AI Adherence Prediction via Transforming Icon Interfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current healthcare systems face challenges in effectively addressing patient treatment adherence due to excessive provider workload, burnout, and the complexity of understanding individual patients' emotional and social factors, which are critical in predicting adherence to medical recommendations.
Innovation Solution
The use of person-specific subjective experience and social-environmental factors, captured and analyzed through transforming icon technology, to provide actionable intelligence for healthcare providers, leveraging machine learning to predict treatment adherence and suggest interventions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If healthcare providers spend more time understanding individual patients' emotional and social factors, then treatment adherence prediction improves, but provider workload increases
Solution Approach 1:
The patent introduces an AI-based intermediary system that collects, processes, and analyzes patient data (emotional, social, and clinical factors) to generate adherence predictions. This intermediary handles the time-consuming analysis work, allowing providers to access accurate predictions without directly investing time in comprehensive patient assessments.
Solution Approach 2:
The patent replaces the manual mechanical process of providers analyzing patient emotional and social factors through direct interaction with an automated AI system. The AI system performs data collection, processing, and prediction generation, substituting the time-consuming manual analysis with automated computational processes.
2Measurement precision
If healthcare systems collect and analyze more patient data, then treatment adherence prediction improves, but system complexity increases
Solution Approach 1:
The patent segments the complex data analysis system into distinct functional modules: data collection components (surveys, EHR integration), data processing components (cleaning, normalization), analysis components (machine learning models), and output components (prediction reports). This segmentation makes the overall complex system more manageable and maintainable.
Solution Approach 2:
The patent designs a multi-functional AI platform that handles diverse data types (emotional, social, clinical) and performs multiple functions (data collection, processing, analysis, prediction, and report generation) within a single integrated system, reducing the need for separate specialized systems.
3Productivity
If healthcare providers focus on volume-based care, then productivity improves, but quality of service decreases
Solution Approach 1:
The patent performs preliminary adherence risk assessment and prediction before patient encounters using AI analysis of patient data. This allows providers to identify high-risk patients in advance and prepare targeted intervention strategies, enabling quality-focused care while maintaining efficient workflow and productivity.
Solution Approach 2:
The patent implements feedback mechanisms where adherence prediction results and patient outcome data are fed back into the system to continuously improve the AI models. This feedback loop enables the system to adapt to changing patient needs and improve prediction accuracy over time, supporting both productivity and quality improvement.
Data Source
AI summary
Disclosed methodologies provide improved predictors of patient treatment adherence by using person-specific subjective experience and social-environmental factors. Methodologies combine emotion and data sciences. Advanced tools capture, measure, store, and analyze self-report of subjective experiences using digital applications and platforms. Patient-specific data is obtained regarding emotional or affective determinants and social determinants for generating a calculated composite score of the patient's probability of adherence or achievement relative to target outcomes, e.g. adherence to treatment plans, wellness activities, etc. for a subject individual. Internal/subjective factors are judged by self-report measures designed to validly judge tested factors based on a patient adjusting continuously-variable graphical interfaces to capture and measure subjective experiences. Emotional characteristics may include perception and intensity in each category of sickness versus wellness, stress, depression, anxiety, pain, and feelings about most recent health provider/staff interaction (with determined intensity for choices of Delighted, Satisfied, Meh, Disappointed, Frustrated). Emotional characteristics may be considered among health, and social characteristics in measuring potential obstacles to adherence.