{"type":"ScholarlyArticle","title":"Medical Concept Representation Learning from Multi-source Data","authors":[{"name":"Tian Bai","slug":"tian-bai","given":"Tian","family":"Bai","affiliation":"Department of Computer and Information Sciences , Temple University , USA"},{"name":"Brian L. Egleston","slug":"brian-l-egleston","given":"Brian","family":"L. Egleston","affiliation":"Fox Chase Cancer Center , USA"},{"name":"Richard Bleicher","slug":"richard-bleicher","given":"Richard","family":"Bleicher","affiliation":"Fox Chase Cancer Center , USA"},{"name":"Slobodan Vucetic","slug":"slobodan-vucetic","given":"Slobodan","family":"Vucetic","affiliation":"Department of Computer and Information Sciences , Temple University , USA"}],"abstract":"Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations.  To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. We first modify the Pointwise Mutual Information (PMI) measure of similarity between the codes. We then develop a new negative sampling method for word2vec model that implicitly factorizes the modified PMI matrix. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we evaluated cross-referencing between ICD-9 and CPT medical code ontologies. Our results indicate that vector representations of codes learned by the proposed approach provide superior cross-referencing when compared to several existing approaches.","doi":"10.24963/ijcai.2019/680","url":"https://ijcai.org/proceedings/2019/680","pdf":"https://ijcai.org/proceedings/2019/0680.pdf","markdown":"https://ijcai.org/proceedings/2019/680.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/680","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":680,"pages":{"first":4897,"last":4903},"keywords":["Multidisciplinary Topics and Applications: Biology and Medicine","Natural Language Processing: Natural Language Processing","Natural Language Processing: NLP Applications and Tools","Machine Learning Applications: Bio;Medicine"],"videos":[],"references":[{"position":1,"raw":"[Bai and Vucetic, 2019] Tian Bai and Slobodan Vucetic. Im- proving medical code prediction from clinical text via in- corporating online knowledge sources. In The World Wide Web Conference, pages 72-82. ACM, 2019.","title":"Improving medical code prediction from clinical text via incorporating online knowledge sources","authors":"Vucetic ; ] Tian Bai, Slobodan Bai, Vucetic","year":"2019","venue":"The World Wide Web Conference","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bai et al., 2017] Tian Bai, Ashis Kumar Chanda, Brian L Egleston, and Slobodan Vucetic. Joint learning of repre- sentations of medical concepts and words from ehr data. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 764-769. IEEE, 2017.","title":"Joint learning of representations of medical concepts and words from ehr data","authors":"Tian Bai, Ashis Kumar Chanda, Brian L Egleston, Slobodan Vucetic","year":"2017","venue":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai et al., 2018a] Tian Bai, Ashis Kumar Chanda, Brian L Egleston, and Slobodan Vucetic. Ehr phenotyping via jointly embedding medical concepts and words into a uni- fied vector space. BMC medical informatics and decision making, 18(4):123, 2018.","title":"Ehr phenotyping via jointly embedding medical concepts and words into a unified vector space","authors":"Bai","year":"2018","venue":"BMC medical informatics and decision making","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bai et al., 2018b] Tian Bai, Shanshan Zhang, Brian L Egle- ston, and Slobodan Vucetic. Interpretable representa- tion learning for healthcare via capturing disease pro- gression through time. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discov- ery & Data Mining, pages 43-51. ACM, 2018.","title":"Interpretable representation learning for healthcare via capturing disease progression through time","authors":"Bai","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bleicher et al., 2012] RJ Bleicher, K Ruth, ER Sigurdson, E Ross, YN Wong, SA Patel, M Boraas, NS Topham, and BL Egleston. Preoperative delays in the us medicare pop- ulation with breast cancer. Journal of Clinical Oncology, 30(36):4485-4492, 2012.","title":"Preoperative delays in the us medicare population with breast cancer","authors":"Rj Bleicher, E R Ruth, E Sigurdson, Y N Ross, Wong, M Patel, Boraas, Topham, Bl Egleston","year":"2012","venue":"Journal of Clinical Oncology","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bleicher et al., 2016] Richard J Bleicher, Karen Ruth, Elin R Sigurdson, J Robert Beck, Eric Ross, Yu-Ning Wong, Sameer A Patel, Marcia Boraas, Eric I Chang, Neal S Topham, et al. Time to surgery and breast cancer survival in the united states. JAMA oncology, 2(3):330- 339, 2016.","title":"Time to surgery and breast cancer survival in the united states","authors":"J Richard, Karen Bleicher, Elin R Ruth, Robert Sigurdson, Eric Beck, Yu-Ning Ross, Wong, A Sameer, Marcia Patel, Eric I Boraas, Neal S Chang, Topham","year":"2016","venue":"JAMA oncology","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Brouch, 2004] K Brouch. Ahima project offers insights into snomed, icd-9-cm mapping process. Health Information Management, 32(1):31-34, 2004.","title":"Ahima project offers insights into snomed, icd-9-cm mapping process","authors":"Brouch","year":"2004","venue":"Health Information Management","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Butler, 2007] RR Butler. Icd-10 general equivalence map- pings: Bridging the translation gap from icd-9. Journal of AHIMA, 78(9):84-86, 2007.","title":"RR Butler. Icd-10 general equivalence mappings: Bridging the translation gap from icd-9","authors":"Butler","year":"2007","venue":"Journal of AHIMA","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cai and Wang, 2018] Liwei Cai and William Yang Wang. Kbgan: Adversarial learning for knowledge graph em- beddings. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, New Orleans, LA, USA, 2018. ACL.","title":"Kbgan: Adversarial learning for knowledge graph embeddings","authors":"Liwei Cai, William Yang, Wang","year":"2018","venue":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cai et al., 2018] Xiangrui Cai, Jinyang Gao, Kee Yuan Ngiam, Beng Chin Ooi, Ying Zhang, and Xiaojie Yuan. Medical concept embedding with time-aware attention. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pages 3984-3990. International Joint Conferences on Artificial Intelligence Organization, 7 2018.","title":"Medical concept embedding with time-aware attention","authors":"Cai","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18","doi":null,"url":null,"internal_url":"/proceedings/2018/554"},{"position":11,"raw":"[Choi et al., 2016a] E Choi, MT Bahadori, E Searles, C Cof- fey, and J Sun. Multi-layer representation learning for medical concepts. In KDD, 2016.","title":"Multi-layer representation learning for medical concepts","authors":"Choi","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Choi et al., 2016b] Y Choi, CY Chiu, and D Sontag. Learn- ing low-dimensional representations of medical concepts. In AMIA Summits on Translational Science Proceedings, pages 123-345, 2016.","title":"Learning low-dimensional representations of medical concepts","authors":"Choi","year":"2016","venue":"AMIA Summits on Translational Science Proceedings","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Choi et al., 2017] Edward Choi, Mohammad Taha Ba- hadori, Le Song, Walter F Stewart, and Jimeng Sun. Gram: Graph-based attention model for healthcare representation learning. In Proceedings of the 23rd ACM SIGKDD Inter- national Conference on Knowledge Discovery and Data Mining, pages 787-795. ACM, 2017.","title":"Gram: Graph-based attention model for healthcare representation learning","authors":"Edward Choi, Mohammad Taha Bahadori, Le Song, Walter F Stewart, Jimeng Sun","year":"2017","venue":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Grbovic and Cheng, 2018] Mihajlo Grbovic and Haibin Cheng. Real-time personalization using embeddings for search ranking at airbnb. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discov- ery & Data Mining, KDD '18, pages 311-320, New York, NY, USA, 2018. ACM.","title":"Real-time personalization using embeddings for search ranking at airbnb","authors":"Cheng Grbovic, Mihajlo Grbovic, Haibin Cheng","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD '18","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Järvelin and Kekäläinen, 2002] Kalervo Järvelin and Jaana Kekäläinen. Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422-446, 2002.","title":"Cumulated gain-based evaluation of ir techniques","authors":"Järvelin, Kekäläinen, Kalervo Järvelin, Jaana Kekäläinen","year":"2002","venue":"ACM Transactions on Information Systems (TOIS)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Levy and Goldberg, 2014] O Levy and Y Goldberg. Neural word embedding as implicit matrix factorization. In Pro- ceedings of the 27th International Conference on Neural Information Processing Systems, pages 2177-2185, 2014.","title":"Neural word embedding as implicit matrix factorization","authors":"O Levy, Y Goldberg","year":"2014","venue":"Proceedings of the 27th International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mikolov et al., 2013] T Mikolov, I Sutskever, K Chen, G Corrado, and J Dean. Distributed representations of words and phrases and their compositionality. In Proceed- ings of the 26th International Conference on Neural Infor- mation Processing Systems, NIPS'13, pages 3111-3119, 2013.","title":"Distributed representations of words and phrases and their compositionality","authors":"Mikolov, K Sutskever, G Chen, Corrado, Dean","year":"2013","venue":"Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS'13","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pennington et al., 2014] J Pennington, R Socher, and CD Manning. Glove: Global vectors for word represen- tation. In Empirical Methods in Natural Language Pro- cessing (EMNLP), pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"R Pennington, Socher, Manning","year":"2014","venue":"Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schulz et al., 1998] S Schulz, A Zaiss, R Brunner, D Spin- ner, and R Klar. Conversion problems concerning auto- mated mapping from icd-10 to icd-9. Methods of Informa- tion in Medicine, 37(3):254-259, 1998.","title":"Conversion problems concerning automated mapping from icd-10 to icd-9","authors":"Schulz, R Zaiss, D Brunner, Spinner, Klar","year":"1998","venue":"Methods of Information in Medicine","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Topaz and Shafran-Topaz, 2013] M Topaz and L Shafran- Topaz. Icd-9 to icd-10: evolution, revolution, and current debates in the united states. Perspectives in Health Infor- mation Management, page 1, 2013.","title":"Icd-9 to icd-10: evolution, revolution, and current debates in the united states","authors":"M Topaz, L Shafran-Topaz","year":"2013","venue":"Perspectives in Health Information Management","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Turney and Pantel, 2010] PD Turney and P Pantel. From frequency to meaning: Vector space models of semantics. J. Artif. Int. Res., 37:141-188, 2010.","title":"From frequency to meaning: Vector space models of semantics","authors":"Pantel ; ] Pd Turney, P Turney, Pantel","year":"2010","venue":"J. Artif. Int. Res","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2018] Peifeng Wang, Shuangyin Li, and Rong Pan. Incorporating gan for negative sampling in knowl- edge representation learning. In Thirty-Second AAAI Con- ference on Artificial Intelligence, 2018.","title":"Incorporating gan for negative sampling in knowledge representation learning","authors":"Wang","year":"2018","venue":"Thirty-Second AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Warren et al., 2002] Joan L Warren, Carrie N Klabunde, Deborah Schrag, Peter B Bach, and Gerald F Riley. Overview of the seer-medicare data: content, research ap- plications, and generalizability to the united states elderly population. Medical care, pages IV3-IV18, 2002.","title":"Overview of the seer-medicare data: content, research applications, and generalizability to the united states elderly population","authors":"Carrie N Joan L Warren, Deborah Klabunde, Peter B Schrag, Gerald F Bach, Riley","year":"2002","venue":"Medical care","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}