ML-Based Electronic Health Record Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inaccurate and inefficient maintenance of electronic health records due to errors and inconsistencies in textual data entered by caregivers, which can lead to detrimental effects on patient care and treatment.
Innovation Solution
A method using machine learning models to parse textual descriptions of patient medical examinations, identify attributes, and predict changes to electronic health records, ensuring accurate and up-to-date patient information by automatically updating records.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If caregivers manually enter textual data into electronic health records, then the records can be updated with patient information, but errors and inconsistencies occur reducing accuracy
Solution Approach 1:
The system automatically processes textual descriptions by parsing them with machine learning models to extract attributes and generate predicted changes to electronic health records, eliminating the need for manual data entry while maintaining accuracy through automated self-updating
Solution Approach 2:
Manual mechanical data entry operations are replaced with automated machine learning-based text parsing and prediction systems that automatically extract information and update records, substituting human effort with computational processing
2Reliability
If caregivers spend more time updating records to improve accuracy, then fewer errors occur, but time efficiency decreases
Solution Approach 1:
The machine learning models are pre-trained on historical data to automatically perform the complex task of parsing textual descriptions and identifying record changes, so that when new data arrives, the system can immediately process it without requiring caregiver time for analysis or verification
3Reliability
If manual review and correction of textual data is performed, then accuracy improves, but computational efficiency decreases
Solution Approach 1:
Manual review and correction processes are replaced with automated machine learning models that parse textual descriptions, extract attributes, and predict necessary record changes computationally, maintaining high accuracy through algorithmic processing rather than human review
Solution Approach 2:
The system changes the state of data from unstructured textual descriptions to structured extracted attributes through automated parsing, enabling efficient computational processing and comparison to determine necessary record updates without manual intervention
Data Source
AI summary
Certain aspects of the present disclosure provide techniques for predicting electronic health record data using ML. This includes determining a plurality of attributes of a textual description of a patient medical examination, including: detecting the plurality of attributes based on analyzing the textual description using a first ML model trained to parse patient textual descriptions. This further includes predicting a change to an electronic health record for the patient, including: providing to a second ML model the plurality of attributes of the textual description and patient medical data for the patient, where the second ML model is trained to predict changes to patient electronic health records based on attributes of textual data relating to the patient and patient medical data. The predicted change is provided to an electronic system to change the electronic health record and affect medical treatment for the patient.