Prospective validation of clinical deterioration predictive models prior to intensive care unit transfer among patients admitted to acute care cardiology wards.

Objective. Very few predictive models have been externally validated in a prospective cohort following the implementation of an artificial intelligence analytic system. This type of real-world validation is critically important due to the risk of data drift, or changes in data definitions or clinical practices over time, that could impact model performance in contemporaneous real-world cohorts. In this work, we report the model performance of a predictive analytics tool developed before COVID-19 and demonstrate model performance during the COVID-19 pandemic.Approach. The analytic system (CoMETⓇ, Nihon Kohden Digital Health Solutions LLC, Irvine, CA) was implemented in a randomized controlled trial that enrolled 10 422 patient visits in a 1:1 display-on display-off design. The CoMET scores were calculated for all patients but only displayed in the display-on arm. Only the control/display-off group is reported here because the scores could not alter care patterns.Main results.Of the 5184 visits in the display-off arm, 311 experienced clinical deterioration and care escalation, resulting in transfer to the intensive care unit, primarily due to respiratory distress. The model performance of CoMET was assessed based on areas under the receiver operating characteristic curve, which ranged from 0.725 to 0.737.Significance.The models were well-calibrated, and there were dynamic increases in the model scores in the hours preceding the clinical deterioration events. A hypothetical alerting strategy based on a rise in score and duration of the rise would have had good performance, with a positive predictive value more than 10-fold the event rate. We conclude that predictive statistical models developed five years before study initiation had good model performance despite the passage of time and the impact of the COVID-19 pandemic.

Beyond prediction: Off-target uses of artificial intelligence-based predictive analytics in a learning health system.

Introduction: Artificial-intelligence (AI)-based predictive analytics provide new opportunities to leverage rich sources of continuous data to improve patient care through early warning of the risk of clinical deterioration and improved situational awareness.Part of the success of predictive analytic implementation relies on integration of the analytic within complex clinical workflows. Pharmaceutical interventions have off-target uses where a drug indication has not been formally studied for a different indication but has potential for clinical benefit. An analog has not been described in the context of AI-based predictive analytics, that is, when a predictive analytic has been trained on one outcome of interest but is used for additional applications in clinical practice. Methods: In this manuscript we present three clinical vignettes describing off-target use of AI-based predictive analytics that evolved organically through real-world practice. Results: Off-target uses included:real-time feedback about treatment effectiveness, indication of readiness to discharge, and indication of the acuity of a hospital unit. Conclusion: Such practice fits well with the learning health system goals to continuously integrate data and experience to provide.

Signatures of illness in children requiring unplanned intubation in the pediatric intensive care unit: A retrospective cohort machine-learning study.

Acute respiratory failure requiring the initiation of invasive mechanical ventilation remains commonplace in the pediatric intensive care unit (PICU). Early recognition of patients at risk for respiratory failure may provide clinicians with the opportunity to intervene and potentially improve outcomes. Through the development of a random forest model to identify patients at risk for requiring unplanned intubation, we tested the hypothesis that subtle signatures of illness are present in physiological and biochemical time series of PICU patients in the early stages of respiratory decompensation. We included 116 unplanned intubation events as recorded in the National Emergency Airway Registry for Children in 92 PICU admissions over a 29-month period at our institution. We observed that children have a physiologic signature of illness preceding unplanned intubation in the PICU. Generally, it comprises younger age, and abnormalities in electrolyte, hematologic and vital sign parameters. Additionally, given the heterogeneity of the PICU patient population, we found differences in the presentation among the major patient groups - medical, cardiac surgical, and non-cardiac surgical. At four hours prior to the event, our random forest model demonstrated an area under the receiver operating characteristic curve of 0.766 (0.738 for medical, 0.755 for cardiac surgical, and 0.797 for non-cardiac surgical patients). The multivariable statistical models that captured the physiological and biochemical dynamics leading up to the event of urgent unplanned intubation in a PICU can be repurposed for bedside risk prediction.

Principles for Real-World Implementation of Bedside Predictive Analytics Monitoring.

A new development in the practice of medicine is Artificial Intelligence-based predictive analytics that forewarn clinicians of future deterioration of their patients. This proactive opportunity, though, is different from the reactive stance that clinicians traditionally take. Implementing these tools requires new ideas about how to educate clinician users to facilitate trust and adoption and to promote sustained use. Our real-world hospital experience implementing a predictive analytics monitoring system that uses electronic health record and continuous monitoring data has taught us principles that we believe to be applicable to the implementation of other such analytics systems within the health care environment. These principles are mentioned below:• To promote trust, the science must be understandable.• To enhance uptake, the workflow should not be impacted greatly.• To maximize buy-in, engagement at all levels is important.• To ensure relevance, the education must be tailored to the clinical role and hospital culture.• To lead to clinical action, the information must integrate into clinical care.• To promote sustainability, there should be periodic support interactions after formal implementation.

Predictive Monitoring-Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial.

BACKGROUND: Patients in acute care wards who deteriorate and are emergently transferred to intensive care units (ICUs) have poor outcomes. Early identification of patients who are decompensating might allow for earlier clinical intervention and reduced morbidity and mortality. Advances in bedside continuous predictive analytics monitoring (ie, artificial intelligence [AI]-based risk prediction) have made complex data easily available to health care providers and have provided early warning of potentially catastrophic clinical events. We present a dynamic, visual, predictive analytics monitoring tool that integrates real-time bedside telemetric physiologic data into robust clinical models to estimate and communicate risk of imminent events. This tool, Continuous Monitoring of Event Trajectories (CoMET), has been shown in retrospective observational studies to predict clinical decompensation on the acute care ward. There is a need to more definitively study this advanced predictive analytics or AI monitoring system in a prospective, randomized controlled, clinical trial. OBJECTIVE: The goal of this trial is to determine the impact of an AI-based visual risk analytic, CoMET, on improving patient outcomes related to clinical deterioration, response time to proactive clinical action, and costs to the health care system. METHODS: We propose a cluster randomized controlled trial to test the impact of using the CoMET display in an acute care cardiology and cardiothoracic surgery hospital floor. The number of admissions to a room undergoing cluster randomization was estimated to be 10,424 over the 20-month study period. Cluster randomization based on bed number will occur every 2 months. The intervention cluster will have the CoMET score displayed (along with standard of care), while the usual care group will receive standard of care only. RESULTS: The primary outcome will be hours free from events of clinical deterioration. Hours of acute clinical events are defined as time when one or more of the following occur: emergent ICU transfer, emergent surgery prior to ICU transfer, cardiac arrest prior to ICU transfer, emergent intubation, or death. The clinical trial began randomization in January 2021. CONCLUSIONS: Very few AI-based health analytics have been translated from algorithm to real-world use. This study will use robust, prospective, randomized controlled, clinical trial methodology to assess the effectiveness of an advanced AI predictive analytics monitoring system in incorporating real-time telemetric data for identifying clinical deterioration on acute care wards. This analysis will strengthen the ability of health care organizations to evolve as learning health systems, in which bioinformatics data are applied to improve patient outcomes by incorporating AI into knowledge tools that are successfully integrated into clinical practice by health care providers. TRIAL REGISTRATION: ClinicalTrials.gov NCT04359641; https://clinicaltrials.gov/ct2/show/NCT04359641. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/29631.

Nursing and precision predictive analytics monitoring in the acute and intensive care setting: An emerging role for responding to COVID-19 and beyond.

As the global response to COVID-19 continues, nurses will be tasked with appropriately triaging patients, responding to events of clinical deterioration, and developing family-centered plans of care within a healthcare system exceeding capacity. Predictive analytics monitoring, an artificial intelligence (AI)-based tool that translates streaming clinical data into a real-time visual estimation of patient risks, allows for evolving acuity assessments and detection of clinical deterioration while the patient is in pre-symptomatic states. While nurses are on the frontline for the COVID-19 pandemic, the use of AI-based predictive analytics monitoring may help cognitively complex clinical decision-making tasks and pave a pathway for early detection of patients at risk for decompensation. We must develop strategies and techniques to study the impact of AI-based technologies on patient care outcomes and the clinical workflow. This paper outlines key concepts for the intersection of nursing and precision predictive analytics monitoring.

Major complications and mortality within 30 days of an electrophysiological procedure at an academic medical center: implications for developing national standards.

BACKGROUND: Despite growing attention to performance and quality measures, national standards for reporting of outcomes after all electrophysiology (EP) procedures have not yet been developed. We sought to characterize the incidence and timing of adverse events up to 30 days after EP procedures at a tertiary academic medical center. METHODS AND RESULTS: We prospectively followed all patients undergoing EP procedures between January 2010 and September 2012. All were followed for 30 days postprocedure either in clinic or by telephone. Major complications were defined as events related to the procedure that led to prolongation of hospital stay or readmission, required additional procedural intervention, or resulted in death or significant injury. These were further categorized as intraprocedure, postprocedure, or postdischarge events. Seven EP physicians collectively adjudicated whether complications were directly related to the procedure. A total of 3,213 procedures were performed. Major complications occurred in 2.2% of patients; 49% of these events occurred after discharge. Death occurred in 0.6% of patients; 73% of these deaths were found to be secondary to worsening of the patient's underlying comorbid conditions and unrelated to the procedure. CONCLUSIONS: When considering national standards for reporting outcomes of all EP procedures, continued follow-up after discharge is important. In our cohort, half of major complications occurring within 30 days occurred after discharge. In addition, three-quarters of deaths within 30 days were not directly related to the procedure and caution should be used in using all-cause mortality as an outcome measure for EP procedures.

Cost of a recall of a single-center experience managing the Riata defibrillator lead.

Riata and Riata ST defibrillator leads (St. Jude Medical, Sylmar, California) were recalled in 2011 due to increased risk of insulation failure leading to externalized cables. Fluoroscopic screening can identify insulation failure, although the relation between mechanical failure and electrical failure is unclear. At the time of the recall, the University of Virginia developed a screening program, including fluoroscopic evaluation, education sessions, device interrogation, and remote monitoring for patients with this defibrillator lead. The aim of this study was to review the outcomes of the screening program, including costs, which were absorbed by our institution. Costs were calculated using Medicare reimbursement estimates. Forty-eight patients participated in the screening program. At initial screening, 31% were found to have evidence of insulation failure but electrical function was normal in all leads. The cost of this program was $35,358.72. The cost per diagnosis of mechanical lead failure was $2,357.25. During 2 years of follow-up, 1 patient experienced Riata lead electrical failure without fluoroscopic evidence of insulation failure. Patients were more likely to have a lead revision if there was evidence of insulation failure. Lead revisions occurred at the time of generator change in 88% of patients with insulation failure but in only 14% of patients with a fluoroscopically normal lead (p = 0.04). The cost of recall-related defibrillator lead revisions was $81,704.55. In conclusion, our Riata screening program added expense without clear benefit to patients. In fact, patients may have been put at more risk by undergoing defibrillator lead revisions based solely on the results of the fluoroscopic screening.

Increasing lead burden correlates with externalized cables during systematic fluoroscopic screening of Riata leads.

PURPOSE: Riata and Riata ST defibrillator leads (St. Jude Medical, Sylmar, CA, USA) have been recalled due to increased risk of insulation failure leading to externalized cables. As this mechanical failure does not necessarily correlate with electrical failure, it can be difficult to diagnose. Fluoroscopic screening can identify insulation failure. Studies have suggested that insulation failure is predominantly seen in 8-Fr, single-coil models. Our patients have exclusively dual-coil leads and a high proportion of 7-Fr leads. METHODS: Fluoroscopic screening was performed in 48 patients with recalled Riata leads. Twenty-three patients had 8-Fr Riata leads and 25 patients had 7-Fr Riata ST leads. Images were recorded in at least three projections and studies were reviewed by seven attending electrophysiologists. RESULTS: Externalized cables were seen in ten patients (21 %), and another five patients (10 %) had abnormal cable spacing. All device interrogations showed normal parameters. Patients with abnormal leads had more leads in situ (2.5 ± 0.7 vs. 1.6 ± 0.8 leads; P = 0.002) and a higher rate of nonischemic cardiomyopathy (80 vs. 24 %; P = 0.03). There were no differences between the groups with regards to patient age, body mass index, lead age, lead parameters, or vascular access site. There was no difference with regard to lead size (P = 0.76). CONCLUSIONS: The Riata family of leads has a high incidence of mechanical failure, as demonstrated on fluoroscopic screening. In this study, the 7-Fr models were just as likely to mechanically fail as the 8-Fr models. Increasing lead burden and a diagnosis of nonischemic cardiomyopathy correlated with insulation failure.

Impact of the CHA2DS2-VASc score on anticoagulation recommendations for atrial fibrillation.

BACKGROUND: The Congestive heart failure, Hypertension, Age ≥ 75 years, Diabetes mellitus, Stroke (CHADS(2)) score is used to predict the need for oral anticoagulation for stroke prophylaxis in patients with atrial fibrillation. The Congestive heart failure, Hypertension, Age ≥ 75 years, Diabetes mellitus, Stroke, Vascular disease, Age 65-74 years, Sex category (CHA(2)DS(2)-VASc) schema has been proposed as an improvement. Our objective is to determine how adoption of the CHA(2)DS(2)-VASc score alters anticoagulation recommendations. METHODS: Between 2004 and 2008, 1664 patients were seen at the University of Virginia Atrial Fibrillation Center. We calculated the CHADS(2) and CHA(2)DS(2)-VASc scores for each patient. The 2006 American College of Cardiology/American Heart Association/Heart Rhythm Society guidelines for atrial fibrillation management were used to determine anticoagulation recommendations based on the CHADS(2) score, and the 2010 European Society of Cardiology guidelines were used to determine anticoagulation recommendations based on the CHA(2)DS(2)-VASc score. RESULTS: The average age was 62±13 years, and 34% were women. Average CHADS(2) and CHA(2)DS(2)-VASc scores were 1.1±1.1 and 1.8±1.5, respectively (P<.0001). The CHADS(2) score classified 33% as requiring oral anticoagulation. The CHA(2)DS(2)-VASc score classified 53% as requiring oral anticoagulation. For women, 31% had a CHADS(2) score ≥ 2, but 81% had a CHA(2)DS(2)-VASc score ≥ 2 (P = .0001). Also, 32% of women with a CHADS(2) score of zero had a CHA(2)DS(2)-VASc score ≥ 2. For men, 25% had a CHADS(2) score ≥ 2, but 39% had a CHA(2)DS(2)-VASc score ≥ 2 (P<.0001). CONCLUSION: Compared with the CHADS(2) score, the CHA(2)DS(2)-VASc score more clearly defines anticoagulation recommendations. Many patients, particularly older women, are redistributed from the low- to high-risk categories.

Gender and Racial Characteristics of Patients Referred to a Tertiary Atrial Fibrillation Center.

Atrial Fibrillation Centers (AFCs) are becoming increasingly common and are often developed at institutions to provide comprehensive evaluation and management for patients with atrial fibrillation (AF) including catheter and surgical ablation. Studies have shown that women and racial minority patients are less likely to be offered aggressive or invasive therapies. The University of Virginia (UVA) AFC was opened in 2004. We analyzed data collected during initial visits to our AFC from 2004-2008 to determine the gender and racial characteristics of a tertiary AFC population. Multivariable regression analysis was used to compare clinical characteristics. There were a total of 1664 consecutive initial patient visits. Cardiologists referred 61% and primary care physicians referred 37% of patients. Twice as many men were referred as women (570 vs. 1094; P<0.0001). Women were older (68.0±11.9 vs. 62.4±13.0 years; P<0.0001) and more symptomatic with palpitations (80% vs. 73%; P=0.008), but otherwise were not substantially different from men. Our referring physicians treated the majority of both men and women with anticoagulant and rate-controlling medications. African American patients accounted for 2.8% of AFC initial visits. In contrast, they accounted for 7.4% of patients seen for a primary diagnosis of AF at all other UVA outpatient clinics (P<0.0001). In conclusion, the demographics of a tertiary AFC are different than those of the general population. Women and racial minority patients are underrepresented, and the women have few comorbidities and symptoms than the known epidemiology would lead us to expect.