Automated Health Data Processing for Electronic Health Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional healthcare applications fail to efficiently process patient health data captured in a question and answer format, leading to increased documentation time for healthcare providers and physician burnout, as the data is not easily consumable in electronic health records.
Innovation Solution
A computer-implemented method and system that processes question and answer data from automated patient interviews by identifying parent and child symptoms using a mapping technique, categorizing symptoms, and generating a graphical History of Present Illness (HPI) notation, reducing the time healthcare providers spend reviewing records and allowing for quicker patient interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If patient health data is captured in question and answer format by conventional healthcare applications, then the data collection is automated, but the data is not easily consumable by healthcare providers and requires reading the entire transcript to distill the History of Present Illness
Solution Approach 1:
The patent introduces an intermediary processing system that translates the automated interview transcript into a structured clinical format. This intermediary layer converts the raw question-and-answer data into a standardized History of Present Illness notation that healthcare providers can easily consume, resolving the contradiction between automation and ease of data consumption.
Solution Approach 2:
The system changes the parameter of data representation from unstructured transcript format to structured clinical notation format. By transforming the data parameters (from free-text Q&A to organized HPI with specific fields like chief complaint, symptom duration, associated symptoms), the system makes the automated data easily consumable while maintaining the automation benefit.
2Loss of information
If healthcare providers review the entire transcript to distill patient symptoms, then complete information is obtained, but documentation time increases significantly
Solution Approach 1:
The system extracts the essential clinical information from the complete transcript and presents it in a condensed, structured format. By taking out only the relevant symptoms and organizing them into a standardized HPI notation, the system preserves complete patient information while eliminating the need to read the entire transcript, thus reducing documentation time.
Solution Approach 2:
The system performs preliminary processing of the transcript data to pre-distill the History of Present Illness before the healthcare provider needs to review it. This preliminary action of automatically extracting and organizing symptoms reduces the provider's workload and time requirement while ensuring no critical information is lost.
3Loss of information
If symptom data is stored as a transcript in the electronic health record, then all patient responses are preserved, but the format does not enable efficient processing to provide insights
Solution Approach 1:
The system segments the continuous transcript into discrete, structured components representing different clinical elements (chief complaint, symptom characteristics, associated symptoms, negative findings). This segmentation enables efficient processing and analysis of specific symptom elements while preserving the complete patient response information in the original transcript.
Solution Approach 2:
The system changes the data parameters from unstructured text to structured clinical attributes that can be efficiently processed. By transforming the transcript into a formatted HPI with defined parameters (symptom type, duration, severity, associated features), the system enables efficient processing and insight generation while maintaining the complete patient response record.
Data Source
AI summary
Systems and methods for automatic health data processing are disclosed. One or more complaints are extracted from question and answer data of an automated patient interview. A parent-child symptom mapping is referenced to identify a respective parent symptom corresponding to each complaint. Based on the question and answer data, a presence or absence of evidence of the child symptoms associated with each identified parent symptom is determined. The child symptoms are categorized into a positive or negative category based on the determination. An object is generated that includes, for each of the complaints, a positive and negative list of any of the child symptoms included in the positive and negative category, respectively. The object is processed to generate a history of present illness (HPI) portion of a notation in a graphical format. The notation is stored in the patient's electronic health record, and a healthcare provider notification is transmitted.