A Novel Coupled Reaction-Diffusion System for Explainable Gene Expression Profiling.

Machine learning (ML)-based algorithms are playing an important role in cancer diagnosis and are increasingly being used to aid clinical decision-making. However, these commonly operate as 'black boxes' and it is unclear how decisions are derived. Recently, techniques have been applied to help us understand how specific ML models work and explain the rational for outputs. This study aims to determine why a given type of cancer has a certain phenotypic characteristic. Cancer results in cellular dysregulation and a thorough consideration of cancer regulators is required. This would increase our understanding of the nature of the disease and help discover more effective diagnostic, prognostic, and treatment methods for a variety of cancer types and stages. Our study proposes a novel explainable analysis of potential biomarkers denoting tumorigenesis in non-small cell lung cancer. A number of these biomarkers are known to appear following various treatment pathways. An enhanced analysis is enabled through a novel mathematical formulation for the regulators of mRNA, the regulators of ncRNA, and the coupled mRNA-ncRNA regulators. Temporal gene expression profiles are approximated in a two-dimensional spatial domain for the transition states before converging to the stationary state, using a system comprised of coupled-reaction partial differential equations. Simulation experiments demonstrate that the proposed mathematical gene-expression profile represents a best fit for the population abundance of these oncogenes. In future, our proposed solution can lead to the development of alternative interpretable approaches, through the application of ML models to discover unknown dynamics in gene regulatory systems.

Safety of day-case endovascular interventions for peripheral arterial disease in a rural, underserved area.

BACKGROUND: We aimed to investigate the safety of endovascular procedures undertaken in a single outpatient center located in a rural, underserved area. Endovascular procedures for Peripheral Arterial Disease (PAD) have become increasingly common in outpatient settings; their safety is yet to be determined in a rural, underserved area with no stand-by vascular surgeon on site. METHODS: We undertook a retrospective case review of endovascular procedures for the investigation and management of lower extremity PAD between December 2012 and August 2015. Patients were classified by Rutherford score, degree of stenosis and length of lesions. Complications were major (requiring hospitalization) or minor, including perforation, distal embolization, hematoma, and allergic reactions, which could be treated immediately in the catheterization laboratory with no sequelae. Patients were monitored in the facility and followed up using clinical, biochemical and radiological parameters at 24 h and 1 month. RESULTS: A total of 692 patients underwent endovascular procedures for the investigation and/or treatment of PAD, of which 608 were interventional. Of these patients, 10.20% experienced procedural complications, of which 0.66% were classified as major, including wire retention and retroperitoneal hemorrhage. In total, 99.34% were discharged safely on the same day as the procedure. No adverse events were reported at follow up. CONCLUSION: Endovascular procedures for PAD can be performed safely in a rural outpatient setting with low complication rates. Most complications are minor and do not require hospitalization. Outpatient procedures for PAD are safe and may widen access to specialist procedures in areas of socio-economic deprivation.