# US 2026/0074080 A1 · Translation of medical evidence into computational evidence and applications thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0074080 A1 - Document ID: US20260074080A1 - Status: Published application - Kind: A1 - Application number: 19/387,112 - Filed: 2025-11-12 - Published: 2026-03-12 - Earliest claimed: 2022-04-15 - Assignees: Evidium, Inc. - Applicants: Evidium, Inc. - Inventors: Carl BATE; Wian STIPP; Thomas UNGER; David A. EPSTEIN; Matthew MCSORLEY; Fady NAKHLA; David ROBINSON; Jennifer May LEE; Arthur BÖÖK - Web page: https://patentgrep.com/patent/US20260074080A1 ## CPC - G06F 40/279: Recognition of textual entities - G16H 70/20: relating to practices or guidelines - G06F 40/237: Lexical tools - G06F 40/30: Semantic analysis - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A computational evidence platform extracts clinical concepts from medical evidence sources and creates a database of elemental diagnostic factors and elemental investigations links to medical conditions. Input from a person groups factors and investigations makes corrections and adds a ranking. Elemental factors and investigations do not include information specific to their associated conditions but include synonyms and a link to a medical ontology. A patient state is determined by extracting patient known diagnostic factors and investigation results from the patient chart. These known factors and results are matched to the database and a ranking of likely conditions are output. Next-best actions per condition are output by determining factors not yet known and investigations not yet performed. Next-best actions across conditions are determined by performing a recursive tree search of the database and assuming that unknown factors are now known to generate a score for each assumption. ## Claims ### Claim 1 A method of querying a knowledge graph, said method comprising: receiving, via an application programming interface (API), a medical query from a software application for querying said knowledge graph, wherein said knowledge graph includes a plurality of medical condition nodes and a plurality of diagnostic factor nodes, each of said diagnostic factor nodes being linked to at least one of said medical condition nodes; using a code in one of said diagnostic factor nodes, following a link to a factor within an electronic medical ontology corresponding to said one of said diagnostic factor nodes, and traversing within said electronic medical ontology to obtain a result; using said result from said traversing, matching a portion of said medical query to at least one of said medical condition nodes or to at least one of said diagnostic factor nodes to produce an output; and outputting, responsive to said medical query, said output to said software application. ### Claim 2 (depends on 1) A method as recited in claim 1 wherein said software application is an artificial intelligence (AI) application. ### Claim 3 (depends on 1) A method as recited in claim 1 wherein said medical query includes at least one patient diagnostic factor extracted from an electronic health record (EHR) of a patient, wherein said matching a portion includes matching said patient diagnostic factor to one of said diagnostic factor nodes, and wherein said output is a medical condition associated with one of said medical condition nodes to which said one of said diagnostic factor nodes is linked. ### Claim 4 (depends on 1) A method as recited in claim 1 wherein said medical query is a clinical state of a patient including at least one likely medical condition of said patient and at least one patient diagnostic factor, wherein said matching a portion includes matching said patient diagnostic factor to one of said diagnostic factor nodes, and wherein said output is an unknown diagnostic factor associated with one of said diagnostic factor nodes that is not yet known to be present or absent in said patient. ### Claim 5 (depends on 1) A method as recited in claim 1 wherein said each diagnostic factor node does not include information specific to a medical condition associated with one of said medical condition nodes to which said each diagnostic factor node is linked. ### Claim 6 (depends on 1) A method as recited in claim 1 wherein at least one of said diagnostic factor nodes is linked to at least two of said medical condition nodes, and wherein said at least one of said diagnostic factor nodes does not include information specific to medical conditions associated with said at least two of said medical condition nodes. ### Claim 7 (depends on 1) A method as recited in claim 1 wherein said knowledge graph further includes on a path between each medical condition node and each of said diagnostic factor nodes to which said each medical condition node is linked, a rank value indicating how likely it is that a diagnostic factor represented by said each diagnostic factor node is indicative of a medical condition represented by said each medical condition node. ### Claim 8 (depends on 1) A method as recited in claim 1 wherein said knowledge graph further includes on a path between each medical condition node and each of said diagnostic factor nodes to which said each medical condition node is linked, at least one condition-dependent attribute of a medical condition represented by said each medical condition node. ### Claim 9 A system for querying a knowledge graph, said system comprising: a database that stores a knowledge graph including a plurality of medical condition nodes and a plurality of diagnostic factor nodes, each of said diagnostic factor nodes being linked to at least one of said medical condition nodes; a computer system comprising one or more processors and memory that stores instructions, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: receive, via an application programming interface (API), a medical query from a software application for querying said knowledge graph; use a code in one of said diagnostic factor nodes to follow a link to a factor within an electronic medical ontology corresponding to said one of said diagnostic factor nodes, and traverse within said electronic medical ontology to obtain a result; use said result from said traverse and match a portion of said medical query to at least one of said medical condition nodes or to at least one of said diagnostic factor nodes to produce an output; and output, responsive to said medical query, said output to said software application. ### Claim 10 (depends on 9) A system as recited in claim 9 wherein said medical query includes at least one patient diagnostic factor extracted from an electronic health record (EHR) of a patient, wherein said matching a portion includes matching said patient diagnostic factor to one of said diagnostic factor nodes, and wherein said output is a medical condition associated with one of said medical condition nodes to which said one of said diagnostic factor nodes is linked. ### Claim 11 (depends on 9) A system as recited in claim 9 wherein said medical query is a clinical state of a patient including at least one likely medical condition of said patient and at least one patient diagnostic factor, wherein said matching a portion includes matching said patient diagnostic factor to one of said diagnostic factor nodes, and wherein said output is an unknown diagnostic factor associated with one of said diagnostic factor nodes that is not yet known to be present or absent in said patient. ### Claim 12 (depends on 9) A system as recited in claim 9 wherein said each diagnostic factor node does not include information specific to a medical condition associated with one of said medical condition nodes to which said each diagnostic factor node is linked. ### Claim 13 (depends on 9) A system as recited in claim 9 wherein at least one of said diagnostic factor nodes is linked to at least two of said medical condition nodes, and wherein said at least one of said diagnostic factor nodes does not include information specific to medical conditions associated with said at least two of said medical condition nodes. ### Claim 14 (depends on 9) A system as recited in claim 9 wherein said knowledge graph further includes on a path between each medical condition node and each of said diagnostic factor nodes to which said each medical condition node is linked, a rank value indicating how likely it is that a diagnostic factor represented by said each diagnostic factor node is indicative of a medical condition represented by said each medical condition node. ### Claim 15 (depends on 9) A system as recited in claim 9 wherein said knowledge graph further includes on a path between each medical condition node and each of said diagnostic factor nodes to which said each medical condition node is linked, at least one condition-dependent attribute of a medical condition represented by said each medical condition node.