01/06/2023
In recent years, there has been an explosion in the amount of patient Electronic Health Records (EHR) made publicly available. This presents an opportunity to create predictive models that leverage the large amount of data to help guide healthcare worker’s decision-making capacity.
Previous work in this field has not leveraged the full potential of the data, since they opt to only deal with a single modality of data, or do not leverage the temporality of the data.
Hence we would like to share a newly accepted paper
'Adversarial Learning for Improved Patient Representations'. The first author of this paper is Bharat Shankar, a student that our Director, Carol Hargreaves supervised. They attempted to create a network that creates a multimodal representation of EHR data by modeling it as a multiple sparse time series fusion task.
They show that the patient representation extracted is meaningful and useful for downstream classification tasks. Read this paper here: https://lnkd.in/g3XDybUf
In recent years, there has been an explosion in the amount of patient Electronic Health Records (EHR) made publicly available. This presents an opportunity to create predictive models that leverage the large amount of data to help guide healthcare worker’s...