AI Telemonitoring Apparatus Predicting Patient Therapy Adherence

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current telemedicine systems face challenges in effectively monitoring and predicting patient adherence to therapy, particularly for chronic disease management, due to unequal access to healthcare and the complexity of managing multiple patients with varying health parameters, leading to poor adherence and increased caregiver burden.

Innovation Solution

A tele-monitoring apparatus that collects health data from patients using connected devices, processes it through a central unit with an artificial intelligence module employing learning algorithms to determine parameter weights and predict adherence trends, enabling prioritization of care interventions and optimizing resource allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If telemedicine systems collect and analyze health data from multiple patients, then the ability to monitor patient parameters improves, but the complexity of managing heterogeneous data from dissimilar applications increases

Engineering Contradiction:
Improvepatient parameter monitoringVSAvoiddata management complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a universal data processing platform that can handle heterogeneous data from multiple dissimilar telemedicine applications. The system uses standardized data structures and interoperable communication protocols to integrate data from different sources, allowing the same infrastructure to manage diverse patient monitoring data without requiring separate systems for each application type.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system transforms heterogeneous data from different applications into standardized parameters through data normalization and conversion layers. By changing the representation format of incoming data to a common standard, the system enables consistent analysis and comparison across different telemedicine applications while maintaining the ability to handle diverse input formats.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If telemedicine applications are developed for heterogeneous environments, then adaptability to different health contexts improves, but the difficulty of sharing and analyzing data across applications increases

Engineering Contradiction:
Improvehealth context adaptabilityVSAvoiddata sharing efficiency
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent introduces intermediary components including standardized data exchange protocols and interoperability layers that act as mediators between heterogeneous telemedicine applications. These intermediaries translate and normalize data from different sources into a common format, enabling efficient sharing and analysis while preserving the adaptability of individual applications to their specific health contexts.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If clinical monitoring is performed remotely, then access to healthcare services improves, but patient adherence to therapy deteriorates due to lack of direct supervision

Engineering Contradiction:
Improvehealthcare accessVSAvoidtherapy adherence
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system implements continuous feedback loops where patient data is automatically collected, analyzed, and used to generate real-time alerts and notifications. When adherence patterns deviate from expected trends, the system automatically notifies healthcare providers and patients, enabling timely interventions to correct non-adherence behaviors while maintaining the convenience of remote monitoring.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent employs predictive analytics and machine learning algorithms to identify potential adherence problems before they occur. By analyzing historical data and detecting early warning signs of non-adherence, the system enables proactive interventions that prevent therapy failure, maintaining high adherence rates throughout the treatment course.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4411747A1Apparatus for monitoring the parameters of a plurality of patients and for predicting the trend of the adherence by the plurality of patients to a therapy
Publication Date: 2024.08.07 WIRELESS SENSOR NETWORKS SRL
  • EP4411747A1 patent drawingFigure 1~2
  • EP4411747A1 patent drawingFigure 3
  • EP4411747A1 patent drawingFigure 4

AI summary

An apparatus (1) for monitoring the parameters of a plurality of patients and for predicting the trend of the adherence by the plurality of patients to a therapy set by a specialist is described, said apparatus comprising: - a plurality of devices (100) adapted to collect a plurality of health parameters of the plurality of patients relative to said therapy and to process health data in relation to said parameters, - a central unit (500) adapted to receive health data of the plurality of patients from said plurality of devices; said central unit comprising - a memory (25) in which a database (DB) containing said health data on the plurality of patients is installed, - an artificial intelligence module (400) connected with said database and comprising at least one learning algorithm (401), said artificial intelligence module being adapted to determine the weight of the parameter and/or the weight of the patient for each parameter and patient of the previous plurality of patients as a function of the health data of the previous plurality of patients, - a prediction module (501) connected with said database and configured to predict the trend of the adherence to said therapy by the current plurality of patients as a function of the health data contained in the database and as a function of the weight of the parameter and/or of the weight of the patient for each parameter and patient of the previous plurality of patients in output from the artificial intelligence module.