Decision Support
❯
Predict
❯Machine-learning based triage to determine low-severity patients that can be fast-tracked to admission in ED due to their short discharge length
A fairer and more personalised credit decision
For:
Payment and credit providers
Goal:
Improved Customer Experience
Moving Beyond Generalised Linear Models: A sophisticated pricing strategy incorporating competitor pricing
For:
Customer pricing
Actuaries
Goal:
Increase Revenues
Machine-learning based triage to determine low-severity patients that can be fast-tracked to admission in ED due to their short discharge length
For:
Emergency Departments in hospitals.
Goal:
Improved Employee Efficiency
Disaster and Emergency Prediction & Impact Model
For:
National-level disaster management professionals, Climate change adaptation experts, Government agencies, At-risk communities
Automated threat enrichment intelligence in Cyber security
Goal:
Improve Operation Efficiency
Deep reinforcement learning for personalized treatment recommendation
For:
Clinicians who prescribe long-term and adjustable treatments
Goal:
Improved Employee Efficiency
Applying machine learning to predict patient risk for in-hospital new infections
For:
Hospitals
Goal:
Improved Customer Experience, Anticipate Risks
Large Companies
Small Companies
Management - Market Intelligence
For:
Product managers and Marketers.
Scope:
Growing active users for a music streaming service by identifying high-value customer behavior.
Goal:
Improved Customer Experience, Increase Revenues
Weather Forecasting in Agriculture
For:
Farmers
Goal:
Anticipate Risks, Improve Operation Efficiency
AI for customers' loss prevention of telecommunication services
For:
Telecommunication companies
Goal:
Improved Customer Experience
Large Companies
Manufacturing and Factories – Predictive Maintenance
For:
Operation, R&D
Scope:
Avoiding unplanned shutdowns in Manufacturing using Machine Learning to predict failure states in equipment.
Goal:
Anticipate Risks, Improve Operation Efficiency
Disaster and Emergency Prediction & Impact Model
For:
National-level disaster management professionals, Climate change adaptation experts, Government agencies, At-risk communities.
Machine-learning based triage to determine low-severity patients that can be fast-tracked to admission in ED due to their short discharge length
For:
Emergency Departments in hospitals.
Goal:
Improved Employee EfficiencyProblem addressed
Overcrowding in emergency departments (ED) is a critical problem worldwide, and streaming can alleviate crowding to improve patient flows. Among triage scales, patients labeled as “triage level 3” or “urgent” generally comprise the majority, but there is no uniform criterion for classifying low-severity patients in this diverse population.
The goal was to establish a machine learning model for prediction of low-severity patients with short discharge length of stay. These patients could then be fast-tracked into admission and release.
Description
Both internal and external validation had to be performed in order to build and test the model. A Jan. 2018 to Dec. 2018 dataset from China Medical University Hospital (CMUH) was used for model construction and internal validation, and another from Jan. 2018 to Dec. 2019 from Asia University Hospital (AUH) was applied for external validation.
Raw Data
AI: Perceive
Machine Learning
AI: Understand
Predict / Forecast
AI: Act