{"type":"ScholarlyArticle","title":"Chronic Disease Management with Personalized Lab Test Response Prediction","authors":[{"name":"Suman Bhoi","slug":"suman-bhoi","given":"Suman","family":"Bhoi","affiliation":"National University of Singapore"},{"name":"Mong Li Lee","slug":"mong-li-lee","given":"Mong Li","family":"Lee","affiliation":"National University of Singapore"},{"name":"Wynne Hsu","slug":"wynne-hsu","given":"Wynne","family":"Hsu","affiliation":"National University of Singapore"},{"name":"Hao Sen Andrew Fang","slug":"hao-sen-andrew-fang","given":"Hao Sen Andrew","family":"Fang","affiliation":"SingHealth Polyclinics"},{"name":"Ngiap Chuan Tan","slug":"ngiap-chuan-tan","given":"Ngiap","family":"Chuan Tan","affiliation":"SingHealth Polyclinics"}],"abstract":"Chronic disease management involves frequent administration of invasive lab procedures in order for\r\nclinicians to determine the best course of treatment\r\nregimes for these patients. However, patients are\r\noften put off by these invasive lab procedures and\r\ndo not follow the appointment schedules. This has\r\nresulted in poor management of their chronic conditions leading to unnecessary disease complications. An AI system that is able to personalize the\r\nprediction of individual patient lab test responses\r\nwill enable clinicians to titrate the medications to\r\nachieve the desired therapeutic outcome.  Accurate prediction of lab test response is a challenge because these patients typically have co-morbidities and their treatments might influence the target lab test response. To address this,\r\nwe model the complex interactions among different medications, diseases, lab test response, and\r\nfine-grained dosage information to learn a strong\r\npatient representation. Together with information\r\nfrom similar patients and external knowledge such\r\nas drug-lab interactions and diagnosis-lab interaction, we design a system called KALP to perform\r\npersonalized prediction of patients’ response for a\r\ntarget lab result and identify the top influencing\r\nfactors for the prediction. Experiment results on\r\nreal-world datasets demonstrate the effectiveness of\r\nKALP in reducing prediction errors by a significant\r\nmargin. Case studies show that the identified factors are consistent with clinicians’ understanding.","doi":"10.24963/ijcai.2022/699","url":"https://ijcai.org/proceedings/2022/699","pdf":"https://ijcai.org/proceedings/2022/0699.pdf","markdown":"https://ijcai.org/proceedings/2022/699.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/699","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":"Research Papers","track":"AI for Good","number":699,"pages":{"first":5038,"last":5044},"keywords":["Multidisciplinary Topics and Applications: Health and Medicine","Humans and AI: Personalization and User Modeling"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987141","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985284","length_sec":634,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Baytas et al., 2017] I. Baytas, C. Xiao, X. Zhang, F. Wang, A. K. Jain, and J. Zhou. Patient subtyping via time-aware lstm net- works. In ACM SIGKDD, 2017.","title":"Patient subtyping via time-aware lstm networks","authors":"Baytas","year":"2017","venue":"ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bhoi et al., 2021] Suman Bhoi, M. L. Lee, W. Hsu, H. S. A. Fang, and N. C. Tan. Personalizing medication recommendation with a graph-based approach. TOIS, 40(3):1-23, 2021.","title":"Personalizing medication recommendation with a graph-based approach","authors":"M L Suman Bhoi, W Lee, H S A Hsu, N C Fang, Tan","year":"2021","venue":"TOIS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Brody et al., 2021] S. Brody, U. Alon, and E. Yahav. How attentive are graph attention networks? arXiv:2105.14491, 2021.","title":"How attentive are graph attention networks","authors":"S Brody, U Alon, E Yahav","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Choi et al., 2016] E. Choi, M. T. Bahadori, J. Sun, J. Kulas, A. Schuetz, and W. Stewart. Retain: An interpretable predic- tive model for healthcare using reverse time attention mechanism. NeurIPS, 2016.","title":"Retain: An interpretable predictive model for healthcare using reverse time attention mechanism","authors":"E Choi, M T Bahadori, J Sun, J Kulas, A Schuetz, W Stewart","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Darabi et al., 2020] Sajad Darabi, Mohammad Kachuee, Shayan Fazeli, and Majid Sarrafzadeh. Taper: Time-aware patient ehr representation. JBHI, 24(11):3268-3275, 2020.","title":"Taper: Time-aware patient ehr representation","authors":"Sajad Darabi, Mohammad Kachuee, Shayan Fazeli, Majid Sarrafzadeh","year":"2020","venue":"JBHI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dornhorst et al., 1985] Anne Dornhorst, StephenH Powell, and Jack Pensky. Aggravation by propranolol of hyperglycaemic ef- fect of hydrochlorothiazide in type ii diabetics without alteration of insulin secretion. The Lancet, 325(8421):123-126, 1985.","title":"Anne Dornhorst, StephenH Powell, and Jack Pensky. Aggravation by propranolol of hyperglycaemic effect of hydrochlorothiazide in type ii diabetics without alteration of insulin secretion","authors":"Dornhorst","year":"1985","venue":"The Lancet","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fisher, 1992] Ronald Aylmer Fisher. Statistical methods for re- search workers. In Breakthroughs in statistics, pages 66-70. Springer, 1992.","title":"Statistical methods for research workers","authors":"Ronald Aylmer Fisher, Fisher","year":"1992","venue":"Breakthroughs in statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jia et al., 2020] Zheng Jia, Xian Zeng, Huilong Duan, Xudong Lu, and Haomin Li. A patient-similarity-based model for diagnostic prediction. IJMI, 135:104073, 2020.","title":"A patient-similarity-based model for diagnostic prediction","authors":"Zheng Jia, Xian Zeng, Huilong Duan, Xudong Lu, Haomin Li","year":"2020","venue":"IJMI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Johnson et al., 2016] Alistair EW Johnson, Tom J Pollard, et al. Mimic-iii, a freely accessible critical care database. Scientific data, 3(1):1-9, 2016.","title":"Mimic-iii, a freely accessible critical care database","authors":"E W Alistair, Tom J Johnson, Pollard","year":"2016","venue":"Scientific data","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kang et al., 2015] Seokho Kang, Pilsung Kang, Taehoon Ko, Sungzoon Cho, Su-jin Rhee, and Kyung-Sang Yu. An effi- cient and effective ensemble of support vector machines for anti- diabetic drug failure prediction. ESA, 42(9):4265-4273, 2015.","title":"An efficient and effective ensemble of support vector machines for antidiabetic drug failure prediction","authors":"Kang","year":"2015","venue":"ESA","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kang et al., 2017] Seokho Kang, Sungzoon Cho, Su-jin Rhee, and Kyung-Sang Yu. Reliable prediction of anti-diabetic drug failure using a reject option. PAA, 20(3):883-891, 2017.","title":"Reliable prediction of anti-diabetic drug failure using a reject option","authors":"Kang","year":"2017","venue":"PAA","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kang, 2018] Seokho Kang. Personalized prediction of drug effi- cacy for diabetes treatment via patient-level sequential modeling with neural networks. AIM, 85:1-6, 2018.","title":"Personalized prediction of drug efficacy for diabetes treatment via patient-level sequential modeling with neural networks","authors":"Seokho Kang, Kang","year":"2018","venue":"AIM","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kenton and Toutanova, 2019] Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In Pro- ceedings of NAACL-HLT, pages 4171-4186, 2019.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton, Lee Kristina, Toutanova","year":"2019","venue":"Proceedings of NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kuhn et al., 2016] Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, and Peer Bork. The sider database of drugs and side effects. Nu- cleic acids research, 44(D1):D1075-D1079, 2016.","title":"The sider database of drugs and side effects","authors":"Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, Peer Bork","year":"2016","venue":"Nucleic acids research","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Le et al., 2018] Hung Le, Truyen Tran, and Svetha Venkatesh. Dual memory neural computer for asynchronous two-view se- quential learning. In SIGKDD, pages 1637-1645, 2018.","title":"Dual memory neural computer for asynchronous two-view sequential learning","authors":"Hung Le, Truyen Tran, Svetha Venkatesh","year":"2018","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2020] Yikuan Li, Shishir Rao, Jose Roberto Ayala So- lares, et al. Behrt: transformer for electronic health records. Sci- entific reports, 10(1):1-12, 2020.","title":"Behrt: transformer for electronic health records","authors":"Li","year":"2020","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lu et al., 2021] Chang Lu, Chandan K. Reddy, Prithwish Chakraborty, Samantha Kleinberg, and Yue Ning. Collaborative graph learning with auxiliary text for temporal event prediction in healthcare. In IJCAI, pages 3529-3535, 2021.","title":"Collaborative graph learning with auxiliary text for temporal event prediction in healthcare","authors":"Chang Lu, K Chandan, Prithwish Reddy, Samantha Chakraborty, Yue Kleinberg, Ning","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/486"},{"position":18,"raw":"[Luo et al., 2016] Yuan Luo, Peter Szolovits, Anand S Dighe, and Jason M Baron. Using machine learning to predict laboratory test results. AJCP, 145(6):778-788, 2016.","title":"Using machine learning to predict laboratory test results","authors":"Yuan Luo, Peter Szolovits, Jason M Anand S Dighe, Baron","year":"2016","venue":"AJCP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Luo et al., 2020] Junyu Luo, Muchao Ye, et al. Hitanet: Hierar- chical time-aware attention networks for risk prediction on elec- tronic health records. In SIGKDD, pages 647-656, 2020.","title":"Hitanet: Hierarchical time-aware attention networks for risk prediction on electronic health records","authors":"Luo","year":"2020","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ma et al., 2017] Fenglong Ma, Radha Chitta, Jing Zhou, Quanzeng You, Tong Sun, and Jing Gao. Dipole: Diagno- sis prediction in healthcare via attention-based bidirectional recurrent neural networks. In SIGKDD, pages 1903-1911, 2017.","title":"Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks","authors":"Fenglong Ma, Radha Chitta, Jing Zhou, Quanzeng You, Tong Sun, Jing Gao","year":"2017","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[MacDonald et al., 2010] Michael R MacDonald, Dean T Eurich, et al. Treatment of type 2 diabetes and outcomes in patients with heart failure: a nested case-control study from the uk gen- eral practice research database. Diabetes care, 33(6):1213-1218, 2010.","title":"Treatment of type 2 diabetes and outcomes in patients with heart failure: a nested case-control study from the uk general practice research database","authors":"Dean T Michael R Macdonald, Eurich","year":"2010","venue":"Diabetes care","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ni et al., 2017] Jingchao Ni, Hongliang Fei, Wei Fan, and Xiang Zhang. Cross-network clustering and cluster ranking for medical diagnosis. In ICDE, pages 163-166. IEEE, 2017.","title":"Cross-network clustering and cluster ranking for medical diagnosis","authors":"Ni","year":"2017","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Oei et al., 2021] R. W. Oei, A. Fang, W. Y. Tan, , W. Hsu, M. L. Lee, and N. C. Tan. Using domain knowledge and data-driven insights for patient similarity analytics. JPM, 11(8), 2021.","title":"Using domain knowledge and data-driven insights for patient similarity analytics","authors":"R W Oei, A Fang, W Y Tan, W Hsu, M L Lee, N C Tan","year":"2021","venue":"JPM","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Prakash et al., 2021] PKS Prakash, S. Chilukuri, N. Ranade, and S. Viswanathan. Rarebert: Transformer architecture for rare dis- ease patient identification using administrative claims. In AAAI, volume 35, pages 453-460, 2021.","title":"Rarebert: Transformer architecture for rare disease patient identification using administrative claims","authors":"S Pks Prakash, N Chilukuri, S Ranade, Viswanathan","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shang et al., 2019] Junyuan Shang, Cao Xiao, Tengfei Ma, Hongyan Li, and Jimeng Sun. Gamenet: Graph augmented mem- ory networks for recommending medication combination. In AAAI, volume 33, pages 1126-1133, 2019.","title":"Gamenet: Graph augmented memory networks for recommending medication combination","authors":"Junyuan Shang, Cao Xiao, Tengfei Ma, Hongyan Li, Jimeng Sun","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sukhbaatar et al., 2015] Sainbayar Sukhbaatar, Arthur Szlam, Ja- son Weston, and Rob Fergus. End-to-end memory networks. NeurIPS, 2015:2440-2448, 2015.","title":"End-to-end memory networks","authors":"Sukhbaatar","year":"2015","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tan et al., 2019] Qingxiong Tan, Andy Jinhua Ma, et al. Ua- crnn: Uncertainty-aware convolutional recurrent neural network for mortality risk prediction. In CIKM, pages 109-118, 2019.","title":"Uacrnn: Uncertainty-aware convolutional recurrent neural network for mortality risk prediction","authors":"Tan","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Unnikrishnan et al., 2012] Ranjit Unnikrishnan, Ranjit Mohan Anjana, and Viswanathan Mohan. Drugs affecting hba1c levels. IJEM, 16(4):528, 2012.","title":"Drugs affecting hba1c levels","authors":"Ranjit Unnikrishnan, Ranjit Mohan Anjana, Viswanathan Mohan","year":"2012","venue":"IJEM","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, et al. At- tention is all you need. In NeurIPS, pages 6000-6010, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2019] Shanshan Wang, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, and Maarten de Rijke. Order-free medicine combination prediction with graph convolutional rein- forcement learning. In CIKM, pages 1623-1632, 2019.","title":"Order-free medicine combination prediction with graph convolutional reinforcement learning","authors":"Shanshan Wang, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Jun Ma, Maarten De Rijke","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wei et al., 2013] Wei-Qi Wei, Robert M Cronin, Hua Xu, Thomas A Lasko, Lisa Bastarache, and Joshua C Denny. De- velopment and evaluation of an ensemble resource linking medi- cations to their indications. JAMIA, 20(5):954-961, 2013.","title":"Development and evaluation of an ensemble resource linking medications to their indications","authors":"Wei-Qi Wei, Robert M Cronin, Hua Xu, Thomas A Lasko, Lisa Bastarache, Joshua C Denny","year":"2013","venue":"JAMIA","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wirbka et al., 2020] Lucas Wirbka, Walter E Haefeli, and An- dreas D Meid. A framework to build similarity-based cohorts for personalized treatment advice-a standardized, but flexible work- flow with the r package simbaco. PloS one, 15(5):e0233686, 2020.","title":"A framework to build similarity-based cohorts for personalized treatment advice-a standardized, but flexible workflow with the r package simbaco","authors":"Lucas Wirbka, Walter E Haefeli, Andreas D Meid","year":"2020","venue":"PloS one","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}