Machine-Learning Error Reporting for In-Vitro Diagnostic Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current in-vitro diagnostic systems lack effective methods for detecting and reporting operation errors, particularly in determining bodily fluid samples, with existing quality control relying on camera-based solutions that do not account for system behavior, leading to potential operational inefficiencies and errors.
Innovation Solution
A method and system for detecting and reporting operation errors in in-vitro diagnostic systems that utilize a machine learning process to analyze error report data, including both error data and user-provided labelling data, to update application software and improve operational control, allowing for centralized error analysis and software updates across multiple systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If camera-based quality control algorithms are used, then sample detection capability is provided, but system behavior adaptation and error detection accuracy deteriorate
Solution Approach 1:
The system implements feedback by collecting error data from multiple diagnostic systems and using machine learning to generate software updates that are distributed back to the systems. This closed-loop feedback mechanism enables continuous improvement of error detection accuracy based on real-world operational data.
Solution Approach 2:
The system performs self-service through automated machine learning processes that analyze error data and generate software updates without requiring manual intervention. The diagnostic systems automatically receive and apply updates, enabling self-improving error detection capabilities across the network.
2Adaptability or versatility
If pre-installed quality control algorithms are used, then initial error detection capability is provided, but continuous improvement and adaptation to real-world errors deteriorate
Solution Approach 1:
The system performs preliminary action by continuously collecting and analyzing error data in the background, preparing software updates in advance based on accumulated insights. This allows updates to be ready and waiting when needed, reducing the actual deployment time while maintaining continuous improvement capabilities.
Solution Approach 2:
The system ensures continuity of useful action by maintaining constant error data collection and analysis operations. The machine learning process runs continuously to process error data and generate updates, ensuring that improvement activities never stop while minimizing disruption to operational systems.
3Quantity of substance
If centralized error analysis is implemented, then learning from multiple systems is enabled, but data transmission and processing complexity increase
Solution Approach 1:
The system uses an intermediary approach by implementing a centralized server that acts as a mediator between multiple diagnostic systems. This server collects, standardizes, and processes error data from various sources, managing the complexity of data aggregation and analysis while enabling comprehensive learning across the network.
Solution Approach 2:
The error analysis system implements universality by creating a multi-functional platform that handles data collection, storage, analysis, software update generation, and distribution. This universal system serves multiple purposes simultaneously, reducing overall complexity compared to separate specialized systems for each function.
Data Source
AI summary
The present disclosure refers to a method for detecting and reporting an operation error in an in-vitro diagnostic system (1) for determining a sample of a bodily fluid, comprising: providing a plurality of sample vessels (2) each containing a sample of a bodily fluid; and providing a plurality of functional modules (3), comprising an analysis device (4) configured to determine the sample, a handling system (5) configured to handle the plurality of sample vessels (2), and an automation track (6) provided by the handling system (5) and configured to transport the plurality of sample vessels (2) to the analysis device (4). The method further comprises: providing an operation control device (7) connected to at least one of the functional modules (3) and configured to control operation of the at least one functional module (3), and comprising one or more data processors (8), wherein an application software is running on the one or more data processors (8) for controlling operation of the at least one functional module (3); controlling operation of the at least one functional module (3) by the operation control device (7); and detecting and reporting an operation error by an error detecting and reporting device (9), comprising: detecting the operating error for the operation of at least one of the plurality of functional modules (3) and the operation control device (7), providing error data indicative of the operation error, receiving a user input through a user interface (10) after detecting the operation error, providing labelling data in response to receiving the user input, the labelling data being indicative of information related to the operating error in addition to the error data, providing error report data comprising the error data and the labelling data, and transmitting the error report data to an error repository (11) remotely located with respect to both the plurality of functional modules (3) and the operation control device (7); receiving the error report data in a machine learning process running in a data processing device connected to the error repository (11); processing the error report data by the machine learning process in the data processing device; providing a application software update for the application software in response to the processing of the error report data by the machine learning process in the data processing device; providing the application software update to the operation control device (7); and controlling operation of the at least one functional module (3) by the operation control device (7) comprising running the application software including the application software update. Further, an in-vitro diagnostic system for determining a sample of a bodily fluid is provided.