Systems and methods for optimizing medical interventions using predictive models
A computer implemented method for prescribing optimized medical interventions includes retrieving a patient's updated electronic medical record (EMR) and mapping the diagnosis of the patient to a medical treatment database to select a plurality of likely medical intervention choices based on a score exceeding a defined threshold score. The method includes determining a rank order of the selected plurality of medical intervention choices by comparing simulation outcomes for each choice executed by the medical predictive algorithm, on respective choices among each of the selected likely medical interventions. The method also includes receiving by the patient's physician or patient's electronic medical record database, a rank order of recommended medical intervention choices including possible options and associated metrics based on an accepted level of simulated outcome.
1. A computer implemented method for prescribing optimal treatment paths, comprising:
retrieving data relevant to a diagnosis of a disease, the data comprising a patient's updated electronic medical record (EMR) comprising medical images and at least one of: the patient's demographic data, morbid symptoms, vital signs, medications, surgery history, family medical history, genetic data, laboratory test data, diseases records, and allergies;
identifying treatment path options based on selections made by medical professional personnel or according to guidelines generated by medical societies, wherein the treatment path options comprise at least one surgical treatment or intervention;
using a trained predictive life-expectancy model to predict a life expectancy for each of the treatment path options based on the data and probability distribution functions conditioned on adverse outcomes of the at least one surgical treatment or intervention, wherein the adverse outcomes are generated by predictive models comprising a biomechanical model based on the medical images;
performing Monte-Carlo simulations using the probability distribution functions of the adverse outcomes to calculate a total probability function of the life expectancy for each of the treatment path options; and
interactively displaying a decision tree to the medical professional personnel and the patient, the decision tree comprising the treatment path options and corresponding total probability functions of the life expectancies, presenting real time predicted life expectancies, sorting the life expectancies from a maximum probability to a minimum probability, and presenting the life expectancies and temporal and monetary costs for each of the treatment path options.
2. The computer implemented method of claim 1 , wherein the predictive models further comprise one or more of a trained artificial neural net model, a statistical model, a reduced order model, a semi-empirical, and an empirical model.
3. The computer implemented method of claim 1 , wherein the probability distribution functions comprise individual probabilities of each of the adverse outcomes and pre-calculated probability distribution functions of life expectancy after each of the at least one surgical treatment or intervention.
4. The computer implemented method of claim 1 , wherein the adverse outcomes are due to uncertainties during deployment of at least one surgical device.
5. The computer implemented method of claim 1 , further comprising displaying the decision tree in real time when there is new data added to the patient's EMR.
6. The computer implemented method of claim 1 , wherein the medical images comprise X-ray images and/or computer generated tomography images.
7. The computer implemented method of claim 3 , wherein the pre-calculated probability distribution functions are conditioned on at least one of the patient's demographic data, morbid symptoms, vital signs, medications, surgery history, family medical history, genetic data, laboratory test data, diseases records, allergies, hospital, and geographic region.
8. The computer implemented method of claim 3 , wherein the pre-calculated probability distribution functions are conditioned on at least one of a selection of at least one valve for the at least one surgical treatment or intervention, geographic location, age of the patient at time of the at least one surgical treatment or intervention, and co-morbidities of the patient.
9. The computer implemented method of claim 3 , wherein the pre-calculated probability distribution functions are conditioned on each of the adverse outcomes due to one or more of root rupture, paravalvular leakage level, patient prosthesis mismatch, valve thrombosis, coronary obstruction, valve embolization, placement of permanent pacemaker, stroke, patient prosthesis mismatch, and valve thrombosis.
10. The computer implemented method of claim 5 , further comprising retrieving the new data from a wearable device, wherein the data comprises biological, physiological, cognitive, mental, and/or biomarker data of the patient.
11. A system for prescribing optimal treatment paths, comprising:
at least one memory comprising instructions; and
at least one processor configured to execute the instructions, which, when executed, cause the at least one processor to:
retrieve data relevant to a diagnosis of a disease, the data comprising a patient's updated electronic medical record (EMR) comprising medical images and at least one of: the patient's demographic data, morbid symptoms, vital signs, medications, surgery history, family medical history, genetic data, laboratory test data, diseases records, and allergies;
identify treatment path options based on selections made by medical professional personnel or according to guidelines generated by medical societies, wherein the treatment path options comprise at least one surgical treatment or intervention;
use a trained predictive life-expectancy model to predict a life expectancy for each of the treatment path options based on the data and probability distribution functions conditioned on adverse outcomes of the at least one surgical treatment or intervention, wherein the adverse outcomes are generated by predictive models comprising a biomechanical model based on the medical images;
perform Monte-Carlo simulations using the probability distribution functions of the adverse outcomes to calculate a total probability function of the life expectancy for each of the treatment path options; and
interactively display a decision tree to the medical professional personnel and the patient, the decision tree comprising the treatment path options and corresponding total probability functions of the life expectancies, present real time predicted life expectancies, sort the life expectancies from a maximum probability to a minimum probability, and present the life expectancies and temporal and monetary costs for each of the treatment path options.
12. The system of claim 11 , wherein the predictive models further comprise one or more of a trained artificial neural net model, a statistical model, a reduced order model, a semi-empirical, and an empirical model.
13. The system of claim 11 , wherein the probability distribution functions comprise individual probabilities of each of the adverse outcomes and pre-calculated probability distribution functions of life expectancy after each of the at least one surgical treatment or intervention.
14. The system of claim 11 , wherein the adverse outcomes are due to uncertainties during deployment of at least one surgical device.
15. The system of claim 11 , wherein the instructions, which, when executed, cause the at least one processor to display the decision tree in real time when there is new data added to the patient's EMR.
16. The system of claim 11 , wherein the medical images comprise X-ray images and/or computer generated tomography images.
17. The system of claim 13 , wherein the pre-calculated probability distribution functions are conditioned on at least one of the patient's demographic data, morbid symptoms, vital signs, medications, surgery history, family medical history, genetic data, laboratory test data, diseases records, allergies, hospital, and geographic region.
18. The system of claim 13 , wherein the pre-calculated probability distribution functions are conditioned on at least one of a selection of at least one valve for the at least one surgical treatment or intervention, geographic location, age of the patient at time of the at least one surgical treatment or intervention, and co-morbidities of the patient.
19. The system of claim 13 , wherein the pre-calculated probability distribution functions are conditioned on each of the adverse outcomes due to one or more of root rupture, paravalvular leakage level, patient prosthesis mismatch, valve thrombosis, coronary obstruction, valve embolization, placement of permanent pacemaker, stroke, patient prosthesis mismatch, and valve thrombosis.
20. The system of claim 15 , wherein the instructions, which, when executed, cause the at least one processor to retrieve the new data from a wearable device, wherein the data comprises biological, physiological, cognitive, mental, and/or biomarker data of the patient.