Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models

Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models. Yang, Z., Liu, W., Berlowitz, D., & Yu, H. December, 2022. arXiv:2212.12067 [cs]

Paper doi abstract bibtex

Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions? Findings: In this prognostic study of 6.8 million patients, our denoising sequence-to-sequence prediction model of multiple outcomes outperformed state-of-the-art models scuh pretrained BERT on a broad range of patient outcomes, including intentional self-harm and pancreatic cancer. Meaning: Deep bidirectional and autoregressive representation improves patient outcome prediction.

@misc{yang_enhancing_2022,
	title = {Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models},
	url = {http://arxiv.org/abs/2212.12067},
	doi = {10.48550/arXiv.2212.12067},
	abstract = {Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions? Findings: In this prognostic study of 6.8 million patients, our denoising sequence-to-sequence prediction model of multiple outcomes outperformed state-of-the-art models scuh pretrained BERT on a broad range of patient outcomes, including intentional self-harm and pancreatic cancer. Meaning: Deep bidirectional and autoregressive representation improves patient outcome prediction.},
	urldate = {2023-02-19},
	publisher = {arXiv},
	author = {Yang, Zhichao and Liu, Weisong and Berlowitz, Dan and Yu, Hong},
	month = dec,
	year = {2022},
	note = {arXiv:2212.12067 [cs]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Machine Learning},
}

Downloads: 0

{"_id":"q28YM2jejvADkyHps","bibbaseid":"yang-liu-berlowitz-yu-enhancingthepredictionofdiseaseoutcomesusingelectronichealthrecordsandpretraineddeeplearningmodels-2022","author_short":["Yang, Z.","Liu, W.","Berlowitz, D.","Yu, H."],"bibdata":{"bibtype":"misc","type":"misc","title":"Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models","url":"http://arxiv.org/abs/2212.12067","doi":"10.48550/arXiv.2212.12067","abstract":"Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions? Findings: In this prognostic study of 6.8 million patients, our denoising sequence-to-sequence prediction model of multiple outcomes outperformed state-of-the-art models scuh pretrained BERT on a broad range of patient outcomes, including intentional self-harm and pancreatic cancer. Meaning: Deep bidirectional and autoregressive representation improves patient outcome prediction.","urldate":"2023-02-19","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Yang"],"firstnames":["Zhichao"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Weisong"],"suffixes":[]},{"propositions":[],"lastnames":["Berlowitz"],"firstnames":["Dan"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"December","year":"2022","note":"arXiv:2212.12067 [cs]","keywords":"Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Machine Learning","bibtex":"@misc{yang_enhancing_2022,\n\ttitle = {Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models},\n\turl = {http://arxiv.org/abs/2212.12067},\n\tdoi = {10.48550/arXiv.2212.12067},\n\tabstract = {Question: Can an encoder-decoder architecture pretrained on a large dataset of longitudinal electronic health records improves patient outcome predictions? Findings: In this prognostic study of 6.8 million patients, our denoising sequence-to-sequence prediction model of multiple outcomes outperformed state-of-the-art models scuh pretrained BERT on a broad range of patient outcomes, including intentional self-harm and pancreatic cancer. Meaning: Deep bidirectional and autoregressive representation improves patient outcome prediction.},\n\turldate = {2023-02-19},\n\tpublisher = {arXiv},\n\tauthor = {Yang, Zhichao and Liu, Weisong and Berlowitz, Dan and Yu, Hong},\n\tmonth = dec,\n\tyear = {2022},\n\tnote = {arXiv:2212.12067 [cs]},\n\tkeywords = {Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Machine Learning},\n}\n\n","author_short":["Yang, Z.","Liu, W.","Berlowitz, D.","Yu, H."],"key":"yang_enhancing_2022","id":"yang_enhancing_2022","bibbaseid":"yang-liu-berlowitz-yu-enhancingthepredictionofdiseaseoutcomesusingelectronichealthrecordsandpretraineddeeplearningmodels-2022","role":"author","urls":{"Paper":"http://arxiv.org/abs/2212.12067"},"keyword":["Computer Science - Artificial Intelligence","Computer Science - Computers and Society","Computer Science - Machine Learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"misc","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":["computer science - artificial intelligence","computer science - computers and society","computer science - machine learning"],"search_terms":["enhancing","prediction","disease","outcomes","using","electronic","health","records","pretrained","deep","learning","models","yang","liu","berlowitz","yu"],"title":"Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models","year":2022}