{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T19:32:04Z","timestamp":1784489524811,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,8,13]],"date-time":"2017-08-13T00:00:00Z","timestamp":1502582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1514204"],"award-info":[{"award-number":["IIS-1514204"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,8,13]]},"DOI":"10.1145\/3097983.3098088","type":"proceedings-article","created":{"date-parts":[[2017,8,4]],"date-time":"2017-08-04T18:35:54Z","timestamp":1501871754000},"page":"1903-1911","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":446,"title":["Dipole"],"prefix":"10.1145","author":[{"given":"Fenglong","family":"Ma","sequence":"first","affiliation":[{"name":"SUNY Buffalo &amp; Xerox, Buffalo, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radha","family":"Chitta","sequence":"additional","affiliation":[{"name":"Conduent Labs US, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Conduent Labs US, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanzeng","family":"You","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Sun","sequence":"additional","affiliation":[{"name":"United Technologies Research Center &amp; Xerox, East Hartford, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Gao","sequence":"additional","affiliation":[{"name":"SUNY Buffalo, Buffalo, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR'15)","author":"Ba Jimmy","year":"2015","unstructured":"Jimmy Ba , Volodymyr Mnih , and Koray Kavukcuoglu 2015 . Multiple Object Recognition with Visual Attention . Proceedings of the 3rd International Conference on Learning Representations (ICLR'15) . Jimmy Ba, Volodymyr Mnih, and Koray Kavukcuoglu 2015. Multiple Object Recognition with Visual Attention. Proceedings of the 3rd International Conference on Learning Representations (ICLR'15)."},{"key":"e_1_3_2_1_2_1","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate Proceedings of the 3rd International Conference on Learning Representations (ICLR'15)","author":"Bahdanau Dzmitry","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2015. Neural Machine Translation by Jointly Learning to Align and Translate Proceedings of the 3rd International Conference on Learning Representations (ICLR'15) . Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate Proceedings of the 3rd International Conference on Learning Representations (ICLR'15)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783365"},{"key":"e_1_3_2_1_6_1","volume-title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values. arXiv preprint arXiv:1606.01865","author":"Che Zhengping","year":"2016","unstructured":"Zhengping Che , Sanjay Purushotham , Kyunghyun Cho , David Sontag , and Yan Liu 2016. Recurrent Neural Networks for Multivariate Time Series with Missing Values. arXiv preprint arXiv:1606.01865 ( 2016 ). Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu 2016. Recurrent Neural Networks for Multivariate Time Series with Missing Values. arXiv preprint arXiv:1606.01865 (2016)."},{"key":"e_1_3_2_1_7_1","volume-title":"Risk Prediction with Electronic Health Records: A Deep Learning Approach Proceedings of the 2016 SIAM International Conference on Data Mining (SDM'16)","author":"Cheng Yu","year":"2016","unstructured":"Yu Cheng , Fei Wang , Ping Zhang , and Jianying Hu . 2016 . Risk Prediction with Electronic Health Records: A Deep Learning Approach Proceedings of the 2016 SIAM International Conference on Data Mining (SDM'16) . 432--440. Yu Cheng, Fei Wang, Ping Zhang, and Jianying Hu. 2016. Risk Prediction with Electronic Health Records: A Deep Learning Approach Proceedings of the 2016 SIAM International Conference on Data Mining (SDM'16). 432--440."},{"key":"e_1_3_2_1_8_1","volume-title":"Dzmitry Bahdanau, and Yoshua Bengio","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart Van Merri\u00ebnboer , Dzmitry Bahdanau, and Yoshua Bengio 2014 . On the Properties of Neural Machine Translation: Encoder-Decoder Approaches . arXiv preprint arXiv:1409.1259 (2014). Kyunghyun Cho, Bart Van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_3_2_1_9_1","volume-title":"Multi-layer Representation Learning for Medical Concepts Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16)","author":"Choi Edward","year":"2016","unstructured":"Edward Choi , Mohammad Taha Bahadori , Elizabeth Searles , Catherine Coffey , Michael Thompson , James Bost , Javier Tejedor-Sojo , and Jimeng Sun . 2016 . Multi-layer Representation Learning for Medical Concepts Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16) . 1495--1504. Edward Choi, Mohammad Taha Bahadori, Elizabeth Searles, Catherine Coffey, Michael Thompson, James Bost, Javier Tejedor-Sojo, and Jimeng Sun. 2016. Multi-layer Representation Learning for Medical Concepts Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'16). 1495--1504."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098126"},{"key":"e_1_3_2_1_11_1","volume-title":"Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart.","author":"Choi Edward","year":"2016","unstructured":"Edward Choi , Mohammad Taha Bahadori , Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. 2016 . RETAIN : An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism. In Advances in Neural Information Processing Systems (NIPS '16). 3504--3512. Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. 2016. RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism. In Advances in Neural Information Processing Systems (NIPS'16). 3504--3512."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.144"},{"key":"e_1_3_2_1_13_1","unstructured":"Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based Models for Speech Recognition. In Advances in Neural Information Processing Systems (NIPS'15). 577--585. Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based Models for Speech Recognition. In Advances in Neural Information Processing Systems (NIPS'15). 577--585."},{"key":"e_1_3_2_1_14_1","unstructured":"Karl Moritz Hermann Tomas Kocisky Edward Grefenstette Lasse Espeholt Will Kay Mustafa Suleyman and Phil Blunsom 2015. Teaching Machines to Read and Comprehend. In Advances in Neural Information Processing Systems (NIPS'15). 1693--1701. Karl Moritz Hermann Tomas Kocisky Edward Grefenstette Lasse Espeholt Will Kay Mustafa Suleyman and Phil Blunsom 2015. Teaching Machines to Read and Comprehend. In Advances in Neural Information Processing Systems (NIPS'15). 1693--1701."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3208"},{"key":"e_1_3_2_1_17_1","volume-title":"Ying Zhang, Saizheng Zhang, Aaron C Courville, and Yoshua Bengio","author":"Lamb Alex M","year":"2016","unstructured":"Alex M Lamb , Anirudh Goyal ALIAS PARTH GOYAL , Ying Zhang, Saizheng Zhang, Aaron C Courville, and Yoshua Bengio 2016 . Professor Forcing : A New Algorithm for Training Recurrent Networks Advances In Neural Information Processing Systems (NIPS '16). 4601--4609. Alex M Lamb, Anirudh Goyal ALIAS PARTH GOYAL, Ying Zhang, Saizheng Zhang, Aaron C Courville, and Yoshua Bengio 2016. Professor Forcing: A New Algorithm for Training Recurrent Networks Advances In Neural Information Processing Systems (NIPS'16). 4601--4609."},{"key":"e_1_3_2_1_18_1","volume-title":"Modeling Missing Data in Clinical Time Series with RNNs Proceedings of Machine Learning for Healthcare (MLHC'16)","author":"Lipton Zachary C","year":"2016","unstructured":"Zachary C Lipton , David C Kale , and Randall Wetzel . 2016 . Modeling Missing Data in Clinical Time Series with RNNs Proceedings of Machine Learning for Healthcare (MLHC'16) . Zachary C Lipton, David C Kale, and Randall Wetzel. 2016. Modeling Missing Data in Clinical Time Series with RNNs Proceedings of Machine Learning for Healthcare (MLHC'16)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Chuanren Liu Fei Wang Jianying Hu and Hui Xiong. 2015. Temporal Phenotyping from Longitudinal Electronic Health Records: A Graph based Framework Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'15). ACM 705--714. Chuanren Liu Fei Wang Jianying Hu and Hui Xiong. 2015. Temporal Phenotyping from Longitudinal Electronic Health Records: A Graph based Framework Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'15). ACM 705--714.","DOI":"10.1145\/2783258.2783352"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP'15). 1412--1421. Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP'15). 1412--1421.","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_1_21_1","volume-title":"Unsupervised Discovery of Drug Side-Effects from Heterogeneous Data Sources Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17). ACM","author":"Ma Fenglong","unstructured":"Fenglong Ma , Chuishi Meng , Houping Xiao , Qi Li , Jing Gao , Lu Su , and Aidong Zhang 2017. Unsupervised Discovery of Drug Side-Effects from Heterogeneous Data Sources Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17). ACM . Fenglong Ma, Chuishi Meng, Houping Xiao, Qi Li, Jing Gao, Lu Su, and Aidong Zhang 2017. Unsupervised Discovery of Drug Side-Effects from Heterogeneous Data Sources Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17). ACM."},{"key":"e_1_3_2_1_22_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean 2013. Distributed Representations of Words and Phrases and Their Compositionality Advances in Neural Information Processing Systems (NIPS'13). 3111--3119. Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean 2013. Distributed Representations of Words and Phrases and Their Compositionality Advances in Neural Information Processing Systems (NIPS'13). 3111--3119."},{"key":"e_1_3_2_1_23_1","volume-title":"Deepr: A Convolutional Net for Medical Records","author":"Nguyen Phuoc","year":"2016","unstructured":"Phuoc Nguyen , Truyen Tran , Nilmini Wickramasinghe , and Svetha Venkatesh 2016. Deepr: A Convolutional Net for Medical Records . IEEE Journal of Biomedical and Health Informatics ( 2016 ). Phuoc Nguyen, Truyen Tran, Nilmini Wickramasinghe, and Svetha Venkatesh 2016. Deepr: A Convolutional Net for Medical Records. IEEE Journal of Biomedical and Health Informatics (2016)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the AMIA 2017 Annual Symposium (AMIA'17)","author":"Suo Qiuling","year":"2017","unstructured":"Qiuling Suo , Fenglong Ma , Giovanni Canino , Jing Gao , Aidong Zhang , Pierangelo Veltri , and Agostino Gnasso 2017 . A Multi-task Framework for Monitoring Health Conditions via Attention-based Recurrent Neural Networks . In Proceedings of the AMIA 2017 Annual Symposium (AMIA'17) . Qiuling Suo, Fenglong Ma, Giovanni Canino, Jing Gao, Aidong Zhang, Pierangelo Veltri, and Agostino Gnasso 2017. A Multi-task Framework for Monitoring Health Conditions via Attention-based Recurrent Neural Networks. In Proceedings of the AMIA 2017 Annual Symposium (AMIA'17)."},{"key":"e_1_3_2_1_26_1","volume-title":"Unsupervised Learning of Disease Progression Models Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14)","author":"Wang Xiang","year":"2014","unstructured":"Xiang Wang , David Sontag , and Fei Wang 2014 . Unsupervised Learning of Disease Progression Models Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14) . ACM, 85--94. Xiang Wang, David Sontag, and Fei Wang 2014. Unsupervised Learning of Disease Progression Models Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14). ACM, 85--94."},{"key":"e_1_3_2_1_27_1","volume-title":"Turaga","author":"Xiao Houping","year":"2017","unstructured":"Houping Xiao , Jing Gao , Long Vu , and Deepak S . Turaga . 2017 . Learning Temporal State of Diabetes Patients via Combining Behavioral and Demographic Data Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17). ACM. Houping Xiao, Jing Gao, Long Vu, and Deepak S. Turaga. 2017. Learning Temporal State of Diabetes Patients via Combining Behavioral and Demographic Data Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'17). ACM."},{"key":"e_1_3_2_1_28_1","volume-title":"Attend and Tell: Neural Image Caption Generation with Visual Attention Proceedings of the 32nd International Conference on Machine Learning (ICML'15)","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Ba , Ryan Kiros , Kyunghyun Cho , Aaron Courville , Ruslan Salakhutdinov , Richard S Zemel , and Yoshua Bengio . 2015 . Show , Attend and Tell: Neural Image Caption Generation with Visual Attention Proceedings of the 32nd International Conference on Machine Learning (ICML'15) . CoRR , 2048--2057. Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhutdinov, Richard S Zemel, and Yoshua Bengio. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention Proceedings of the 32nd International Conference on Machine Learning (ICML'15). CoRR, 2048--2057."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"e_1_3_2_1_30_1","volume-title":"ADADELTA: An Adaptive Learning Rate Method. arXiv preprint arXiv:1212.5701","author":"Zeiler Matthew D","year":"2012","unstructured":"Matthew D Zeiler . 2012 . ADADELTA: An Adaptive Learning Rate Method. arXiv preprint arXiv:1212.5701 (2012). Matthew D Zeiler. 2012. ADADELTA: An Adaptive Learning Rate Method. arXiv preprint arXiv:1212.5701 (2012)."},{"key":"e_1_3_2_1_31_1","volume-title":"Patient Risk Prediction Model via Top-k Stability Selection Proceedings of the 13th SIAM International Conference on Data Mining (SDM'13)","author":"Zhou Jiayu","unstructured":"Jiayu Zhou , Jimeng Sun , Yashu Liu , Jianying Hu , and Jieping Ye 2013. Patient Risk Prediction Model via Top-k Stability Selection Proceedings of the 13th SIAM International Conference on Data Mining (SDM'13) . SIAM , 55--63. Jiayu Zhou, Jimeng Sun, Yashu Liu, Jianying Hu, and Jieping Ye 2013. Patient Risk Prediction Model via Top-k Stability Selection Proceedings of the 13th SIAM International Conference on Data Mining (SDM'13). SIAM, 55--63."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623711"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Jiayu Zhou Lei Yuan Jun Liu and Jieping Ye. 2011. A Multi-Task Learning Formulation for Predicting Disease Progression Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'11). ACM 814--822. endthebibliography Jiayu Zhou Lei Yuan Jun Liu and Jieping Ye. 2011. A Multi-Task Learning Formulation for Predicting Disease Progression Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'11). ACM 814--822. endthebibliography","DOI":"10.1145\/2020408.2020549"}],"event":{"name":"KDD '17: The 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","location":"Halifax NS Canada","acronym":"KDD '17","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3098088","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097983.3098088","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3097983.3098088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T20:39:09Z","timestamp":1750797549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3097983.3098088"}},"subtitle":["Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks"],"short-title":[],"issued":{"date-parts":[[2017,8,13]]},"references-count":33,"alternative-id":["10.1145\/3097983.3098088","10.1145\/3097983"],"URL":"https:\/\/doi.org\/10.1145\/3097983.3098088","relation":{},"subject":[],"published":{"date-parts":[[2017,8,13]]},"assertion":[{"value":"2017-08-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}