Method and system for providing dynamic orthodontic assessment and treatment profiles

1. A computer-implemented method for designing orthodontic appliances to treat a patient's teeth, the method comprising:

receiving digital data representing a scan of an initial arrangement of the patient's teeth;

customizing a treatment plan using a treatment planning learning algorithm, the treatment plan comprising one or more paths for moving the patient's teeth from the initial arrangement towards a final arrangement, wherein the treatment planning learning algorithm is trained on a database of previous treatment outcome data, the previous treatment outcome data including achieved and goal tooth movement data, and wherein the one or more paths are determined based on deviations between goal tooth movements and achieved tooth movements obtained from the database of the previous treatment outcome data;

determining, using the treatment planning learning algorithm, tooth surface geometries of one or more of the patient's teeth at a plurality of phases of the treatment plan; and

determining, using the treatment planning learning algorithm, appliance surface geometries of a plurality of polymeric orthodontic appliances for the plurality of phases of the treatment plan, the appliance surface geometries being associated with the tooth surface geometries for each of the plurality of phases of the determined treatment plan.

2. The method of claim 1 , wherein the treatment planning learning learning algorithm implements one or more of: a parametric statistical model, a non-parametric statistical model, a clustering model, a nearest neighbor model, a regression method, a neural network, a Hidden Markov Model, a dynamic programming model, a fuzzy logic model, or a template matcher model.

3. The method of claim 1 , wherein the previous treatment outcome data comprises performance data indicative of goal tooth movements and achieved tooth movements with one or more appliances.

4. The method of claim 1 , wherein the previous treatment outcome data comprises data indicative of predictability of a plurality of different tooth movement types.

5. The method of claim 1 , wherein the treatment planning learning algorithm is trained on the database of the previous treatment outcome data in order to detect a plurality of treatment patterns in the previous treatment outcome data, and wherein the treatment planning learning algorithm classifies the digital data into at least one of the plurality of treatment patterns.

6. The method of claim 1 , wherein the treatment planning learning algorithm is trained on the database of the previous treatment outcome data in order to detect a plurality of case clusters in the previous treatment outcome data, and wherein the treatment planning learning algorithm classifies the digital data into at least one of the plurality of case clusters.

7. The method of claim 6 , wherein the plurality of case clusters are detected based on one or more of: follow-up data, diagnosis, treatment parameters, treatment outcomes, or demographic variables.

8. The method of claim 6 , wherein the treatment plan is determined based on the classification of the digital data into the at least one of the plurality of case clusters.

9. The method of claim 1 , wherein the digital data comprises one or more of: scan data, X-ray data, Cone Beam Computed Tomography (CBCT) data, tomographic imaging data, sonographic imaging data, or wax bite data.

10. The method of claim 1 , further comprising generating data for manufacturing the plurality of polymeric orthodontic appliances having the determined geometries.

11. A system for designing orthodontic appliances to treat a patient's teeth, the system comprising:

one or more processors; and

memory comprising instructions that, when executed by the one or more processors, cause the system to:

receive digital data representing a scan of an initial arrangement of the patient's teeth;

customize a treatment plan using a treatment planning learning algorithm, the treatment plan comprising one or more paths for moving the patient's teeth from the initial arrangement towards a final arrangement, wherein the treatment planning learning algorithm is trained on a database of previous treatment outcome data, the previous treatment outcome data including achieved and goal tooth movement data, and wherein the one or more paths are determined based on deviations between goal tooth movements and achieved tooth movements obtained from the database of previous treatment outcome data;

determine, using the treatment planning learning algorithm, tooth surface geometries of one or more of the patient's teeth at a plurality of phases of the treatment plan; and

determine, using the treatment planning learning algorithm, appliance surface geometries of a plurality of polymeric orthodontic appliances for the plurality of phases of the treatment plan, the appliance surface geometries being associated with the tooth surface geometries for each of the plurality of phases of the determined treatment plan.

12. The system of claim 11 , wherein the treatment planning learning algorithm implements one or more of: a parametric statistical model, a non-parametric statistical model, a clustering model, a nearest neighbor model, a regression system, a neural network, a Hidden Markov Model, a dynamic programming model, a fuzzy logic model, or a template matcher model.

13. The system of claim 11 , wherein the previous treatment outcome data comprises performance data indicative of goal tooth movements and achieved tooth movements with one or more appliances.

14. The system of claim 11 , wherein the previous treatment outcome data comprises data indicative of predictability of a plurality of different tooth movement types.

15. The system of claim 11 , wherein the treatment planning learning algorithm is trained on the database of the previous treatment outcome data in order to detect a plurality of treatment patterns in the previous treatment outcome data, and wherein the treatment planning learning algorithm classifies the digital data into at least one of the plurality of treatment patterns.

16. The system of claim 11 , wherein the treatment planning learning algorithm is trained on the database of the previous treatment outcome data in order to detect a plurality of case clusters in the previous treatment outcome data, and wherein the treatment planning learning algorithm classifies the digital data into at least one of the plurality of case clusters.

17. The system of claim 16 , wherein the plurality of case clusters are detected based on one or more of: follow-up data, diagnosis, treatment parameters, treatment outcomes, or demographic variables.

18. The system of claim 16 , wherein the treatment plan is determined based on the classification of the digital data into the at least one of the plurality of case clusters.

19. The system of claim 11 , wherein the digital data comprises one or more of: scan data, X-ray data, Cone Beam Computed Tomography (CBCT) data, tomographic imaging data, sonographic imaging data, or wax bite data.

20. The system of claim 11 , wherein the instructions further cause the system to generate data for manufacturing the plurality of orthodontic polymeric appliances having the determined geometries.