Inhaler Operation Classification via Sensor Data Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Asthma and COPD patients often misuse inhalers due to inadequate education and follow-up, leading to poor disease control, increased emergency room visits, and high costs, highlighting the need for improved monitoring and coaching technologies to enhance inhaler adherence and technique.

Innovation Solution

A data processing system that uses a camera and audio sensors to monitor and coach patients on proper inhaler use through real-time feedback, employing RGB, depth, and audio data analysis to detect incorrect usage and provide personalized guidance, allowing for accurate classification and correction of inhaler operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If patients receive traditional inhaler education and follow-up, then inhaler technique knowledge is provided, but actual inhaler usage correctness remains poor with up to 85% of patients using inhalers incorrectly

Engineering Contradiction:

Improveinhaler technique accuracyVSAvoidinhaler usage correctness

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system captures video of patient inhaler usage, automatically analyzes the technique using image processing algorithms, and provides immediate visual feedback showing correct vs. actual technique. This closed-loop feedback mechanism transforms static education into dynamic correction, allowing patients to see their mistakes and improve in real-time

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent replaces manual clinical assessment of inhaler technique with an automated computer vision system. The mechanical/physical process of a clinician observing and evaluating patient technique is substituted with digital image capture, processing, and automated analysis algorithms that objectively measure technique correctness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If clinicians provide comprehensive inhaler education during office visits, then patient knowledge improves, but time constraints prevent adequate instruction and follow-up

Engineering Contradiction:

Improveinhaler technique instruction qualityVSAvoidoffice visit time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary automated analysis of inhaler technique before clinical review. Video capture and initial algorithmic assessment occur outside the time-constrained office visit, allowing clinicians to review pre-analyzed results and focus instruction only on specific errors rather than providing comprehensive education from scratch during each visit

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables patients to self-assess their inhaler technique through automated video analysis and feedback. Patients can review their own technique errors and corrections at home without requiring repeated clinical appointments, making the education process independent of clinician time availability

Inventive Principle:

Principle #25Self-service

3Measurement precision

If multiple data sources are integrated for comprehensive inhaler monitoring, then classification accuracy improves, but data processing complexity increases

Engineering Contradiction:

Improveinhaler operation classification accuracyVSAvoiddata processing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the complex task of inhaler technique analysis into distinct components: video capture, keyframe extraction, region identification (inhaler, mouth, hands), technique parameter measurement, and correctness classification. Each component is handled by specialized algorithms, making the overall complex system manageable and modular

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11676713B2Data processing system for classifying keyed data representing inhaler device operation

Publication Date: 2023.06.13 CARNEGIE MELLON UNIV

AI summary

A data processing system digitally processes data feeds of inhaler device operation. The data feed represents operation of an inhaler device. The system indexes the live data feed with a key value representing the inhaler device for which the live data feed is obtained. For a particular key value indexed in the in-memory data storage, the system queries, a data feed representing physical operation of an inhaler device, segments the live data feed for that particular key value into a plurality of data samples, process at least a portion of the data samples to classify each of the processed data samples; outputs a prompt specifying whether operation of the inhaler device is within a threshold range of operation. Audio data, temperature data, image data, and ranging data can be processed to classify operation of the inhaler device and the order of operations of the inhaler device.