System Architecture Learning Tier 1 Clinical Database Trigg WSN Learning Tier 2 - Feedback Warning .Tier 1: EWs (early warning system) Clinical data, lab tests, manually collected, low frequency Tier 2: RDs (real-time data sensing) Body sensor data, automatically collected, wirelessly transmitted, high frequency
System Architecture •Tier 1: EWS (early warning system) • Clinical data, lab tests, manually collected, low frequency •Tier 2: RDS (real-time data sensing) • Body sensor data, automatically collected, wirelessly transmitted, high frequency
Agenda Background and overview Early warning system(EWS) Real-time data sensing(RDS) Future work
Agenda 1 Background and overview 3 Real-time data sensing (RDS) 5 Future work Early warning system (EWS) 2
Medical Record(34 vital signs: pulse, temperature, oXygen saturation, shock index, respirations, age, blood pressure..) -H- Respiration -HI-Temperature 160-吾-Bp.syso Oxygen Satuarion 阜 口--口 都普一---
Medical Record (34 vital signs: pulse, temperature, oxygen saturation, shock index, respirations, age, blood pressure …) Time/second Time/second
Related work Medical data mIning medica machine knowledge learning methods Acute Physiology Score, Chronic Health Score, and Modified Early decision neural SCAP and PSI APACHE score are Warning SVM used to predict Score(MEWS) trees networks renal failures Main problems: Most previous general work uses a snapshot method that takes all the features at a given time as input to a model, discarding the temporal evolving of data
Related Work Main problems : Most previous general work uses a snapshot method that takes all the features at a given time as input to a model, discarding the temporal evolving of data Medical data mining medical knowledge machine learning methods SCAP and PSI Acute Physiology Score, Chronic Health Score , and APACHE score are used to predict renal failures Modified Early Warning Score (MEWS) decision trees neural networks SVM
Overview of ews Goal: Design an data mining algorithm that can automatically identify patients at risk of clinical deterioration based on their existing electronic medical records time-series Challenges Classification of high in different scale dimensional time series data Irregular data gaps 25000 o measurement errors 20000 class imbalance 口Non-cU 15000 口IcU
Overview of EWS Goal: Design an data mining algorithm that can automatically identify patients at risk of clinical deterioration based on their existing electronic medical records time-series. 0 5000 10000 15000 20000 25000 30000 Non-ICU ICU Challenges: • Classification of highdimensional time series data • Irregular data gaps • measurement errors • class imbalance