US-12626799-B2 - Systems and methods for weakly-supervised reportability and context prediction, and for multi-modal risk identification for patient populations

Abstract

Presented herein are systems and methods for automated analysis of patient data. More particularly, in certain embodiments, the invention relates to systems and methods for predicting the context of a particular phrase (e.g. the name of a diagnosis/condition) in a clinical record of a patient using a reportability classifier. In another aspect, the invention relates to systems and methods for automatically identifying a potential care gap and/or adverse health trend for a patient from clinical data.

Inventors

• Neel Master
• Joseph Max Kaufmann
• Michael Alan Nossal
• Jennifer O. Clarke
• David Andrew Miller
• Maren Beus
• Amit Patel

Assignees

• SQ CARE MANAGEMENT, LLC

Dates

Publication Date

20260512

Application Date

20220805

Claims (20)

1. 1 . A method for automatically assigning a context label to each of one or more named entity phrases from a clinical record of a patient, the method comprising: receiving and/or accessing, by a processor of a computing device, the clinical record of the patient and a problem list of the patient; automatically identifying, by the processor, the one or more named entity phrases in the clinical record of the patient; determining, via a reportability classifier, the one or more named entity phrases correspond to an International Classification of Diseases (ICD) code at least associated with a “not reportable” code or a “family history” code, wherein the reportability classifier comprises a machine learning algorithm; automatically assigning, by the processor, the context label to each of the one or more named entity phrases corresponding to the ICD code; automatically triggering a human review workflow based on the context label of the one or more named entity phrases; receiving, via a control interface, feedback from a human reviewer based at least in part on the human reviewer updating a status of a problem in the problem list; and updating the machine learning algorithm of the reportability classifier using training data based at least in part on the feedback received from the human reviewer during the human review workflow, wherein the training data further comprises a weakly-labeled training dataset, wherein the reportability classifier uses distant supervision for updating the machine learning algorithm with the weakly-labeled training dataset, wherein updating the machine learning algorithm further comprises replacing the one or more named entity phrases with a mask such that the reportability classifier is forced to key off surrounding text, wherein the mask yields one or more features from the surrounding text that are used by the reportability classifier for automatically assigning the context label to the one or more named entity phrases.
2. 2 . The method of claim 1 , wherein the one or more named entity phrases comprises a diagnosis, a disease, a condition, a clinical entity, or the ICD code.
3. 3 . The method of claim 1 , wherein the problem list comprises a combination of one or more of: an illness, an injury, a diagnosis, a condition, and a social problem.
4. 4 . The method of claim 1 , wherein the problem list comprises one or more diagnoses.
5. 5 . The method of claim 1 , wherein updating the status of the problem comprises adding the problem or removing the problem in the problem list following the feedback received from the human review workflow.
6. 6 . The method of claim 5 , wherein the machine learning algorithm of the reportability classifier is a deep-learning algorithm.
7. 7 . The method of claim 1 , wherein the training data further comprises data from the clinical record of the patient.
8. 8 . The method of claim 1 , wherein the method comprises identifying, by the processor, the problem corresponding to the patient based on the one or more named entity phrases and the context label of the one or more named entity phrases.
9. 9 . The method of claim 1 , wherein the method comprises determining, by the processor, whether each of the one or more named entity phrases is a negated concept by using the reportability classifier.
10. 10 . The method of claim 1 , wherein the method comprises automatically identifying a care gap using the problem list.
11. 11 . The method of claim 10 , wherein automatically identifying the care gap comprises identifying a therapy and/or a treatment the patient could be receiving but is not currently receiving.
12. 12 . The method of claim 10 , wherein automatically identifying the care gap comprises recommending a therapy using the problem list.
13. 13 . The method of claim 1 , wherein the clinical record is an electronic medical record (EMR).
14. 14 . The method of claim 1 , wherein the clinical record comprises unstructured data.
15. 15 . The method of claim 14 , wherein the unstructured data comprises clinical dictation, clinical notes, and/or clinical reports.
16. 16 . The method of claim 14 , wherein the unstructured data comprises one or more strings of alphanumeric characters.
17. 17 . The method of claim 1 , wherein the clinical record comprises laboratory results of the patient, patient vitals, patient demographics, patient problems, patient medications, clinical notes, clinical dictation, clinical reports, and/or past medical history.
18. 18 . The method of claim 1 , wherein the method does not require receiving or accessing an encounter document comprising billable codes corresponding to the patient.
19. 19 . The method of claim 1 , wherein the one or more named entity phrases is a disease, a condition, or a social circumstance.
20. 20 . The method of claim 1 , wherein the method comprises automatically mapping, by the processor, each of the one or more named entity phrases to a corresponding ontological code by using a first code classifier.

Description

CROSS-REFERENCE TO RELATED APPLICATION This application claims the benefit of and priority to U.S. Provisional Application No. 63/272,074, filed Oct. 26, 2021, entitled “Systems and Methods for Weakly-Supervised Reportability and Context Prediction, and for Multi-Modal Risk Identification for Patient Populations,” the contents of which is hereby incorporated by reference in its entirety. FIELD This invention relates generally to systems and methods for automated analysis of patient clinical data. BACKGROUND Patients have a wide variety of clinical data associated with their care, arising from diverse sources including diagnostic test results from different labs and narrative notes from different practitioners. The use of digital tools such as medical records, digitized lab reporting, and digital dictations provides electronic sources of clinical data that can be very effective at conveying a significant range of information related to patient care. While managing, analyzing, and tracking this clinical data is important to properly coordinate treatments and care for the patient, especially for chronic care management, it is challenging for patients and their caregivers to do so using the currently available tools. Accordingly, there exists a need for systems and methods which efficiently and effectively interpret clinical data. SUMMARY Presented herein are systems and methods for automated analysis of patient data. More particularly, in certain embodiments, the invention relates to systems and methods for predicting the context of a particular phrase (e.g. the name of a diagnosis/condition) in a clinical record of a patient using a reportability classifier. In certain embodiments, the reportability classifier comprises a deep-learning algorithm. A masking technique presented herein improves the performance of the reportability classifier. In another aspect, the invention relates to systems and methods for automatically identifying a potential care gap and/or an adverse health trend for a patient from clinical data. This involves integration of machine learning into the workflow in the context of care coordination to identify, confirm, and close care gaps and provide suggested actions for maintaining the patient's overall health. For example, techniques are presented for updating the machine learning algorithm with feedback received from a triggered human review, e.g., wherein the feedback received from the triggered human review is used as training data for an update of the machine learning algorithm. In one aspect, the invention is directed to a method for automatically assigning a context label to each of one or more named entity phrases from a clinical record of a patient, the method comprising: receiving and/or accessing, by a processor of a computing device, a clinical record (e.g., a document comprising clinical dictation) of a patient; automatically identifying, by the processor, one or more named entity phrases in the clinical record of the patient; and automatically assigning, by the processor, a context label to each of the one or more named entity phrases by using a reportability classifier. In certain embodiments, the one or more named entity phrases comprises a diagnosis, a disease, a condition, a clinical entity, or an International Classification of Diseases code (e.g., ICD-10). In certain embodiments, the context label comprises a label corresponding to a member selected from the group consisting of: “not reportable”, “clinical finding”, family history”, or “personal history”. In certain embodiments, the method comprises receiving a problem list corresponding to the patient. In certain embodiments, the problem list comprises a combination of one or more of: an illness, an injury, a diagnosis, a condition, and a social problem. In certain embodiments, problem list comprises one or more diagnoses (e.g., current and/or resolved diagnoses). In certain embodiments, the method comprises automatically triggering a human review workflow (e.g., a workflow that, upon confirmation, automatically notifies a care team or care individual assigned to the patient of a discrepancy) based on the context label of said named entity phrase. In certain embodiments, the method comprises adding a problem, removing the problem, or updating a status of the problem in the problem list (e.g., identifying if a problem is resolved, inactive, active, improving, or worsening) following feedback received from the triggered human review. In certain embodiments, the method comprises updating the reportability classifier with feedback received from the triggered human review. In certain embodiments, the reportability classifier comprises a deep-learning algorithm. In certain embodiments, the feedback received from the triggered human review is used as training data for an update of the reportability classifier. In certain embodiments, the training data further comprises data from the clinical record (e.g., the EMR) of the patie