AIH focuses on developing knowledge representation and machine learning platforms to support knowledge discovery from healthcare data. AIH is also involved in the development of multi-agent platforms to support healthcare delivery and e-health infrastructures.
This interdisciplinary theme aims to improve health care by transforming the way we learn from and utilize healthcare data created at all levels of the patient journey (including clinical records, linked data sets). The goal is to better understand the etiology and epidemiology of disease and provide better business intelligence tools, such as alerting systems which directly improve care of patients.
We are building a knowledge graph that integrates research and clinical (EHR) data, and in parallel developing new graph prediction algorithms that can use both types of information to infer unknown properties of nodes, such as new (post-marketing) side effects of drugs.
We applied graph theory to analyse the movement of patients between wards in two hospital sites (King’s College Hospital, Denmark Hill and the Princess Royal University Hospital) over an 18 month period. We were able to identify a “core” sub-graph in each site that is critical to the flow of patients, and also to associate changes in flow throughout the network with extremes of A&E performance against the 4-hour waiting time target.
Using the NGSeasy pipeline, a user can quickly deploy any pipeline version in any environment. While this might also be achieved with a VM; VMs lack portability, have substantial overhead, and require allocated resources to be provisioned statically – Docker, to a large extent, solves these issues.
KCL & NIHR Maudsley BRC/U Precision Health Informatics Core Bioinformatics Service provides a wide range of bioinformatics solutions to fully support genomic-related research. The team specialises in comprehensive data analyses for in-house and external generated microarray and next generation sequencing (NGS) projects.
More recently, we have developed a programme of mHealth related feasibility studies around interventions using real-time monitoring of data collected from smartphones and wearable devices as well as remote monitoring platform (RADAR-CNS) will be extended to other disease areas.
The groups work has required the extensive use of computational approaches such machine learning methods and the creation of software tools as well as the construction and administration of high performance computing infrastructure which has been uniquely developed behind the NHS firewall.
The Rosalind Research IT Service provides a bare-metal Beowulf High Performance Compute Cluster (~2K Haswell cores, 1.5K Ivy Bridge cores, 4 Tesla GPU nodes), connected by low-latency Infiniband networking and backed by ~ 0.9PB of performance Lustre filesystem to facilitate data-driven research.
NIHR Biomedical Rearch Centre for Mental Health (BRC-MH) Linux Cluster, located within the SLAM NHS Datacentre and behind the NHS firewall. Incorporated into the cluster are two HP C7000 enclosures, each containing 15 x HP BL460c G6 blades. Each blade is configured with 2 x 4-core Intel® Xeon® Processor X5550. Of the 30 blades, 15 blades contain 78 GB RAM and the remaining 15 blades contain 54 GB of RAM.
Our goal for Software Development is to foster good practices and ensure the maintainability of critical tools developed by the group.
Technologies such as Docker are now establishing themselves as a lightweight solution to packaging applications together with their dependencies, solving a range of problems from reproducible research to simplifying deployment of complex code. This channel highlights literature in F1000Research on uses of containers, published container images, workflows and microservices.