System and method for analyzing medical data to determine diagnosis and treatment

• US 20090083075A1
• Filed: 10/06/2008
• Published: 03/26/2009
• Est. Priority Date: 09/02/2004
• Status: Abandoned Application

• Current Assignee: Cornell University
• Original Assignee: Cornell University
• Inventors: Reeves, Anthony P., Yankelevitz, David F., Henschke, Claudia Ingrid
• Application Number:
  US12/245,888
• Publication Number:
  US 20090083075A1
• Time in Patent Office: Days
• US Class Current: 705/3
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system and method for generating an action plan for diagnosis and treatment of a patient. In particular, a historical database is complied which includes a plurality of records. Each record includes a personal profile and diagnosis data for a person. A plurality of characterizations and corresponding weighting coefficients are derived based on the records in the historical database. Pre-diagnostic patient profile data for a selected patient is obtained for the selected patient. One or more computing modules generate output data for the selected patient as a function of (i) the pre-diagnostic patient profile data, along with the physician'"'"'s modifications, if any and (ii) the plurality of characterizations and corresponding weighting coefficients. The output data includes at least one of a diagnostic action plan, a confirmation action plan, a confirmation patient profile data and a therapeutic action plan. is

Claims

1. A method, comprising:

compiling a historical database including a plurality of records based on a sample group of patients, each record including a personal profile and diagnosis data for one of the sample group of patients;

deriving a plurality of characterizations and corresponding weighting coefficients based on the plurality of records in the historical database;

obtaining pre-diagnostic patient profile data for a selected patient wherein the pre-diagnostic patient profile data comprises medical imaging data;

generating, with at least one computing module, output data as a function of (i) the pre-diagnostic patient profile data and (ii) the plurality of characterizations and corresponding weighting coefficients, the output data comprising at least one of a preliminary diagnostic data, a confirmation action plan, a confirmation patient profile is data and a therapeutic action plan, where the at least one computing module includes a computer architecture;

updating the historical database to add the pre-diagnostic patient profile data and the output data; and

updating the at least one computing module by adaptively adjusting a set of internal parameters and modifying the computer architecture of the at least one computing module based on field use experience that highlights where the at least one computing module makes errors.

2. The method according to claim 1, further comprising:

repeating the deriving step based on the records in the updated historical database to generate an updated plurality of characterizations and weighting coefficients.

3. The method according to claim 1, wherein the characterizations comprise at least one of patient'"'"'s height, weight, size of a nodule, a location of the nodule, demographics data and physical data.

4. The method according to claim 1, wherein the medical imaging data is generated by performing at least one of Computerized Tomography scan, Magnetic Resonance Imaging, Positron Emission Technology, X-Rays, Vascular Interventional and Angiogram/Angiography procedures, ultrasound imaging, radiographs, optical imaging, pathological imaging, molecular imaging and medical genetic imaging.

5. The method according to claim 1, wherein the computing module comprises at least one of a programmable data processor, an adaptive processor, an adaptive self-learning error correction system, an automated recognition system and a neural network.

6. The method according to claim 1, wherein the personal profile comprises at least one of patient'"'"'s symptoms, family history, state of health, chronic diseases, allergies, illnesses and lifestyle information correlated to patient'"'"'s diagnosis data.

7. The method according to claim 6, wherein the diagnosis data comprises at least one of a patient diagnosis, a suggested diagnosis plan, an actualized diagnostic plan, a treatment plan, an actual treatment plan and information utilized for diagnosis and treatment of the patient.

8. The method according to claim 1, wherein generating output data comprises:

(a) generating, using a diagnostic computing module, the preliminary diagnostic data as a function of (i) the pre-diagnostic patient profile data and (ii) the plurality of characterizations and weighting coefficients.

9. The method according to claim 8, wherein generating output data further comprises:

(b) providing the pre-diagnostic patient profile data to a physician for adjustment;

(c) adjusting the pre-diagnostic patent profile data to produce adjusted pre-diagnostic patient profile data;

(d) obtaining the adjusted pre-diagnostic patient profile data from the physician; and

(e) repeating the sub-step (a), to generate further preliminary diagnostic data as a function of (i) the adjusted pre-diagnostic patient profile data and (ii) the plurality of characterizations and weighting coefficients.

10. The method according to claim 1, wherein generating output data further comprises:

(a) generating, using a confirmation computing module, the confirmation action plan as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients.

12. The method according to claim 1, wherein generating output data further comprises:

(a) obtaining the confirmation patient profile data from the patient based on the confirmation action plan.

13. The method according to claim 12, wherein generating output data further comprises:

(b) providing the confirmation action plan to the physician for adjustment;

(c) adjusting the confirmation action plan to produce an adjusted confirmation action plan;

(d) obtaining the adjusted confirmation action plan from the physician; and

(e) obtaining the confirmation patient profile data from the patient according to the adjusted confirmation action plan.

14. The method according to claim 1, wherein generating output data further comprises:

(a) generating, using a treatment computing module, the therapeutic action plan as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnosis data, (iii) the confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.

15. The method according to claim 14, wherein generating output data further comprises:

(b) providing the pre-diagnostic patient profile data, the preliminary diagnostic data, and the confirmation patient profile data to the physician for adjustment;

(c) adjusting the pre-diagnostic patient profile data, the preliminary diagnostic data, and the confirmation patient profile data to produce adjusted pre-diagnostic patient profile data, adjusted preliminary diagnostic data, and adjusted confirmation patient profile data;

(d) obtaining at least one of (i) the adjusted pre-diagnostic patient profile data, (ii) the adjusted preliminary diagnostic data and (iii) the adjusted confirmation patient profile data from the physician; and

(e) repeating the sub-step (a) to generate a further therapeutic action plan as a function of at least one of (i) the adjusted pre-diagnostic patient profiled data, (ii) the adjusted preliminary diagnostic data, (iii) the adjusted confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.

16. The method according to claim 1, wherein generating output data further comprises:

(a) generating, using a diagnostic computing module, the preliminary diagnostic data as a function of (i) the pre-diagnostic patient profile data and (ii) the plurality of characterizations and weighting coefficients;

(b) generating, using a confirmation computing module, the confirmation action plan as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients;

(c) obtaining the confirmation patient profile data from the patient based on the confirmation action plan; and

(d) generating, using a treatment computing module, the therapeutic action plan as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnosis data, (iii) the confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.

11. The method according to claim 11, wherein generating output data further comprises:

(b) providing the pre-diagnostic patient profile data and the preliminary diagnostic data to the physician for adjustment;

(c) adjusting the pre-diagnostic patent profile data to produce adjusted pre-diagnostic patient profile data;

(d) adjusting the preliminary diagnostic data to produce adjusted preliminary diagnostic data;

(e) obtaining at least one of (i) the adjusted pre-diagnostic patient profile data and (ii) the adjusted preliminary diagnostic data from the physician; and

(f) repeating the sub-step (a) to generate a further confirmation action plan as a function of at least one of (i) the adjusted pre-diagnostic patient profiled data, (ii) the adjusted preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients.

17. A system, comprising:

a historical database adapted to compile a plurality of records based on a sample group of patients, each record including a personal profile and diagnosis data for one of the sample group of patients; and

at least one computing module adapted to generate output data for a selected patient as a function of (i) the pre-diagnostic patient profile data and (ii) a plurality of characterizations and corresponding weighting coefficients, the output data including at least one of a preliminary diagnostic data, a confirmation action plan, a confirmation patient profile data and a therapeutic action plan, wherein the plurality of characterizations and corresponding weighting coefficients are derived based on the records in the historical database, and wherein the historical database is updated to add the pre-diagnostic patient profile data and the output data, and wherein the at least one computing module is continuously updated by adaptively adjusting a set of internal parameters and modifying the computer architecture of the at least one computing module based on field use experience that highlights where the at least one computing module makes errors.

18. The system according to claim 17, wherein the plurality of characterizations and weighting coefficients are derived based on the records in the updated historical database.

19. The system according to claim 17, wherein the plurality of characterizations comprise at least one of the patient'"'"'s height, weight, size of a nodule, a location of the nodule, demographics data and physical data.

20. The system according to claim 17, wherein the pre-diagnostic patient profile data comprises medical imaging data.

21. The system according to claim 20, wherein the medical imaging data is generated by performing at least one of Computerized Tomography scan, Magnetic Resonance Imaging, Positron Emission Technology, X-Rays, Vascular Interventional and Angiogram/Angiography procedures, ultrasound imaging, radiographs, optical imaging, pathological imaging, molecular imaging and medical genetic imaging.

22. The system according to claim 17, wherein the computing module comprises at least one of a programmable data processor, an adaptive processor, an adaptive self-learning error correction system, an automated recognition system and a neural network.

23. The system according to claim 17, wherein the personal profile data comprises at least one of patient'"'"'s symptoms, family history, state of health, chronic diseases, allergies, illnesses and lifestyle information correlated to patient'"'"'s diagnosis data.

24. The system according to claim 17, wherein the diagnosis data comprises at least one of a patient diagnose, a suggested diagnosis plan, an actualized diagnostic plan, a treatment plan, an actual treatment plan and information utilized for diagnosis and treatment of the patient.

25. The system according to claim 18, wherein the preliminary diagnostic data of the output data is generated using a diagnostic computing module of the at least one computing module as a function of (i) the pre-diagnostic patient profile data and (ii) the plurality of characterizations and corresponding weighting coefficients.

26. The system according to claim 27, wherein the pre-diagnostic patient profile data is adjusted by a physician to produce adjusted pre-diagnostic patient profile data;

and wherein the preliminary diagnostic data is further generated as a function of (i) the adjusted pre-diagnostic patient profile data and (ii) the plurality of characterizations and weighting coefficients.

27. The system according to claim 17, wherein the confirmation action plan of the output data is generated using a confirmation computing module of the at least one computing module as a function of at least one of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnostic data and (iii) the plurality of characterizations and corresponding weighting coefficients.

28. The system according to claim 27, wherein at least one of (i) the pre-diagnostic patient profile data and (ii) the preliminary diagnostic data is adjusted by a physician to produce at least one of (i) adjusted pre-diagnostic patient profile data and (ii) adjusted preliminary diagnostic data;

and wherein the confirmation action plan is further generated as a function of at least one of (i) the adjusted pre-diagnostic patient profiled data, (ii) the adjusted preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients.

29. The system according to claim 17, wherein the confirmation patient profile data is collected from the patient based on the confirmation action plan.

30. The system according to claim 29, wherein the confirmation action plan is adjusted by a physician to produce an adjusted confirmation action plan;

and wherein an updated confirmation patient profile is collected from the patient according to the adjusted confirmation action plan.

31. The system according to claim 17, wherein the therapeutic action plan of the output data is generated using a treatment computing module of the at least one computing module as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnosis data, (iii) the confirmation patient profile data and (iv) the plurality of characterizations and corresponding weighting coefficients.

32. The system according to claim 31, wherein at least one of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnostic data and (iii) the confirmation patient profile data is adjusted by a physician to produce at least one of (i) adjusted pre-diagnostic patient profiled data, (ii) adjusted preliminary diagnostic data, and (iii) adjusted confirmation patient profile data;

and wherein the therapeutic action plan is further generated as a function of at least one of (i) the adjusted pre-diagnostic patient profiled data, (ii) the adjusted preliminary diagnostic data, (iii) the adjusted confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.

33. The system according to claim 17, wherein the preliminary diagnostic data of the output data is generated using a diagnostic computing module of the at least one computing module as a function of (i) the pre-diagnostic patient profile data and (ii) the plurality of characterizations and corresponding weighting coefficients;

wherein the confirmation action plan of the output data is generated using a confirmation computing module of the at least one computing module as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients;

wherein the confirmation patient profile data is collected from the patient based on the confirmation action plan; and

wherein the therapeutic action plan of the output data is generated using a treatment computing module of the at least one computing module as a function of (i) the pre-diagnostic patient profile data, (ii) the preliminary diagnosis data, (iii) the confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.

34. The system according to claim 33, wherein the pre-diagnostic patient profile is adjusted by a physician to produce adjusted pre-diagnostic patient profile data;

wherein the preliminary diagnostic data of the output data is further generated using a diagnostic computing module as a function of at least one of (i) the adjusted pre-diagnostic patient profile data and (ii) the plurality of characterizations and weighting coefficients;

wherein the preliminary diagnostic data is adjusted by the physician to produce adjusted preliminary diagnostic data;

wherein the confirmation action plan of the output data is further generated using the confirmation action plan as a function of at least one of (i) the adjusted pre-diagnostic patient profile data, (ii) the adjusted preliminary diagnostic data and (iii) the plurality of characterizations and weighting coefficients;

wherein the confirmation action plan is adjusted by the physician to produce an adjusted confirmation action plan;

wherein the confirmation patient profile data is further collected from the patient based on the adjusted confirmation action plan; and

wherein the confirmation patient profile data is adjusted by the physician to produce adjusted confirmation patient profile data;

wherein the therapeutic action plan of the output data is further generated using a treatment computing module as a function of at least one of (i) the adjusted pre-diagnostic patient profile data, (ii) the adjusted preliminary diagnosis data, (iii) the adjusted confirmation patient profile data and (iv) the plurality of characterizations and weighting coefficients.