Machine Learning Personalized Communications for Patient Adherence

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Treatment adherence among patients with chronic illnesses is low due to factors such as cost, complexity, and lack of understanding, leading to serious consequences for patients, healthcare providers, and the public.

Innovation Solution

Utilizing machine learning models to generate personalized communications tailored to individual patient needs, considering treatment plan complexity and patient persona, to improve adherence through targeted educational and motivational strategies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional treatment plan delivery methods are used, then implementation is simple, but treatment adherence remains low due to lack of personalization and motivational delivery

Engineering Contradiction:

Improvetreatment adherenceVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the treatment adherence problem into multiple components: treatment plan complexity analysis, patient persona identification, motivational delivery customization, and adherence tracking. Each component is handled by specialized ML models that process specific aspects of patient data independently, then integrate their results to generate personalized communications.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes multiple parameters simultaneously: it analyzes treatment plan parameters (number of medications, dosage frequency), transforms patient data into persona indicators (communication style preferences, ability to follow regime), and dynamically adjusts communication parameters (tone, complexity, channel selection) based on ML model predictions of adherence probability.

Inventive Principle:

Principle #35Parameter changes

2Ease of operation

If treatment plans are simplified to improve adherence, then ease of operation increases, but treatment effectiveness may be compromised

Engineering Contradiction:

Improvetreatment plan simplicityVSAvoidtreatment effectiveness

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system applies local quality by customizing the explanation and presentation of treatment plan elements based on individual patient needs. Complex medications and dosing instructions are explained at different levels of detail and complexity according to each patient's persona indicators, while the actual treatment plan content remains medically appropriate and effective.

Inventive Principle:

Principle #3Local quality

3Reliability

If personalized communications are generated for each patient, then treatment adherence improves, but computational resources and processing time increase

Engineering Contradiction:

Improvetreatment adherenceVSAvoidcomputational energy consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary action by pre-processing patient data into standardized formats, pre-training ML models on historical adherence data, and pre-identifying patient personas before actual communication generation. This allows the system to quickly generate personalized communications when needed without performing full analysis from scratch each time.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses copying by leveraging historical adherence data and patterns from similar patients to inform current communication strategies. ML models are trained on copies of historical interactions and outcomes, allowing the system to apply learned patterns to new patients without requiring extensive new data processing for each individual case.

Inventive Principle:

Principle #26Copying

4Reliability

If comprehensive patient data is collected to improve personalization, then communication effectiveness increases, but data privacy and security concerns increase

Engineering Contradiction:

Improvecommunication effectivenessVSAvoiddata privacy risks

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system extracts only the specific data elements needed for personalization (treatment plan details, basic patient demographics, communication preferences) while leaving sensitive personal information separate. The ML models process extracted features rather than raw personal data, reducing privacy risks while maintaining personalization effectiveness.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20250246321A1Devices, Systems, and Methods for Generating and Providing Personalized Communications to Improve Adherence to Patient Treatment Plans

Publication Date: 2025.07.31 ELEVANCE HEALTH INC

AI summary

The present disclosure regards an electronic device configured to generate personalized communications regarding patient treatment plans. The electronic device includes a processor configured to perform various operations. These operations include receiving data regarding a patient, where the data includes treatment plan data regarding a treatment plan prescribed for the patient and other data regarding a healthcare provider, a clinician, a medical record, a social media account, a laboratory, or a pharmacy associated with the patient. The operations also include providing the data to a plurality of machine learning (ML) models configured to generate a personalized communication for the patient based on the data. Additionally, the operations include receiving the personalized from the plurality of ML models, where the personalized communication is addressed to the patient and regards the treatment plan prescribed for the patient. Further, the operations include delivering the personalized communication to the patient.