Artificial intelligence system for determining clinical values through medical imaging
Systems and methods for establishing a patient's current or future clinical or lab values are provided. A neural network is trained on a dataset of medical images, such as ultrasound images, that are tagged with information concerning the lab values of people who were imaged to produce the medical images. The trained neural network can then be provided with medical images of a patient, and the neural network can then make a determination as to the patient's current or future clinical or lab values.
1. A system configured to make a medical determination, the system comprising:
an image storage configured to store non-invasive images of a body part of a patient,
the non-invasive images previously acquired via process that does not require cutting or puncturing the patient's skin;
image analysis logic comprising a trained neural network in communication with the image storage and configured to provide a determination regarding a clinical or lab value of the patient, the determination based on the stored non-invasive images and additionally based on a clinical data set;
a user interface configured to provide the determination to a user; and
a processor configured to execute at least the image analysis logic.
2. The system of claim 1 wherein the image analysis logic includes first logic configured to analyze the stored non-invasive images to determine a present clinical or lab value at the time the stored images were acquired.
3. The system of claim 1 wherein the image analysis logic includes second logic configured to determine a future clinical or lab value within a timeframe.
4. The system of claim 1 wherein the image analysis logic is configured to employ a regression algorithm to provide the determination as a range.
5. The system of claim 1 wherein the image analysis logic is configured to employ a classification algorithm to provide the determination as one of a plurality of categories.
6. The system of claim 1 wherein the image analysis logic is further configured to provide the determination based additionally on a clinical data set.
7. The system of claim 1 further comprising an image generator configured to acquire images, some of the images becoming the stored non-invasive images.
8. The system of claim 7 further comprising feedback logic configured to provide guidance to a user of the image generator in acquiring the stored non-invasive images.
9. The method of claim 8 wherein the feedback logic further processes the determination based on the stored non-invasive images and the clinical data set, as provided by the trained neural network, to provide the guidance to the user to acquire additional non-invasive images.
10. The method of claim 8 wherein the guidance depends on a quality of the determination based on the stored non-invasive images and the clinical data set.
11. The method of claim 8 wherein the guidance comprises instructing the user to obtain non-invasive images of specific portions of the patient's anatomy.
12. The system of claim 3 wherein the second logic is configured to determine the future clinical or future lab value that depends on a probability that the medical determination will occur within a future timeframe based on analysis of the stored non-invasive images.
13. The method of claim 1 wherein the guidance depends on a quality of the quantitative determination and/or a classification of non-invasive images already acquired.
14. The method of claim 1 wherein the guidance informs the user that additional non-invasive images can be expected to improve accuracy of the determination regarding a clinical or lab value of the patient.
15. A method for training a neural network to make a medical determination, the method comprising:
receiving a set of non-invasive images of body parts of a plurality of patients, the non-invasive images tagged with information concerning the current or future lab values, the non-invasive images having been previously generated without puncturing or cutting the patient's skin;
dividing the set of non-invasive images into a training set and a validation set;
providing the images of the training set, and their tags, to a neural network to train the neural network to determine a current or future, lab or clinical, quantitative values based on the non-invasive images of the body parts; and
providing images of a single patient from the validation set to the neural network to make the medical determination, and comparing the medical determination to the tag associated with the non-invasive images.
16. The method of claim 15 wherein the non-invasive images are ultrasound images.
17. The method of claim 15 further comprising classifying the non-invasive images before providing the images of the training set to the neural network.
18. The method of claim 15 further comprising resizing the non-invasive images before providing the images of the training set to the neural network.
19. The method of claim 15 wherein the neural network is configured to determine future clinical quantitative values that includes a probability that the medical determination will occur within a future time range as based on analysis of the non-invasive medical images.
20. A method for making a medical determination, the method comprising:
obtaining a non-invasive image of a body part of a patient, the non-invasive image acquired without puncturing or cutting the patient's skin;
providing the non-invasive image to a neural network that has been trained to determine the patient's current or future clinical or lab quantitative values from the image of the body part; and
receiving the determination of the clinical or lab value.
21. The method of claim 20 wherein the non-invasive image is an ultrasound image.
22. The method of claim 20 wherein the neural network employs a regression algorithm and receiving the determination includes receiving a range.
23. The method of claim 20 wherein the neural network employs a classification algorithm and receiving the determination includes receiving one of a plurality of categories.
24. A system configured to make a medical determination, the system comprising:
an image storage configured to store non-invasive images of a body part of a patient, the non-invasive image acquired without puncturing or cutting the patient's skin;
image analysis logic comprising a trained neural network in communication with the image storage and configured to provide a probability that a future clinical or future lab value of the patient will occur within a future time frame, the determination based on the stored non-invasive images and additionally based on a clinical data set;
a user interface configured to provide the determination to a user; and
one or more processors configured to execute at least the image analysis logic.
25. A method for training a neural network to make a medical determination, the method comprising:
receiving a set of non-invasive images of body parts of a plurality of patients, the non-invasive images, the non-invasive image acquired without puncturing or cutting the patient's skin, and the non-invasive images tagged with information concerning future lab values;
dividing the set of non-invasive images into a training set and a validation set;
providing the images of the training set, and their tags, to a neural network to train the neural network to determine a probability that a future lab or clinical quantitative values will occur within a future time frame based on the non-invasive images of the body parts; and
providing non-invasive images of a single patient from the validation set to the neural network to make the medical determination, and comparing the medical determination to the tag associated with the non-invasive images.