Quality-Guaranteed and Cost-Effective Population Health Profiling: A Deep Active Learning Approach

被引：1
作者：
Chen L. [1 ]
Wang J. [1 ]
Thakuriah P. [2 ]
机构：
[1] Center for Intelligent Healthcare, Coventry University, P.O. Box 412, West Midlands, Coventry
[2] Rutgers Urban and Civic Informatics Lab, Rutgers University, Civic Square Building, Rutgers, New Brunswick, NJ
来源：
ACM Transactions on Computing for Healthcare | 2023年 / 4卷 / 04期
基金：
英国工程与自然科学研究理事会;
关键词：
convolutional neural networks (CNN); generative adversarial network; Profiling of prevalence; spatio-temporal correlations;
D O I：
10.1145/3617179
中图分类号：
学科分类号：
摘要：
Reliability and cost are two primary considerations for profiling population-scale prevalence (PPP) of multiple non-communicable diseases (NCDs). In this paper, we exploit intra-disease and inter-disease correlation in different traditionally-sensed-areas (TS-A) to reduce the number of profiling tasks required without compromising data reliability. Specifically, we propose a novel approach called Compressive Population Health TS-A Selection (CPH-TS), which blends the state-of-the-art profile inference, data augmentation and active learning in a unified deep learning framework. It can actively select the minimum number of TS-A regions for profiling task allocation in each profiling cycle, while deducing the missing data on the unprofiled regions with a probabilistic guarantee of reliability. We evaluate our approach on real-world prevalence datasets of London, which shows the effectiveness of CPH-TS. In general, CPH-TS assigned 11.1-27.3% fewer tasks than baselines, assigning tasks to only 34.7% of the sub-regions while the profiling error was below 5% for 95% of the cycles. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.
引用
收藏
相关论文
共 46 条
  • [21] Janz D., van der Westhuizen J., Hernandez-Lobato J.M., Actively learning what makes a discrete sequence valid, (2017)
  • [22] Jiang L., Chen C.-X., Chen C., L2MM: Learning to map matching with deep models for low-quality GPS trajectory data, ACM Transactions on Knowledge Discovery from Data, 17, 3, pp. 1-25, (2023)
  • [23] Kirsch A., van Amersfoort J., Gal Y., BatchBALD: Efficient and diverse batch acquisition for deep Bayesian active learning, Advances in Neural Information Processing Systems, 32, 2019, pp. 7026-7037, (2019)
  • [24] Kroll M., Phalkey R.K., Kraas F., Challenges to the surveillance of non-communicable diseases–a review of selected approaches, BMC Public Health, 15, 1, pp. 1-12, (2015)
  • [25] Li J., Manitz J., Bertuzzo E., Kolaczyk E.D., Sensor-based localization of epidemic sources on human mobility networks, PLoS Computational Biology, 17, 1, (2021)
  • [26] Liu Z., Zhang W., Lin S., Quek T.Q.S., Heterogeneous sensor data fusion by deep multimodal encoding, IEEE Journal of Selected Topics in Signal Processing, 11, 3, pp. 479-491, (2017)
  • [27] Lucero M., Evaluating the Effectiveness of Active Learning Methods in Predicting Biochemical Properties, (2021)
  • [28] Ma L., Gao J., Wang Y., Zhang C., Wang J., Ruan W., Tang W., Gao X., Ma X., AdaCare: Explainable clinical health status representation learning via scale-adaptive feature extraction and recalibration, Proceedings of the AAAI Conference on Artificial Intelligence, 34, pp. 825-832, (2020)
  • [29] Ma L., Ma X., Gao J., Jiao X., Yu Z., Zhang C., Ruan W., Wang Y., Tang W., Wang J., Distilling knowledge from publicly available online EMR data to emerging epidemic for prognosis, Proceedings of the Web Conference, 2021, pp. 3558-3568, (2021)
  • [30] Ma L., Zhang C., Wang Y., Ruan W., Wang J., Tang W., Ma X., Gao X., Gao J., Con-Care: Personalized clinical feature embedding via capturing the healthcare context, Proceedings of the AAAI Conference on Artificial Intelligence, 34, pp. 833-840, (2020)
12345