Predicting healthcare trajectories from medical records: A deep learning approach

By Trang Pham, Truyen Tran, Dinh Q. Phung, Svetha Venkatesh. 2017

393 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yuan Luo
2. Benjamin M. Marlin
3. Satya Narayan Shukla
4. Dennis DeCoste

In Signal Processing

1. Yuan Luo
2. Benjamin M. Marlin
3. Satya Narayan Shukla

Citations in the corpus

• Recurrent Neural Networks for Classifying Relations in Clinical Notes (2017, positive): “[43] used LSTMs to model the longitudinal records of diagnoses, medications and procedures and made dynamic predictions of future diagnoses, medications and procedures.”
• Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review (2018, neutral): “49 54, 55 disease”
• Medical image analysis using deep learning algorithms (2023, methodology): “Pham et al. (47) discussed the use of DL to predict healthcare trajectories from medical records.”
• The Internet of Things: Impact and Implications for Health Care Delivery (2020, background): “Some examples of this include predicting risk, future medical outcomes, and care decisions in diabetes and mental health [57] and predicting the progression of congestive heart failure [58,59], bone disease [60], Alzheimer disease [61], benign and malignant tumor classification [62,63], and cardiac…”
• Multi-Time Attention Networks for Irregularly Sampled Time Series (2020, background): “Pham et al. (2017) proposed to capture time irregularity by modifying the forget gate of an LSTM (Hochreiter & Schmidhuber, 1997), while Neil et al. (2016) introduced a new time gate that regulates access to the hidden and cell state of the LSTM.”
• The rise of artificial intelligence in healthcare applications (2020, background): “As AI tools mature it will be possible to extract all kinds of information such as related disease effects and correlations between historical and future medical events [37].”