Patent Issued for Performing analytics on protected health information (USPTO 11217333): 3M Innovative Properties Company

2022 JAN 20 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Wolniewicz, Richard H. (Longmont, CO, US), filed on July 18, 2018, was published online on January 4, 2022.

The patent’s assignee for patent number 11217333 is 3M Innovative Properties Company (St. Paul, Minnesota, United States).

News editors obtained the following quote from the background information supplied by the inventors: “In the medical field, accurate processing of records relating to patient visits to hospitals and clinics ensures that the records contain reliable and up-to-date information for future reference. Accurate processing may also be useful for medical systems and professionals to receive prompt and precise reimbursements from insurers and other payers. Some medical systems may include electronic health record (EHR) technology that assists in ensuring records of patient visits and files are accurate in identifying information needed for reimbursement purposes. These EHR systems generally have multiple specific interfaces into which medical professionals may input information about the patients and their visits.

“The patient files within the EHR usually include protected health information (PHI). PHI represents personal information to which limited access is desirable and often required by government laws and regulations, such as the Health Insurance Portability and Accountability Act of 1996 (HIPAA) and Health Information Technology for Economic and Clinical Health (HITECH) in the United States. Similar laws to restrict access to PHI exist in many other countries.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “In general, this disclosure describes techniques for analytic modeling of PHI in a way that can limit user access to the PHI. In this manner, the PHI can be sheltered from view by the user so as to ensure its protected status. Accordingly, the techniques may improve the ability to ensure privacy of patients, and may be useful for legal or regulatory compliance.

“In one example, this disclosure is directed to a method for analyzing patient data. The method includes accessing, by a computer system, one or more databases comprising health information for a plurality of patients, wherein the health information includes protected health information, randomly selecting, by the computer system, a subset of the health information from the one or more databases, wherein the subset of the health information corresponds to a subset of the plurality of patients, removing, by the computer system, the protected health information from the subset of health information to produce a de-identified analytics subset of patient data suitable for analytical model construction and evaluation, and storing, by the computer system, the de-identified analytics subset of the patient data in the one or more databases.

“In another example, this disclosure is directed to a computer system for storing and analyzing health information for a plurality of patients comprising one or more databases comprising health information for a plurality of patients, wherein the health information includes protected health information, and health information, for a randomly-selected subset of the plurality of patients within the protected health information removed for the randomly-selected subset of the plurality of patients, and a user interface that facilitates user access to health information for a randomly-selected subset of the plurality of patients within the protected health information removed for the randomly-selected subset of the plurality of patients for analytical model construction and evaluation.

“In a further example, this disclosure is directed to a computer-readable storage medium comprising instructions that, when executed, cause a processor to access one or more databases comprising health information for a plurality of patients, wherein the health information includes protected health information, randomly select health information from the one or more databases corresponding to a subset of the plurality of patients, remove the protected health information from the health information corresponding to the randomly-selected subset of the plurality of patients to produce a de-identified analytics subset of patient data suitable for analytical model construction and evaluation, and store the updated de-identified analytics subset of patient data in the one or more databases.

“In another example, this disclosure is directed to a method for analyzing patient data. The method includes accessing, by a computer system, one or more databases comprising health information, with protected health information, for a plurality of patients, accessing, by the computer system, an analytical model, and receiving, by the computer system via a user interface, instructions to apply the analytical model to health information for each of the plurality of patients. The protected health information is isolated from the user interface to restrict access to the protected health information. The method further includes applying, by the computer system, the analytical model to health information for each of the plurality of patients, and storing a result of the analytical model to the one or more databases.”

The claims supplied by the inventors are:

“1. A method for analyzing patient data, the method comprising: accessing, by a computer system, one or more databases comprising health information data, including protected health information, for a plurality of patients; accessing, by the computer system, an analytical model; de-identifying, by the computer system, the protected health information in the health information data for each of the plurality of patients to form a de-identified analytics subset; applying, by the computer system, the analytical model using a machine-learning algorithm to the de-identified analytics subset to train the analytical model, the trained analytical model comprising trained weights of the analytical model; storing the trained weights of the trained analytical model to the one or more databases, wherein the trained analytical model is configured to analyze patient records; presenting, by the computer system via a user interface, a summary of a result of the trained analytical model, wherein the summary of the result of the trained analytical model excludes any of the protected health information; and updating, by the computer system, within the one or more databases, the health information data associated with at least some of the plurality of patients according to the result of the trained analytical model.

“2. The method of claim 1, wherein the summary includes a statistical summary that facilitates user evaluation of the trained analytical model.

“3. The method of claim 1, wherein the updating includes updating patient care information for at least some of the plurality of patients.

“4. The method of claim 1, wherein the updating includes updating a patient health event risk assessment for at least some of the plurality of patients.

“5. The method of claim 1, further comprising: receiving, via the user interface, a request to access protected health information within one or more databases; presenting, by the computer system via the user interface, the requested protected health information via the user interface; and storing a record of the request to access the protected health information within the one or more databases.

“6. The method of claim 1, further comprising: applying, by the computer system, the analytical model using a machine-learning algorithm to health information for each of the plurality of patients to train the analytical model with the health information including the protected health information and form a second trained analytical model, the second trained analytical model comprising trained weights; comparing a first result of the application of second trained analytical model to a second result of the application of the trained analytical model; and presenting a summary of the comparison of the first and second result via the user interface.

“7. A computer system for storing and analyzing health information for a plurality of patients comprising: one or more databases comprising health information data, with protected health information, for a plurality of patients; one or more processors configured to: de-identify the protected health information in the health information data for each of the plurality of patients to form a deidentified analytics subset, apply, based on instructions received via the user interface, the analytical model using a machine-learning algorithm to the deidentified analytics subset to train the analytical model, the trained analytical model comprising trained weights of the analytical model; and store the trained weights of the trained analytical model to the one or more databases, wherein the trained analytical model is configured to analyze patient records; and a display device in communication with the one or more processors that is configured to present a user interface, wherein the one or more processors are further configured to present, via the user interface, a visual representation of a result of the trained analytical model, wherein the visual representation excludes any of the protected health information, wherein the one or more processors are further configured to update, within the one or more databases, the health information data associated with at least some of the plurality of patients according to the results of the trained analytical model.

“8. The computer system of claim 7, wherein the visual representation includes a statistical summary to facilitate user evaluation of the trained analytical model.

“9. The computer system of claim 7, wherein updating includes updating patient care information for at least some of the plurality of patients.

“10. The computer system of claim 7, wherein updating includes updating patient health event risk assessments for at least some of the plurality of patients.

“11. The computer system of claim 7, wherein the one or more processors are further configured to: receive, via the user interface, a request to access protected health information within one or more databases; present, via the user interface, the requested protected health information via the user interface; and store a record of the request to access the protected health information within the one or more databases.

“12. The system of claim 7, wherein the one or more databases is an enhanced patient record store that combines operation data storage for an operational healthcare system and analytics data storage for an analytics grid.

“13. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause one or more processors to: access one or more databases comprising health information data, with protected health information, for a plurality of patients; de-identify the protected health information in the health information data for each of the plurality of patients to form a deidentified analytics subset; apply the analytical model using a machine-learning algorithm to the deidentified analytics subset to train the analytical model, the trained analytical model comprising trained weights of the analytical model; store the trained weights of the trained analytical model to the one or more databases, wherein the trained analytical model is configured to analyze patient records; present, via a user interface, a summary of a result of the trained analytical model, wherein the summary excludes any of the protected health information; and update, within the one or more databases, the health information data associated with at least some of the plurality of patients according to the results of the trained analytical model.

“14. The computer-readable storage medium of claim 13, wherein the summary includes a statistical summary to facilitate user evaluation of the trained analytical model.

“15. The computer-readable storage medium of claim 13, wherein updating includes updating patient care information for at least some of the plurality of patients.

“16. The computer-readable storage medium of claim 13, wherein updating includes updating patient health event risk assessments for at least some of the plurality of patients.

“17. The computer-readable storage medium of claim 13, comprising further instructions that, when executed, cause the processor to: receive, via the user interface, a request to access protected health information within one or more databases; present, via the user interface, the requested protected health information via the user interface; and store a record of the request to access the protected health information within the one or more databases.”

For additional information on this patent, see: Wolniewicz, Richard H. Performing analytics on protected health information. U.S. Patent Number 11217333, filed July 18, 2018, and published online on January 4, 2022. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=11217333.PN.&OS=PN/11217333RS=PN/11217333

(Our reports deliver fact-based news of research and discoveries from around the world.)