Multi-threaded ML for Medical Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning systems struggle to accurately and efficiently process medical records, failing to identify a wide variety of patterns, such as comorbidity terms, ICD codes, body part information, and prescription details, due to limitations in parsing and processing medical data from diverse sources.
Innovation Solution
The system employs a multi-threaded approach with dedicated computational threads for executing machine learning models, including sentence classification, comorbidity, ICD, body parts, and prescription models, utilizing combined convolutional neural networks and long short-term models (CNN+LSTMs) to process medical records in parallel, extracting relevant information like service providers, medical specializations, and dates of service.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing machine learning systems process medical records using traditional sequential methods, then they can identify some patterns, but the processing time and computational complexity are excessive
Solution Approach 1:
The patent segments the medical record processing task into multiple parallel machine learning models, each dedicated to identifying specific patterns (comorbidity terms, ICD codes, body part information, prescription details). These models execute simultaneously in parallel, dramatically reducing overall processing time compared to sequential execution of a single model.
Solution Approach 2:
The patent combines multiple specialized machine learning models into an integrated parallel processing system. Each model is optimized for a specific type of medical data pattern, and they work together simultaneously to comprehensively analyze medical records, achieving both speed and accuracy.
2Adaptability or versatility
If existing machine learning systems use simplified processing approaches, then computational time is reduced, but they fail to identify a wide variety of patterns in medical data
Solution Approach 1:
The system divides the complex task of medical record analysis into specialized sub-tasks, with each machine learning model focused on identifying a specific type of pattern (comorbidities, ICD codes, body parts, prescriptions). This segmentation allows each model to be optimized for its specific function while collectively providing comprehensive pattern recognition.
Solution Approach 2:
The parallel machine learning system is designed to handle multiple types of medical data patterns simultaneously through a unified architecture. Each model contributes a specific function, and together they provide universal capability to extract diverse information from various forms of medical records.
3Measurement precision
If existing machine learning systems process medical records with high accuracy requirements, then they can identify sparse information, but they require significant computational resources and time
Solution Approach 1:
The patent segments the computational workload across multiple specialized models that execute in parallel. Each model processes a specific aspect of the medical record with focused computational resources, achieving high accuracy for each pattern type while distributing the overall computational burden efficiently.
Data Source
AI summary
Systems and methods for machine learning of medical records are provided. The system can execute multiple machine learning models on the medical records in parallel using multi-threaded approach wherein each machine learning model executes using its own, dedicated computational thread in order to significantly speed up the time with which relevant information can be identified from documents by the system. The multi-threaded machine learning models can include, but are not limited to, sentence classification models, comorbidity models, ICD models, body parts models, prescription models, and provider name models. The system can also utilize combined convolutional neural networks and long short-term models (CNN+LSTMs) as well as ensemble machine learning models to categorize sentences in medical records. The system can also extract service provider, medical specializations, and dates of service information from medical records.