Transformers for cardiac patient mortality risk prediction from heterogeneous electronic health records

被引:0
作者
Emmi Antikainen
Joonas Linnosmaa
Adil Umer
Niku Oksala
Markku Eskola
Mark van Gils
Jussi Hernesniemi
Moncef Gabbouj
机构
[1] VTT Technical Research Centre of Finland Ltd.,Faculty of Medicine and Health Technology
[2] Tampere University,Vascular Centre
[3] Finnish Cardiovascular Research Center Tampere,Tays Heart Hospital
[4] Tampere University Hospital,Faculty of Information Technology and Communication Sciences
[5] Tampere University Hospital,undefined
[6] Tampere University,undefined
来源
Scientific Reports | / 13卷
关键词
D O I
暂无
中图分类号
学科分类号
摘要
With over 17 million annual deaths, cardiovascular diseases (CVDs) dominate the cause of death statistics. CVDs can deteriorate the quality of life drastically and even cause sudden death, all the while inducing massive healthcare costs. This work studied state-of-the-art deep learning techniques to predict increased risk of death in CVD patients, building on the electronic health records (EHR) of over 23,000 cardiac patients. Taking into account the usefulness of the prediction for chronic disease patients, a prediction period of six months was selected. Two major transformer models that rely on learning bidirectional dependencies in sequential data, BERT and XLNet, were trained and compared. To our knowledge, the presented work is the first to apply XLNet on EHR data to predict mortality. The patient histories were formulated as time series consisting of varying types of clinical events, thus enabling the model to learn increasingly complex temporal dependencies. BERT and XLNet achieved an average area under the receiver operating characteristic curve (AUC) of 75.5% and 76.0%, respectively. XLNet surpassed BERT in recall by 9.8%, suggesting that it captures more positive cases than BERT, which is the main focus of recent research on EHRs and transformers.
引用
收藏
相关论文
共 47 条
  • [1] Kruse CS(2018)The use of electronic health records to support population health: A systematic review of the literature J. Med. Syst. 42 1736-1788
  • [2] Stein A(2021)Deep representation learning of patient data from electronic health records (EHR): A systematic review J. Biomed. Inform. 115 300-313
  • [3] Thomas H(2018)Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: A systematic analysis for the global burden of disease study 2017 Lancet 392 1481-1495
  • [4] Kaur H(2020)Advances in the relationship between coronavirus infection and cardiovascular diseases Biomed. Pharmacother. 127 3596-3607
  • [5] Si Y(2021)Machine learning and the future of cardiovascular care J. Am. Coll. Cardiol. 77 3121-3129
  • [6] Roth GA(2017)Big data from electronic health records for early and late translational cardiovascular research: Challenges and potential Eur. Heart J. 39 278-287
  • [7] Zhao M(2021)Limitations of transformers on clinical text classification IEEE J. Biomed. Health Inform. 25 1549-1565
  • [8] Quer G(2020)BEHRT: Transformer for electronic health records Sci. Rep. 10 218-229
  • [9] Arnaout R(2021)Med-BERT: Pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction NPJ Digit. Med. 4 156-163
  • [10] Henne M(2021)Bidirectional representation learning from transformers using multimodal electronic health record data to predict depression IEEE J. Biomed. Health Inform. 25 380-385