pure supervised and semi-supervised machine learning approaches (i.e., without also applying domain relevant rules) still struggle with achieving the high recall and precision rates that are required for patient diagnosis and treatment [18,27
We conducted a cohort study of individuals aged 15–65 with a diagnosis of severe mental illness through linkage of population-based registers in Sweden divided into derivation and external validation datasets. We included schizophrenia-spectrum disorders (ICD-8: 295, 297–299; ICD-9: 295, 297–...