Method and system for assessing drug efficacy using multiple graph kernel fusion

Patent metadata

Field	Value
Publication number	US-11238966-B2
Application number	US-202017088172-A
Country	US
Kind code	B2
Filing date	Nov 3, 2020
Priority date	Nov 4, 2019
Publication date	Feb 1, 2022
Grant date	Feb 1, 2022

Abstract

Embodiments of the present systems and methods may provide techniques to predict the success or failure of a drug used for disease treatment. For example, a method of determining drug efficacy may include, for a plurality of patients, generating a directed acyclic graph from health related information of each patient comprising nodes representing a medical event of the patient, at least one first edge connecting the first node to an additional node, each additional edge connecting nodes representing two consecutive medical events, the edge having a weight based on a time difference between the two consecutive medical events, capturing a plurality of features from each directed acyclic graph, generating a binary graph classification model on captured features of each directed acyclic graph, determining a probability that a drug or treatment will be effective using the binary graph classification model, and determining a drug to be prescribed to a patient based on the determined probability.

First claim

What is claimed is:

1. A method of computing a probable drug efficacy implemented in a computer system comprising a processor, memory accessible by the processor and storing computer program instructions and data, and computer program instructions to perform:
for a plurality of patients, generating and storing in the memory a directed acyclic graph as an extraction and transformation from electronic health records of each patient, the electronic health records comprising demographic information for each patient and medical event information for each patient, using the processor to extract demographic data and medical events data records from the electronic health records and to transform each extracted medical events data record into a node in a directed acyclic graph, each directed acyclic graph comprising: a first node representing first demographic information of the patient, a plurality of additional nodes, each additional node representing a medical event of the patient, at least one first edge connecting the first node to an additional node, the first edge having a weight based on second demographic information of the patient, and a plurality of additional edges, each additional edge connecting nodes representing two consecutive medical events, the edge having a weight based on a time difference between the two consecutive medical events;
capturing, using the processor, a plurality of features from each directed acyclic graph stored in the memory;
training a neural network classification model using a plurality of the captured features of each directed acyclic graph;
applying the neural network classification model to determine a probability that a drug or treatment will be effective for a particular patient; and
determining, using the processor, a drug or treatment to be prescribed to the particular patient based on the determined probability.

2. The method of claim 1 , wherein the plurality of features are captured by:
transforming each directed acyclic graph to a shortest path graph;
generating a temporal topological kernel by recursively calculating similarity among temporal ordering on a plurality of groups of additional nodes; and
generating a temporal substructure kernel on additional edges connecting additional nodes in each group of additional nodes.

3. The method of claim 1 , wherein the plurality of features are captured by:
generating a topological ordering of each directed acyclic graph based on an order of occurrence of a label associated with each additional node in each directed acyclic graph;
generating a topological sequence of each directed acyclic graph comprising a plurality of levels indicating an order of occurrence of a same node label in the topological sequence;
generating a temporal signature for each directed acyclic graph comprising a series of total passage times from the first node to each additional node in a union of a plurality of topological sequences;
generating a temporal proximity kernel between a plurality of pairs of temporal signatures;
generating a shortest path kernel by calculating an edge walk similarity on shortest path graphs for a plurality of pairs of directed acyclic graphs;
generating a node kernel by comparing node labels of a plurality of pairs of directed acyclic graphs; and
fusing the temporal proximity kernel, the shortest path kernel, and the node kernel.

4. The method of claim 3 , wherein the fusing comprises:
reducing dimensions of the temporal proximity kernel, the shortest path kernel, and the node kernel for the plurality of pairs of directed acyclic graphs; and
averaging embeddings of the temporal proximity kernel, the shortest path kernel, and the node kernel for the plurality of pairs of directed acyclic graphs.

5. The method of claim 4 , further comprising determining a success or failure of the fusion using a sigmoid layer.

6. The method of claim 1 , wherein the patient is a non-human animal.

7. The method of claim 1 , wherein the drug to be prescribed is to treat covid-19.

8. The method of claim 1 , wherein the first demographic information of the patient is a gender of the patient and the second first demographic information of the patient is an age of the patient.

9. A system for computing a probable drug efficacy comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor to perform:
for a plurality of patients, generating and storing in the memory a directed acyclic graph as an extraction and transformation from electronic health records of each patient, the electronic health records comprising demographic information for each patient and medical event information for each patient, using the processor to extract demographic data and medical events data records from the electronic health records and to transform each extracted medical events data record into a node in a directed acyclic graph, each directed acyclic graph comprising a first node representing first demographic information of the patient, a plurality of additional nodes, each additional node representing a medical event of the patient, at least one first edge connecting the first node to an additional node, the first edge having a weight based on second demographic information of the patient, and a plurality of additional edges, each additional edge connecting nodes representing two consecutive medical events, the edge having a weight based on a time difference between the two consecutive medical events;
capturing, using the processor, a plurality of features from each directed acyclic graph stored in the memory;
training a neural network classification model using a plurality of the captured features of each directed acyclic graph;
applying the neural network classification model to determine a probability that a drug or treatment will be effective for a particular patient; and
determining, using the processor, a drug or treatment to be prescribed to the particular patient based on the determined probability.

10. The system of claim 9 , wherein the plurality of features are captured by:
transforming each directed acyclic graph to a shortest path graph;
generating a temporal topological kernel by recursively calculating similarity among temporal ordering on a plurality of groups of additional nodes; and
generating a temporal substructure kernel on additional edges connecting additional nodes in each group of additional nodes.

11. The system of claim 9 , wherein the plurality of features are captured by:
generating a topological ordering of each directed acyclic graph based on an order of occurrence of a label associated with each additional node in each directed acyclic graph;
generating a topological sequence of each directed acyclic graph comprising a plurality of levels indicating an order of occurrence of a same node label in the topological sequence;
generating a temporal signature for each directed acyclic graph comprising a series of total passage times from the first node to each additional node in a union of a plurality of topological sequences;
generating a temporal proximity kernel between a plurality of pairs of temporal signatures;
generating a shortest path kernel by calculating an edge walk similarity on shortest path graphs for a plurality of pairs of directed acyclic graphs;
generating a node kernel by comparing node labels of a plurality of pairs of directed acyclic graphs; and
fusing the temporal proximity kernel, the shortest path kernel, and the node kernel.

12. The system of claim 11 , wherein the fusing comprises:
reducing dimensions of the temporal proximity kernel, the shortest path kernel

Assignees

• Univ Georgetown

Inventors

• Frieder Ophir
• Yao Hao-Ren
• Chang Der-Chen

Classifications

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H20/10 Primary

  relating to drugs or medications, e.g. for ensuring correct administration to patients · CPC title

• G06F18/24137

  Distances to cluster centroïds · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title