Enhanced Care Management - Prediction model for hospitalisation/assistance

Responsible organisation: Estonian Health Insurance Fund (Governmental)

In 2015, the Estonian Health Insurance Fund started cooperating with the World Bank to develop and pilot a risk-based management model that would help increase the integration of health services. With risk-based management, GPs can identify patients with multiple chronic diseases on their list for whom additional prevention, counseling and monitoring would be most beneficial to their health and quality of life. If these patients are neglected by the GP teams, this can lead to serious problems, including unnecessary deterioration in health, which not only causes health damage but also unnecessary costs to the healthcare system (avoidable hospitalizations, duplication of examinations, etc.). The created solution finds the best algorithm for predicting which patients with selected diagnoses are likely to be hospitalized. In the solution, the EHIF database of medical bills first finds certain conditions / diagnoses to be included in the algorithm. Different models have their own strengths, but the differences should not be big. The results of the solution are comparable to the results of research presented in the literature: John Hopkins Adjusted Clinical Groups (the leading proprietary risk stratification tool) - Haas et al .; Risk-Stratification Methods for Identifying Patients for Care Coordination; The American Journal of Managed Care (September 2013). The machine learning model is better than the old mechanical model in finding patients at risk. The solution makes it possible to create a practical model for GP centers to predict which patients are more likely to end up in hospital or at other health risks.

Additional information

Source AI Watch - Artificial Intelligence in public services. Overview of the use and impact of AI in public services in the EU
Web site https://www.kratid.ee/haigekassa-kasutuslug
Start/end date 2021/01/01 -
Still active? Unknown

Related AI cases