Precision Delivery in Critical Care: Balancing Prediction and Personalization

  • V. X. LiuEmail author
  • H. C. Prescott
Part of the Annual Update in Intensive Care and Emergency Medicine book series (AUICEM)


Recent developments in healthcare data availability, advanced analytic algorithms, and high-performance computing have produced incredible enthusiasm about a new age of data-driven healthcare [1–8]. When it comes to clinical care specifically, ‘precision delivery’ is an emerging term to describe the “routine use of patients’ electronic health record (EHR) data to predict risk and personalize care to substantially improve value” (Table 2.1) [7, 9, 10]. While clinical risk prediction tools have a long history in critical care, novel machine learning applications can offer improved predictive performance by maximally leveraging large-scale, complex EHR and other data [5]. Perhaps, even more importantly, these approaches may help overcome the problem of heterogeneity, which is routinely noted to be a hallmark of critical illness as well as a major barrier to improved treatment [11–13]. In this chapter, we discuss the overarching concept of ‘precision delivery’, the important balance between clinical risk prediction and personalization, and the future challenges and applications of data-driven critical care delivery.


  1. 1.
    Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;375:1216–9.CrossRefGoogle Scholar
  2. 2.
    Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA. 2013;309:1351–2.CrossRefGoogle Scholar
  3. 3.
    Celi LA, Mark RG, Stone DJ, Montgomery RA. “Big data” in the intensive care unit. Closing the data loop. Am J Respir Crit Care Med. 2013;187:1157–60.CrossRefGoogle Scholar
  4. 4.
    Naylor CD. On the prospects for a (deep) learning health care system. JAMA. 2018;320:1099–100.CrossRefGoogle Scholar
  5. 5.
    Hinton G. Deep learning—a technology with the potential to transform health care. JAMA. 2018;320:1101–2.CrossRefGoogle Scholar
  6. 6.
    Darcy AM, Louie AK, Roberts LW. Machine learning and the profession of medicine. JAMA. 2016;315:551–2.CrossRefGoogle Scholar
  7. 7.
    Bates DW, Saria S, Ohno-Machado L, Shah A, Escobar G. Big data in health care: using analytics to identify and manage high-risk and high-cost patients. Health Aff (Millwood). 2014;33:1123–31.CrossRefGoogle Scholar
  8. 8.
    Liu VX. Toward the “plateau of productivity”: enhancing the value of machine learning in critical care. Crit Care Med. 2018;46:1196–7.CrossRefGoogle Scholar
  9. 9.
    Parikh RB, Kakad M, Bates DW. Integrating predictive analytics into high-value care: the dawn of precision delivery. JAMA. 2016;315:651–2.CrossRefGoogle Scholar
  10. 10.
    Parikh RB, Schwartz JS, Navathe AS. Beyond genes and molecules—a precision delivery initiative for precision medicine. N Engl J Med. 2017;376:1609–12.CrossRefGoogle Scholar
  11. 11.
    Cohen J, Vincent JL, Adhikari NK, et al. Sepsis: a roadmap for future research. Lancet Infect Dis. 2015;15:581–614.CrossRefGoogle Scholar
  12. 12.
    Seymour CW, Coopersmith CM, Deutschman CS, et al. Application of a framework to assess the usefulness of alternative sepsis criteria. Crit Care Med. 2016;44:e122–30.CrossRefGoogle Scholar
  13. 13.
    Prescott HC, Calfee CS, Thompson BT, Angus DC, Liu VX. Toward smarter lumping and smarter splitting: rethinking strategies for sepsis and acute respiratory distress syndrome clinical trial design. Am J Respir Crit Care Med. 2016;194:147–55.CrossRefGoogle Scholar
  14. 14.
    National Academies of Sciences, Engineering, and Medicine. The fourth industrial revolution: proceedings of a workshop-in brief. Washington: National Academies Press; 2017.Google Scholar
  15. 15.
    Schwab K. The fourth industrial revolution. New York: Crown Publishing Group; 2017.Google Scholar
  16. 16.
    Smith B, Linden G. Two decades of recommender systems at IEEE Internet Comput. 2017;21:12–8.CrossRefGoogle Scholar
  17. 17.
    Gomez-Uribe CA, Hunt N. The Netflix recommender system: algorithms, business value, and innovation. ACM Trans Manage Inf Syst. 2016;6:1–19.CrossRefGoogle Scholar
  18. 18.
    Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning. New York: Springer Science+Business Media; 2017.Google Scholar
  19. 19.
    Kuhn M, Johnson K. Applied predictive modeling. New York: Springer; 2016.Google Scholar
  20. 20.
    Vincent JL. The future of critical care medicine: integration and personalization. Crit Care Med. 2016;44:386–9.CrossRefGoogle Scholar
  21. 21.
    Vincent JL. Critical care—where have we been and where are we going? Crit Care. 2013;17(Suppl 1):S2.PubMedPubMedCentralGoogle Scholar
  22. 22.
    Vincent JL, Moreno R. Clinical review: scoring systems in the critically ill. Crit Care. 2010;14:207.CrossRefGoogle Scholar
  23. 23.
    Liu V. Keeping score of severity scores: taking the next step. Crit Care Med. 2016;44:639–40.CrossRefGoogle Scholar
  24. 24.
    Castella X, Artigas A, Bion J, Kari A. A comparison of severity of illness scoring systems for intensive care unit patients: results of a multicenter, multinational study. The European/North American Severity Study Group. Crit Care Med. 1995;23:1327–35.CrossRefGoogle Scholar
  25. 25.
    Knaus WA, Draper EA, Wagner DP, Zimmerman JE. APACHE II: a severity of disease classification system. Crit Care Med. 1985;13:818–29.CrossRefGoogle Scholar
  26. 26.
    Vincent JL, de Mendonca A, Cantraine F, et al. Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: results of a multicenter, prospective study. Working group on “sepsis-related problems” of the European Society of Intensive Care Medicine. Crit Care Med. 1998;26:1793–800.CrossRefGoogle Scholar
  27. 27.
    Ferreira FL, Bota DP, Bross A, Melot C, Vincent JL. Serial evaluation of the SOFA score to predict outcome in critically ill patients. JAMA. 2001;286:1754–8.CrossRefGoogle Scholar
  28. 28.
    Singer M, Deutschman CS, Seymour CW, et al. The third international consensus definitions for sepsis and septic shock (Sepsis-3). JAMA. 2016;315:801–10.CrossRefGoogle Scholar
  29. 29.
    Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N. Scalable and accurate deep learning for electronic health records. NPJ Digital Med. 2018;18:1–10.Google Scholar
  30. 30.
    Osheroff J, Teich JM, Levick D, et al. Improving outomes with clinical decision support: an implementer’s guide. Chicago: HIMSS Publishing; 2012.CrossRefGoogle Scholar
  31. 31.
    Sendelbach S, Funk M. Alarm fatigue: a patient safety concern. AACN Adv Crit Care. 2013;24:378–86.CrossRefGoogle Scholar
  32. 32.
    Badawi O, Liu X, Hassan E, Amelung PJ, Swami S. Evaluation of ICU risk models adapted for use as continuous markers of severity of illness throughout the ICU stay. Crit Care Med. 2018;46:361–7.CrossRefGoogle Scholar
  33. 33.
    Weissman GE, Hubbard RA, Ungar LH, et al. Inclusion of unstructured clinical text improves early prediction of death or prolonged ICU stay. Crit Care Med. 2018;46:1125–32.CrossRefGoogle Scholar
  34. 34.
    Lee J, Maslove DM, Dubin JA. Personalized mortality prediction driven by electronic medical data and a patient similarity metric. PLoS One. 2015;10:e0127428.CrossRefGoogle Scholar
  35. 35.
    Sjoding MW, Liu VX. Can you read me now? Unlocking narrative data with natural language processing. Ann Am Thorac Soc. 2016;13:1443–5.CrossRefGoogle Scholar
  36. 36.
    Alam N, Hobbelink EL, van Tienhoven AJ, van de Ven PM, Jansma EP, Nanayakkara PW. The impact of the use of the early warning score (EWS) on patient outcomes: a systematic review. Resuscitation. 2014;85:587–94.CrossRefGoogle Scholar
  37. 37.
    McGaughey J, Alderdice F, Fowler R, Kapila A, Mayhew A, Moutray M. Outreach and Early Warning Systems (EWS) for the prevention of intensive care admission and death of critically ill adult patients on general hospital wards. Cochrane Database Syst Rev. 2007;Issue 3:CD005529.Google Scholar
  38. 38.
    Escobar GJ, LaGuardia JC, Turk BJ, Ragins A, Kipnis P, Draper D. Early detection of impending physiologic deterioration among patients who are not in intensive care: development of predictive models using data from an automated electronic medical record. J Hosp Med. 2012;7:388–95.CrossRefGoogle Scholar
  39. 39.
    Kipnis P, Turk BJ, Wulf DA, et al. Development and validation of an electronic medical record-based alert score for detection of inpatient deterioration outside the ICU. J Biomed Inform. 2016;64:10–9.CrossRefGoogle Scholar
  40. 40.
    Green M, Lander H, Snyder A, Hudson P, Churpek M, Edelson D. Comparison of the between the flags calling criteria to the MEWS, NEWS and the electronic Cardiac Arrest Risk Triage (eCART) score for the identification of deteriorating ward patients. Resuscitation. 2018;123:86–91.CrossRefGoogle Scholar
  41. 41.
    Churpek MM, Yuen TC, Winslow C, et al. Multicenter development and validation of a risk stratification tool for ward patients. Am J Respir Crit Care Med. 2014;190:649–55.CrossRefGoogle Scholar
  42. 42.
    Finlay GD, Rothman MJ, Smith RA. Measuring the modified early warning score and the Rothman index: advantages of utilizing the electronic medical record in an early warning system. J Hosp Med. 2014;9:116–9.CrossRefGoogle Scholar
  43. 43.
    Olenick EM, Zimbro KS, D'Lima GM, Ver Schneider P, Jones D. Predicting Sepsis risk using the “sniffer” algorithm in the electronic medical record. J Nurs Care Qual. 2017;32:25–31.CrossRefGoogle Scholar
  44. 44.
    Harrison AM, Thongprayoon C, Kashyap R, et al. Developing the surveillance algorithm for detection of failure to recognize and treat severe sepsis. Mayo Clin Proc. 2015;90:166–75.CrossRefGoogle Scholar
  45. 45.
    Alsolamy S, Al Salamah M, Al Thagafi M, et al. Diagnostic accuracy of a screening electronic alert tool for severe sepsis and septic shock in the emergency department. BMC Med Inform Decis Mak. 2014;14:105.CrossRefGoogle Scholar
  46. 46.
    Rolnick J, Downing NL, Shepard J, et al. Validation of test performance and clinical time zero for an electronic health record embedded severe sepsis alert. Appl Clin Inform. 2016;7:560–72.CrossRefGoogle Scholar
  47. 47.
    Herasevich V, Pieper MS, Pulido J, Gajic O. Enrollment into a time sensitive clinical study in the critical care setting: results from computerized septic shock sniffer implementation. J Am Med Inform Assoc. 2011;18:639–44.CrossRefGoogle Scholar
  48. 48.
    Despins LA. Automated detection of sepsis using electronic medical record data: a systematic review. J Healthc Qual. 2017;39:322–33.CrossRefGoogle Scholar
  49. 49.
    Manaktala S, Claypool SR. Evaluating the impact of a computerized surveillance algorithm and decision support system on sepsis mortality. J Am Med Inform Assoc. 2017;24:88–95.CrossRefGoogle Scholar
  50. 50.
    Henry KE, Hager DN, Pronovost PJ, Saria S. A targeted real-time early warning score (TREWScore) for septic shock. Sci Transl Med. 2015;7:299ra122.CrossRefGoogle Scholar
  51. 51.
    Wassenaar A, Schoonhoven L, Devlin JW, et al. Delirium prediction in the intensive care unit: comparison of two delirium prediction models. Crit Care. 2018;22:114.CrossRefGoogle Scholar
  52. 52.
    Lindroth H, Bratzke L, Purvis S, et al. Systematic review of prediction models for delirium in the older adult inpatient. BMJ Open. 2018;8:e019223.CrossRefGoogle Scholar
  53. 53.
    Marra A, Pandharipande PP, Shotwell MS, et al. Acute brain dysfunction: development and validation of a daily prediction model. Chest. 2018;154:293–301.CrossRefGoogle Scholar
  54. 54.
    Mestres Gonzalvo C, de Wit H, van Oijen BPC, et al. Validation of an automated delirium prediction model (DElirium MOdel (DEMO)): an observational study. BMJ Open. 2017;7:e016654.CrossRefGoogle Scholar
  55. 55.
    Hodgson LE, Roderick PJ, Venn RM, Yao GL, Dimitrov BD, Forni LG. Correction: the ICE-AKI study: impact analysis of a clinical prediction rule and electronic AKI alert in general medical patients. PLoS One. 2018;13:e0203183.CrossRefGoogle Scholar
  56. 56.
    Mohamadlou H, Lynn-Palevsky A, Barton C, et al. Prediction of acute kidney injury with a machine learning algorithm using electronic health record data. Can J Kidney Health Dis. 2018;5:1–9.CrossRefGoogle Scholar
  57. 57.
    Klein SJ, Brandtner AK, Lehner GF, et al. Biomarkers for prediction of renal replacement therapy in acute kidney injury: a systematic review and meta-analysis. Intensive Care Med. 2018;44:323–36.CrossRefGoogle Scholar
  58. 58.
    Haines RW, Lin SP, Hewson R, et al. Acute kidney injury in trauma patients admitted to critical care: development and validation of a diagnostic prediction model. Sci Rep. 2018;8:3665.CrossRefGoogle Scholar
  59. 59.
    Koyner JL, Adhikari R, Edelson DP, Churpek MM. Development of a multicenter ward-based AKI prediction model. Clin J Am Soc Nephrol. 2016;11:1935–43.CrossRefGoogle Scholar
  60. 60.
    Bauman ZM, Gassner MY, Coughlin MA, Mahan M, Watras J. Lung injury prediction score is useful in predicting acute respiratory distress syndrome and mortality in surgical critical care patients. Crit Care Res Pract. 2015;2015:157408.PubMedPubMedCentralGoogle Scholar
  61. 61.
    Beitler JR, Schoenfeld DA, Thompson BT. Preventing ARDS: progress, promise, and pitfalls. Chest. 2014;146:1102–13.CrossRefGoogle Scholar
  62. 62.
    Levitt JE, Calfee CS, Goldstein BA, Vojnik R, Matthay MA. Early acute lung injury: criteria for identifying lung injury prior to the need for positive pressure ventilation. Crit Care Med. 2013;41:1929–37.CrossRefGoogle Scholar
  63. 63.
    Levitt JE, Bedi H, Calfee CS, Gould MK, Matthay MA. Identification of early acute lung injury at initial evaluation in an acute care setting prior to the onset of respiratory failure. Chest. 2009;135:936–43.CrossRefGoogle Scholar
  64. 64.
    LaFaro RJ, Pothula S, Kubal KP, et al. Neural network prediction of ICU length of stay following cardiac surgery based on pre-incision variables. PLoS One. 2015;10:e0145395.CrossRefGoogle Scholar
  65. 65.
    Verburg IW, Atashi A, Eslami S, et al. Which models can I use to predict adult ICU length of stay? A systematic review. Crit Care Med. 2017;45:e222–31.CrossRefGoogle Scholar
  66. 66.
    Escobar GJ, Baker JM, Kipnis P, et al. Prediction of recurrent Clostridium difficile infection using comprehensive electronic medical records in an integrated healthcare delivery system. Infect Control Hosp Epidemiol. 2017;38:1196–203.CrossRefGoogle Scholar
  67. 67.
    Zilberberg MD, Reske K, Olsen M, Yan Y, Dubberke ER. Development and validation of a recurrent Clostridium difficile risk-prediction model. J Hosp Med. 2014;9:418–23.CrossRefGoogle Scholar
  68. 68.
    Reveles KR, Mortensen EM, Koeller JM, et al. Derivation and validation of a Clostridium difficile infection recurrence prediction rule in a national cohort of veterans. Pharmacotherapy. 2018;38:349–56.CrossRefGoogle Scholar
  69. 69.
    Oh J, Makar M, Fusco C, et al. A generalizable, data-driven approach to predict daily risk of Clostridium difficile infection at two large academic health centers. Infect Control Hosp Epidemiol. 2018;39:425–33.CrossRefGoogle Scholar
  70. 70.
    Delucchi K, Famous KR, Ware LB, et al. Stability of ARDS subphenotypes over time in two randomised controlled trials. Thorax. 2018;73:439–45.CrossRefGoogle Scholar
  71. 71.
    Wong HR, Sweeney TE, Hart KW, Khatri P, Lindsell CJ. Pediatric sepsis endotypes among adults with sepsis. Crit Care Med. 2017;45:e1289–91.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Kaiser Permanente Division of ResearchOaklandUSA
  2. 2.Department of Medicine and Institute for Social ResearchUniversity of Michigan and VA Center for Clinical Management Research, VA Ann Arbor Healthcare SystemAnn ArborUSA

Personalised recommendations