Discovering context-specific complexity and utilization sequences

• US 10,769,241 B1
• Filed: 05/19/2014
• Issued: 09/08/2020
• Est. Priority Date: 02/07/2013
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: McNair, Douglas S.
• Primary Examiner(s): Najarian, Lena
• Application Number:
  US14/281,593
• Time in Patent Office: 2,304 Days
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/00 ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Systems, methods, and computer-readable media are provided for patient case and care complexity characterization, and detecting matches of an individual patient'"'"'s record with collections of other patients'"'"' records, based on serial, longitudinal patterns, for facilitating efficient health services utilization, implementing programs to reduce complexity, preventive medicine, and risk management in health care. In an embodiment, time series are formed by electronically representing information pertaining to successive longitudinal episodes of health services utilization and the circumstances in which the episodes were incurred; calculating time-series K-nearest-neighbor clusters and distances for each combination; determining the cluster to which a given candidate patient complexity record is nearest, and prescribing one or more interventions specific to the plurality of hazards that are characteristic of trajectories that are members of that cluster, or that are deemed to be relevant to mitigating those hazards, thereby preventing the adverse outcomes and subsequent excess utilization that are prevalent in that cluster.

Claims

1. One or more non-transitory computer-readable media having computer-usable instructions embodied thereon that, when executed, enable a given processor to perform a method for facilitating clinical decision making, the method comprising:

receiving patient information associated with a target patient having a clinical condition from a first set of records of a health-records system in communication with a clinician interface, the patient information including a patient sequence of clinical events associated with the clinical condition;

creating a target patient data frame based on the received patient information;

generating a timeseries for the target patient based on the target patient data frame, the timeseries including one or more patient case or patient care complexity indicators;

based on the patient information, identifying a reference set of patient health records for a population of patients with the clinical condition, each patient health record in the reference set of records including a clinical event sequence, thereby forming a reference set of clinical event sequences;

generating at least one reference cluster based on the clinical event sequences;

determining, based on the timeseries for the target patient, at least one patient condition trajectory;

automatically matching the patient condition trajectory to the reference set of clinical event sequences to determine a subset of the reference set of clinical event sequences that is similar to the patient sequence of clinical events thereby forming a matching set of clinical event sequences, the matching including at least a determined inter-event pattern;

automatically recommending, by the processor, a condition intervention to mitigate the clinical condition based on the matching set of clinical event sequences including the inter-event pattern; and

displaying the condition intervention on the clinician interface.

2. The computer-readable media of claim 1, further comprising:

determining one or more frequently occurring baskets of order-events present in the matching set of clinical event sequences; and

based on the one or more frequently occurring baskets, determining a set of order recommendations for the target patient.

3. The computer-readable media of claim 2, wherein the set of order recommendations comprises a ranked list of alternative orders.

4. The computer-readable media of claim 2, wherein each basket of order-events comprises at least one clinical order, and wherein each basket is determined as frequently occurring where it occurs in at least ten percent of the sequences in the matching set of clinical event sequences.

5. The computer-readable media of claim 2, further comprising providing the set of order recommendations for the target patient to a caregiver.

6. The computer-readable media of claim 2, wherein the set of order recommendations comprises one or more orders including order sentence, dosage, or frequency information.

7. The computer-readable media of claim 2, wherein each basket of order-events is ranked based on frequency of occurrence in the matching set of clinical event sequences.

8. The computer-readable media of claim 7, wherein a greater frequency of occurrence corresponds to a higher ranking.

9. The computer-readable media of claim 1, wherein the subset of the reference set of clinical event sequences that is similar to the patient sequence of clinical events comprises a subset of the reference set of clinical event sequences having one or more salient sequences in common with the patient sequence of clinical events.

10. The computer-readable media of claim 1, wherein the matching comprises comparing inter-event patterns in the timeseries for the target patient to inter-event patterns in the reference set of clinical event sequences.

11. The computer-readable media of claim 1, wherein the matching comprises comparing subsequences in the timeseries for the target patient to subsequences in the reference set of clinical event sequences.

12. The computer-readable media of claim 1, wherein a clinical event comprises one or more treatments, episodes, diagnoses, orders, or caregiver actions.

13. One or more non-transitory computer-readable media having computer-usable instructions embodied thereon that, when executed, enable a given processor to perform a method for facilitating clinical decision making, the method comprising:

receiving patient information associated with a target patient having a clinical condition from a first set of records of a health-records system in communication with a clinician interface, the patient information including a patient sequence of clinical events;

receiving information associated with a reference set of patient health records for a population of patients with a clinical condition, each patient health record in the reference set of records including a clinical event sequence, thereby forming a reference set of clinical event sequences;

creating a target patient data frame based on the received patient information;

generating a timeseries for the target patient based on the target patient data frame, the timeseries including one or more patient case or patient care complexity indicators;

generating at least one reference cluster based on the clinical event sequences;

determining, based on the timeseries for the target patient at least one patient condition trajectory;

determining a frequently occurring inter-event pattern of clinical events from the reference set of clinical event sequences and the at least one reference cluster, thereby determining a salient sequence of clinical events;

based on the salient sequence of clinical events, automatically recommending, by the processor, a condition intervention to mitigate the clinical condition; and

displaying the condition intervention on the clinician interface.

14. The computer-readable media of claim 13, further comprising associating the salient sequence with the clinical condition.

15. The computer-readable media of claim 13, further comprising:

identifying health records for a target patient, the health records including a sequence of clinical events that matches the salient sequence of clinical events; and

designating the target patient as a candidate for having the clinical condition.

16. The computer-readable media of claim 13, wherein a clinical event comprises one or more treatments, episodes, diagnoses, orders, or caregiver actions.

17. The computer-readable media of claim 13, further comprising displaying the salient sequence to a caregiver.