×
Towards Interpretability and Personalization: A Predictive Framework for Clinical Time-series Analysis. Abstract: Clinical time-series is receiving long-term ...
We propose a novel predictive clinical time-series analysis framework. Specifically, our framework uses task-specific information to rule out the task- ...
Towards Interpretability and Personalization: A Predictive Framework for Clinical Time-series Analysis. December 2021. DOI:10.1109/ICDM51629.2021.00045.
The proposed framework consists of four modules: (i) a rationale selector that rules out vari- ables irrelevant to the predicted outcomes at patient level,. (ii) ...
Clinical time-series is receiving long-term attention in data mining and machine learning communities and has boosted a variety of data-driven applications.
We propose a personalized clinical time-series representation learning framework via abnormal offsets analysis named PARSE for clinical risk prediction.
Clinical time-series is receiving long-term attention in data mining and machine learning communities and has boosted a variety of data-driven applications.
a novel end-to-end deep learning framework that converts citation signals from dynamic heterogeneous information networks (DHIN) into citation time series.
To provide a solid foundation upon which to clarify goals and elements for interpretable MLMI, we start by enumerating the use cases of medical image analysis, ...
We propose a personalized clinical time-series representation learning framework via abnormal offsets analysis named PARSE for clinical risk prediction.