Readmission Risk Prediction Using Sequential Pattern Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current healthcare systems face challenges in identifying and managing co-existing conditions that contribute to patient readmissions, often relying on human clinical acumen rather than data-driven approaches, which are not customizable and lack accuracy in predicting readmission risks.

Innovation Solution

A computerized system analyzes medical data to identify correlation clusters between conditions associated with readmissions, using sequential pattern analysis and multivariate logistic regression to predict readmission risks and provide interventions, thereby reducing healthcare costs and improving patient care.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If healthcare providers focus solely on addressing the current condition for admission, then the immediate treatment effectiveness is improved, but the readmission risk increases due to overlooked co-existing conditions

Engineering Contradiction:

Improvetreatment effectivenessVSAvoidreadmission risk

Core Design Contradiction:

Manufacturing precisionVSReliability

Solution Approach 1:

The system performs preliminary identification of co-existing conditions during the initial admission by analyzing medical data and generating predictions about conditions that may contribute to future readmissions. This allows healthcare providers to address these conditions proactively during the current admission rather than waiting for readmission to occur

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors patient data and provides feedback to healthcare providers about identified co-existing conditions and their potential impact on readmission risk. This feedback loop enables providers to adjust treatment plans based on data-driven insights about correlated conditions

Inventive Principle:

Principle #23Feedback

2Reliability

If healthcare providers allocate more time and resources to identify co-existing conditions, then the readmission risk decreases, but the time and resource constraints worsen

Engineering Contradiction:

Improvereadmission risk reductionVSAvoidprovider time availability

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system replaces manual clinical assessment with an automated computerized system that analyzes medical data to identify co-existing conditions. This substitution of mechanical/data-driven analysis for human provider time enables comprehensive condition identification without adding to provider workload or time constraints

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system autonomously processes medical data, identifies correlation clusters, and generates predictions about co-existing conditions without requiring direct provider intervention. The system serves itself by automatically querying databases, performing analyses, and presenting results to providers

Inventive Principle:

Principle #25Self-service

3Ease of manufacture

If traditional human clinical acumen is used to identify co-existing conditions, then the approach is simple to implement, but the accuracy and customization capability deteriorate

Engineering Contradiction:

Improveimplementation simplicityVSAvoidreadmission prediction accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system changes the parameters of condition identification from subjective clinical judgment to objective data-driven analysis using sequential pattern analysis and multivariate logistic regression. This transformation enables precise measurement of readmission risk based on quantifiable correlations between conditions

Inventive Principle:

Principle #35Parameter changes

4Measurement precision

If a data-driven approach with sequential pattern analysis is implemented, then the readmission prediction accuracy improves, but the system complexity increases

Engineering Contradiction:

Improvereadmission prediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces a computerized intermediary that bridges the gap between complex data analysis and simple provider decision-making. This intermediary automatically performs sophisticated statistical analyses and presents results in an easily interpretable format, shielding providers from system complexity while maintaining high prediction accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20210193327A1Reducing Readmission Risk Through Co-Existing Condition Prediction

Publication Date: 2021.06.24 CERNER INNOVATION INC

AI summary

Methods, systems, and computer-storage media are provided for determining the probability of readmission of an individual to a facility after a first admission. Medical data elements are identified that are associated with a first admission and at least one readmission for at least one individual at a facility over a predetermined period. Sequential pattern analysis is performed to determine correlation clusters between two or more conditions. Additionally, multivariate logistic regression may be performed to further support the correlation clusters determined. Based on the analysis, a prediction is generated and communicated to a first user regarding the risk of readmission of an individual and interventional treatments are proposed to decrease the risk of readmission based on the prediction comprising the correlation cluster.