Abstract
Accurate prediction of patients’ ICU transfer events is of great significance for improving ICU treatment efficiency. ICU transition prediction task based on Electronic Health Records (EHR) is a temporal mining task like many other health informatics mining tasks. In the EHR-based temporal mining task, existing approaches are usually unable to mine and exploit patterns used to improve model performance. This article proposes a network based on Interval Pattern-Aware, Multi-Scale Interval Pattern-Aware (MSIPA) network. MSIPA mines different interval patterns in temporal EHR data according to the short, medium, and long intervals. MSIPA utilizes the Scaled Dot-Product Attention mechanism to query the contexts corresponding to the three scale patterns. Furthermore, Transformer will use all three types of contextual information simultaneously for ICU transfer prediction. Extensive experiments on real-world data demonstrate that an MSIPA network outperforms state-of-the-art methods.
- Lei Jimmy Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer normalization. arxiv:1607.06450. Retrieved from https://arxiv.org/abs/1607.06450.Google Scholar
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations. Retrieved from http://arxiv.org/abs/1409.0473.Google Scholar
- Smaranda Belciug and Florin Gorunescu. 2020. Intelligent Decision Support Systems—A Journey to Smarter Healthcare. Springer. DOI:https://doi.org/10.1007/978-3-030-14354-1 Google ScholarDigital Library
- Yoshua Bengio, Patrice Y. Simard, and Paolo Frasconi. 1994. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 5, 2 (1994), 157–166. DOI:https://doi.org/10.1109/72.279181 Google ScholarDigital Library
- William Caicedo-Torres and Jairo A. Gutiérrez. 2020. ISeeU2: Visually interpretable ICU mortality prediction using deep learning and free-text medical notes. arxiv:2005.09284. Retrieved from https://arxiv.org/abs/2005.09284.Google Scholar
- Zhengping Che, David C. Kale, Wenzhe Li, Mohammad Taha Bahadori, and Yan Liu. 2015. Deep computational phenotyping. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 507–516. DOI:https://doi.org/10.1145/2783258.2783365 Google ScholarDigital Library
- Wanyu Chen, Fei Cai, Honghui Chen, and Maarten de Rijke. 2019. A dynamic co-attention network for session-based recommendation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 1461–1470. DOI:https://doi.org/10.1145/3357384.3357964 Google ScholarDigital Library
- Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter F. Stewart. 2016. RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism. In Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS’16). Daniel D. Lee, Masashi Sugiyama, Ulrike von Luxburg, Isabelle Guyon, and Roman Garnett (Eds.). 3504–3512. Google ScholarDigital Library
- Chun-An Chou, Qingtao Cao, Shao-Jen Weng, and Che-Hung Tsai. 2020. Mixed-integer optimization approach to learning association rules for unplanned ICU transfer. Artificial Intelligence in Medicine 103, 2 (2020), 101806. DOI:https://doi.org/10.1016/j.artmed.2020.101806Google ScholarCross Ref
- Junyoung Chung, Çaglar Gülçehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In Proceedings of the NIPS 2014 Workshop on Deep Learning.Google Scholar
- David Cuadrado, David Riaño, Josep Gómez, María Bodí, Gonzalo Sirgo, Federico Esteban, Rafael García, and Alejandro Rodríguez. 2019. Pursuing optimal prediction of discharge time in ICUs with machine learning methods. In Proceedings of the 17th Conference on Artificial Intelligence in Medicine. David Riaño, Szymon Wilk, and Annette ten Teije (Eds.), Lecture Notes in Computer Science, Vol. 11526. Springer, 150–154. DOI:https://doi.org/10.1007/978-3-030-21642-9_20Google Scholar
- Jeffrey L. Elman. 1990. Finding structure in time. Cognitive Science 14, 2 (1990), 179-211. DOI:https://doi.org/10.1016/0364-0213(90)90002-EGoogle ScholarCross Ref
- Tom Fawcett. 2005. An introduction to ROC analysis. Pattern Recognition Letters 27, 8 (2005), 861–874. Google ScholarDigital Library
- Felix A. Gers, Jürgen Schmidhuber, and Fred A. Cummins. 2000. Learning to forget: Continual prediction with LSTM. Neural Computation 12, 10 (2000), 2451–2471. DOI:https://doi.org/10.1162/089976600300015015 Google ScholarDigital Library
- Julien Grand-Clément, Carri W. Chan, Vineet Goyal, and Gabriel J. Escobar. 2020. Robust policies for proactive ICU transfers. arxiv:2002.06247. Retrieved from https://arxiv.org/abs/2002.06247.Google Scholar
- Joyce C. Ho, Joydeep Ghosh, and Jimeng Sun. 2014. Marble: High-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 115–124. DOI:https://doi.org/10.1145/2623330.2623658 Google ScholarDigital Library
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780. DOI:https://doi.org/10.1162/neco.1997.9.8.1735 Google ScholarDigital Library
- Wenqi Hu, Carri W. Chan, José R. Zubizarreta, and Gabriel J. Escobar. 2018. An examination of early transfers to the ICU based on a physiologic risk score. Manufacturing & Service Operations Management 20, 3 (2018), 531–549. DOI:https://doi.org/10.1287/msom.2017.0658 Google ScholarDigital Library
- Bo Jin, Haoyu Yang, Leilei Sun, Chuanren Liu, Yue Qu, and Jianing Tong. 2018. A treatment engine by predicting next-period prescriptions. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1608–1616. DOI:https://doi.org/10.1145/3219819.3220095 Google ScholarDigital Library
- Alistair E. W. Johnson, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G. Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific Data 3, 1 (2016), 160035. DOI:https://doi.org/10.1038/sdata.2016.35Google ScholarCross Ref
- Jens Keilwagen, Ivo Grosse, and Jan Grau. 2014. Area under precision-recall curves for weighted and unweighted data. PLoS ONE 9, 3 (2014), e92209.Google ScholarCross Ref
- Ahmad F. Klaib and Maryam S. Nuser. 2019. Evaluating EHR and health care in Jordan according to the international health metrics network (HMN) framework and standards: A case study of Hakeem. IEEE Access 7 (2019), 51457–51465. DOI:https://doi.org/10.1109/ACCESS.2019.2911684Google ScholarCross Ref
- Xuanjing Li, Dacheng Liu, Na Geng, and Xiaolei Xie. 2019. Optimal ICU admission control with premature discharge. IEEE Transactions on Automation Science and Engineering 16, 1 (2019), 148–164. DOI:https://doi.org/10.1109/TASE.2018.2827664Google ScholarCross Ref
- Zhaohui Liang, Jun Liu, Aihua Ou, Honglai Zhang, Ziping Li, and Jimmy Xiangji Huang. 2019. Deep generative learning for automated EHR diagnosis of traditional Chinese medicine. Computer Methods and Programs in Biomedicine 174 (2019), 17–23. DOI:https://doi.org/10.1016/j.cmpb.2018.05.008Google ScholarCross Ref
- Donghua Liu, Jing Li, Bo Du, Jun Chang, and Rong Gao. 2019. DAML: Dual attention mutual learning between ratings and reviews for item recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 344–352. DOI:https://doi.org/10.1145/3292500.3330906 Google ScholarDigital Library
- Melina Loreto, Thiago Lisboa, and Viviane P. Moreira. 2020. Early prediction of ICU readmissions using classification algorithms. Computers in Biology and Medicine, 118 (2020), 103636. DOI:https://doi.org/10.1016/j.compbiomed.2020.103636Google ScholarDigital Library
- Fenglong Ma, Radha Chitta, Jing Zhou, Quanzeng You, Tong Sun, and Jing Gao. 2017. Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 1903–1911. DOI:https://doi.org/10.1145/3097983.3098088 Google ScholarDigital Library
- Liantao Ma, Junyi Gao, Yasha Wang, Chaohe Zhang, Jiangtao Wang, Wenjie Ruan, Wen Tang, Xin Gao, and Xinyu Ma. 2020. AdaCare: Explainable clinical health status representation learning via scale-adaptive feature extraction and recalibration. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference , and the 10th AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI Press, 825–832. Retrieved from https://aaai.org/ojs/index.php/AAAI/article/view/5427.Google Scholar
- Xin Ma, Yabin Si, Zifan Wang, and Youqing Wang. 2020. Length of stay prediction for ICU patients using individualized single classification algorithm. Computer Methods and Programs in Biomedicine 186 (2020), 105224. DOI:https://doi.org/10.1016/j.cmpb.2019.105224Google ScholarCross Ref
- Seyedsalim Malakouti and Milos Hauskrecht. 2019. Predicting patient’s diagnoses and diagnostic categories from clinical-events in EHR data. In Proceedings of the 17th Conference on Artificial Intelligence in Medicine. 125–130. DOI:https://doi.org/10.1007/978-3-030-21642-9_17Google ScholarDigital Library
- Oleg G. Metsker, Vozniuk Igor, Georgy Kopanitsa, Elena Morozova, and Prohorova Maria. 2020. Stroke ICU patient mortality day prediction. In Proceedings of the 20th International Conference on Computational Science, Valeria V. Krzhizhanovskaya, Gábor Závodszky, Michael Harold Lees, Jack J. Dongarra, Peter M. A. Sloot, Sérgio Brissos, and João Teixeira (Eds.), Lecture Notes in Computer Science, Vol. 12140, Springer, 390–405. DOI:https://doi.org/10.1007/978-3-030-50423-6_29Google Scholar
- Volodymyr Mnih, Nicolas Heess, Alex Graves, and Koray Kavukcuoglu. 2014. Recurrent models of visual attention. In Proceedings of the 27th International Conference on Neural Information Processing Systems. 2204–2212. Retrieved from http://papers.nips.cc/paper/5542-recurrent-models-of-visual-attention. Google ScholarDigital Library
- Dinh C. Nguyen, Pubudu N. Pathirana, Ming Ding, and Aruna Seneviratne. 2019. Blockchain for secure EHRs sharing of mobile cloud based e-health systems. IEEE Access 7 (2019), 66792–66806. DOI:https://doi.org/10.1109/ACCESS.2019.2917555Google ScholarCross Ref
- Alvin Rajkomar, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Peter J. Liu, Xiaobing Liu, Mimi Sun, Patrik Sundberg, Hector Yee, Kun Zhang, Gavin E. Duggan, Gerardo Flores, Michaela Hardt, Jamie Irvine, Quoc V. Le, Kurt Litsch, Jake Marcus, Alexander Mossin, Justin Tansuwan, De Wang, James Wexler, Jimbo Wilson, Dana Ludwig, Samuel L. Volchenboum, Katherine Chou, Michael Pearson, Srinivasan Madabushi, Nigam H. Shah, Atul J. Butte, Michael Howell, Claire Cui, Greg Corrado, and Jeff Dean. 2018. Scalable and accurate deep learning for electronic health records. NPJ Digital Medicine 1, 1 (2018), 1–10.Google ScholarCross Ref
- Satya Narayan Shukla and Benjamin M. Marlin. 2020. Integrating physiological time series and clinical notes with deep learning for improved ICU mortality prediction. arxiv:2003.11059. Retrieved from https://arxiv.org/abs/2003.11059.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, United states, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.), Advances in Neural Information Processing Systems, Vol. 30, 5998–6008. Retrieved from http://papers.nips.cc/paper/7181-attention-is-all-you-need. Google ScholarDigital Library
- Teeradache Viangteeravat, Oguz Akbilgic, and Robert L. Davis. 2017. Analyzing electronic medical records to predict risk of DIT (death, intubation, or transfer to ICU) in pediatric respiratory failure or related conditions. In Proceedings of the Summit on Clinical Research Informatics,. AMIA. Retrieved from http://knowledge.amia.org/amia-64484-cri2017-1.3520710/t002-1.3521687/t002-1.3521688/a041-1.3521699/a042-1.3521696.Google Scholar
- Xin Wang, Wenwu Zhu, and Chenghao Liu. 2019. Social recommendation with optimal limited attention. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1518–1527. DOI:https://doi.org/10.1145/3292500.3330939 Google ScholarDigital Library
- Jingyi Wu, Ke Lin, Yu Lin, Yonghua Hu, and Guilan Kong. 2019. Predicting length of ICU stay via random forest. In Proceedings of the American Medical Informatics Association Annual Symposium. AMIA. Retrieved from http://knowledge.amia.org/69862-amia-1.4570936/t006-1.4574499/t006-1.4574500/3203507-1.4574519/3199832-1.4574516.Google Scholar
- Qitian Wu, Yirui Gao, Xiaofeng Gao, Paul Weng, and Guihai Chen. 2019. Dual sequential prediction models linking sequential recommendation and information dissemination. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 447–457. DOI:https://doi.org/10.1145/3292500.3330959 Google ScholarDigital Library
- Rongjun Xie, Ibrahim Khalil, Shahriar Badsha, and Mohammed Atiquzzaman. 2020. An intelligent healthcare system with data priority based on multi vital biosignals. Computer Methods and Programs in Biomedicine 185 (2020), 105126. DOI:https://doi.org/10.1016/j.cmpb.2019.105126Google ScholarCross Ref
- Pranjul Yadav, Michael S. Steinbach, Vipin Kumar, and György J. Simon. 2018. Mining electronic health records (EHRs): A survey. ACM Computing Surveys 50, 6 (2018), 85:1–85:40. DOI:https://doi.org/10.1145/3127881 Google ScholarDigital Library
- Yuan Yuan, Yuwei Lu, and Qi Wang. 2017. Tracking as a whole: Multi-target tracking by modeling group behavior with sequential detection. IEEE Transactions on Intelligent Transportation Systems 18, 12 (2017), 3339–3349. DOI:https://doi.org/10.1109/TITS.2017.2686871 Google ScholarDigital Library
- Yuan Yuan, Dong Wang, and Qi Wang. 2017. Anomaly detection in traffic scenes via spatial-aware motion reconstruction. IEEE Transactions on Intelligent Transportation Systems 18, 5 (2017), 1198–1209. DOI:https://doi.org/10.1109/TITS.2016.2601655 Google ScholarDigital Library
- Yutao Zhang, Robert Chen, Jie Tang, Walter F. Stewart, and Jimeng Sun. 2017. LEAP: Learning to prescribe effective and safe treatment combinations for multimorbidity. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 1315–1324. DOI:https://doi.org/10.1145/3097983.3098109 Google ScholarDigital Library
Index Terms
- MSIPA: Multi-Scale Interval Pattern-Aware Network for ICU Transfer Prediction
Recommendations
Time interval uncertainty-aware and text-enhanced based disease prediction
AbstractDeep learning methods have achieved success in disease prediction using electronic health records (EHR) data. Most of the existing methods have some limitations. First, most of the methods adopt a homogeneous decay way to deal with the effect of ...
Graphical abstractDisplay Omitted
Highlights- We propose a Time Interval Uncertainty-Aware and Text-Enhanced Based Disease Prediction Model, which utilizes the uncertain effects of time intervals and patient's text information for disease prediction.
- We use the cross-attention ...
A continual prediction model for inpatient acute kidney injury
AbstractAcute kidney injury (AKI) commonly occurs in hospitalized patients and can lead to serious medical complications. But it is preventable and potentially reversible with early diagnosis and management. Therefore, several machine learning ...
Highlights- Introduced a novel framework for continual prediction form EHR data.
- It was ...
EEMI-An Electronic Health Record for Pediatricians: Adoption Barriers, Services and Use in Mexico
The use of paper health records and handwritten prescriptions are prone to preset errors of misunderstanding instructions or interpretations that derive in affecting patients' health. Electronic Health Records EHR systems are useful tools that among ...
Comments