Alcibiade Lichterowicz, partner at Tekliko explains how SPE3DLab is used to integrate data analysis in the processes of healthcare units.
SPE3DLAB, is presented by Thomas Lefèvre (ISIS, EHESS, Paris, France) as a federation tool in a multicentric study in forensic medicine.
11:45am On the use of optimal transportation to merge databases
On the occasion of the meeting of Société française de médecine légale of forensic medecine in Tours on the 13th of Nov. 2017, SPE3DLAB is presented as the tool used for the proof of concept of federation and analysis of unstructured data originating from several French forensic units.
SPE3DLAB allows you to explore your data in an interactive 3D space. The sample is reduced using a t-distributed stochastic neighbor embedding (t-SNE) algorithm and plotted in an interactive map where the user can select individuals and groups to display their characteristics.
SPE3DLAB is present at the 50th international francophone symposium of forensic medecine (Paris 29th June – 1st July) for the presentation of the work carried out in the forensic department of the CHU Jean Verdier.
Thomas Lefèvre 30th June: Big data, médecine légale et aide à la décision : des données à la prédiction contextualisée de la durée d’Incapacité Totale de Travail en temps réel, exemple de SPE3DLAB.
SPE3DLAB allows you to find the best number of clusters based on consensus clustering techniques.
You can then decide the number of clusters to use for the final clustering. The clustering can be analyzed and saved as an additional variable available in all analyses.
SPE3DLAB allows you to modify the network built by HC or IAMB. You can specify the directions of the arcs and also delete them.
SPE3DLAB allows you to choose between different learning algorithms for finding the structure of the network. It lets you choose between a ‘hill climbing’ greedy search on the space of the directed graphs and the Incremental Association Markov Blanket (IAMB) algorithm.
SPE3DLab allows you to work with and visualize georeferenced data
SPE3DLab allows you to use the data provided by the Twitter API