{"type":"ScholarlyArticle","title":"Joint Learning of Phenotypes and Diagnosis-Medication Correspondence via Hidden Interaction Tensor Factorization","authors":[{"name":"Kejing Yin","slug":"kejing-yin","given":"Kejing","family":"Yin","affiliation":"Department of Computer Science , Hong Kong Baptist University , Hong Kong SAR , China"},{"name":"William K. Cheung","slug":"william-k-cheung","given":"William K.","family":"Cheung","affiliation":"Department of Computer Science , Hong Kong Baptist University , Hong Kong SAR , China"},{"name":"Yang Liu","slug":"yang-liu","given":"Yang","family":"Liu","affiliation":"Department of Computer Science , Hong Kong Baptist University , Hong Kong SAR , China"},{"name":"Benjamin C. M. Fung","slug":"benjamin-c-m-fung","given":"Benjamin C. M.","family":"Fung","affiliation":"School of Information Studies , McGill University , Montreal , Canada"},{"name":"Jonathan Poon","slug":"jonathan-poon","given":"Jonathan","family":"Poon","affiliation":"Hong Kong Hospital Authority , Hong Kong SAR , China"}],"abstract":"Non-negative tensor factorization has been shown effective for discovering phenotypes from the EHR data with minimal human supervision. In most cases, an interaction tensor of the elements in the EHR (e.g., diagnoses and medications) has to be first established before the factorization can be applied. Such correspondence information however is often missing. While different heuristics can be used to estimate the missing correspondence, any errors introduced will in turn cause inaccuracy for the subsequent phenotype discovery task. This is especially true for patients with multiple diseases diagnosed (e.g., under critical care). To alleviate this limitation, we propose the hidden interaction tensor factorization (HITF) where the diagnosis-medication correspondence and the underlying phenotypes are inferred simultaneously. We formulate it under a Poisson non-negative tensor factorization framework and learn the HITF model via maximum likelihood estimation. For performance evaluation, we applied HITF to the MIMIC III dataset. Our empirical results show that both the phenotypes and the correspondence inferred are clinically meaningful. In addition, the inferred HITF model outperforms a number of state-of-the-art methods for mortality prediction.","doi":"10.24963/ijcai.2018/504","url":"https://ijcai.org/proceedings/2018/504","pdf":"https://ijcai.org/proceedings/2018/0504.pdf","markdown":"https://ijcai.org/proceedings/2018/504.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/504","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning Applications","track":"Main track","number":504,"pages":{"first":3627,"last":3633},"keywords":["Machine Learning Applications: Bio;Medicine","Machine Learning: Unsupervised Learning","Machine Learning: Dimensionality Reduction and Manifold Learning"],"videos":[],"references":[{"position":1,"raw":"[Chi and Kolda, 2012] Eric C. Chi and Tamara G. Kolda. On tensors, sparsity, and nonnegative factorizations. SIAM Journal on Matrix Analysis and Applications, 33(4):1272- 1299, 2012.","title":"On tensors, sparsity, and nonnegative factorizations","authors":"Eric C Chi, Tamara G Kolda","year":"2012","venue":"SIAM Journal on Matrix Analysis and Applications","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Gunasekar et al., 2016] Suriya Gunasekar, Joyce C. Ho, Joydeep Ghosh, Stephanie Kreml, Abel N. Kho, Joshua C Denny, Bradley A Malin, and Jimeng Sun. Phenotyping using structured collective matrix factorization of multi- source EHR data. ArXiv e-prints, September 2016.","title":"Phenotyping using structured collective matrix factorization of multisource EHR data","authors":"Suriya Gunasekar, Joyce C Ho, Joydeep Ghosh, Stephanie Kreml, Abel N Kho, Joshua C Denny, Bradley A Malin, Jimeng Sun","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ho et al., 2014a] Joyce C Ho, Joydeep Ghosh, Steve R Steinhubl, Walter F Stewart, Joshua C Denny, Bradley A Malin, and Jimeng Sun. Limestone: High-throughput can- didate phenotype generation via tensor factorization. Jour- nal of Biomedical Informatics, 52:199-211, 2014.","title":"Limestone: High-throughput candidate phenotype generation via tensor factorization","authors":"Ho","year":"2014","venue":"Journal of Biomedical Informatics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ho et al., 2014b] Joyce C Ho, Joydeep Ghosh, and Jimeng Sun. Marble: High-throughput phenotyping from elec- tronic health records via sparse nonnegative tensor factor- ization. In Proceedings of the 20th ACM SIGKDD Inter- national Conference on Knowledge Discovery and Data Mining, pages 115-124. ACM, 2014.","title":"Marble: High-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization","authors":"Ho","year":"2014","venue":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hripcsak and Albers, 2013] George Hripcsak and David J Albers. Next-generation phenotyping of electronic health records. Journal of the American Medical Informatics As- sociation, 20(1):117-121, 2013.","title":"Next-generation phenotyping of electronic health records","authors":"Albers Hripcsak, George Hripcsak, David J Albers","year":"2013","venue":"Journal of the American Medical Informatics Association","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jensen et al., 2012] Peter B Jensen, Lars J Jensen, and Søren Brunak. Mining electronic health records: Towards better research applications and clinical care. Nature Re- views Genetics, 13(6):395-405, 2012.","title":"Mining electronic health records: Towards better research applications and clinical care","authors":"Lars J Peter B Jensen, Søren Jensen, Brunak","year":"2012","venue":"Nature Reviews Genetics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Johnson et al., 2016] Alistair EW Johnson, Tom J Pollard, Lu Shen, H Lehman Li-wei, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo An- thony Celi, and Roger G Mark. MIMIC-III, a freely ac- cessible critical care database. Scientific Data, 3, 2016.","title":"MIMIC-III, a freely accessible critical care database","authors":"E W Alistair, Tom J Johnson, Lu Pollard, H Shen, Mengling Lehman Li-Wei, Mohammad Feng, Benjamin Ghassemi, Peter Moody, Leo Szolovits, Roger G Anthony Celi, Mark","year":"2016","venue":"Scientific Data","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kim et al., 2017] Yejin Kim, Robert El-Kareh, Jimeng Sun, Hwanjo Yu, and Xiaoqian Jiang. Discriminative and dis- tinct phenotyping by constrained tensor factorization. Sci- entific Reports, 7(1):1114, 2017.","title":"Discriminative and distinct phenotyping by constrained tensor factorization","authors":"Yejin Kim, Robert El-Kareh, Jimeng Sun, Hwanjo Yu, Xiaoqian Jiang","year":"2017","venue":"Scientific Reports","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kolda and Bader, 2009] Tamara G. Kolda and Brett W. Bader. Tensor decompositions and applications. SIAM Review, 51(3):455-500, 2009.","title":"Tensor decompositions and applications","authors":"Tamara G Kolda, Brett W Bader","year":"2009","venue":"SIAM Review","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lasko et al., 2013] Thomas A. Lasko, Joshua C. Denny, and Mia A. Levy. Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and ir- regular clinical data. PLOS One, 8(6):e66341, 2013.","title":"Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data","authors":"Thomas A Lasko, Joshua C Denny, Mia A Levy","year":"2013","venue":"PLOS One","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2014] Yuanyuan Liu, Fanhua Shang, Hong Cheng, James Cheng, and Hanghang Tong. Factor matrix trace norm minimization for low-rank tensor completion. In Proceedings of the 2014 SIAM International Confer- ence on Data Mining, pages 866-874. SIAM, 2014.","title":"Factor matrix trace norm minimization for low-rank tensor completion","authors":"Yuanyuan Liu, Fanhua Shang, Hong Cheng, James Cheng, Hanghang Tong","year":"2014","venue":"Proceedings of the 2014 SIAM International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Luo et al., 2016] Yuan Luo, Fei Wang, and Peter Szolovits. Tensor factorization toward precision medicine. Briefings in Bioinformatics, 18(3):511-514, 2016.","title":"Tensor factorization toward precision medicine","authors":"Yuan Luo, Fei Wang, Peter Szolovits","year":"2016","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Nocedal and Wright, 2006] Jorge Nocedal and Stephen J. Wright. Numerical Optimization. Springer, New York, NY, USA, 2nd edition, 2006.","title":"Numerical Optimization","authors":"Jorge Nocedal, Stephen J Wright","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ravì et al., 2017] Daniele Ravì, Charence Wong, Fani Deli- gianni, Melissa Berthelot, Javier Andreu-Perez, Benny Lo, and Guang-Zhong Yang. Deep learning for health infor- matics. IEEE Journal of Biomedical and Health Informat- ics, 21(1):4-21, 2017.","title":"Deep learning for health informatics","authors":"Daniele Ravì, Charence Wong, Fani Deligianni, Melissa Berthelot, Javier Andreu-Perez, Benny Lo, Guang-Zhong Yang","year":"2017","venue":"IEEE Journal of Biomedical and Health Informatics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Singh and Gordon, 2008] Ajit P. Singh and Geoffrey J. Gor- don. Relational learning via collective matrix factoriza- tion. In Proceedings of the 14th ACM SIGKDD Interna- tional Conference on Knowledge Discovery and Data Min- ing, pages 650-658. ACM, 2008.","title":"Relational learning via collective matrix factorization","authors":"P Ajit, Geoffrey J Singh, Gordon","year":"2008","venue":"Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2015] Yichen Wang, Robert Chen, Joydeep Ghosh, Joshua C Denny, Abel Kho, You Chen, Bradley A Malin, and Jimeng Sun. Rubik: Knowledge guided tensor factorization and completion for health data analytics. In Proceedings of the 21st ACM SIGKDD International Con- ference on Knowledge Discovery and Data Mining, pages 1265-1274. ACM, 2015.","title":"Rubik: Knowledge guided tensor factorization and completion for health data analytics","authors":"Yichen Wang, Robert Chen, Joydeep Ghosh, Joshua C Denny, Abel Kho, You Chen, Bradley A Malin, Jimeng Sun","year":"2015","venue":"Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu and Yin, 2013] Yangyang Xu and Wotao Yin. A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor fac- torization and completion. SIAM Journal on Imaging Sci- ences, 6(3):1758-1789, 2013.","title":"A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion","authors":"Yin Xu, Yangyang Xu, Wotao Yin","year":"2013","venue":"SIAM Journal on Imaging Sciences","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Yamaguchi and Hayashi, 2017] Yuto Yamaguchi and Kohei Hayashi. Tensor decomposition with missing indices. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, pages 3217-3223. AAAI Press, 2017.","title":"Tensor decomposition with missing indices","authors":"Hayashi Yamaguchi, Yuto Yamaguchi, Kohei Hayashi","year":"2017","venue":"Proceedings of the 26th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/449"},{"position":19,"raw":"[Yang et al., 2017] Kai Yang, Xiang Li, Haifeng Liu, Jing Mei, Guo Tong Xie, Junfeng Zhao, Bing Xie, and Fei Wang. TaGiTeD: Predictive task guided tensor decom- position for representation learning from electronic health records. In Thirty-First AAAI Conference on Artificial In- telligence. AAAI, 2017.","title":"TaGiTeD: Predictive task guided tensor decomposition for representation learning from electronic health records","authors":"Kai Yang, Xiang Li, Haifeng Liu, Jing Mei, Guo Tong Xie, Junfeng Zhao, Bing Xie, Fei Wang","year":"2017","venue":"Thirty-First AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yu et al., 2015] Sheng Yu, Katherine P Liao, Stanley Y Shaw, Vivian S Gainer, Susanne E Churchill, Peter Szolovits, Shawn N Murphy, Isaac S Kohane, and Tianxi Cai. Toward high-throughput phenotyping: Unbiased au- tomated feature extraction and selection from knowledge sources. Journal of the American Medical Informatics As- sociation, 22(5):993-1000, 2015.","title":"Toward high-throughput phenotyping: Unbiased automated feature extraction and selection from knowledge sources","authors":"Sheng Yu, Katherine P Liao, Stanley Y Shaw, Vivian S Gainer, Susanne E Churchill, Peter Szolovits, Shawn N Murphy, Isaac S Kohane, Tianxi Cai","year":"2015","venue":"Journal of the American Medical Informatics Association","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}