Feasibility of machine learning based predictive modelling of postoperative hyponatremia after pituitary surgery.
Stefanos VoglisChristiaan H B van NiftrikVictor E StaartjesGiovanna BrandiOliver TschoppLuca RegliCarlo SerraPublished in: Pituitary (2021)
Our trained ML-model was able to learn the complex risk factor interactions and showed a high discriminative capability on unseen patient data. In conclusion, ML-methods can predict postoperative hyponatremia and thus potentially reduce morbidity and improve patient safety.
Keyphrases
- patient safety
- machine learning
- patients undergoing
- quality improvement
- minimally invasive
- risk factors
- big data
- coronary artery bypass
- case report
- electronic health record
- artificial intelligence
- acute heart failure
- resistance training
- surgical site infection
- heart failure
- deep learning
- atrial fibrillation
- acute coronary syndrome
- body composition