Integrating Machine Learning

Integrating machine learning to better predict patient readmission rates

Sep 16, 2020

Share to |

High rate of patient readmission

A rural health district in NSW was battling the high rates of unexpected hospital readmissions. Although doctors and clinicians review patient information to the best of their ability before discharge, there are often little to no signs that patients are of risk of readmission. This pre-existing problem costs enormous amounts of money and resources.

Case Details

Client: Health Care sector

Category: Healthcare

Period: 6 months

Tech: SQL

Predicting chance of patient readmission

The client needed an AI solution that would automatically detect potential risks of readmission. The solution would help the hospital to make patient-personalised interventions to manage and reduce the readmission rate.

Over 10 years of electronic medical records were integrated with machine learning algorithms to create the final solution to meet the above requirements. As a result, an AI powered patient risk machine learning model was developed to analyse features of patient demographic, health condition history, and treatment results during admission. Upon analysing the data, the model can predict which patients had a potential high readmission risk and it explains the predicted severity for each case.

Total Completion time

It took six months from understanding the client’s needs, over to collecting data and building predictive analysis models to delivering the final product.

Prediction accuracy level of the model

When test data was applied to our trained model on a daily basis, the model targeted patients who had an unexpected readmission within 28 days of their initial admission with an overall 70% accuracy.

Our solution demonstrated the potential to drive real-time intervention, improve outcomes, assist hospital service efficiency, and enhance resource utilisation.

Hospitals can use this AI powered decision-making tool to assist doctors and clinicians to make real time decisions to prevent readmission after discharge. As each decision is made, the savings add-up to several thousand dollars per readmission, creating funding to solve the next problem.