Patient Data Availability Analysis for Clinical Research

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Clinical data repositories (CDR) contain noisy and incomplete data due to human involvement in processing and recording, making it challenging to extract relevant variables for clinical research, which affects data availability and quality, hindering efficient hypothesis validation and prediction modeling.

Innovation Solution

An apparatus and method for patient data availability analysis that includes an input module for specifying models and data sources, a data and model analysis module to determine clean data records and availability measures, and an optimization module to rank and select top models based on data availability, enabling users to understand data quality and optimize data usage for clinical research.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data is collected from multiple sources through different rules to extract variables for clinical research, then the variety and completeness of data increases, but noise and data quality issues increase due to human involvement in processing and recording

Engineering Contradiction:
Improvedata completenessVSAvoiddata quality
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary data quality assessment and availability analysis before actual clinical research modeling. By evaluating data completeness, cleanliness, and availability metrics in advance, researchers can identify suitable data sources and models beforehand, preventing the propagation of noisy data through the research pipeline.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by providing availability measures and data quality metrics back to the research process. This enables continuous monitoring and adjustment of data sources, allowing researchers to refine their variable extraction rules based on observed data quality patterns from multiple sources.

Inventive Principle:
Principle #23Feedback

2Reliability

If multiple models are used for predicting disease outcomes in clinical research, then the accuracy and robustness of predictions improve, but the complexity of data availability analysis increases

Engineering Contradiction:
Improveprediction accuracyVSAvoidanalysis complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the complex analysis task into distinct modular components: data retrieval modules for each source, variable extraction modules for each model variable, cleanliness determination modules, and availability measure calculation modules. This segmentation allows independent evaluation of each model's data requirements without analyzing all models simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary layer between multiple data sources and multiple prediction models. This intermediary layer standardizes data availability assessment by applying uniform cleanliness criteria and availability measures across all models, simplifying the comparison and selection process despite the diversity of models.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If researchers manually assess data availability and quality for each model, then the accuracy of model selection improves, but the time and labor required increases significantly

Engineering Contradiction:
Improvemodel selection accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service automated data availability analysis that researchers can execute independently without manual intervention. The automated retrieval, extraction, and assessment processes run autonomously, providing accurate availability measures for multiple models without requiring researcher time for manual data checking.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system replaces manual mechanical assessment processes with automated computational processes. Instead of researchers manually reviewing data for each model variable, automated modules retrieve data, apply extraction rules, determine cleanliness, and calculate availability measures through algorithmic processing, dramatically reducing analysis time while maintaining precision.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3718116B1Apparatus for patient data availability analysis
Publication Date: 2024.01.10 KONINKLIJKE PHILIPS NV
  • EP3718116B1 patent drawingFigure 1~3h
  • EP3718116B1 patent drawingFigure 4
  • EP3718116B1 patent drawingFigure 5

AI summary

The present invention relates to an apparatus (10) for patient data availability analysis. It is described to specify (210) a plurality of models, wherein each model provides output as a function of model variables. At least some model variables are defined (220) for the plurality of models. Source variables are specified (230), wherein a model variable can be derived from one or more source variables. At least one data source is specified (240). A plurality of data records are received (250) from the at least one data source, wherein each data record comprises at least one attribute. A set of available data records are determined (260) for each model from the plurality of data records, the determination for a model comprising utilizing the model variables for that model, the associated source variables and the at least one attribute for the plurality of data records. A plurality of availability measures are determined (270) for the corresponding plurality of models, the determination comprising utilizing the determined set of available data records for each model. A sub-set of models of the plurality of models is selected (280) as top models of data availability, wherein the selection comprises utilizing the plurality of availability measures.