Search

Abstract Background There is an increasing interest in the use of Deep Learning (DL) based methods as a supporting analytical framework in oncology. However, most direct applications of DL will deliver models with limited transparency and explainability, which constrain their deployment in biomedical settings. Methods This systematic review discusses DL models used to support inference in cancer biology with a particular emphasis on multi-omics analysis. It focuses on how existing models address the need for better dialogue with prior knowledge, biological plausibility and interpretability, fundamental properties in the biomedical domain. For this, we retrieved and analyzed 42 studies focusing on emerging architectural and methodological advances, the encoding of biological domain knowledge and the integration of explainability methods. Results We discuss the recent evolutionary arch of DL models in the direction of integrating prior biological relational and network knowledge to support better generalisation (e.g. pathways or Protein-Protein-Interaction networks) and interpretability. This represents a fundamental functional shift towards models which can integrate mechanistic and statistical inference aspects. We introduce a concept of bio-centric interpretability and according to its taxonomy, we discuss representational methodologies for the integration of domain prior knowledge in such models. Conclusions The paper provides a critical outlook into contemporary methods for explainability and interpretability used in DL for cancer. The analysis points in the direction of a convergence between encoding prior knowledge and improved interpretability. We introduce bio-centric interpretability which is an important step towards formalisation of biological interpretability of DL models and developing methods that are less problem- or application-specific.

Specialized transformers-based models (such as BioBERT and BioMegatron) are adapted for the biomedical domain based on publicly available biomedical corpora. As such, they have the potential to encode large-scale biological knowledge. We investigate the encoding and representation of biological knowledge in these models, and its potential utility to support inference in cancer precision medicine—namely, the interpretation of the clinical significance of genomic alterations. We compare the performance of different transformer baselines; we use probing to determine the consistency of encodings for distinct entities; and we use clustering methods to compare and contrast the internal properties of the embeddings for genes, variants, drugs, and diseases. We show that these models do indeed encode biological knowledge, although some of this is lost in fine-tuning for specific tasks. Finally, we analyze how the models behave with regard to biases and imbalances in the dataset.

Objectives COVID-19 is a heterogeneous disease, and many reports have described variations in demographic, biochemical and clinical features at presentation influencing overall hospital mortality. However, there is little information regarding longitudinal changes in laboratory prognostic variables in relation to disease progression in hospitalised patients with COVID-19.Design and setting This retrospective observational report describes disease progression from symptom onset, to admission to hospital, clinical response and discharge/death among patients with COVID-19 at a tertiary centre in South East England.Participants Six hundred and fifty-one patients treated for SARS-CoV-2 between March and September 2020 were included in this analysis. Ethical approval was obtained from the HRA Specific Review Board (REC 20/HRA/2986) for waiver of informed consent.Results The majority of patients presented within 1 week of symptom onset. The lowest risk patients had low mortality (1/45, 2%), and most were discharged within 1 week after admission (30/45, 67%). The highest risk patients, as determined by the 4C mortality score predictor, had high mortality (27/29, 93%), with most dying within 1 week after admission (22/29, 76%). Consistent with previous reports, most patients presented with high levels of C reactive protein (CRP) (67% of patients >50 mg/L), D-dimer (98%>upper limit of normal (ULN)), ferritin (65%>ULN), lactate dehydrogenase (90%>ULN) and low lymphocyte counts (81%

Health care needs to continuously evolve and innovate to maintain the health of populations. Technology has the potential to enable better patient engagement and ownership, as well as optimise therapeutic interventions and data-science approaches to facilitate improved health care decisions. Yet, to date, technological innovation has not resulted in the rate of change that could have been predicted from other sectors. This article discusses multiple reasons for this and proposes a newly tested and deployed solution: the technology clinical trial. The technology clinical trial methodology has been developed through working directly with patients, clinical and medical devicetrial experts. This approach enables researchers to use the complex environment of health care as an opportunity to transform the pace of innovation and create new care pathways. Instead of testing a single innovation, researchers can ‘step back’ and systematically review all areas of the patient's journey for potential optimization. Then integrate novel data science, technological advances, process updates, behavioural science, and patient engagement to co-create a streamlined multidisciplinary solution. As a result, this research has the potential for larger advances due to the emergent benefits that can arise when the individual elements work together as a whole. These potential benefits are then robustly tested, characterised and measured in the trial environment to ensure that future application of the innovative pathway is supported by the robust empirical data health care requires.

Introduction The COVID-19 pandemic caused by SARS-CoV-2 places immense worldwide demand on healthcare services. Earlier identification of patients at risk of severe disease may allow intervention with experimental targeted treatments, mitigating the course of their disease and reducing critical care service demand.Methods and analysis This prospective observational study of patients tested or treated for SARS-CoV-2, who are under the care of the tertiary University Hospital Southampton NHS Foundation Trust (UHSFT), captured data from admission to discharge; data collection commenced on 7 March 2020. Core demographic and clinical information, as well as results of disease-defining characteristics, was captured and recorded electronically from hospital clinical record systems at the point of testing. Manual data were collected and recorded by the clinical research team for assessments which are not part of the structured electronic healthcare record, for example, symptom onset date. Thereafter, participant records were continuously updated during hospital stay and their follow-up period. Participants aged >16 years were given the opportunity to provide consent for excess clinical sample storage with optional further biological sampling. These anonymised samples were linked to the clinical data in the Real-time Analytics for Clinical Trials platform and were stored within a biorepository at UHSFT.Ethics and dissemination Ethical approval was obtained from the HRA Specific Review Board (REC 20/HRA/2986) for waiver of informed consent for the database-only cohort; the procedures conform with the Declaration of Helsinki. The study design, protocol and patient-facing documentation for the biobanking arm of the study have been approved by North West Research Ethics Committee (REC 17/NW/0632) as an amendment to the National Institute for Health Research Southampton Clinical Research Facility-managed Southampton Research Biorepository. This study will be published as peer-reviewed articles and presented at conferences, presentations and workshops.