A Comparative Study of Machine Learning Algorithms in Predicting Severe Complications after Bariatric Surgery.
Dhanisha Jayesh TrivediXin FangJohan OttossonNäslund ErikStenberg ErikPublished in: Journal of clinical medicine (2019)
In predicting the severe postoperative complication among the bariatric surgery patients, ensemble algorithms outperform base algorithms. When compared to other ML algorithms, deep NN has the potential to improve the accuracy and it deserves further investigation. The oversampling technique should be considered in the context of imbalanced data where the number of the interested outcome is relatively small.
Keyphrases
- machine learning
- big data
- bariatric surgery
- artificial intelligence
- deep learning
- end stage renal disease
- ejection fraction
- newly diagnosed
- early onset
- chronic kidney disease
- weight loss
- prognostic factors
- peritoneal dialysis
- risk factors
- patients undergoing
- electronic health record
- patient reported outcomes
- risk assessment
- climate change
- data analysis
- patient reported