ML-Based Patient Admission Classification System

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current manual processes for classifying patient admissions in healthcare settings are inefficient and prone to misclassification, leading to resource wastage and increased costs, as they rely on limited data and lack automated prediction capabilities.

Innovation Solution

An intelligent classification computing system utilizing a machine learning model that receives admission data, configures it for classification, and generates authorization messages based on predicted admission types, incorporating additional data sources and features like risk scores and trimester visit dates to improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual processes are used to classify patient admissions, then flexibility and adaptability are maintained, but misclassification errors increase and resource efficiency decreases

Engineering Contradiction:

Improveclassification accuracyVSAvoidresource wastage

Core Design Contradiction:

Measurement precisionVSLoss of energy

Solution Approach 1:

The system enables self-service classification by training the machine learning model to automatically categorize admissions using historical data and patterns, eliminating the need for manual review of routine cases while maintaining high accuracy through the model's learned decision-making capabilities

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual classification process with an automated machine learning system that uses algorithms to analyze admission data, diagnose reasons for admission, and generate authorizations, thereby eliminating human error and resource wastage associated with manual processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual classification processes are implemented, then human judgment and adaptability are preserved, but processing time increases and productivity decreases

Engineering Contradiction:

Improveauthorization processing speedVSAvoidclassification time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary classification and diagnosis using the trained machine learning model before human intervention is needed, pre-processing admission data to identify the reason for admission and generate authorization recommendations, thereby accelerating the overall workflow

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent substitutes manual classification operations with automated machine learning-based processing that instantly analyzes admission data and determines authorization categories, eliminating the time-consuming nature of manual review while increasing throughput

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Extent of automation

If automated machine learning classification is implemented, then processing speed and productivity increase, but system complexity and implementation difficulty increase

Engineering Contradiction:

Improveclassification automation levelVSAvoidsystem implementation complexity

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The machine learning model serves multiple functions simultaneously: it classifies admissions, diagnoses reasons for admission, predicts authorization outcomes, and generates recommendations, thereby reducing the need for separate systems and simplifying overall implementation despite the advanced capabilities

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system manages complexity by transforming unstructured admission data into structured features and parameters that the machine learning model can process, using techniques like one-hot encoding and feature extraction to convert diverse input types into a unified format suitable for automated classification

Inventive Principle:

Principle #35Parameter changes

4Reliability

If limited data from ADT messages is used for classification, then data processing simplicity is maintained, but classification accuracy and reliability decrease

Engineering Contradiction:

Improveclassification reliabilityVSAvoiddata completeness

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The system merges multiple data sources including ADT messages, patient demographic data, historical admission patterns, and clinical information into a comprehensive dataset that feeds the machine learning model, thereby enriching the input data and improving classification reliability through more complete information

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS20240006060A1Machine learning based systems and methods for classifying electronic data and generating messages

Publication Date: 2024.01.04 CENTENE CORP

AI summary

Described herein are an intelligent classification (IC) computing system including at least one processor in communication with at least one database, a non-transitory computer-readable storage medium having computer-executable instructions embodied thereon that are executable by the IC computing system, and a method implemented using the IC computing system. The at least one processor is configured to receive a message including admission data associated with at least one patient and configure the admission data into input data for a machine learning (ML) model configured to automatically classify the data by admission type, to input the input data into the ML model and based upon an output from the ML model, determine an admission type associated with the at least one patient, and to generate an authorization message associated with the at least one patient and transmit the authorization message to an external computing device for approval.