Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CDANs: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Data (2302.03246v2)

Published 7 Feb 2023 in cs.LG, cs.AI, and stat.ME

Abstract: Time series data are found in many areas of healthcare such as medical time series, electronic health records (EHR), measurements of vitals, and wearable devices. Causal discovery, which involves estimating causal relationships from observational data, holds the potential to play a significant role in extracting actionable insights about human health. In this study, we present a novel constraint-based causal discovery approach for autocorrelated and non-stationary time series data (CDANs). Our proposed method addresses several limitations of existing causal discovery methods for autocorrelated and non-stationary time series data, such as high dimensionality, the inability to identify lagged causal relationships, and overlooking changing modules. Our approach identifies lagged and instantaneous/contemporaneous causal relationships along with changing modules that vary over time. The method optimizes the conditioning sets in a constraint-based search by considering lagged parents instead of conditioning on the entire past that addresses high dimensionality. The changing modules are detected by considering both contemporaneous and lagged parents. The approach first detects the lagged adjacencies, then identifies the changing modules and contemporaneous adjacencies, and finally determines the causal direction. We extensively evaluated our proposed method on synthetic and real-world clinical datasets, and compared its performance with several baseline approaches. The experimental results demonstrate the effectiveness of the proposed method in detecting causal relationships and changing modules for autocorrelated and non-stationary time series data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Critical care and the global burden of critical illness in adults. The Lancet, 376:1339–1346, 2010. 10.1016/S0140-6736(10)60446-1. PMID: 24171518.
  2. Ckh: Causal knowledge hierarchy for estimating structural causal models from data and priors. arXiv preprint arXiv:2204.13775, 2022.
  3. A temporal pattern mining approach for classifying electronic health record data. ACM Transactions on Intelligent Systems and Technology, 8(1):1–19, 2016.
  4. Richard Bellman. Dynamic programming. Science, 153(3731):34–37, 1966.
  5. Alexis Bellot and Mihaela van der Schaar. Conditional independence testing using generative adversarial networks. Advances in Neural Information Processing Systems, 32, 2019.
  6. James R Bence. Analysis of short time series: correcting for autocorrelation. Ecology, 76(2):628–639, 1995.
  7. Structural causal model with expert augmented knowledge to estimate the effect of oxygen therapy. CHEST, 158(4):A636, 2020.
  8. Neural additive vector autoregression models for causal discovery in time series. In International Conference on Discovery Science, pages 446–460. Springer, 2021.
  9. Using electronic health records for population health research: a review of methods and applications. Annual review of public health, 37:61–81, 2016.
  10. David Maxwell Chickering. Optimal structure identification with greedy search. Journal of machine learning research, 3(Nov):507–554, 2002.
  11. Search for additive nonlinear time series causal models. Journal of Machine Learning Research, 9(5), 2008.
  12. Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards. Critical Care Medicine, 44(2):368–374, 2016.
  13. A large-scale clinical validation of an integrated monitoring system in the emergency department. IEEE Journal of Biomedical and Health Informatics, 16(3):471–477, 2012.
  14. Learning high-dimensional directed acyclic graphs with latent and selection variables. The Annals of Statistics, pages 294–321, 2012.
  15. Order-independent constraint-based causal structure learning. J. Mach. Learn. Res., 15(1):3741–3782, 2014.
  16. Electronic health records to facilitate clinical research. Clinical Research in Cardiology, 106(1):1–9, 2017.
  17. On causal discovery from time series data using fci. Probabilistic graphical models, pages 121–128, 2010.
  18. ecdans: Efficient temporal causal discovery from autocorrelated and non-stationary data (student abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13):16208–16209, Jun. 2023. 10.1609/aaai.v37i13.26964. URL https://ojs.aaai.org/index.php/AAAI/article/view/26964.
  19. Structural causal model with expert augmented knowledge to estimate the effect of oxygen therapy on mortality in the icu. Artificial Intelligence in Medicine, 137:102493, 2023.
  20. Causal inference in statistics: A primer. John Wiley & Sons, 2016.
  21. Clive WJ Granger. Investigating causal relations by econometric models and cross-spectral methods. Econometrica: journal of the Econometric Society, pages 424–438, 1969.
  22. Measuring statistical dependence with hilbert-schmidt norms. In International conference on algorithmic learning theory, pages 63–77. Springer, 2005.
  23. Edward J Hannan. The estimation of a lagged regression relation. Biometrika, 54(3-4):409–418, 1967.
  24. Kcrl: A prior knowledge based causal discovery framework with reinforcement learning. Proceedings of Machine Learning Research, 182(2022):1–24, 2022.
  25. A survey on causal discovery methods for temporal and non-temporal data. arXiv preprint arXiv:2303.15027, 2023. Under review in TMLR: https://openreview.net/forum?id=YdMrdhGx9y.
  26. Causal discovery from heterogeneous nonstationary data. J. Mach. Learn. Res., 21(89):1–53, 2020.
  27. Precision medicine—personalized, problematic, and promising. New England Journal of Medicine, 372(23):2229–2234, 2015.
  28. MIMIC-III, a freely accessible critical care database. Scientific Data, 3(160035), 2016. https://doi.org/10.1038/sdata.2016.35.
  29. Unsuitability of notears for causal graph discovery when dealing with dimensional quantities. Neural Processing Letters, pages 1–9, 2022.
  30. Greedy relaxations of the sparsest permutation algorithm. In The 38th Conference on Uncertainty in Artificial Intelligence, 2022.
  31. Richard Lawton et al. Time series analysis and its applications: Robert h. shumway and david s. stoffer; springer texts in statistics; 2000, springer-verlag. International Journal of Forecasting, 17(2):299–301, 2001.
  32. A fast pc algorithm for high dimensional causal discovery with multi-core pcs. IEEE/ACM transactions on computational biology and bioinformatics, 16(5):1483–1495, 2016.
  33. Causal structure learning from multivariate time series in settings with unmeasured confounding. In Proceedings of 2018 ACM SIGKDD Workshop on Causal Discovery, pages 23–47. PMLR, 2018.
  34. Mariusz Maziarz. A review of the granger-causality fallacy. The journal of philosophical economics: Reflections on economic and social issues, 8(2):86–105, 2015.
  35. Ventilation Strategy Using Low Tidal Volumes, Recruitment Maneuvers, and High Positive End-Expiratory Pressure for Acute Lung Injury and Acute Respiratory Distress Syndrome: A Randomized Controlled Trial. JAMA, 299(6):637–645, 02 2008. ISSN 0098-7484. 10.1001/jama.299.6.637. URL https://doi.org/10.1001/jama.299.6.637.
  36. Christopher Meek. Causal inference and causal explanation with background knowledge. arXiv preprint arXiv:1302.4972, 2013.
  37. Ccmi: Classifier based conditional mutual information estimation. In Uncertainty in artificial intelligence, pages 1083–1093. PMLR, 2020.
  38. An interpretable machine learning model for accurate prediction of sepsis in the icu. Critical Care Medicine, 46(4):547–553, 2016.
  39. Use of ehrs data for clinical research: Historical progress and current applications. Learning health systems, 3(1):e10076, 2019.
  40. Hamming distance metric learning. In Advances in neural information processing systems, pages 1061–1069, 2012.
  41. A hybrid causal search algorithm for latent variable models. In Conference on probabilistic graphical models, pages 368–379. PMLR, 2016.
  42. Dynotears: Structure learning from time-series data. In International Conference on Artificial Intelligence and Statistics, pages 1595–1605. PMLR, 2020.
  43. Current oxygenation practice in ventilated patients—an observational cohort study. Anaesthesia and Intensive Care, 41(4):505–514, 2013. 10.1177/0310057X1304100412. URL https://doi.org/10.1177/0310057X1304100412. PMID: 23808511.
  44. Conservative versus liberal oxygenation targets for mechanically ventilated patients. a pilot multicenter randomized controlled trial. American journal of respiratory and critical care medicine, 193(1):43–51, 2016.
  45. Scalable and accurate deep learning with electronic health records. NPJ digital medicine, 1(1):18, 2018.
  46. A million variables and more: the fast greedy equivalence search algorithm for learning high-dimensional graphical causal models, with an application to functional magnetic resonance images. International journal of data science and analytics, 3(2):121–129, 2017.
  47. Beware of the simulated dag! causal discovery benchmarks may be easy to game. Advances in Neural Information Processing Systems, 34:27772–27784, 2021.
  48. Jakob Runge. Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets. In Conference on Uncertainty in Artificial Intelligence, pages 1388–1397. PMLR, 2020.
  49. Inferring causation from time series in earth system sciences. Nature communications, 10(1):1–13, 2019a.
  50. Detecting and quantifying causal associations in large nonlinear time series datasets. Science Advances, 5(11):eaau4996, 2019b.
  51. The acute respiratory distress syndrome network. N Engl J Med, 342:1301–1308, 2000.
  52. Christopher A Sims. Macroeconomics and reality. Econometrica: journal of the Econometric Society, pages 1–48, 1980.
  53. Consistency guarantees for greedy permutation-based causal inference algorithms. Biometrika, 108(4):795–814, 2021.
  54. Causation, prediction, and search. MIT press, 2000.
  55. Nts-notears: Learning nonparametric temporal dags with time-series data and prior knowledge. arXiv preprint arXiv:2109.04286, 2021.
  56. Circulatory shock. New England Journal of Medicine, 369(18):1726–1734, 2013.
  57. The epidemiology of mechanical ventilation use in the united states. Critical Care Medicine — Society of Critical Care Medicine, 38(10):1947–1953, 2010. 10.1097/CCM.0b013e3181ef4460. PMID: 24171518.
  58. Kernel-based conditional independence test and application in causal discovery. arXiv preprint arXiv:1202.3775, 2012.
  59. Causal discovery from nonstationary/heterogeneous data: Skeleton estimation and orientation determination. In IJCAI: Proceedings of the Conference, volume 2017, page 1347. NIH Public Access, 2017.
  60. Dags with no tears: Continuous optimization for structure learning. arXiv preprint arXiv:1803.01422, 2018.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now