A Real-Time Automated Machine Learning Algorithm for Predicting Mortality in Trauma Patients: Survey Says it's Ready for Prime-Time

被引:3
作者
Park, Caroline [1 ,4 ]
Loza-Avalos, Sandra E. [1 ]
Harvey, Jalen [1 ]
Hirschkorn, Carol [2 ]
Dultz, Linda A. [1 ]
Dumas, Ryan P. [1 ]
Sanders, Drew [3 ]
Chowdhry, Vikas [2 ]
Starr, Adam [3 ]
Cripps, Michael [1 ]
机构
[1] Univ Texas Southwestern Med Ctr, Dept Surg, Div Burns Trauma & Acute Care Surg, Dallas, TX 75390 USA
[2] Parkland Mem Hosp & Affiliated Inst, Dallas, TX USA
[3] Univ Texas Southwestern Med Ctr, Dept Orthoped Surg, Dallas, TX 75390 USA
[4] Univ Texas Southwestern Med Ctr, Dept Surg, 5323 Harry Hines Blvd, Dallas, TX 75390 USA
关键词
artificial intelligence; machine learning; trauma mortality; INJURY; FUTURE;
D O I
10.1177/00031348231207299
中图分类号
R61 [外科手术学];
学科分类号
摘要
Background: Though artificial intelligence ("AI") has been increasingly applied to patient care, many of these predictive models are retrospective and not readily available for real-time decision-making. This survey-based study aims to evaluate implementation of a new, validated mortality risk calculator (Parkland Trauma Index of Mortality, "PTIM") embedded in our electronic healthrecord ("EHR") that calculates hourly predictions of mortality with high sensitivity and specificity. Methods: This is a prospective, survey-based study performed at a level 1 trauma center. An anonymous survey was sent to surgical providers and regarding PTIM implementation. The PTIM score evaluates 23 variables including Glasgow Coma Score (GCS), vital signs, and laboratory data. Results: Of the 40 completed surveys, 35 reported using PTIM in decision-making. Prior to reviewing PTIM, providers identified perceived top 3 predictors of mortality, including GCS (22/38, 58%), age (18/35, 47%), and maximum heart rate (17/35, 45%). Most providers reported the PTIM assisted their treatment decisions (27/35, 77%) and timing of operative intervention (23/35, 66%). Many providers agreed that PTIM integrated into rounds and patient assessment (22/36, 61%) and that it improved efficiency in assessing patients' potential mortality (21/36, 58%). Conclusions: Artificial intelligence algorithms are mostly retrospective and lag in real-time prediction of mortality. To our knowledge, this is the first real-time, automated algorithm predicting mortality in trauma patients. In this small survey-based study, we found PTIM assists in decision-making, timing of intervention, and improves accuracy in assessing mortality. Next steps include evaluating the short- and long-term impact on patient outcomes.
引用
收藏
页码:655 / 661
页数:7
相关论文
共 21 条
  • [1] The impact of machine learning on patient care: A systematic review
    Ben-Israel, David
    Jacobs, W. Bradley
    Casha, Steve
    Lang, Stefan
    Ryu, Won Hyung A.
    de Lotbiniere-Bassett, Madeleine
    Cadotte, David W.
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2020, 103 (103)
  • [2] Damage control surgery: current state and future directions
    Benz, Daniel
    Balogh, Zsolt J.
    [J]. CURRENT OPINION IN CRITICAL CARE, 2017, 23 (06) : 491 - 497
  • [3] Surgical Risk Is Not Linear: Derivation and Validation of a Novel, User-friendly, and Machine-learning-based Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) Calculator
    Bertsimas, Dimitris
    Dunn, Jack
    Velmahos, George C.
    Kaafarani, Haytham M. A.
    [J]. ANNALS OF SURGERY, 2018, 268 (04) : 574 - 583
  • [4] EVALUATING TRAUMA CARE - THE TRISS METHOD
    BOYD, CR
    TOLSON, MA
    COPES, WS
    [J]. JOURNAL OF TRAUMA-INJURY INFECTION AND CRITICAL CARE, 1987, 27 (04) : 370 - 378
  • [5] A Systematic Review on Machine Learning in Neurosurgery: The Future of Decision-Making in Patient Care
    Celtikci, Emrah
    [J]. TURKISH NEUROSURGERY, 2018, 28 (02) : 167 - 173
  • [6] A NEW CHARACTERIZATION OF INJURY SEVERITY
    CHAMPION, HR
    COPES, WS
    SACCO, WJ
    LAWNICK, MM
    BAIN, LW
    GANN, DS
    GENNARELLI, T
    MACKENZIE, E
    SCHWAITZBERG, S
    [J]. JOURNAL OF TRAUMA-INJURY INFECTION AND CRITICAL CARE, 1990, 30 (05) : 539 - 546
  • [7] TRAUMA SCORE
    CHAMPION, HR
    SACCO, WJ
    CARNAZZO, AJ
    COPES, W
    FOUTY, WJ
    [J]. CRITICAL CARE MEDICINE, 1981, 9 (09) : 672 - 676
  • [8] Clark DE, 2017, AM SURGEON, V83, P1401
  • [9] Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care
    Dong, Junzi
    Feng, Ting
    Thapa-Chhetry, Binod
    Cho, Byung Gu
    Shum, Tunu
    Inwald, David P.
    Newth, Christopher J. L.
    Vaidya, Vinay U.
    [J]. CRITICAL CARE, 2021, 25 (01)
  • [10] Predicting venous thromboembolism in hospitalized trauma patients: a combination of the Caprini score and data-driven machine learning model
    He, Lingxiao
    Luo, Lei
    Hou, Xiaoling
    Liao, Dengbin
    Liu, Ran
    Ouyang, Chaowei
    Wang, Guanglin
    [J]. BMC EMERGENCY MEDICINE, 2021, 21 (01)