Patients in step-down units (SDU) undergo continuous noninvasive vital sign (VS) monitoring to facilitate nurse detection of cardiorespiratory instability (CRI) in need of a diagnostic and/or therapeutic response. Yet, our data and others show nurses do not readily identify CRI nor necessarily react in a timely fashion. Further, 75% of monitored SDU patients never become unstable, diffusing surveillance away from those in need. Current nursing surveillance strategies are imprecise and untargeted, leading to failure to detect CRI, and failure to rescue patients needing intervention. Smart clinical decision support systems (SDSS) that continuously process complex data from disparate sources can apply detection algorithms to alert clinicians of ongoing events (nowcasting) and those developing in future (forecasting) to refocus clinicians on high-risk patients, and apply supportive care earlier, or even care to prevent the CRI. In our prior R01 we developed a prototype SDSS using machine learning (ML) to process time series data and learn data patterns systematically preceding events in the near or far term. In that study, we: 1) assembled a complex expert-annotated multidimensional dataset from our existing 1/20 Hz physiologic monitoring data as the learning platform; 2) developed and validated ML models for dynamic CRI prediction, tested which were most effective in CRI nowcasting; and 3) used the SDSS to develop an early prototype CRI prediction graphical user interface (GUI) for nurses. Importantly, our models were also able to discriminate between real CRI and artifact in real-time with high sensitivity and specificity. We now propose to build on this work and enhance our models by: 1) prospectively collecting a multidimensional high-resolution (100-250Hz) dataset of non-invasive physiologic monitoring and electronic health record (EHR) data from two different medical center SDUs to create enhanced and generalizable CRI nowcasting capability, 2) using our existing and the expanding multicenter clinical datasets to precisely forecast CRI events and online artifact discrimination, and 3) create a robust SDSS platform for real-time precision CRI nowcast and forecast alerting; present alerts in a graphical user interface (GUI), iteratively develop the GUI in the simulation setting; and then pilot its use in a SDU. Permitting nurses to move toward SDSS-supported precision nursing surveillance, and know who will become unstable, when they will do so, and why-all in advance of overt instability manifestation-can shift CRI nursing care from reactive to preemptive. Developing a sensitive, specific, parsimonious and clinically practical means to predict patient instability has important implications for reducing preventable morbidity and mortality, eliminating alarm fatigue, improving patient safety, nursing care (monitoring frequency, case load and mixture, staff allocation) and care delivery systems (triage, bed allocation, prevention of adverse events).
It is very difficult for nurses using current monitoring standards to know who will develop cardiorespiratory instability (CRI), when they will do so, and why, leading to imprecise nursing surveillance, and failure-to-rescue. We propose to expand on our prior machine learning (ML) techniques that continuously process complex data from disparate sources, and further develop a smart clinical decision support system (SDSS) to apply CRI detection algorithms to alert nurses to ongoing CRI events (nowcasting) and those developing in future (forecasting). Study findings will enable a tangible move toward precision nursing surveillance (knowing who, when, why in advance of overt CRI), so that nurses can detect CRI better, intervene sooner, and shift CRI nursing care from reactive to preemptive. Developing a sensitive, specific and parsimonious means to nowcast and forecast CRI also has important implications for improving nursing care processes (case load mixture, workload, staff allocation) and delivery systems (patient triage to monitored or non-monitored units, higher vs. lower cost bed allocation, adverse events prevention).
|Morris, Alan H (2018) Human Cognitive Limitations. Broad, Consistent, Clinical Application of Physiological Principles Will Require Decision Support. Ann Am Thorac Soc 15:S53-S56|
|Pinsky, Michael R (2018) Cardiopulmonary Interactions: Physiologic Basis and Clinical Applications. Ann Am Thorac Soc 15:S45-S48|
|Hravnak, Marilyn; Pellathy, Tiffany; Chen, Lujie et al. (2018) A call to alarms: Current state and future directions in the battle against alarm fatigue. J Electrocardiol 51:S44-S48|
|Yoon, Joo H; Pinsky, Michael R (2018) Predicting adverse hemodynamic events in critically ill patients. Curr Opin Crit Care 24:196-203|
|Mahmood, Syed S; Pinsky, Michael R (2018) Heart-lung interactions during mechanical ventilation: the basics. Ann Transl Med 6:349|
|Bose, Eliezer L; Clermont, Gilles; Chen, Lujie et al. (2018) Cardiorespiratory instability in monitored step-down unit patients: using cluster analysis to identify patterns of change. J Clin Monit Comput 32:117-126|
|Chen, Lujie; Ogundele, Olufunmilayo; Clermont, Gilles et al. (2017) Dynamic and Personalized Risk Forecast in Step-Down Units. Implications for Monitoring Paradigms. Ann Am Thorac Soc 14:384-391|
|Bose, Eliezer; Hravnak, Marilyn; Sereika, Susan M (2017) Vector Autoregressive Models and Granger Causality in Time Series Analysis in Nursing Research: Dynamic Changes Among Vital Signs Prior to Cardiorespiratory Instability Events as an Example. Nurs Res 66:12-19|
|Guillame-Bert, Mathieu; Dubrawski, Artur; Wang, Donghan et al. (2017) Learning temporal rules to forecast instability in continuously monitored patients. J Am Med Inform Assoc 24:47-53|
|Hravnak, Marilyn; Chen, Lujie; Dubrawski, Artur et al. (2016) Real alerts and artifact classification in archived multi-signal vital sign monitoring data: implications for mining big data. J Clin Monit Comput 30:875-888|
Showing the most recent 10 out of 33 publications