Premature birth prediction
Systems and methods of predicting future medical events are based on the processing of medical image. The prediction of premature birth and estimation of gestational age based on ultrasound images are presented as illustrative examples. The new abilities to estimate the probability of future medical events, before they otherwise could be predicted, provides new avenues for the development of preventative treatments.
1. A method of identifying a beneficial therapy based on medical predictions, the method comprising:
determining a quantitative prediction of a future medical condition, the quantitative prediction including a probability that the medical condition will occur within a future time range and being based on analysis of medical images of a patient;
providing a candidate therapy for the medical condition to the patient;
repeating the steps of determining the quantitative prediction of the future medical condition and providing the candidate therapy for the plurality of patients;
performing a study of a benefit seen for the candidate therapy in the plurality of patients at their respective time ranges; and identifying the candidate therapy as the beneficial therapy based on the study.
2. The method of claim 1 , wherein the medical images include ultrasound images of a fetus or a mother of the fetus.
3. The method of claim 1 , wherein the medical images include ultrasound images.
4. The method of claim 1 , further comprising receiving clinical data regarding the fetus or a mother of the fetus, wherein an estimated time until birth of the fetus is based on the clinical data.
5. The method of claim 1 , further comprising providing a user with feedback regarding acquisition of the medical images based on a quality of the prediction or a subject classification of images already acquired.
6. The method of claim 1 , further comprising training a machine learning system to estimate a time until birth of the fetus, a gestational age of the fetus at birth, and/or a current gestational age of the fetus.
7. The method of claim 1 , wherein analyzing the medical images includes using a quantile regression algorithm to provide an estimate that the fetus will be born prematurely, and optionally to estimate the time until birth, the quantile regression algorithm being configured to classify an estimated gestational age of the fetus at birth into one of at least two time ranges.
8. The method of claim 1 , wherein the quantitative prediction is further based on the clinical data received via a data input and regarding a mother of the fetus.
9. The method of claim 1 , wherein analyzing the medical images includes using a quantile regression algorithm or a classification algorithm to make the prediction that the fetus will be born prematurely.
10. The method of 1 , further comprising balancing the images based on a subject matter classification of views or features.
11. The method of 1 , further comprising balancing quantities of the images based on gestational age at birth.
12. The method of claim 1 , wherein the candidate therapy is only provided to patients having a quantitative prediction of greater than 50%, 66% or 75% that the medical condition will occur within the future time range.
13. The method of claim 1 , wherein the medical condition is the premature birth of a fetus.
14. The method of claim 1 , wherein the medical condition is not present or apparent in the medical images at a time the quantitative prediction is determined.
15. The method of claim 1 , wherein the candidate therapy includes a pharmaceutical or physical treatment.
16. The method of claim 1 , wherein the candidate therapy is provided to the plurality of patients prior to the patients exhibiting any symptoms of the medical condition.
17. The method of claim 1 , wherein performing the study includes providing placebos to some patients of the plurality of patients.
18. The method of claim 1 , wherein a time between determining the quantitative prediction and the future time range is at least one month.
19. The method of claim 1 , wherein the medical condition comprises cancer.
20. The method of claim 1 , further comprising generating the medical images with an ultrasound machine.
21. A method of generating a quantitative prediction of premature birth, the method comprising:
obtaining a set of medical images, the medical images including a fetus;
analyzing the medical images using a machine learning system to produce the quantitative prediction, the quantitative prediction including an estimate of time until birth of the fetus or an estimate of a gestational age of the fetus at birth;
and providing the quantitative prediction to a user.
22. A method of training a medical prediction system, the method comprising:
receiving a plurality of medical images, the medical images including ultrasound images of a fetus during pregnancy; classifying the images according to the views or features included within the images; training the neural network to provide a quantitative prediction regarding birth of the fetus, the quantitative prediction including an estimate of a gestational age of the fetus at birth, or including an estimate of a current gestational age of the fetus and an estimate of remaining time until birth of the fetus; and testing the trained neural network, to determine accuracy of the quantitative predictions.