{"type":"ScholarlyArticle","title":"Cumulative Stay-time Representation for Electronic Health Records in Medical Event Time Prediction","authors":[{"name":"Takayuki Katsuki","slug":"takayuki-katsuki","given":"Takayuki","family":"Katsuki","affiliation":"IBM Research -Tokyo"},{"name":"Kohei Miyaguchi","slug":"kohei-miyaguchi","given":"Kohei","family":"Miyaguchi","affiliation":"IBM Research -Tokyo"},{"name":"Akira Koseki","slug":"akira-koseki","given":"Akira","family":"Koseki","affiliation":"IBM Research -Tokyo"},{"name":"Toshiya Iwamori","slug":"toshiya-iwamori","given":"Toshiya","family":"Iwamori","affiliation":"IBM Research -Tokyo"},{"name":"Ryosuke Yanagiya","slug":"ryosuke-yanagiya","given":"Ryosuke","family":"Yanagiya","affiliation":"Fujita Health University"},{"name":"Atsushi Suzuki","slug":"atsushi-suzuki","given":"Atsushi","family":"Suzuki","affiliation":"Fujita Health University"}],"abstract":"We address the problem of predicting when a disease will develop, i.e., medical event time (MET), from a patient's electronic health record (EHR).\r\nThe MET of non-communicable diseases like diabetes is highly correlated to cumulative health conditions, more specifically, how much time the patient spent with specific health conditions in the past.\r\nThe common time-series representation is indirect in extracting such information from EHR because it focuses on detailed dependencies between values in successive observations, not cumulative information.\r\nWe propose a novel data representation for EHR called cumulative stay-time representation (CTR), which directly models such cumulative health conditions.\r\nWe derive a trainable construction of CTR based on neural networks that has the flexibility to fit the target data and scalability to handle high-dimensional EHR.\r\nNumerical experiments using synthetic and real-world datasets demonstrate that CTR alone achieves a high prediction performance, and it enhances the performance of existing models when combined with them.","doi":"10.24963/ijcai.2022/536","url":"https://ijcai.org/proceedings/2022/536","pdf":"https://ijcai.org/proceedings/2022/0536.pdf","markdown":"https://ijcai.org/proceedings/2022/536.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/536","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":536,"pages":{"first":3861,"last":3867},"keywords":["Machine Learning: Applications","Machine Learning: Representation learning","Machine Learning: Feature Extraction, Selection and Dimensionality Reduction","Multidisciplinary Topics and Applications: Health and Medicine"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986836","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984979","length_sec":332,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Agrawal et al., 1993] Rakesh Agrawal, Christos Faloutsos, and Arun Swami. Efficient similarity search in sequence databases. In FODO, pages 69-84, 1993.","title":"Efficient similarity search in sequence databases","authors":"Rakesh Agrawal, Christos Faloutsos, Arun Swami","year":"1993","venue":"FODO","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Alaa and van der Schaar, 2019] Ahmed Alaa and Mihaela van der Schaar. Attentive state-space modeling of disease progression. In NeurIPS, 2019. [Am Diabetes Assoc, 2019] Am Diabetes Assoc. Classification and diagnosis of diabetes: standards of medical care in diabetes. Di- abetes care, 42(Supplement 1):S13-S28, 2019.","title":"Am Diabetes Assoc. Classification and diagnosis of diabetes: standards of medical care in diabetes","authors":"Alaa, Van Der Schaar, Ahmed Alaa, Mihaela Van Der Schaar","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Andrienko et al., 2007] Gennady Andrienko, Natalia Andrienko, and Stefan Wrobel. Visual analytics tools for analysis of move- ment data. ACM SIGKDD Explorations Newsletter, 9(2):38-46, 2007.","title":"Visual analytics tools for analysis of movement data","authors":"Gennady Andrienko, Natalia Andrienko, Stefan Wrobel","year":"2007","venue":"ACM SIGKDD Explorations Newsletter","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bagnall et al., 2006] Anthony Bagnall, Eamonn Keogh, Stefano Lonardi, Gareth Janacek, et al. A bit level representation for time series data mining with shape based similarity. Data Mining and Knowledge Discovery, 13(1):11-40, 2006.","title":"A bit level representation for time series data mining with shape based similarity","authors":"Anthony Bagnall, Eamonn Keogh, Stefano Lonardi, Gareth Janacek","year":"2006","venue":"Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Boukhechba et al., 2018] Mehdi Boukhechba, Philip Chow, Karl Fua, Bethany A Teachman, and Laura E Barnes. Predicting social anxiety from global positioning system traces of college students: feasibility study. JMIR mental health, 5(3):e10101, 2018.","title":"Predicting social anxiety from global positioning system traces of college students: feasibility study","authors":"Mehdi Boukhechba, Philip Chow, Karl Fua, Bethany A Teachman, Laura E Barnes","year":"2018","venue":"JMIR mental health","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2016] Yu Cheng, Fei Wang, Ping Zhang, and Jiany- ing Hu. Risk prediction with electronic health records: A deep learning approach. In SDM, pages 432-440, 2016.","title":"Risk prediction with electronic health records: A deep learning approach","authors":"Yu Cheng, Fei Wang, Ping Zhang, Jianying Hu","year":"2016","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fu, 2011] Tak-chung Fu. A review on time series data mining. En- gineering Applications of Artificial Intelligence, 24(1):164-181, 2011.","title":"A review on time series data mining","authors":"Tak-Chung Fu","year":"2011","venue":"Engineering Applications of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ho et al., 2014] Joyce C Ho, Joydeep Ghosh, and Jimeng Sun. Marble: high-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization. In KDD, pages 115-124, 2014.","title":"Marble: high-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization","authors":"Joydeep Joyce C Ho, Jimeng Ghosh, Sun","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hussain et al., 2021] Zeshan Hussain, Rahul G Krishnan, and David Sontag. Neural pharmacodynamic state space modeling. In ICML, 2021.","title":"Neural pharmacodynamic state space modeling","authors":"Zeshan Hussain, Rahul G Krishnan, David Sontag","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Inaguma et al., 2020] Daijo Inaguma, Akimitsu Kitagawa, Ryosuke Yanagiya, Akira Koseki, Toshiya Iwamori, Michiharu Kudo, and Yukio Yuzawa. Increasing tendency of urine protein is a risk factor for rapid egfr decline in patients with ckd: A machine learning-based prediction model by using a big database. PLoS One, 15(9 September), September 2020.","title":"Increasing tendency of urine protein is a risk factor for rapid egfr decline in patients with ckd: A machine learning-based prediction model by using a big database","authors":"Inaguma","year":"2020","venue":"PLoS One","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[James et al., 2014] Paul A James, Suzanne Oparil, Barry L Carter, William C Cushman, Cheryl Dennison-Himmelfarb, Joel Han- dler, Daniel T Lackland, Michael L LeFevre, Thomas D MacKenzie, Olugbenga Ogedegbe, et al. 2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the eighth joint na- tional committee (jnc 8). Jama, 311(5):507-520, 2014.","title":"2014 evidence-based guideline for the management of high blood pressure in adults: report from the panel members appointed to the eighth joint national committee (jnc 8)","authors":"A Paul, Suzanne James, Oparil, L Barry, William C Carter, Cheryl Cushman, Joel Dennison-Himmelfarb, Handler, Daniel T Lackland, Thomas D Michael L Lefevre, Olugbenga Mackenzie, Ogedegbe","year":"2014","venue":"Jama","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jiang et al., 2018] Jianguo Jiang, Xiaonan Lv, Yanfang Zhang, and Siye Wang. Research on hotspots finding in indoor space based on regression analysis. In ICCDE, pages 98-102, 2018.","title":"Research on hotspots finding in indoor space based on regression analysis","authors":"Jianguo Jiang, Xiaonan Lv, Yanfang Zhang, Siye Wang","year":"2018","venue":"ICCDE","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liao et al., 2018] Lyuchao Liao, Jianping Wu, Fumin Zou, Jeng- shyang Pan, and Tingting Li. Trajectory topic modelling to char- acterize driving behaviors with gps-based trajectory data. Journal of Internet Technology, 19(3):815-824, 2018.","title":"Trajectory topic modelling to characterize driving behaviors with gps-based trajectory data","authors":"Lyuchao Liao, Jianping Wu, Fumin Zou, Jengshyang Pan, Tingting Li","year":"2018","venue":"Journal of Internet Technology","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2018] Bin Liu, Ying Li, Zhaonan Sun, Soumya Ghosh, and Kenney Ng. Early prediction of diabetes complications from electronic health records: A multi-task survival analysis ap- proach. In AAAI, 2018. [Lovrić et al., 2014]","title":"Early prediction of diabetes complications from electronic health records: A multi-task survival analysis approach","authors":"Bin Liu, Ying Li, Zhaonan Sun, Soumya Ghosh, Kenney Ng","year":"2014","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"Miodrag Lovrić, Marina Milanović, and Mi- lan Stamenković. Algoritmic methods for segmentation of time series: An overview. Journal of Contemporary Economic and Business Issues, 1(1):31-53, 2014.","title":"Algoritmic methods for segmentation of time series: An overview","authors":"Miodrag Lovrić, Marina Milanović, Milan Stamenković","year":"2014","venue":"Journal of Contemporary Economic and Business Issues","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Luo et al., 2020] Junyu Luo, Muchao Ye, Cao Xiao, and Fenglong Ma. Hitanet: Hierarchical time-aware attention networks for risk prediction on electronic health records. In KDD, pages 647-656, 2020.","title":"Hitanet: Hierarchical time-aware attention networks for risk prediction on electronic health records","authors":"Luo","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Makino et al., 2019] Masaki Makino, Ryo Yoshimoto, Masaki Ono, Toshinari Itoko, Takayuki Katsuki, Akira Koseki, Michi- haru Kudo, Kyoichi Haida, Jun Kuroda, Ryosuke Yanagiya, et al. Artificial intelligence predicts the progression of diabetic kid- ney disease using big data machine learning. Scientific reports, 9(1):1-9, 2019.","title":"Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning","authors":"Masaki Makino, Ryo Yoshimoto, Masaki Ono, Toshinari Itoko, Takayuki Katsuki, Akira Koseki, Michiharu Kudo, Kyoichi Haida, Jun Kuroda, Ryosuke Yanagiya","year":"2019","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nair and Hinton, 2010] Vinod Nair and Geoffrey E Hinton. Rec- tified linear units improve restricted boltzmann machines. In ICML, pages 807-814, 2010.","title":"Rectified linear units improve restricted boltzmann machines","authors":"Vinod Nair, Geoffrey E Hinton","year":"2010","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rajaraman and Ullman, 2011] Anand Rajaraman and Jef- frey David Ullman. Mining of massive datasets. Cambridge University Press, 2011.","title":"Mining of massive datasets","authors":"Ullman Rajaraman, Anand Rajaraman, Jeffrey David Ullman","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rubanova et al., 2019] Yulia Rubanova, Ricky TQ Chen, and David K Duvenaud. Latent ordinary differential equations for irregularly-sampled time series. In NeurIPS, pages 5320-5330, 2019.","title":"Latent ordinary differential equations for irregularly-sampled time series","authors":"Yulia Rubanova, Ricky Tq Chen, David K Duvenaud","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Silva et al., 2012] Ikaro Silva, George Moody, Daniel J Scott, Leo A Celi, and Roger G Mark. Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge 2012. In Computing in Cardiology, pages 245-248. IEEE, 2012.","title":"Predicting in-hospital mortality of icu patients: The physionet/computing in cardiology challenge","authors":"Ikaro Silva, George Moody, J Daniel, Leo A Scott, Roger G Celi, Mark","year":"2012","venue":"Computing in Cardiology","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Takahashi and Idé, 2012] Toshihiro Takahashi and Tsuyoshi Idé. Predicting battery life from usage trajectory patterns. In ICPR, pages 2946-2949. IEEE, 2012.","title":"Predicting battery life from usage trajectory patterns","authors":"Toshihiro Takahashi, Tsuyoshi Idé","year":"2012","venue":"ICPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tan et al., 2020] Qingxiong Tan, Mang Ye, Baoyao Yang, Siqi Liu, Andy Jinhua Ma, Terry Cheuk-Fung Yip, Grace Lai-Hung Wong, and PongChi Yuen. Data-gru: Dual-attention time-aware gated recurrent unit for irregular multivariate time series. In AAAI, pages 930-937, 2020.","title":"Data-gru: Dual-attention time-aware gated recurrent unit for irregular multivariate time series","authors":"Qingxiong Tan, Mang Ye, Baoyao Yang, Siqi Liu, Andy Jinhua Ma, Terry Cheuk-Fung Yip, Grace Lai, -Hung Wong, Pongchi Yuen","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xiao et al., 2017] Shuai Xiao, Junchi Yan, Xiaokang Yang, Hongyuan Zha, and Stephen M Chu. Modeling the intensity function of point process via recurrent neural networks. In AAAI, pages 1597-1603, 2017.","title":"Modeling the intensity function of point process via recurrent neural networks","authors":"Shuai Xiao, Junchi Yan, Xiaokang Yang, Hongyuan Zha, Stephen M Chu","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yin et al., 2019] Kejing Yin, Dong Qian, William K Cheung, Ben- jamin CM Fung, and Jonathan Poon. Learning phenotypes and dynamic patient representations via rnn regularized collective non-negative tensor factorization. In AAAI, pages 1246-1253, 2019.","title":"Learning phenotypes and dynamic patient representations via rnn regularized collective non-negative tensor factorization","authors":"Kejing Yin, Dong Qian, William K Cheung, Benjamin Cm Fung, Jonathan Poon","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yu et al., 2016] Hsiang-Fu Yu, Nikhil Rao, and Inderjit S Dhillon. Temporal regularized matrix factorization for high-dimensional time series prediction. In NIPS, pages 847-855, 2016.","title":"Temporal regularized matrix factorization for high-dimensional time series prediction","authors":"Hsiang-Fu Yu, Nikhil Rao, Inderjit S Dhillon","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang, 2019] Yuan Zhang. Attain: Attention-based time-aware lstm networks for disease progression modeling. In IJCAI, pages 4369-4375, 2019.","title":"Attain: Attention-based time-aware lstm networks for disease progression modeling","authors":"Yuan Zhang","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/607"},{"position":28,"raw":"[Zuo et al., 2016] Yi Zuo, Katsutoshi Yada, and ABM Shawkat Ali. Prediction of consumer purchasing in a grocery store using ma- chine learning techniques. In APWC on CSE, pages 18-25, 2016.","title":"Prediction of consumer purchasing in a grocery store using machine learning techniques","authors":"Yi Zuo, Katsutoshi Yada, Ali Shawkat","year":"2016","venue":"APWC on CSE","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}