Systems and Methods for Mapping New Patient Information to Historic Outcomes for Treatment Assistance

• US 20130144916A1
• Filed: 10/09/2012
• Published: 06/06/2013
• Est. Priority Date: 02/10/2009
• Status: Abandoned Application

• Current Assignee: SymphonyAI Sensa LLC (Fortive Corp.)
• Original Assignee: Ayasdi, Inc. (Fortive Corp.)
• Inventors: Carlsson, Gunnar, Sexton, Harlan, Lum, Pek Yee, Singh, Gurjeet
• Application Number:
  US13/648,237
• Publication Number:
  US 20130144916A1
• Time in Patent Office: Days
• US Class Current: 707/790
• CPC Class Codes: F04C 2270/0421 Controlled or regulated
• CPC Class Codes: G01N 33/48 Biological material, e.g. blood, urine G01N33/02, G01N33/26, G01N33/44, G01N33/46 take precedence; Haemocytometers counting blood corpuscules distributed over a surface by scanning the surface G06M11/02
• CPC Class Codes: G01N 33/53 Immunoassay; Biospecific binding assay; Materials therefor
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/90328 using search space presentation or visualization, e.g. category or range presentation and selection
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 40/30 Unsupervised data analysis
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Exemplary systems and methods for predictive visualization of patients are provided. In various embodiments, a system comprises a map and a location engine. The map includes a plurality of groupings and interconnections of the groupings, each grouping having one or more patient members that share biological similarities, each interconnection interconnecting groupings that share at least one common patient member, the map identifying a set of groupings and a set of interconnections having a medical characteristic of a set of medical characteristics. The location engine may be configured to determine whether a new patient shares the biological similarities with the one or more patient members of each grouping thereby enabling association of the new patient with one or more of the set of medical characteristics.

Claims

1. A system comprising:

a map including a plurality of groupings and interconnections of the groupings, each grouping having one or more patient members that share biological similarities, each interconnection interconnecting groupings that share at least one common patient member, the map identifying a set of groupings and a set of interconnections having a medical characteristic of a set of medical characteristics; and

a location engine configured to determine whether a new patient shares the biological similarities with the one or more patient members of each grouping,

thereby enabling association of the new patient with one or more of the set of medical characteristics.

2. The system of claim 1 wherein the biological similarities represent similarities of measurements of gene expressions.

3. The system of claim 1 wherein the biological similarities represent similarities of sequencing.

4. The system of claim 1 wherein the map is generated by an analysis server configured to receive biological data associated with the one or more patient members, apply a filtering function to generate a reference space, generate a cover of the reference space based on a resolution, the cover including cover data associated with the filtered biological data, cluster the cover data based on a metric, and display the groupings and the interconnections based on the clusters.

5. The system of claim 4 wherein the filtering function is a density estimation function.

6. The system of claim 4 wherein the metric is a Pearson correlation.

7. The system of claim 1 wherein the location engine configured to determine whether the new patient shares the biological similarities with the one or more patient members of each grouping comprises the patient location engine configured to determine a distance between biological data of each patient member and new biological data of the new patient, compare distances between the patient members of each grouping and the distances determined for the new patient, and determine a location of the new patient relative to at least one of the member patients.

8. The system of claim 7 wherein the location engine is further configured to compare distances to one or more of the patient members closest to the new patient'"'"'s filtered biological data with a diameter of at least one grouping and to indicate that the new patient is associated with the grouping based on the comparison.

9. The system of claim 7 wherein the location engine is further configured to determine if the distance to one or more of the patient members closest to the new patient'"'"'s filtered biological data is greater than a diameter of each grouping and to indicate that the new patient is not associated with each grouping based on the comparison.

10. The system of claim 1 wherein the medical characteristic comprises a clinical outcome.

11. A method comprising:

receiving biological data of a new patient;

determining distances between biological data of patient members of a map and new biological data from the new patient, the map including a plurality of groupings and interconnections of the groupings, each grouping having one or more of the patient members that share biological similarities, each interconnection interconnecting groupings that share at least one common patient member, the map identifying a set of groupings and a set of interconnections having a medical characteristic of a set of medical characteristics;

comparing distances between the one or more patient members and the distances determined for the new patient; and

determining a location of the new patient relative to the member patients of the map based on the comparison, thereby enabling association of the new patient with one or more of the set of medical characteristics.

12. The method of claim 11 wherein the biological similarities represent similarities of measurements of gene expressions.

13. The method of claim 11 wherein the biological similarities represent similarities of sequencing.

14. The method of claim 11 further comprising:

receiving biological data associated with the one or more patient members;

applying a filtering function to generate a reference space, generate a cover of the reference space based on a resolution, the cover including cover data associated with the filtered biological data;

clustering the cover data based on a metric; and

displaying the groupings and the interconnections based on the clusters.

15. The method of claim 14 wherein the filtering function is a density estimation function.

16. The method of claim 14 wherein the metric is a Pearson correlation.

17. The method of claim 14 further comprising comparing distances to one or more of the patient members closest to the new patient'"'"'s filtered biological data with a diameter of at least one grouping and indicating that the new patient is associated with the grouping based on the comparison.

18. The method of claim 14 further comprising determining if the distance to one or more of the patient members closest to the new patient'"'"'s filtered biological data is greater than a diameter of each grouping and indicating that the new patient is not associated with each grouping based on the comparison.

19. The method of claim 11 wherein the medical characteristic comprises a clinical outcome.

20. A computer readable medium comprising instructions, the instructions being executable by a processor to perform a method, the method comprising:

receiving biological data of a new patient;

determining distances between biological data of patient members of a map and new biological data from the new patient, the map including a plurality of groupings and interconnections of the groupings, each grouping having one or more of the patient members that share biological similarities, each interconnection interconnecting groupings that share at least one common patient member, the map identifying a set of groupings and a set of interconnections having a medical characteristic of a set of medical characteristics;

comparing distances between the one or more patient members and the distances determined for the new patient; and

determining a location of the new patient relative to the member patients of the map based on the comparison, thereby enabling association of the new patient with one or more of the set of medical characteristics.