ABSTRACT
Acute hospital care as performed in the intensive care unit (ICU) is characterized by its frequent, but short-term interventions for patients who are severely ill. Because clinicians have to attend to more than one patient at a time and make decisions in a limited time in acute hospital care environments, the accurate prediction of the in-hospital mortality risk could assist them to pay more attention to patients with a higher in-hospital mortality risk, thereby improving the quality and efficiency of the care. One of the salient features of ICU is the diversity of patients: clinicians are faced by patients with a wide variety of diseases. However, mortality prediction for ICU patients has typically been conducted by building one common predictive model for all the diseases. In this paper, we incorporate disease-specific contexts into mortality modeling by formulating the mortality prediction problem as a multi-task learning problem in which a task corresponds to a disease. Our method effectively integrates medical domain knowledge relating to the similarity among diseases and the similarity among Electronic Health Records (EHRs) into a data-driven approach by incorporating graph Laplacians into the regularization term to encode these similarities. The experimental results on a real dataset from a hospital corroborate the effectiveness of the proposed method. The AUCs of several baselines were improved, including logistic regression without multi-task learning and several multi-task learning methods that do not incorporate the domain knowledge. In addition, we illustrate some interesting results pertaining to disease-specific predictive features, some of which are not only consistent with existing medical domain knowledge, but also contain suggestive hypotheses that could be validated by further investigations in the medical domain.
- H. McGloin, S. Adam, and M. Singer, "Unexpected deaths and referrals to intensive care of patients on general wards. are some cases potentially avoidable?" Journal of the Royal College of Physicians of London, vol. 33, no. 3, pp. 255--259, 1999.Google Scholar
- H. Ksouri, P. Balanant, J. Tadie, G. Heraud, I. Abboud, N. Lerolle, A. Novara, J. Fagon, and C. Faisy, "Impact of morbidity and mortality conferences on analysis of mortality and critical events in intensive care practice," American Journal of Respiratory and Critical Care Medicine, vol. 19, no. 2, pp. 135--145, 2010.Google ScholarCross Ref
- A. A. Zeggwagh, H. Mouad, T. Dendane, K. Abidi, J. Belayachi, N. Madani, and R. Abouqal, "Preventability of death in a medical intensive care unit at a university hospital in a developing country," Indian Journal of Critical Care Medicine, vol. 18, no. 2, pp. 88--94, 2014.Google ScholarCross Ref
- C. W. Hug and P. Szolovits, "Icu acuity: Real-time models versus daily models," in AMIA Annual Symposium Proceedings, vol. 2009, 2009, pp. 260--264.Google Scholar
- J. Rohit and P. Szolovits, "Prognostic physiology: modeling patient severity in intensive care units using radial domain folding," in AMIA Annual Symposium Proceedings, vol. 2012, 2014, pp. 1276--1283.Google Scholar
- M. Ghassemi, T. Naumann, F. Doshi-Velez, N. Brimmer, R. Joshi, A. Rumshisky, and P. Szolovits, "Unfolding physiological state: Mortality modelling in intensive care units," in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 75--84. Google ScholarDigital Library
- Y. Chen and H. Yang, "Heterogeneous postsurgical data analytics for predictive modeling of mortality risks in intensive care units," in Proceedings of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014, pp. 4310--4314.Google Scholar
- M. Ghassemi, A. P. Marco, T. Naumann, B. Thomas, A. C. David, S. Peter, and F. Mengling, "A multivariate timeseries modeling approach to severity of illness assessment and forecasting in icu with sparse, heterogeneous clinical data," in Proceedings of the 29th AAAI Conference on Artificial Intelligence, 2015.Google Scholar
- K. Yamashita, H. Ikai, M. Nishimura, K. Fushimi, and Y. Imanaka, "Effect of certified training facilities for intensive care specialists on mortality in Japan," phCritical Care and Resuscitation, vol. 15, no. 1, pp. 28--32, 2013.Google Scholar
- D. He, S. C. Mathews, A. N. Kalloo, and S. Hutfless, "Mining high-dimensional administrative claims data to predict early hospital readmissions," Journal of the American Medical Informatics Association, vol. 21, no. 2, pp. 272--279, 2014.Google ScholarCross Ref
- S. K. Gupta, S. Rana, D. Q. Phung, and S. Venkatesh, "Keeping up with innovation: A predictive framework for modeling healthcare data with evolving clinical interventions," in Proceedings of the 2014 SIAM International Conference on Data Mining, 2014, pp. 235--243.Google Scholar
- B. E. Himes, Y. Dai, , I. S. Kohane, S. T. Weiss, and M. F. Ramoni, "Prediction of chronic obstructive pulmonary disease (COPD) in asthma patients using electronic medical records," Journal of the American Medical Informatics Association, vol. 16, no. 3, pp. 371--379, 2009.Google ScholarCross Ref
- J. Zhou, L. Yuan, J. Liu, and J. Ye, "A multi-task learning formulation for predicting disease progression," in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2011, pp. 814--822. Google ScholarDigital Library
- J. Zhou, J. Liu, V. A. Narayan, and J. Ye, "Modeling disease progression via fused sparse group lasso," in Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2012, pp. 1095--1103. Google ScholarDigital Library
- X. Wang, D. Sontag, and F. Wang, "Unsupervised learning of disease progression models," in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 85--94. Google ScholarDigital Library
- J. Zhou, F. Wang, J. Hu, and J. Ye, "From micro to macro: Data driven phenotyping by densification of longitudinal electronic medical records," in Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 135--144. Google ScholarDigital Library
- R. Caruana, "Multitask learning," Machine Learning, vol. 28, no. 1, pp. 41--75, 1997. Google ScholarDigital Library
- T. Evgeniou, C. A. Micchelli, M. Pontil, and J. Shawe-Taylor, "Learning multiple tasks with kernel methods." Journal of Machine Learning Research, vol. 6, no. 4, 2005. Google ScholarDigital Library
- A. Argyriou, T. Evgeniou, and M. Pontil, "Multi-task feature learning," in phAdvances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference, 2006, pp. 41--48.Google Scholar
- D. C. Liu and J. Nocedal, "On the limited memory bfgs method for large scale optimization," Mathematical Programming, vol. 45, no. 3, pp. 503--528, 1989. Google ScholarDigital Library
- J. Lee, Y. Imanaka, M. Sekimoto, H. Nishikawa, H. Ikai, and T. Motohashi, "Validation of a novel method to identify healthcare-associated infections," Journal of Hospital Infection, vol. 77, no. 4, pp. 316--320, 2011.Google ScholarCross Ref
- S. Ji and J. Ye, "An accelerated gradient method for trace norm minimization," in Proceedings of the 26th Annual International Conference on Machine Learning, 2009, pp. 457--464. Google ScholarDigital Library
- G. C. Siontis, I. Tzoulaki, and J. P. Ioannidis, "Predicting death: an empirical evaluation of predictive tools for mortality," Archives of internal medicine, vol. 171, no. 19, pp. 1721--1726, 2011.Google ScholarCross Ref
- M. J. Breslow and O. Badawi, "Severity scoring in the critically ill: Part 1-interpretation and accuracy of outcome prediction scoring systems," CHEST Journal, vol. 141, no. 1, pp. 245--252, 2012.Google ScholarCross Ref
- L. wei Lehman, M. Mohammed Saeed, W. Long, J. Lee, and R. Mark, "Risk stratification of icu patients using topic models inferred from unstructured progress notes," in AMIA Annual Symposium Proceedings, vol. 2012, 2012, pp. 505--511.Google Scholar
- D. Zhang and D. Shen, "Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in alzheimer's disease," NeuroImage, vol. 59, no. 2, pp. 895--907, 2012.Google ScholarCross Ref
- X. Wang, F. Wang, J. Hu, and R. Sorrentino, "Exploring joint disease risk prediction," in AMIA Annual Symposium Proceedings, vol. 2014, 2014, pp. 1180--1187.Google Scholar
- P. Zhang, F. Wang, and J. Hu, "Towards drug repositioning: A unified computational framework for integrating multiple aspects of drug similarity and disease similarity," in AMIA Annual Symposium Proceedings, vol. 2014, 2014, pp. 1258--1267.Google Scholar
- B. Quanz and J. Huan, "Aligned graph classification with regularized logistic regression," in Proceedings of Ninth SIAM International Conference on Data Mining, 2009, pp. 353--364.Google Scholar
- G. Chen, Y. Song, F. Wang, and C. Zhang,"Semi-supervised multi-label learning by solving a sylvester equation," in Proceedings of Eighth SIAM International Conference on Data Mining, 2008, pp. 410--419.Google Scholar
Index Terms
- Simultaneous Modeling of Multiple Diseases for Mortality Prediction in Acute Hospital Care
Recommendations
KAME: Knowledge-based Attention Model for Diagnosis Prediction in Healthcare
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementThe goal of diagnosis prediction task is to predict the future health information of patients from their historical Electronic Healthcare Records (EHR). The most important and challenging problem of diagnosis prediction is to design an accurate, robust ...
Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningPredicting the future health information of patients from the historical Electronic Health Records (EHR) is a core research task in the development of personalized healthcare. Patient EHR data consist of sequences of visits over time, where each visit ...
HiTANet: Hierarchical Time-Aware Attention Networks for Risk Prediction on Electronic Health Records
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningDeep learning methods especially recurrent neural network based models have demonstrated early success in disease risk prediction on longitudinal patient data. Existing works follow a strong assumption to implicitly assume the stationary disease ...
Comments