Identifying patients using antidepressants for the treatment of depression: A predictive algorithm for use in pharmaceutical and medical claims data.
Alys HavardPeter StrakaGrant SaraSanja LujicDuong T TranLouisa R JormPublished in: Pharmacoepidemiology and drug safety (2019)
Using this algorithm with a high probability cut-off yields high specificity and facilitates the exclusion of individuals using antidepressants for indications other than depression, thereby mitigating the risk of confounding by indication when evaluating the outcomes of antidepressant use.
Keyphrases
- major depressive disorder
- end stage renal disease
- machine learning
- depressive symptoms
- ejection fraction
- deep learning
- newly diagnosed
- chronic kidney disease
- sleep quality
- peritoneal dialysis
- electronic health record
- type diabetes
- physical activity
- patient reported outcomes
- adipose tissue
- neural network
- weight loss
- data analysis
- glycemic control
- smoking cessation