Software tools that can search and compare patient data at hospitals across Europe are being developed and rolled-out to find children with closely matched conditions.
The software aims to allow doctors to study how matched patients at other hospitals have been treated and whether their treatment was successful.
The tools are being developed as part of the EU funded Health-e-Child project and use a large quantity of data including genetic and clinical data as well as images from CAT and MRI scans to provide in-depth information regarding a child’s condition.
The Health-e-Child’s CaseReasoner tool enables clinicians to search thousands of disease diagnoses, treatments, and outcomes to find a child similar to their own patient by setting the search parameters themselves.
The results are then displayed as network with groups of patients with similar diagnosis arranged together. Clinicians can then drill down to more detailed data to better understand a diagnosis and the success of the procedures the patient has been through.
The developers are also creating another tool, the AITION to allow clinicians to search medical literature, interviews with clinicians and patient data to determine how a disease may develop.
Harry Dimitropoulos, a researcher on the project at Athens University, said: “We have shown the knowledge models to doctors treating brain tumours and juvenile idiopathic arthritis and they have found it quite intuitive.
“Because of the graphical way it presents the data they have found it easy to click on the links. Some training is required if they want to look in depth at how conclusions were reached, or to modify the statistics or the graph but in theory, AITION can be expanded to as many features as you want.”
The project is currently being run in hospitals in Genoa, Paris, Rome and London and there are plans to extend the network to a further 25 hospitals.
The Health-e-child consortium is made up of fifteen partners from eight European member states with Siemens AS and maatG as industrial partners.
Link