Abstract: A system and method for graph-based discovery of geometry of clinical data are disclosed. The method includes receiving vectors of outcomes of trial subjects; generating, based on the vectors of outcomes, a plurality of metric graphs such that each of the metric graphs includes a same set of nodes corresponding to the vectors of outcomes and the nodes are selectively connected based on a first criterion, the first criterion being based on a set of parameters, the set of parameters being uniquely selected, from a plurality of sets of parameters, for each of the metric graphs; determining, based on the plurality of metric graphs and a second criterion, an aggregated graph and a subset of the plurality of metric graphs; selecting, from the subset of the plurality of metric graphs and based on a third criterion, optimal and most representative graphs; and displaying a graphical representation of optimal graphs.

Abstract: Methods and systems for graph-based discovery of geometry of clinical data are provided. An example method includes receiving vectors of outcomes of trial subjects, generating, based on the vectors of outcomes, a plurality of metric graphs, each of the metric graphs including a set of nodes corresponding to the vectors of outcomes and a set of edges, performing an automatic search to identify communities of nodes in the optimal graph, displaying a graphical representation of the optimal graph and highlighting nodes in the graphical representation, the nodes corresponding to the community of nodes. Generating the set of edges includes selecting metrics and projection rules to obtain projections of the vectors of outcomes, and selectively connecting nodes based on determination that projections of corresponding vectors of outcomes belong to the same domain of a set of overlapping domains and a certain cluster within the domain.

Abstract: Methods and systems for graph-based discovery of geometry of clinical data are provided. An example method includes receiving vectors of outcomes of trial subjects, generating, based on the vectors of outcomes, a plurality of metric graphs, each of the metric graphs including a set of nodes corresponding to the vectors of outcomes and a set of edges, performing an automatic search to identify communities of nodes in the optimal graph, displaying a graphical representation of the optimal graph and highlighting nodes in the graphical representation, the nodes corresponding to the community of nodes. Generating the set of edges includes selecting metrics and projection rules to obtain projections of the vectors of outcomes, and selectively connecting nodes based on determination that projections of corresponding vectors of outcomes belong to the same domain of a set of overlapping domains and a certain cluster within the domain.

Abstract: Methods and systems for topology-based clinical data mining are provided. An example system includes a pre-processing module to process the clinical datasets to generate a table of outcomes and a table of predictors of trial subjects. The system includes a graph construction module to generate metric graphs based on the table of outcomes. The metric graphs include nodes representing the subjects and edges selectively connecting the nodes according to pre-determined criteria. The graph construction module may select a graph of interest from the metric graphs and generate a compressed version of the graph of interest. The system may further include an interactive visualization module to display a graphical representation of the graph of interest or the compressed version, receive selection of groups of the trial subjects, automatically highlight groups of related subjects, and perform, using the table of predictors, a statistical analysis of predictors of subjects within the selected groups.

Abstract: Methods and systems for topology-based clinical data mining are provided. An example system includes a pre-processing module to process the clinical datasets to generate a table of outcomes and a table of predictors of trial subjects. The system includes a graph construction module to generate metric graphs based on the table of outcomes. The metric graphs include nodes representing the subjects and edges selectively connecting the nodes according to pre-determined criteria. The graph construction module may select a graph of interest from the metric graphs and generate a compressed version of the graph of interest. The system may further include an interactive visualization module to display a graphical representation of the graph of interest or the compressed version, receive selection of groups of the trial subjects, automatically highlight groups of related subjects, and perform, using the table of predictors, a statistical analysis of predictors of subjects within the selected groups.