Application of machine learning to ICD-10 coded data records of patients hospitalized in Romania over the last 10 years
Project carried out in collaboration with the University of Heidelberg, Germany.
Financing source: own funds
Duration of study: 6 months (2019-2020)
The aim of the study is to inform health policy development and decision-making processes by identifying trends and predictions on the health status of the Romanian population for the next 3 years.
Study objectives:
- Identification of diseases and co-morbidities leading to unnecessary or prolonged hospitalisation;
- Predicting the likelihood and cause of death of any inpatient within the first three days of hospitalisation;
- Predicting the incidence of the ten most deadly diseases, as defined by the WHO (Ischaemic Heart Disease, Stroke, Chronic Obstructive Pulmonary Disease, Lower Respiratory Tract Infections, Alzheimer’s Disease, Lung Cancer, Diabetes Mellitus, Road Traffic Injury, Diarrhoeal Diseases, Tuberculosis), for the next 3 years.
