Development and validation of a machine learning model that predicts next-day extubation

Machine Learning


  • Melsen, W.G. et al. Mortality in ventilator-associated pneumonia: A meta-analysis of individual patient data from randomized prevention studies. lancet infection. Dis. 13(8), 665–671 (2013).

    Article PubMed Google Scholar

  • Epstein, SK & Ciubotaru, RL Independent effects of etiology of failed extubation and time to reintubation on outcome of patients with failed extubation. morning. J. Respier. critical. Care Med. 158(2), 489–493 (1998).

    Article CAS PubMed Google Scholar

  • Ely, E. W. et al. Impact of identifying spontaneously breathing patients on mechanical ventilation duration. N. Engl. J.Med.New English. J.Med. (NEJM/MMS) 35(25), 1864-1869 (1996).

    Article Google Scholar

  • Girard TD et al. Efficacy and safety of a paired protocol of sedation and ventilator weaning for mechanically ventilated patients in intensive care (awake and breathing controlled trial): a randomized controlled trial. lancet 371(9607), 126–134 (2008).

    Article PubMed Google Scholar

  • Burns, KEA, Rizvi, L., Cook, DJ, Lebovic, G., Dodek, P., Villar, J., Slutsky, AS, Jones, A., Kapadia, FN, Gattas, DJ, Epstein, SK, Pelosi, P., Kefala, K., Meade, MO, Canadian Critical Care Group. Practice of ventilator weaning and discontinuation for critically ill patients. Jam Am. medicine. Associate Professor (Amateur) 325(12), 1173–1184 (2021).

    Article Google Scholar

  • Esteban, A. et al. A comparison of four methods for weaning a patient from a ventilator. Spanish Lung Failure Collaborative Group. N. Engl. J.Med. 332(6), 345–350 (1995).

    Article CAS PubMed Google Scholar

  • Brochard, L. et al. Comparison of three methods of gradual weaning from ventilatory support during weaning from mechanical ventilation. morning. J. Respier. critical. Care Med. morning. Chest. society 150(4), 896–903 (1994).

    Article CAS Google Scholar

  • Perkins, G.D. et al. Effects of protocolized weaning to noninvasive ventilation with early extubation versus invasive weaning based on time to release from mechanical ventilation in patients with respiratory failure: A respiratory randomized clinical trial. Jam Am. medicine. Associate Professor (Amateur) 320(18), 1881–1888 (2018).

    Article Google Scholar

  • Dorado, J.H., Navarro, E., Plotnikow, G.A., Gogniat, E., Accocce, M., EpVAr Research Group. Epidemiology of invasive ventilator weaning in patients with COVID-19. Please breathe. care 68(1), 101–109 (2023).

    Article Google Scholar

  • Cimino, JJ Improving electronic health records—are clinicians getting what they wanted? Japan Automobile Manufacturers Association 309(10), 991–992 (2013).

    Article CAS PubMed Google Scholar

  • Wiens, J. & Shenoy, ES Machine learning for healthcare: We are on the brink of a major change in healthcare epidemiology. Clin. Infect. Dis. 66(1), 149–153 (2018).

    Article PubMed Google Scholar

  • Ben-Israel, D. et al. The impact of machine learning on patient care: A systematic review. Artif. intelligence. medicine. 103101785 (2020).

    Article PubMed Google Scholar

  • California Gao et al. Machine learning links unresolved secondary pneumonia to death in patients with severe pneumonia, including COVID-19. J Clin. invest. 133(12), e170682 (2023).

    Article PubMed PubMed Central Google Scholar

  • Grant, R.A. et al. Circuit between infected macrophages and T cells in SARS-CoV-2 pneumonia. nature 590(7847), 635–641 (2021).

    Article ADS CAS PubMed PubMed Central Google Scholar

  • superscript (script)2) Systems Biology Center [Internet]. [cited 2025]. Available at https://script.northwestern.edu/.

  • Starren, JB, Winter, AQ & Lloyd-Jones, DM Enabling learning health systems with an integrated enterprise data warehouse: The experience of the Northwestern University Clinical Translational Sciences (NUCATS) Institute. Clin. translation. Science. 8(4), 269–271 (2015).

    Article PubMed PubMed Central Google Scholar

  • Pickens, CI, Gao, CA, Bodner, J., Walter, JM, Kruser, JM, Donnelly, HK, Donayre, A., Clepp, K., Borkowski, N., Wunderink, RG, Singer, BD, NU SCRIPT study investigators. Sentencing protocol for severe pneumonia. Open forum infection. Dis. 10(7), 336 (2023).

    Article Google Scholar

  • Tang, S. et al. Democratizing EHR analytics with FIDDLE: A flexible data-driven preprocessing pipeline for structured clinical data. J.Am. Medicine. Associate Professor of Information 27(12), 1921-1934 (2020).

    Article Google Scholar

  • Lundberg, S., Lee, SI A unified approach to interpreting model predictions. [Internet]. arXiv [cs.AI]. (2017). Available from http://arxiv.org/abs/1705.07874.

  • Markov, N., Gao, CA, Stoeger, T., Pawlowski, A., Kang, M., Nannapaneni, P., Grant, R., Rasmussen, L., Schneider, D., Starren, J., Wunderink, R., Budinger, GRS, Misharin, A., Singer, B., Research Investigator, NU SCRIPT. SCRIPT CarpeDiem Dataset: Demographics, outcomes, and daily clinical parameters of critically ill patients with suspected pneumonia. physionet (2023) [cited 2023 Oct 16]. Available from: https://physionet.org/content/script-carpediem-dataset/1.1.0/

  • McCullagh, P. Generalized linear models. EUR. J. Oper. resolution 16(3), 285–292 (1984).

    Article MathSciNet MATH Google Scholar

  • Bryman L. Mach Learn. Vol. 45(1), 5–32 (Springer Science and Business Media LLC, 2001).

  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, TY, Research M, University P, Redmond M. LightGBM: Highly Efficient Gradient Boosting Decision Trees [Internet]. [cited 2023 Oct 16]. Available at https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf.

  • Chen, T., Guestrin, C. XGBoost. in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.. (ACM, New York, NY, USA, 2016). https://doi.org/10.1145/2939672.2939785.

  • Medsker, L., Jain, LC Recurrent Neural Networks: Design and Applications. 1st edition (CRC Press, Boca Raton, FL, 1999).

  • Hochreiter, S. & Schmidhuber, J. Long short-term memory. neural computing. 9(8), 1735-1780 (1997).

    Article CAS PubMed Google Scholar

  • Blackwood, B. et al. Use of weaning protocols to reduce mechanical ventilation duration in critically ill adults: a Cochrane systematic review and meta-analysis. BMJ 342(jan132), c7237 (2011).

    Article PubMed PubMed Central Google Scholar

  • Morandi A, Piva S, Ely EW, Myatra SN, Salou JIF, Amare D, Azoulay E, Berelli G, Somos A, Huang E, Fagoni N, Girard TD, Heras-La Calle G, Inoue S, Lim CM, Kaps R, Kotfis K, Koh Y, Misango D, Pandaripande PP, Permpicul C, Chen Tan. C, Wang DX, Sharshar T, Shehabi Y, Skrobik Y, Singh JM, Slooter A, Smith M, Tsuruta R, Latronico N. A global survey of the “Pain Assessment, Both Spontaneous Awakening and Breathing Tests, Medication Selection, Delirium Monitoring/Management, Early Exercise/Mobility, and Family Empowerment” (ABCDEF) bundle. Critical Care Med. Ovid Technologies (Wolters Kluwer Health); 2017 November;45(11):e1111–e1122.

  • Balas, MC, Tate, J., Tan, A., Pinion, B. & Exline, M. Assessing perceived barriers and facilitators to timely extubation of critically ill adults: an interprofessional survey. The worldview is clear. Nurse based. 18(3), 201–209 (2021).

    Article PubMed PubMed Central Google Scholar

  • Olsen, G.H. et al. Arousal and respiratory regulation: A mixed methods analysis of the determinants of performance. Anam Thoracic Society 20(10), 1483–1490 (2023).

    Article PubMed PubMed Central Google Scholar

  • Barras, MC et al. Factors associated with performance on the spontaneous alertness and spontaneous breathing tests in adults with serious illness: Analysis of a multicenter, national cohort study. chest 162(3), 588–602 (2022).

    Article PubMed PubMed Central Google Scholar

  • Costa, D.K. et al. Identifying barriers to providing alertness and respiratory coordination, delirium, and early exercise/mobility bundles to minimize adverse outcomes in mechanically ventilated patients: A systematic review. chest 152(2), 304–311 (2017).

    Article PubMed PubMed Central Google Scholar

  • Chen, K.H. et al. Feasibility of a machine learning approach to predict successful ventilator mode transition for adult patients in a medical intensive care unit. Medicina (Kaunas) 58(3), 360 (2022).

    Article PubMed Google Scholar

  • Esteban, A. et al. A comparison of four methods of weaning a patient from a ventilator. N. Engl. J.Med. 332(6), 345–350 (1995).

    Article CAS PubMed Google Scholar

  • Yuya Igarashi et al.Machine learning to predict extubation success in patients receiving mechanical ventilation. front. medicine. 9961252 (2022).

    Article Google Scholar

  • Yang, C. et al. Predicting changes in brain functional status in critically ill patients through machine learning. J.Am. Medicine. Associate Professor of Information 28(11), 2412–2422 (2021).

    Article Google Scholar



  • Source link