Development of transient ischemic attack risk prediction model suitable for initializing a learning health system unit using electronic medical records

Table 2 Comparison of performance using different numbers of variables in XGBoost TIA risk prediction models

^*XGBoost base models were developed using default settings
**Variables were sorted by the associated patient count in descending order, and various number of variables from the top of the list were selected for building models

ISSN: 1472-6947