Systems and methods for predicting medical conditions usingmachine learning correlating dental images and medical data
View Patent ↗Embodiments of the present disclosure may include a system for associating dental and medical data the system including a processor. Embodiments may also include a memory containing instructions that instruct the processor to receive dental data including a plurality of dental images representative of at least a surface of dental tissue of a patient. Embodiments may also include receive medical data representative of the patient. Embodiments may also include generate training data as a function of a correlation between the dental data and the medical data. Embodiments may also include input the training data into a machine learning algorithm. Embodiments may also include train a machine learning model as a function of the training data and the machine learning algorithm.
1. A system for associating dental and medical data the system comprising:
a processor; and
a memory containing instructions that instruct the processor to:
receive dental data comprising a plurality of dental images representative of at least a surface of dental tissue of a patient;
receive medical data representative of a non-dental medical condition and associated with the patient from an electronic health record (EHR) from hospital;
generate training data as a function of a correlation between the plurality of dental images and the medical data representative of the non-dental medical condition;
input the training data into a machine learning algorithm; and
train a machine learning model to predict the non-dental medical condition using dental images, as a function of the training data and the machine learning algorithm.
2. The system of claim 1 , wherein the dental tissue comprises one or more of dental hard tissue and dental soft tissue.
3. The system of claim 1 , wherein the dental images comprise at least a two-dimensional digital color image representing the at least a surface of the dental tissue.
4. The system of claim 3 , wherein the dental images additionally comprise at least a three-dimensional image representing the at least a surface of the dental tissue.
5. The system of claim 1 , wherein the non-dental medical data comprises ECG data.
6. The system of claim 1 , wherein the memory contains further instructions that instruct the processor to:
pre-process the dental images; and
wherein generating the training data is performed as a function of a correlation between the pre-processed dental images and the medical data.
7. The system of claim 6 , wherein pre-processing the dental images comprising inputting the dental images into a pre-processing machine learning model; and
pre-processing the dental images as a function of the pre-processing machine learning model and the dental images.
8. The system of claim 7 , wherein the pre-processing machine learning model comprises a transformer-based machine learning model.
9. The system of claim 6 , wherein the pre-processing machine learning model comprises a 3D reconstruction model, wherein the 3D reconstruction model is context-aware; and
pre-processing the dental images further comprises:
inputting, into the 3D reconstruction model, at least a two-dimensional digital color image representing the at least a surface of the dental tissue; and
outputting, from the 3D reconstruction model, at least a three-dimensional image comprising a mesh image and representing the at least a surface of the dental tissue as a function of the 3D reconstruction model and the at least a two-dimensional digital color image representing the at least a surface of the dental tissue.
10. The system of claim 9 , wherein the dental data further comprises location data associated with the relative location of the at least a two-dimensional digital color image; and
pre-processing the dental images further comprises:
inputting, into the 3D reconstruction model, the at least a two-dimensional digital color image representing the at least a surface of the dental tissue and the location data; and
outputting, from the 3D reconstruction model, at least a three-dimensional image representing the at least a surface of the dental tissue as a function of the 3D reconstruction model, the at least a two-dimensional digital color image representing the at least a surface of the dental tissue, and the location data.
11. A method of associating dental and medical data the method comprising:
receiving, using a computing device, dental data comprising a plurality of dental images representative of at least a surface of dental tissue of a patient;
receiving, using the computing device, medical data representative of a non-dental medical condition and associated with the patient from an electronic health record (EHR) from a hospital;
generating, using the computing device, training data as a function of a correlation between the plurality of dental images and the medical data representative of the non-dental medical condition;
inputting, using the computing device, the training data into a machine learning algorithm; and
training, using the computing device, a machine learning model to predict the non-dental medical condition using dental images, as a function of the training data and the machine learning algorithm.
12. The method of claim 11 , wherein the dental tissue comprises one or more of dental hard tissue and dental soft tissue.
13. The method of claim 11 , wherein the dental images comprise at least a two-dimensional digital color image representing the at least a surface of the dental tissue.
14. The method of claim 13 , wherein the dental images additionally comprise at least a three-dimensional image representing the at least a surface of the dental tissue.
15. The method of claim 11 , wherein the non-dental medical data comprises ECG data.
16. The method of claim 11 , further comprising pre-processing, using the computing device, the dental images; and
wherein generating the training data is performed as a function of a correlation between the pre-processed dental images and the medical data.
17. The method of claim 16 , wherein pre-processing the dental images comprises inputting the dental images into a pre-processing machine learning model; and
pre-processing the dental images as a function of the pre-processing machine learning model and the dental images.
18. The method of claim 17 , wherein the pre-processing machine learning model comprises transformer-based machine learning model.
19. The method of claim 16 , wherein the pre-processing machine learning model comprises a 3D reconstruction model; and
pre-processing the dental images further comprises:
inputting, into the 3D reconstruction model, at least a two-dimensional digital color image representing the at least a surface of the dental tissue, wherein the 3d reconstruction model is context-aware; and
outputting, from the 3D reconstruction model, at least a three-dimensional image comprising a mesh image and representing the at least a surface of the dental tissue as a function of the 3D reconstruction model and the at least a two-dimensional digital color image representing the at least a surface of the dental tissue.
20. The method of claim 19 , wherein the dental data further comprises location data associated with the relative location of the at least a two-dimensional digital color image; and
pre-processing the dental images further comprises:
inputting, into the 3D reconstruction model, the at least a two-dimensional digital color image representing the at least a surface of the dental tissue and the location data; and
outputting, from the 3D reconstruction model, at least a three-dimensional image representing the at least a surface of the dental tissue as a function of the 3D reconstruction model, the at least a two-dimensional digital color image representing the at least a surface of the dental tissue, and the location data.