD-8) and inflammation (IL-6, VEGF, INF-y, TNFa, MCP-1 and EGF) were observed. CONCLUSION: The results suggest improved tumour regression and downstaging in the exercise intervention group and should prompt larger studies on this topic. TRIAL REGISTRATION NUMBER: NCT03626610.

Interventions to improve physical performances of older people with cancer before complex medico-surgical procedures: Protocol for an umbrella review of systematic reviews and meta-analyses.

BACKGROUND: Current demographics lead increasing older cancer patients to undergo complex medico-surgical procedures, with substantial risk of decompensations and deconditioning. The Prehabilitation & Rehabilitation in Oncology: Adaptation to Disease and Accompaniment of Patients' Trajectories (PROADAPT) project is currently being developed with the aim of improving care, through standardized care pathways guided by existing evidence and implementation programs. A working group will specifically focus on improvement of physical performances before such procedures. These interventions may have been developed in different contexts: before surgery in large, before carcinologic surgery or complex medical interventions (chemotherapy, radiotherapy), or in primary care for elderly patients to prevent sarcopenia and frailty. Post-surgical interventions are out of the scope of this review. The objective of this review is to summarize the level of evidence to support physical reconditioning interventions and identify areas where further work is required. METHODS: This umbrella review will include moderate to high quality systematic reviews, meta-analysis, and pre-existing umbrella or meta-reviews. Two reviewers will independently search the following databases: PubMed/MedLine, Cochrane Library, Embase, and CINAHL. Research strategy will use diverse keywords used to refer to the concepts of "prehabilitation," "preoperative exercise," or "preoperative rehabilitation," with prespecified inclusion and exclusion criteria and only systematic reviews selection. The distinct types of interventions presented using PRISMA guidelines and a narrative reporting of results. A focus will be made on outcomes such as physical performances, quality of life, autonomy in everyday activities, or number of hospital bed days. ETHICS AND DISSEMINATION: Ethical approval is not required for such an umbrella review. Our review will be submitted for publication in a peer-reviewed international journal using open access option if available. It will be complementary to reviews focused on hospital discharge of older people. PROSPERO REGISTRATION NUMBER: CRD42020100110.

Effect of Aß Oligomers on Neuronal APP Triggers a Vicious Cycle Leading to the Propagation of Synaptic Plasticity Alterations to Healthy Neurons.

Alterations of excitatory synaptic function are the strongest correlate to the pathologic disturbance of cognitive ability observed in the early stages of Alzheimer's disease (AD). This pathologic feature is driven by amyloid-ß oligomers (Aßos) and propagates from neuron to neuron. Here, we investigated the mechanism by which Aßos affect the function of synapses and how these alterations propagate to surrounding healthy neurons. We used complementary techniques ranging from electrophysiological recordings and molecular biology to confocal microscopy in primary cortical cultures, and from acute hippocampal and cortical slices from male wild-type and amyloid precursor protein (APP) knock-out (KO) mice to assess the effects of Aßos on glutamatergic transmission, synaptic plasticity, and dendritic spine structure. We showed that extracellular application of Aßos reduced glutamatergic synaptic transmission and long-term potentiation. These alterations were not observed in APP KO neurons, suggesting that APP expression is required. We demonstrated that Aßos/APP interaction increases the amyloidogenic processing of APP leading to intracellular accumulation of newly produced Aßos. Intracellular Aßos participate in synaptic dysfunctions as shown by pharmacological inhibition of APP processing or by intraneuronal infusion of an antibody raised against Aßos. Furthermore, we provide evidence that following APP processing, extracellular release of Aßos mediates the propagation of the synaptic pathology characterized by a decreased spine density of neighboring healthy neurons in an APP-dependent manner. Together, our data unveil a complementary role for Aßos in AD, while intracellular Aßos alter synaptic function, extracellular Aßos promote a vicious cycle that propagates synaptic pathology from diseased to healthy neurons.SIGNIFICANCE STATEMENT Here we provide the proof that a vicious cycle between extracellular and intracellular pools of Aß oligomers (Aßos) is required for the spreading of Alzheimer's disease (AD) pathology. We showed that extracellular Aßos propagate excitatory synaptic alterations by promoting amyloid precursor protein (APP) processing. Our results also suggest that subsequent to APP cleavage two pools of Aßos are produced. One pool accumulates inside the cytosol, inducing the loss of synaptic plasticity potential. The other pool is released into the extracellular space and contributes to the propagation of the pathology from diseased to healthy neurons. Pharmacological strategies targeting the proteolytic cleavage of APP disrupt the relationship between extracellular and intracellular Aß, providing a therapeutic approach for the disease.