Dental data mining

• US 7,987,099 B2
• Filed: 02/27/2004
• Issued: 07/26/2011
• Est. Priority Date: 02/27/2004
• Status: Active Grant

• Current Assignee: Align Technology Incorporated
• Original Assignee: Align Technology Incorporated
• Inventors: De Smedt, Philippe, Nguyen, Cuong Van, Overton, Christopher W, Kuo, Eric E.
• Primary Examiner(s): Gilligan; Luke
• Assistant Examiner(s): SEREBOFF, NEAL
• Application Number:
  US10/788,635
• Publication Number:
  US 20050192835A1
• Time in Patent Office: 2,706 Days
• Field of Search: 705 1- 3, 433/3, 433/6, 433/24, 433/26, 703/1, 707/7
• US Class Current: 705/2
• CPC Class Codes: A61C 7/002 Orthodontic computer assisted systems
• CPC Class Codes: A61C 7/08 Mouthpiece-type retainers or positioners, e.g. for both the lower and upper arch arch-shaped medicament applicators for teeth or gums A61C19/063; mouthguards for protecting the teeth of sportsmen A63B71/085
• CPC Class Codes: B33Y 50/00 Data acquisition or data processing for additive manufacturing
• CPC Class Codes: B33Y 80/00 Products made by additive manufacturing
• CPC Class Codes: G06F 2216/03 Data mining
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Systems and methods are disclosed providing a database comprising a compendium of at least one of patient treatment history; orthodontic therapies, orthodontic information and diagnostics; employing a data mining technique for interrogating said database for generating an output data stream, the output data stream correlating a patient malocclusion with an orthodontic treatment; and applying the output data stream to improve a dental appliance or a dental appliance usage.

Claims

1. A computer implemented method, comprising:

storing in a database data related to each of a plurality of dental patient treatment histories, each including;

an initial data set representing teeth of each dental patient prior to treatment;

an intended dental treatment outcome data set for each dental patient; and

an actual dental treatment outcome data set for each dental patient;

a computer clustering the data into clusters based on at least one of a number of parameters including initial physical dental condition, initial diagnoses, dental treatment parameters, intended dental treatment outcomes, actual dental treatment outcomes, appliance design, manufacturing protocol, clinician, clinician geography, clinician training, size and nature of clinician'"'"'s practice, and patient demographics;

the computer modeling discrepancies between the intended dental treatment outcome data sets and the actual dental treatment outcome data sets within a particular cluster;

the computer correlating the modeled discrepancies to one or more of treatment approach, appliance design, and manufacturing protocol within the particular cluster; and

the computer providing the correlation as feedback for optimizing the one or more of initial physical dental condition, initial diagnoses, dental treatment parameters, intended dental treatment outcomes, actual dental treatment outcomes, appliance design, manufacturing protocol, clinician, clinician geography, clinician training, size and nature of clinician'"'"'s practice, and patient demographics.

2. The method of claim 1, further comprising the computer generating one or more data sets associated with one or more parameters of a plurality of appliances having geometries selected to progressively reposition the teeth, wherein the appliances comprise polymeric shells having cavities and wherein the cavities of successive shells have different geometries shaped to receive and resiliently reposition teeth from one arrangement to a successive arrangement.

3. The method of claim 2, wherein the plurality of appliances includes a sequence of configurations of braces, the braces including brackets and archwires.

4. The method of claim 2, wherein the plurality of appliances includes a sequence of polymeric shells manufactured by fitting polymeric sheets over positive models corresponding to the teeth of the new patient.

5. The method of claim 2, wherein the plurality of appliances includes a sequence of polymeric shells manufactured from digital models.

6. The method of claim 2, wherein one of the plurality of appliances is a positioner for finishing and maintaining teeth positions.

7. The method of claim 2, further comprising:

the computer comparing an actual effect of the plurality of appliances with an intended effect of the plurality of appliances; and

the computer identifying one of the plurality of appliances as an unsatisfactory appliance if the actual effect of one of the plurality of the appliances is more than a threshold different from the intended effect of the plurality of appliances.

8. The method of claim 1, further comprising the computer capturing at least an initial tooth position, a target tooth position;

and one or more intermediate tooth positions.

9. The method of claim 1, further comprising the computer analyzing one of a plurality of intermediate tooth positions with a target position.

10. The method of claim 1, further comprising the computer capturing one or more characteristics data tags associated with a patient case to label captured data.

11. The method of claim 10, further comprising the computer aggregating data of a set of treatments based on the data tags and rating at least one of a plurality of the set of treatments based on the aggregated data.

12. The method of claim 11, further comprising the computer comparing performance of a plurality of sets of treatments.

13. The method of claim 1, further comprising the computer applying a predetermined treatment model to calculate risk of treatment complication.

14. The method of claim 13, further comprising the computer identifying a treatment case for special treatment parameters including clinical constraint.

15. The method of claim 13, further comprising the computer clusterizing a plurality of clinical practitioners based on one or more practice habits.

16. The method of claim 15, wherein treatment parameters are adapted to preferences specific to each cluster.

17. The method of claim 1, further comprising the computer applying a probabilistic model to detect one or more discrepancies between a target and an actual tooth position at one or more stages in the treatment.

18. The method of claim 1, wherein clustering is iteratively performed, and each iteration of clustering includes updating the detected one or more patterns.

19. The method of claim 1, where the method includes the computer setting a flag for solicitation of treatment differences by a particular clinician who achieved better treatment outcomes relative to other correlated clinicians within the particular cluster.

20. The method of claim 1, where the method includes the computer detecting differences in treatment preferences of one or more clinicians by statistical observation of associated treatment histories.

21. The method of claim 20, where clustering data includes the computer clustering based on one or more parameters relating to the one or more clinicians including geographical location, training variables, size of practice, and nature of practice.

22. The method of claim 1, where the method includes the computer modeling risk for undesirable dental treatment outcomes within the particular cluster based at least in part on the modeled discrepancies within each cluster.

23. The method of claim 22, wherein clustering includes iteratively detecting the one or more patterns and updating the modeled risk based on each iteratively detected one or more patterns.

24. The method of claim 22, where the method includes the computer:

assigning a new patient to the particular cluster prior to treatment based at least in part on a similarity between a value of at least one of the number of parameters for the particular cluster and a corresponding value of the at least one parameter for the new patient; and

predicting a dental treatment outcome for the new patient based at least in part on the modeled risk and modeled discrepancies within each cluster.

25. The method of claim 24, wherein the similarity between the value of at least one of the number of parameters for the particular cluster and the corresponding value of the at least one parameter for the new patient is related to one or more clinical constraints.

26. The method of claim 25, wherein the one or more clinical constraints includes one or more of a maximum rate of displacement of a tooth, a maximum force on a tooth, a desired end position of a tooth, or one or more combinations thereof.

27. The method of claim 26, wherein the maximum force is a linear force or a torsional force.

28. The method of claim 26, wherein the maximum rate of displacement is a linear or an angular rate of displacement.

29. The method of claim 24, where the method includes the computer providing a dental treatment plan for the new patient to reach a particular intended dental treatment outcome based at least in part on the particular cluster and the modeled discrepancies for the particular cluster.

30. The method of claim 29, where the computer providing the dental treatment plan includes one or more of providing a dental appliance design, providing a dental appliance manufacturing protocol, and providing a treatment approach for dental appliance usage.

31. The method of claim 1, wherein the method includes providing the feedback to a clinician for use with respect to a new patient.

32. An apparatus, comprising:

one or more processors;

a database including stored information related to a plurality of patient treatment histories, each including;

an initial data set representing teeth of each dental patient prior to treatment;

an intended dental treatment outcome data set for each dental patient; and

an actual dental treatment outcome data set for each dental patient; and

a memory for storing instructions which, when executed by the one or more processors, causes the one or more processors to;

access information from the database;

perform a clustering operation on the accessed information from the database to cluster the information into clusters based on at least one of a number of parameters includini initial physical dental condition, initial diagnoses, dental treatment parameters, intended dental treatment outcomes, actual dental treatment outcomes, appliance design, manufacturing protocol, clinician, clinician geography, clinician training, size and nature of clinician'"'"'s practice, and patient demographics;

model discrepancies between the intended dental treatment outcome data sets and the actual dental treatment outcome data sets within a particular cluster;

correlate the modeled discrepancies to one or more of treatment approach, appliance design, and manufacturing protocol within the particular cluster; and

provide the correlation as feedback for optimizing the one or more of initial physical dental condition, initial diagnoses, treatment approach, intended dental treatment outcomes, actual dental treatment outcomes, appliance design, manufacturing protocol, clinician, clinician geography, clinician training, size and nature of clinician'"'"'s practice, and patient demographics.

33. The apparatus of claim 32 including a display device operatively coupled to the one or more processors, wherein the memory for storing instructions, which, when executed by the one or more processors, causes the one or more processors to display the accessed information on the display device.