Physiological Data Standardization with Age-Specific Outlier Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current healthcare data integration systems face challenges in accurately standardizing and validating medical data, particularly physiological attributes like height and weight, due to errors such as incorrect units, localization issues, and inconsistencies, which lead to inaccurate analytics and inefficient processing.
Innovation Solution
A system that standardizes and validates medical data by converting physiological attribute values into standardized forms, dynamically determining value ranges based on patient age, and detecting outliers using historical and consecutive measurement analysis to ensure data accuracy and reduce processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If medical data is normalized using standard medical ontologies, then data standardization is improved, but data accuracy deteriorates due to errors in source data such as incorrect units and localization issues
Solution Approach 1:
The patent applies preliminary action by performing data validation and outlier detection before the normalization process. The system identifies and flags erroneous data points (such as incorrect units, impossible physiological values) in the source systems before they undergo normalization to medical ontologies. This prevents inaccurate data from being converted into standardized but still erroneous coded values, thereby maintaining both standardization quality and data accuracy.
2Manufacturing precision
If comprehensive data validation and outlier detection are performed, then data quality is improved, but processing time increases
Solution Approach 1:
The patent applies local quality by implementing targeted validation rules specific to each physiological attribute and data type rather than applying uniform comprehensive validation to all data. The system uses age-specific reference ranges, unit-specific validation rules, and attribute-specific outlier detection thresholds. This localized approach validates only the necessary aspects of each data point with appropriate criteria, improving data quality while avoiding the overhead of exhaustive validation across all possible data dimensions.
3Measurement precision
If age-specific value ranges are used for validation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing age-specific value ranges and reference thresholds before the validation process. During data validation, the system simply compares incoming physiological values against these pre-established age-specific ranges rather than performing complex real-time calculations. This approach maintains high measurement precision through age-specific validation while reducing system complexity by replacing complex runtime computations with straightforward lookups of pre-computed reference values.
Data Source
AI summary
A system standardizes and validates data across source systems and includes at least one processor. The system converts a value of a physiological attribute of an entity to a standardized value, and dynamically determines a first value range for the physiological attribute from a corresponding region of clustered physiological data of a population. The first value range is specific to and varies with an age of the entity. The standardized value of the physiological attribute is compared to the first value range, and the standardized value of the physiological attribute is designated as an outlier in response to the standardized value of the physiological attribute residing outside of the first value range. Embodiments of the present invention further include a method and computer program product for standardizing and validating data across source systems in substantially the same manner described above.


