Towards development of alert thresholds for clinical deterioration using continuous predictive analytics monitoring

被引:16
|
作者
Keim-Malpass, Jessica [1 ,2 ]
Clark, Matthew T. [3 ]
Lake, Douglas E. [4 ]
Moorman, J. Randall [3 ,4 ]
机构
[1] Univ Virginia, Dept Acute & Specialty Care, Sch Nursing, POB 800782, Charlottesville, VA 22908 USA
[2] Sch Med, Dept Pediat, Charlottesville, VA 22908 USA
[3] Adv Med Predict Devices Diagnost & Displays Inc, AMP3D, Charlottesville, VA USA
[4] Sch Med, Dept Internal Med, Cardiol Div, Charlottesville, VA USA
关键词
Machine learning; Clinical computing; Clinical deterioration; Predictive analytics; Continuous predictive analytics monitoring; Alert; Implementation science; HEART-RATE CHARACTERISTICS; INTENSIVE-CARE-UNIT; UNPLANNED TRANSFERS; ATRIAL-FIBRILLATION; HEALTH-CARE; BIG DATA; VALIDATION; DYNAMICS; SEPSIS; RHYTHM;
D O I
10.1007/s10877-019-00361-5
中图分类号
R614 [麻醉学];
学科分类号
100217 ;
摘要
Patients who deteriorate while on the acute care ward and are emergently transferred to the Intensive Care Unit (ICU) experience high rates of mortality. To date, risk scores for clinical deterioration applied to the acute care wards rely on static or intermittent inputs of vital sign and assessment parameters. We propose the use of continuous predictive analytics monitoring, or data that relies on real-time physiologic monitoring data captured from ECG, documented vital signs, laboratory results, and other clinical assessments to predict clinical deterioration. A necessary step in translation to practice is understanding how an alert threshold would perform if applied to a continuous predictive analytic that was trained to detect clinical deterioration. The purpose of this study was to evaluate the positive predictive value of 'risk spikes', or large abrupt increases in the output of a statistical model of risk predicting clinical deterioration. We studied 8111 consecutive patient admissions to a cardiovascular medicine and surgery ward with continuous ECG data. We first trained a multivariable logistic regression model for emergent ICU transfer in a test set and tested the characteristics of the model in a validation set of 4059 patient admissions. Then, in a nested analysis we identified large, abrupt spikes in risk (increase by three units over the prior 6 h; a unit is the fold-increase in risk of ICU transfer in the next 24 h) and reviewed hospital records of 91 patients for clinical events such as emergent ICU transfer. We compared results to 59 control patients at times when they were matched for baseline risk including the National Warning Score (NEWS). There was a 3.4-fold higher event rate for patients with risk spikes (positive predictive value 24% compared to 7%,p = 0.006). If we were to use risk spikes as an alert, they would fire about once per day on a 73-bed acute care ward. Risk spikes that were primarily driven by respiratory changes (ECG-derived respiration (EDR) or charted respiratory rate) had highest PPV (30-35%) while risk spikes driven by heart rate had the lowest (7%). Alert thresholds derived from continuous predictive analytics monitoring are able to be operationalized as a degree of change from the person's own baseline rather than arbitrary threshold cut-points, which can likely better account for the individual's own inherent acuity levels. Point of care clinicians in the acute care ward settings need tailored alert strategies that promote a balance in recognition of clinical deterioration and assessment of the utility of the alert approach.
引用
收藏
页码:797 / 804
页数:8
相关论文
共 50 条
  • [1] Towards development of alert thresholds for clinical deterioration using continuous predictive analytics monitoring
    Jessica Keim-Malpass
    Matthew T. Clark
    Douglas E. Lake
    J. Randall Moorman
    [J]. Journal of Clinical Monitoring and Computing, 2020, 34 : 797 - 804
  • [2] Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration
    Monfredi, Oliver J.
    Moore, Christopher C.
    Sullivan, Brynne A.
    Keim-Malpass, Jessica
    Fairchild, Karen D.
    Loftus, Tyler J.
    Bihorac, Azra
    Krahn, Katherine N.
    Dubrawski, Artur
    Lake, Douglas E.
    Moorman, J. Randall
    Clermont, Gilles
    [J]. JOURNAL OF ELECTROCARDIOLOGY, 2023, 76 : 35 - 38
  • [3] A crossroads in predictive analytics monitoring for clinical medicine
    Moorman, J. Randall
    [J]. JOURNAL OF ELECTROCARDIOLOGY, 2018, 51 (06) : S52 - S55
  • [4] Personalized Health Monitoring using Predictive Analytics
    Amin, Poojitha
    Anikireddypally, Nikhitha R.
    Khurana, Suraj
    Vadakkemadathil, Sneha
    Wu, Wencen
    [J]. 2019 IEEE FIFTH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND APPLICATIONS (IEEE BIGDATASERVICE 2019), 2019, : 271 - 278
  • [5] Predicting deterioration in dengue using a low cost wearable for continuous clinical monitoring
    Ming, Damien Keng
    Daniels, John
    Chanh, Ho Quang
    Karolcik, Stefan
    Hernandez, Bernard
    Manginas, Vasileios
    Nguyen, Van Hao
    Nguyen, Quang Huy
    Phan, Tu Qui
    Luong, Thi Hue Tai
    Trieu, Huynh Trung
    Holmes, Alison Helen
    Phan, Vinh Tho
    Georgiou, Pantelis
    Yacoub, Sophie
    [J]. npj Digital Medicine, 2024, 7 (01)
  • [6] Advancing Continuous Predictive Analytics Monitoring Moving from Implementation to Clinical Action in a Learning Health System
    Keim-Malpass, Jessica
    Kitzmiller, Rebecca R.
    Skeeles-Worley, Angela
    Lindberg, Curt
    Clark, Matthew T.
    Tai, Robert
    Calland, James Forrest
    Sullivan, Kevin
    Moorman, J. Randall
    Anderson, Ruth A.
    [J]. CRITICAL CARE NURSING CLINICS OF NORTH AMERICA, 2018, 30 (02) : 273 - +
  • [7] Improved Clinical Diagnosis Using Predictive Analytics
    Divyashree, N.
    Prasad, Nandini K. S.
    [J]. IEEE ACCESS, 2022, 10 : 75158 - 75175
  • [8] Recommending Venues Using Continuous Predictive Social Media Analytics
    Balduini, Marco
    Bozzon, Alessandro
    Della Valle, Emanuele
    Huang, Yi
    Houben, Geert-Jan
    [J]. IEEE INTERNET COMPUTING, 2014, 18 (05) : 28 - 35
  • [9] Diffusing an Innovation: Clinician Perceptions of Continuous Predictive Analytics Monitoring in Intensive Care
    Kitzmiller, Rebecca R.
    Vaughan, Ashley
    Skeeles-Worley, Angela
    Keim-Malpass, Jessica
    Yap, Tracey L.
    Lindberg, Curt
    Kennerly, Susan
    Mitchell, Claire
    Tait, Robert
    Sullivan, Brynne A.
    Anderson, Ruth
    Moorman, Joseph R.
    [J]. APPLIED CLINICAL INFORMATICS, 2019, 10 (02): : 295 - 306
  • [10] An Intelligent Predictive Analytics System for Transportation Analytics on Open Data Towards the Development of a Smart City
    Audu, Abdul-Rasheed A.
    Cuzzocrea, Alfredo
    Leung, Carson K.
    MacLeod, Keaton A.
    Ohin, Nibrasul, I
    Pulgar-Vidal, Nadege C.
    [J]. COMPLEX, INTELLIGENT, AND SOFTWARE INTENSIVE SYSTEMS (CISIS 2019), 2020, 993 : 224 - 236