Abstract: A process is provided for using a graph database (e.g., SPOKE) to generate training vectors (SPOKEsigs) and train a machine learning model to classify biological entities. A cohort's input data records (EHRs) are compared to graph database nodes to identify overlapping concepts. Entry nodes (SEPs) associated with these overlapping concepts are used to generate propagated entry vectors (PSEVs) that encode the importance of each database node for a particular cohort, which helps train the model with only relevant information. Further, the propagated entry vectors for a given entity with a known classification can be aggregated to create training vectors. The training vectors are used as inputs to train a machine learning model. Biological entities with an unknown classification can be classified with a trained machine learning model. Entity signature vectors are generated for entities without a classification and input into the trained machine learning model to obtain a classification.

Abstract: The present invention relates to a method of stratifying a subject with neurological or psychiatric disease manifestation, preferably with neuro-inflammatory autoimmune diseases a) determining i) a level of B cells in a test cerebrospinal fluid (CSF) sample obtained from a subject; ii) a level of immune cells per ?l in said test CSF sample obtained from said subject; iii) a level of NKT cells in said test CSF sample obtained from said subject; iv) a level of monocytes in said test CSF sample obtained from said subject, and v) a level of CD56dim CD16+ NK cells in a test peripheral blood (PB) sample obtained from said subject, and b) stratifying said subject as suffering from neuro-inflammatory autoimmune diseases, if the following are fulfilled: i) the level of B cells is increased relative to corresponding levels of B cells in control CSF samples obtained from subjects not suffering from neuro-inflammatory autoimmune diseases; ii) the level of immune cells per ?l is increased relative to corresponding levels