Naranjo Question Answering using End-to-End Multi-task Learning Model. Rawat, B. P. S., Li, F., & Yu, H. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, of KDD '19, pages 2547–2555, New York, NY, USA, July, 2019. Association for Computing Machinery. ![Naranjo Question Answering using End-to-End Multi-task Learning Model [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex In the clinical domain, it is important to understand whether an adverse drug reaction (ADR) is caused by a particular medication. Clinical judgement studies help judge the causal relation between a medication and its ADRs. In this study, we present the first attempt to automatically infer the causality between a drug and an ADR from electronic health records (EHRs) by answering the Naranjo questionnaire, the validated clinical question answering set used by domain experts for ADR causality assessment. Using physicians' annotation as the gold standard, our proposed joint model, which uses multi-task learning to predict the answers of a subset of the Naranjo questionnaire, significantly outperforms the baseline pipeline model with a good margin, achieving a macro-weighted f-score between 0.3652-0.5271 and micro-weighted f-score between 0.9523-0.9918.
@inproceedings{rawat_naranjo_2019,
address = {New York, NY, USA},
series = {{KDD} '19},
title = {Naranjo {Question} {Answering} using {End}-to-{End} {Multi}-task {Learning} {Model}},
isbn = {978-1-4503-6201-6},
url = {https://doi.org/10.1145/3292500.3330770},
doi = {10.1145/3292500.3330770},
abstract = {In the clinical domain, it is important to understand whether an adverse drug reaction (ADR) is caused by a particular medication. Clinical judgement studies help judge the causal relation between a medication and its ADRs. In this study, we present the first attempt to automatically infer the causality between a drug and an ADR from electronic health records (EHRs) by answering the Naranjo questionnaire, the validated clinical question answering set used by domain experts for ADR causality assessment. Using physicians' annotation as the gold standard, our proposed joint model, which uses multi-task learning to predict the answers of a subset of the Naranjo questionnaire, significantly outperforms the baseline pipeline model with a good margin, achieving a macro-weighted f-score between 0.3652-0.5271 and micro-weighted f-score between 0.9523-0.9918.},
urldate = {2023-05-03},
booktitle = {Proceedings of the 25th {ACM} {SIGKDD} {International} {Conference} on {Knowledge} {Discovery} \& {Data} {Mining}},
publisher = {Association for Computing Machinery},
author = {Rawat, Bhanu Pratap Singh and Li, Fei and Yu, Hong},
month = jul,
year = {2019},
keywords = {attention networks, lstm, multi-task learning, naranjo questionnaire, naranjo scale, question answering, rnn},
pages = {2547--2555},
}
Downloads: 0
{"_id":"ecEs9dQY3BG6Z3wma","bibbaseid":"rawat-li-yu-naranjoquestionansweringusingendtoendmultitasklearningmodel-2019","author_short":["Rawat, B. P. S.","Li, F.","Yu, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"KDD '19","title":"Naranjo Question Answering using End-to-End Multi-task Learning Model","isbn":"978-1-4503-6201-6","url":"https://doi.org/10.1145/3292500.3330770","doi":"10.1145/3292500.3330770","abstract":"In the clinical domain, it is important to understand whether an adverse drug reaction (ADR) is caused by a particular medication. Clinical judgement studies help judge the causal relation between a medication and its ADRs. In this study, we present the first attempt to automatically infer the causality between a drug and an ADR from electronic health records (EHRs) by answering the Naranjo questionnaire, the validated clinical question answering set used by domain experts for ADR causality assessment. Using physicians' annotation as the gold standard, our proposed joint model, which uses multi-task learning to predict the answers of a subset of the Naranjo questionnaire, significantly outperforms the baseline pipeline model with a good margin, achieving a macro-weighted f-score between 0.3652-0.5271 and micro-weighted f-score between 0.9523-0.9918.","urldate":"2023-05-03","booktitle":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","publisher":"Association for Computing Machinery","author":[{"propositions":[],"lastnames":["Rawat"],"firstnames":["Bhanu","Pratap","Singh"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Fei"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"July","year":"2019","keywords":"attention networks, lstm, multi-task learning, naranjo questionnaire, naranjo scale, question answering, rnn","pages":"2547–2555","bibtex":"@inproceedings{rawat_naranjo_2019,\n\taddress = {New York, NY, USA},\n\tseries = {{KDD} '19},\n\ttitle = {Naranjo {Question} {Answering} using {End}-to-{End} {Multi}-task {Learning} {Model}},\n\tisbn = {978-1-4503-6201-6},\n\turl = {https://doi.org/10.1145/3292500.3330770},\n\tdoi = {10.1145/3292500.3330770},\n\tabstract = {In the clinical domain, it is important to understand whether an adverse drug reaction (ADR) is caused by a particular medication. Clinical judgement studies help judge the causal relation between a medication and its ADRs. In this study, we present the first attempt to automatically infer the causality between a drug and an ADR from electronic health records (EHRs) by answering the Naranjo questionnaire, the validated clinical question answering set used by domain experts for ADR causality assessment. Using physicians' annotation as the gold standard, our proposed joint model, which uses multi-task learning to predict the answers of a subset of the Naranjo questionnaire, significantly outperforms the baseline pipeline model with a good margin, achieving a macro-weighted f-score between 0.3652-0.5271 and micro-weighted f-score between 0.9523-0.9918.},\n\turldate = {2023-05-03},\n\tbooktitle = {Proceedings of the 25th {ACM} {SIGKDD} {International} {Conference} on {Knowledge} {Discovery} \\& {Data} {Mining}},\n\tpublisher = {Association for Computing Machinery},\n\tauthor = {Rawat, Bhanu Pratap Singh and Li, Fei and Yu, Hong},\n\tmonth = jul,\n\tyear = {2019},\n\tkeywords = {attention networks, lstm, multi-task learning, naranjo questionnaire, naranjo scale, question answering, rnn},\n\tpages = {2547--2555},\n}\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Rawat, B. P. S.","Li, F.","Yu, H."],"key":"rawat_naranjo_2019","id":"rawat_naranjo_2019","bibbaseid":"rawat-li-yu-naranjoquestionansweringusingendtoendmultitasklearningmodel-2019","role":"author","urls":{"Paper":"https://doi.org/10.1145/3292500.3330770"},"keyword":["attention networks","lstm","multi-task learning","naranjo questionnaire","naranjo scale","question answering","rnn"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/sarveshsoni","dataSources":["taWdMrienBzqHC2tC"],"keywords":["attention networks","lstm","multi-task learning","naranjo questionnaire","naranjo scale","question answering","rnn"],"search_terms":["naranjo","question","answering","using","end","end","multi","task","learning","model","rawat","li","yu"],"title":"Naranjo Question Answering using End-to-End Multi-task Learning Model","year":2019}