The aim of the project is to use data science techniques to quantify the impact of deviations from the “Best Case Scenario” in a patient pathway, this could be diagnostics, surgical or pre-operative assessment.
- Process Mining – analysis is done into the number of deviations from a best-case scenario patient pathway.
- An unsupervised learning model is used to determine the relationship between these deviations, and the level of patient risk.
- The relationships identified in step 2 are validated.
- The End product will be a live reporting suite in Streamlit, presenting statistics in relation to the newly identified measures, plus risk stratification of the patient population.
- Simulation to identify whether risk profile changes as the pathway changes