Learning about Systems Using Machine Learning:Towards More Data-Driven Feedback Loops
- 1. Winter Simulation Conference2017 Learning about SystemsUsing Machine Learning: TowardsMore Data-DrivenFeedback Loops Mahmoud Elbattah, Owen Molloy m.elbattah1@nuigalway.ie
- 2. Winter Simulation Conference2017 Integrating M&S with Machine Learning 2 1.Why? 2.When? 3.How?
- 3. Winter Simulation Conference2017 1.Why? 3 M&S is he systematic study of modeling processes and simulation processes that describe and transform conceptualisations.1 1 Padilla, J. J., Diallo, S. Y., & Tolk, A. (2011). Do we need M&S science?. SCS M&S Magazine, 8(2011), 161-166. 2 Image Source: Huang, Y. (2013). Automated Simulation Model Generation. TU Delft. Sources of System Knowledge.2 Machine Learning is about learning and deriving knowledge from data.
- 4. Winter Simulation Conference2017 2.When? 4 Image Source: Robinson, S. (2004). Simulation: The Practice of Model Development and Use. Chichester: Wiley.
- 5. Winter Simulation Conference2017 Motivational Questions Q1) How can ML be employed to assist the conceptualisation of a system? Q2) Is it possible to integrate mental models with ML models in a way that supports the learning process to develop based on a more data-driven manner? If so, how? Q3) Which ML techniques can be appropriate for the perception of a system’s structure, or the behaviour involved within a problem? Q4) Can the integration of ML lead to a higher level of confidence in simulation models, indicated by the accuracy of ML models? 5
- 6. Winter Simulation Conference2017 Background: Feedback Loop 6Source: Forrester, J.W., 1968. Principles of Systems, Text and Workbook, Wright-Allen Press-US.
- 7. Winter Simulation Conference2017 Background: Feedback Loop (cont’d) 7Source: Sterman, J. D. 1994. Learning in and about Complex Systems. System Dynamics Review, 10(2-3).
- 8. Winter Simulation Conference2017 Our Approach: Incremental Learning to Capture Changes in System's Behaviour 8
- 9. Winter Simulation Conference2017 Use Case in Helathcare: Data Description • Irish Hip Fracture Database (IHFD). • Patient records in the years 2013-2015 (≈8k records)/ • Patients aged 60 and over. • 38 data fields such as gender, age, type of fracture, date of admission, and LOS. 9
- 10. Winter Simulation Conference2017 Modeling the Flow of Patients: Initial SD Model 10 • What is the expected consumption of hospital resources with regard to the inpatient LOS? • What is the expected proportion of elderly patients discharged to home, or long-stay care?
- 11. Winter Simulation Conference2017 Data-Driven Patient Clustering 11 K-Means clustering of patients based on: • LOS • Age • Time to Surgery
- 12. Winter Simulation Conference2017 Insights from Clusters 12
- 13. Winter Simulation Conference2017 Cluster-Based Model 13
- 14. Winter Simulation Conference2017 Simulating Data-Driven Feedback • Simulation new policy to maintain improve care standards: • Keeping the TTA and TTS within 4 hours and 48 hours respectively. • Average inpatient LOS to decrease by 20% and 30% in 2014 and 2015 respectively. • Patients discharged to long-stay residential care to decrease by 5% and 10% in 2014 and 2015 respectively. 14
- 15. Winter Simulation Conference2017 Adjusting Patient Clusters 15
- 16. Winter Simulation Conference2017 Insights from New Clusters 16
- 17. Winter Simulation Conference2017 Updated SD Model 17
- 18. Winter Simulation Conference2017 Further Directions 18
- 19. Winter Simulation Conference2017 Further Directions (Cont’d) 19
- 20. Winter Simulation Conference2017 Closing Thought: • Herbert Simon, 1983: o Changes in the system that are adaptive in the sense that they enable the system to do the same task(s) more efficiently and more effectively the next time. • ML-Aided Simulations: o Changes in the simulation model that are adaptive in the sense that they enable the model to answer the question(s)of interest more efficiently and more effectively the next time. 20Source: Simon, H.A., 1983. Why should machines learn?. In Machine learning (pp. 25-37). Springer Berlin Heidelberg.
- 21. Winter Simulation Conference2017 THANK YOU! m.elbattah1@nuigalway.ie