Computing in cardiology · 2019 · 41 citations · 17 references
ComputingBiomedical InformaticsHealth InformaticsElectronic Health RecordsMachine LearningPredictive AnalyticsDecision Support AnalyticsElectronic Health Record AnalyticsPredictive Health ModelingSepsis DiagnosisSepsis RecognitionTime Series Feature ExtractionEarly Sepsis DetectionHospital Electronic Health RecordsLongitudinal EffectsPredictive Modeling Of SepsisSepsis Prediction ModelsSignature-based DetectionSupervised Signature LearningUtility Function Estimation
Optimal feature selection leads to enhanced efficiency and accuracy when developing both supervised and unsupervised machine-learning models. In this work, a new signature-based regression model is proposed to automatically identify a patient's risk of sepsis based on physiological data streams and to make a positive or negative prediction of sepsis for every time interval since admission to the intensive care unit. The gradient boosting machine algorithm that uses the features at the current time-points and the signature features extracted from the time-series to model the longitudinal effects of sepsis yields the utility function score of 0.360 (officially ranked 1st, team name: 'Can I get your Signature?') on the full test set. The signature method shows a systematic and competitive approach to model sepsis by learning from health data streams.
17
LightGBM: A Highly Efficient Gradient Boosting Decision Tree
Guolin Ke, Qi Meng, Thomas Finley et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2017 · 9.5K citations · Full text
Anand Kumar, Daniel Roberts, Kenneth E. Wood et al. · Critical Care Medicine · 2006 · 6.1K citations
Veterinary Medicine, Infectious Diseases, Antimicrobial Pharmacotherapy +13