Multi-objective semi-supervised clustering to identify health service patterns for injured patients
This is an incremental domain-specific method for healthcare analytics to improve early intervention for injured patients.
The study tackled the problem of identifying injured patients with undesirable outcomes early by developing a multi-objective semi-supervised clustering method to group patients based on health service use patterns in the first week post-injury, which also predicts total medication costs.
This study develops a pattern recognition method that identifies patterns based on their similarity and their association with the outcome of interest. The practical purpose of developing this pattern recognition method is to group patients, who are injured in transport accidents, in the early stages post-injury. This grouping is based on distinctive patterns in health service use within the first week post-injury. The groups also provide predictive information towards the total cost of medication process. As a result, the group of patients who have undesirable outcomes are identified as early as possible based health service use patterns.