Qingxiong Tan1, Mang Ye2, Andy Jinhua Ma3, Terry Cheuk-Fung Yip4, Grace Lai-Hung Wong4, Pong C Yuen1. 1. Department of Computer Science, Hong Kong Baptist University, Hong Kong, Hong Kong. 2. School of Computer Science, Wuhan University, Wuhan, China. 3. School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China. 4. Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Hong Kong, Hong Kong.
Abstract
OBJECTIVE: Accurate risk prediction is important for evaluating early medical treatment effects and improving health care quality. Existing methods are usually designed for dynamic medical data, which require long-term observations. Meanwhile, important personalized static information is ignored due to the underlying uncertainty and unquantifiable ambiguity. It is urgent to develop an early risk prediction method that can adaptively integrate both static and dynamic health data. MATERIALS AND METHODS: Data were from 6367 patients with Peptic Ulcer Bleeding between 2007 and 2016. This article develops a novel End-to-end Importance-Aware Personalized Deep Learning Approach (eiPDLA) to achieve accurate early clinical risk prediction. Specifically, eiPDLA introduces a long short-term memory with temporal attention to learn sequential dependencies from time-stamped records and simultaneously incorporating a residual network with correlation attention to capture their influencing relationship with static medical data. Furthermore, a new multi-residual multi-scale network with the importance-aware mechanism is designed to adaptively fuse the learned multisource features, automatically assigning larger weights to important features while weakening the influence of less important features. RESULTS: Extensive experimental results on a real-world dataset illustrate that our method significantly outperforms the state-of-the-arts for early risk prediction under various settings (eg, achieving an AUC score of 0.944 at 1 year ahead of risk prediction). Case studies indicate that the achieved prediction results are highly interpretable. CONCLUSION: These results reflect the importance of combining static and dynamic health data, mining their influencing relationship, and incorporating the importance-aware mechanism to automatically identify important features. The achieved accurate early risk prediction results save precious time for doctors to timely design effective treatments and improve clinical outcomes.
OBJECTIVE: Accurate risk prediction is important for evaluating early medical treatment effects and improving health care quality. Existing methods are usually designed for dynamic medical data, which require long-term observations. Meanwhile, important personalized static information is ignored due to the underlying uncertainty and unquantifiable ambiguity. It is urgent to develop an early risk prediction method that can adaptively integrate both static and dynamic health data. MATERIALS AND METHODS: Data were from 6367 patients with Peptic Ulcer Bleeding between 2007 and 2016. This article develops a novel End-to-end Importance-Aware Personalized Deep Learning Approach (eiPDLA) to achieve accurate early clinical risk prediction. Specifically, eiPDLA introduces a long short-term memory with temporal attention to learn sequential dependencies from time-stamped records and simultaneously incorporating a residual network with correlation attention to capture their influencing relationship with static medical data. Furthermore, a new multi-residual multi-scale network with the importance-aware mechanism is designed to adaptively fuse the learned multisource features, automatically assigning larger weights to important features while weakening the influence of less important features. RESULTS: Extensive experimental results on a real-world dataset illustrate that our method significantly outperforms the state-of-the-arts for early risk prediction under various settings (eg, achieving an AUC score of 0.944 at 1 year ahead of risk prediction). Case studies indicate that the achieved prediction results are highly interpretable. CONCLUSION: These results reflect the importance of combining static and dynamic health data, mining their influencing relationship, and incorporating the importance-aware mechanism to automatically identify important features. The achieved accurate early risk prediction results save precious time for doctors to timely design effective treatments and improve clinical outcomes.
Authors: Madalina Fiterau; Suvrat Bhooshan; Jason Fries; Charles Bournhonesque; Jennifer Hicks; Eni Halilaj; Christopher Ré; Scott Delp Journal: Proc Mach Learn Res Date: 2017-08
Authors: Zhenxing Xu; Jingyuan Chou; Xi Sheryl Zhang; Yuan Luo; Tamara Isakova; Prakash Adekkanattu; Jessica S Ancker; Guoqian Jiang; Richard C Kiefer; Jennifer A Pacheco; Luke V Rasmussen; Jyotishman Pathak; Fei Wang Journal: J Biomed Inform Date: 2020-01-03 Impact factor: 6.317
Authors: Navin L Kumar; Brian L Claggett; Aaron J Cohen; Jennifer Nayor; John R Saltzman Journal: Gastrointest Endosc Date: 2017-04-02 Impact factor: 9.427
Authors: Paul Moayyedi; John W Eikelboom; Jackie Bosch; Stuart J Connolly; Leanne Dyal; Olga Shestakovska; Darryl Leong; Sonia S Anand; Stefan Störk; Kelly R H Branch; Deepak L Bhatt; Peter B Verhamme; Martin O'Donnell; Aldo P Maggioni; Eva M Lonn; Leopoldo S Piegas; Georg Ertl; Matyas Keltai; Nancy Cook Bruns; Eva Muehlhofer; Gilles R Dagenais; Jae-Hyung Kim; Masatsugu Hori; P Gabriel Steg; Robert G Hart; Rafael Diaz; Marco Alings; Petr Widimsky; Alvaro Avezum; Jeffrey Probstfield; Jun Zhu; Yan Liang; Patricio Lopez-Jaramillo; Ajay Kakkar; Alexander N Parkhomenko; Lars Ryden; Nana Pogosova; Antonio Dans; Fernando Lanas; Patrick J Commerford; Christian Torp-Pedersen; Tomek Guzik; Dragos Vinereanu; Andrew M Tonkin; Basil S Lewis; Camilo Felix; Khalid Yusoff; Kaj Metsarinne; Keith A A Fox; Salim Yusuf Journal: Gastroenterology Date: 2019-05-02 Impact factor: 22.682