Encoding Health Records into Pathway Representations for Deep Learning...European Federation for Medical Informatics (EFMI) Special Topic Conference (Virtual), November 22-24, 2021.
There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient's data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a mach...
| Published in: | Studies in Health Technology & Informatics no. 287; pp. 8 - 13 |
|---|---|
| Main Authors: | , , , , |
| Format: | proceedings research tables/charts Journal Article |
| Published: |
Sage Publications Inc.
2021
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=153781164&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 153781164 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2021 iid: 287 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 153781164 153781164 153781164 10.3233/SHTI210800 153781164 ppf: 8 ppct: 5 formats: tig: atl: Encoding Health Records into Pathway Representations for Deep Learning...European Federation for Medical Informatics (EFMI) Special Topic Conference (Virtual), November 22-24, 2021. aug: au: SBODIO, Marco Luca MULLIGAN, Natasha SPEICHERT, Stefanie LOPEZ, Vanessa BETTENCOURT-SILVA, Joao affil: IBM Research Europe sug: subj: Electronic Health Records Coding Workflow Deep Learning Human Clinical Information Systems Neural Networks (Computer) Minimum Data Set Systems Integration Health Care Delivery, Integrated Congresses and Conferences ab: There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient's data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a machine-processable image-like structure useful for deep learning tasks. Based on this approach, we generated over a million pathways from FAIR synthetic health records and used them to train a convolutional neural network. Our initial experiments show the accuracy of the CNN on a prediction task is comparable or better than other autoencoders trained on the same data, while requiring significantly less computational resources for training. We also assess the impact of the size of the training dataset on autoencoders performances. The source code for generating pathways from health records is provided as open source. pubtype: Academic Journal doctype: proceedings research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|