×

How artificial intelligence and machine learning can help healthcare systems respond to COVID-19. (English) Zbl 07432796

Summary: The COVID-19 global pandemic is a threat not only to the health of millions of individuals, but also to the stability of infrastructure and economies around the world. The disease will inevitably place an overwhelming burden on healthcare systems that cannot be effectively dealt with by existing facilities or responses based on conventional approaches. We believe that a rigorous clinical and societal response can only be mounted by using intelligence derived from a variety of data sources to better utilize scarce healthcare resources, provide personalized patient management plans, inform policy, and expedite clinical trials. In this paper, we introduce five of the most important challenges in responding to COVID-19 and show how each of them can be addressed by recent developments in machine learning (ML) and artificial intelligence (AI). We argue that the integration of these techniques into local, national, and international healthcare systems will save lives, and propose specific methods by which implementation can happen swiftly and efficiently. We offer to extend these resources and knowledge to assist policymakers seeking to implement these techniques.

MSC:

68T05 Learning and adaptive systems in artificial intelligence

Software:

GAIN; KnockoffGAN
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Ahmed, M. A., & van der Schaar, M. (2017). Bayesian inference of individualized treatment effects using multi-task gaussian processes. NeurIPS 2017.
[2] Ahmed, M. A., & van der Schaar, M. (2020). Discriminative Jackknife: Quantifying uncertainty in deep learning via higher order influence functions.
[3] Alaa, A. M., & van der Schaar, M. (2018). AutoPrognosis: Automated clinical prognostic modeling via Bayesian optimization with structured kernel learning.
[4] Alaa, A. M., & van der Schaar, M. (2019). Attentive state-space modeling of disease progression. Advances in Neural Information Processing Systems. 2019.
[5] Alaa, A. M., & van der Schaar, M. (2020). Frequentist uncertainty in recurrent neural networks via blockwise influence functions.
[6] Alaa, A. M, Yoon, J., Hu, S., & van der Schaar, M. (2017). Personalized risk scoring for critical care prognosis using mixtures of gaussian processes. IEEE Transactions on Biomedical Engineering, 2017.
[7] Alaa, AM; Ahuja, K.; van der Schaar, M., A micro-foundation of social capital in evolving social networks, IEEE Transactions on Network Science and Engineering, 5, 1, 14-31 (2018)
[8] Anderson, RM; Hans, H.; Don, K.; Hollingsworth, TD, How will countrybased mitigation measures influence the course of the COVID-19 epidemic?, The Lancet, 395, 10228, 931-934 (2020)
[9] Atan, O., Zame, W. R., & van der Schaar, M. (2019). Sequential patient recruitment and allocation for adaptive clinical trials. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.
[10] Bellot, A., & van der Schaar, M. (2020). Flexible modelling of longitudinal medical data: A Bayesian nonparametric approach. ACM Transactions on Computing for Healthcare, 2020.
[11] Bica, I., Alaa, A. M., Jordon, J., & van der Schaar, M. (2020). Estimating counterfactual treatment outcomes over time through adversarially balanced representations.
[12] Bica, I., Jarrett, D., Hüyük, A., & van der Schaar, M. (2020). Batch inverse reinforcement learning using counterfactuals for understanding decision making.
[13] Chan, A., Alaa, A. M., & van der Schaar, M. (2020). Unlabelled data improves bayesian uncertainty calibration under covariate shift.
[14] Ferguson, N. M., Daniel, L., Gemma, N. -G., Natsuko, I., Kylie, A., Marc, B., Sangeeta, B. et al. (2020). Impact of non-pharmaceutical interventions (NPIs) to reduce COVID-19 mortality and healthcare demand. London: Imperial College COVID-19 Response Team, March 16.
[15] Gao, J., Zhenxue, T., & Xu, Y. (2020). Breakthrough: Chloroquine phosphate has shown apparent efficacy in treatment of COVID-19 associated pneumonia in clinical studies. BioScience Trends (2020).
[16] Goldstein, Larry B.; Samsa, Gregory P.; Matchar, David B.; Horner, Ronnie D., Charlson Index comorbidity adjustment for ischemic stroke outcome studies, Stroke, 35, 8, 1941-1945 (2004)
[17] Hüyük, A., Jarrett, D., van der Schaar, M. (2020). Explaining by Imitating: Understanding Decisions by Direct Policy Learning. Preprint.
[18] Jarrett, D., & van der Schaar, M. (2020). Inverse active sensing: Modeling and understanding timely decision-making. Preprint.
[19] Jiang, F.; Liehua, D.; Liangqing, Z.; Yin, C.; Chi, WC; Zhengyuan, X., Review of the clinical characteristics of coronavirus disease (COVID-19), Journal of General Internal Medicine, 2020, 1-5 (2020)
[20] Jordon, J., Jinsung Y., van der Schaar, M. (2018). KnockoffGAN: Generating knockoffs for feature selection using generative adversarial networks. In International Conference on Learning Representations (ICLR) 2018.
[21] Lee, H. -S., Shen, C., Jordon, J., van der Schaar, M. (2020). Contextual constrained learning for dose-finding clinical trials. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[22] Lee, C., William, R. Z., Jinsung, Y., & van der Schaar, M. (2018). Deephit: A deep learning approach to survival analysis with competing risks. In Thirty-Second AAAI Conference on Artificial Intelligence (AAAI). 2018.
[23] Lee, C., Yoon, J., & van der Schaar, M. (2019). Dynamic-DeepHit: A deep learning approach for dynamic survival analysis with competing risks based on longitudinal data. IEEE Transactions on Biomedical Engineering (TBME), 2019.
[24] Lee, C., Zame, W. R., Alaa, A. M., & van der Schaar, M. (2019). Temporal quilting for survival analysis. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.
[25] Lu, H., Drug treatment options for the 2019-new coronavirus (2019-nCoV), Biosci Trends, 14, 1, 69-71 (2020)
[26] Qian, Z., Ahmed M. A., Alexis, B., Jem, R., & van der Schaar, M. (2020). Learning dynamic and personalized comorbidity networks from event data using deep diffusion processes. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[27] Qian, Z., Alaa, A. M., van Der Schaar, M. & Ercole, A. (2020). Between-centre differences for COVID-19 ICU mortality from early data in England. Intensive Care Medicine (ICM), 2020.
[28] Wang, M., Qianyi, Z., Wenjun, C., Jeff, P., Honghan, W., Cathie, S., & Dave, R. (2020). Building the Knowledge Graph for UK Health Data Science. ERA.
[29] Xu, J.; van der Schaar, M.; Liu, J.; Li, H., Forecasting popularity of videos using social media, IEEE Journal of Selected Topics in Signal Processing (JSTSP), 9, 2, 330-343 (2014)
[30] Yoon, J., Ahmed, A., Scott, H., & Mihaela, S. (2016). ForecastICU: a prognostic decision support system for timely prediction of intensive care unit admission. In International Conference on Machine Learning (pp. 1680-1689).
[31] Yoon, J., James, J. & van der Schaar, M. (2018). NVASE: Instance-wise variable selection using neural networks. In International Conference on Learning Representations (ICLR), 2018.
[32] Yoon, J., James, J., & van der Schaar, M. (2018). GANITE: Estimation of individualized treatment effects using generative adversarial nets. In International Conference on Learning Representations (ICLR) 2018.
[33] Yoon, J., James, J., & van der Schaar, M. (2019). ASAC: Active sensing using Actor-Critic models. Machine Learning for Healthcare 2019.
[34] Yoon, J., Jordon, J. & Van Der Schaar, M. (2018). Gain: Missing data imputation using generative adversarial nets.
[35] Yoon, J., William, R. Z., & van der Schaar, M. (2018). Deep sensing: Active sensing using multidirectional recurrent neural networks. In International Conference on Learning Representations (ICLR) 2018.
[36] Yoon, J.; William, RZ; van der Schaar, M., Estimating missing data in temporal data streams using multi-directional recurrent neural networks, IEEE Transactions on Biomedical Engineering, 66, 5, 1477-1490 (2018)
[37] Zame, W. R., Bica, I., Shen, C., Curth, A., Lee, H. -S., Bailey, S., Weatherall, J., Wright, D., Bretz, F., van der Schaar, M. (2020). Machine learning for clinical trials in the era of COVID-19. Statistics in Biopharmaceutical Research—Special Issue on Covid-19, 2020.
[38] Zhang, Y., Alexis, B., & van der Schaar, M. (2020). Learning overlapping representations for the estimation of individualized treatment effects. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[39] Zhang, Y., Jarrett, D., & van der Schaar, M. (2020). Stepwise model selection for sequence prediction via deep kernel learning. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
[40] Zhang, Y., Jordon, J., Alaa, A. M., & van der Schaar, M. (2019). Lifelong Bayesian Optimization. arXiv preprint, 2019.
[41] Zhou, F., Ting, Y., Ronghui, D., Guohui, F., Ying, L., Zhibo, L., & Jie, X. et al. (2020). Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: A retrospective cohort study. The Lancet.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.