Continuous ECG monitoring should be the heart of bedside AI-based predictive analytics monitoring for early detection of clinical deterioration.

The idea that we can detect subacute potentially catastrophic illness earlier by using statistical models trained on clinical data is now well-established. We review evidence that supports the role of continuous cardiorespiratory monitoring in these predictive analytics monitoring tools. In particular, we review how continuous ECG monitoring reflects the patient and not the clinician, is less likely to be biased, is unaffected by changes in practice patterns, captures signatures of illnesses that are interpretable by clinicians, and is an underappreciated and underutilized source of detailed information for new mathematical methods to reveal.

Evaluation of a novel mechanical compression device for hematoma prevention and wound cosmesis after CIED implantation.

BACKGROUND: An important complication of cardiac implantable electronic devices (CIED) implantation is the development of hematoma and device infection. OBJECTIVE: We aimed to evaluate a novel mechanical compression device for hematoma prevention and cosmetic outcomes following CIED implantation. METHODS: An open, prospective, randomized, single-center clinical trial was performed in patients undergoing CIED implantation. Patients were randomized to receive a novel mechanical compression device (PressRite, PR) or to receive the standard of care post device implantation. Skin pliability was measured with a calibrated durometer; the surgical site was evaluated using the Manchester Scar Scale (MSS) by a blinded plastic surgeon and the Patient and Observer Scar Scale (POSAS). Performance of PR was assessed through pressure measurements, standardized scar scales and tolerability. RESULTS: From the total of 114 patients evaluated for enrollment, 105 patients were eligible for analysis. Fifty-one patients were randomized to management group (PR) and 54 to the control group. No patients required early removal or experienced adverse effects from PR application. There were 11 hematomas (14.8% vs. 5.9% in the control and PR group respectively, p = NS). The control group had higher post procedure durometer readings in the surgical site when compared with the PR group (7.50 ± 3.45 vs. 5.37 ± 2.78; p = < .01). There were lower MSS scores in the PR group after 2 weeks (p = .03). CONCLUSION: We have demonstrated the safety of PR application and removal. In addition, PR appears to improve postoperative skin pliability, which could facilitate wound healing.

Targeting miR-423-5p Reverses Exercise Training-Induced HCN4 Channel Remodeling and Sinus Bradycardia.

RATIONALE: Downregulation of the pacemaking ion channel, HCN4 (hyperpolarization-activated cyclic nucleotide gated channel 4), and the corresponding ionic current, If, underlies exercise training-induced sinus bradycardia in rodents. If this occurs in humans, it could explain the increased incidence of bradyarrhythmias in veteran athletes, and it will be important to understand the underlying processes. OBJECTIVE: To test the role of HCN4 in the training-induced bradycardia in human athletes and investigate the role of microRNAs (miRs) in the repression of HCN4. METHODS AND RESULTS: As in rodents, the intrinsic heart rate was significantly lower in human athletes than in nonathletes, and in all subjects, the rate-lowering effect of the HCN selective blocker, ivabradine, was significantly correlated with the intrinsic heart rate, consistent with HCN repression in athletes. Next-generation sequencing and quantitative real-time reverse transcription polymerase chain reaction showed remodeling of miRs in the sinus node of swim-trained mice. Computational predictions highlighted a prominent role for miR-423-5p. Interaction between miR-423-5p and HCN4 was confirmed by a dose-dependent reduction in HCN4 3'-untranslated region luciferase reporter activity on cotransfection with precursor miR-423-5p (abolished by mutation of predicted recognition elements). Knockdown of miR-423-5p with anti-miR-423-5p reversed training-induced bradycardia via rescue of HCN4 and If. Further experiments showed that in the sinus node of swim-trained mice, upregulation of miR-423-5p (intronic miR) and its host gene, NSRP1, is driven by an upregulation of the transcription factor Nkx2.5. CONCLUSIONS: HCN remodeling likely occurs in human athletes, as well as in rodent models. miR-423-5p contributes to training-induced bradycardia by targeting HCN4. This work presents the first evidence of miR control of HCN4 and heart rate. miR-423-5p could be a therapeutic target for pathological sinus node dysfunction in veteran athletes.

Electrophysiological heterogeneity of pacemaker cells in the rabbit intercaval region, including the SA node: insights from recording multiple ion currents in each cell.

Cardiac pacemaker cells, including cells of the sinoatrial node, are heterogeneous in size, morphology, and electrophysiological characteristics. The exact extent to which these cells differ electrophysiologically is unclear yet is critical to understanding their functioning. We examined major ionic currents in individual intercaval pacemaker cells (IPCs) sampled from the paracristal, intercaval region (including the sinoatrial node) that were spontaneously beating after enzymatic isolation from rabbit hearts. The beating rate was measured at baseline and after inhibition of the Ca2+ pump with cyclopiazonic acid. Thereafter, in each cell, we consecutively measured the density of funny current ( If), delayed rectifier K+ current ( IK) (a surrogate of repolarization capacity), and L-type Ca2+ current ( ICa,L) using whole cell patch clamp. The ionic current densities varied to a greater extent than previously appreciated, with some IPCs demonstrating very small or zero If . The density of none of the currents was correlated with cell size, while ICa,L and If densities were related to baseline beating rates. If density was correlated with IK density but not with that of ICa,L. Inhibition of Ca2+ cycling had a greater beating rate slowing effect in IPCs with lower If densities. Our numerical model simulation indicated that 1) IPCs with small (or zero) If or small ICa,L can operate via a major contribution of Ca2+ clock, 2) If-Ca2+-clock interplay could be important for robust pacemaking function, and 3) coupled If- IK function could regulate maximum diastolic potential. Thus, we have demonstrated marked electrophysiological heterogeneity of IPCs. This heterogeneity is manifested in basal beating rate and response to interference of Ca2+ cycling, which is linked to If. NEW & NOTEWORTHY In the present study, a hitherto unrecognized range of heterogeneity of ion currents in pacemaker cells from the intercaval region is demonstrated. Relationships between basal beating rate and L-type Ca2+ current and funny current ( If) density are uncovered, along with a positive relationship between If and delayed rectifier K+ current. Links are shown between the response to Ca2+ cycling blockade and If density.

Arrhythmic outcome of arrhythmogenic right ventricular cardiomyopathy patients without implantable defibrillators.

BACKGROUND: Implantable defibrillators (ICD) are an important therapy for arrhythmogenic right ventricular cardiomyopathy (ARVC) patients at high risk of sudden death. Given the high appropriate ICD therapy rate, some have argued that the mere act of implanting an ICD inflates the malignant arrhythmia rate in ARVC. OBJECTIVE: To report the arrhythmic course of ARVC patients without ICDs at the fulfillment of the 2010 Task Force Criteria and explore predictors of malignant ventricular arrhythmias. METHODS: We included 131 definite ARVC patients (age 32 ± 15 years, male 39%, proband 50%) either without ICDs (N  =  47) or receiving an ICD at least 6 months after the fulfillment of the diagnostic criteria. The primary outcome was a composite of cardiac arrest (both resuscitated successfully and unsuccessfully) and sustained ventricular tachyarrhythmias (cycle length< 600 milliseconds, at least 30 seconds or requiring an intervention for termination). RESULTS: At the fulfillment of the diagnostic criteria, ICDs were not recommended to 59 (45%) patients and declined by 22 (17%) patients. Forty (31%) patients were not recognized as having ARVC by the treating physicians. Over 8 (interquartile interval: 3-12) years, 38 (29%) patients had primary outcomes (8 cardiac arrests [3 died] and 30 sustained ventricular arrhythmias) while not having ICDs. The 1-year and 5-year event-free survival was 92% and 72%. Spontaneous sustained ventricular arrhythmias, cardiac syncope, men, proband, and inducibility in electrophysiology study were significantly associated with the primary outcome. CONCLUSION: In a contemporary cohort, a considerable risk of malignant arrhythmias existed in ARVC when ICDs were not implanted.

Modern concepts concerning the origin of the heartbeat.

Physiological processes governing the heart beat have been under investigation for several hundred years. Major advances have been made in the recent past. A review of the present paradigm is presented here, including a look back at important steps that led us to where we are today, alongside a glimpse into the exciting future of pacemaker research.

Exercise, Sports Participation, and Quality of Life in Young Patients with Heritable Thoracic Aortic Disease.

INTRODUCTION: Patients with heritable thoracic aortic disease (HTAD)are often restricted from sports and certain types of exercise. This study was designed to investigate the effect of lifetime exercise exposure and competitive sports participation on quality of life (QOL) in patients aged 15-35 with syndromic [Marfan syndrome (MFS), Loeys-Dietz syndrome (LDS), vascular Ehlers-Danlos syndrome (vEDS)] and non-syndromic heritable thoracic aortic disease (nsHTAD). METHODS: This cross-sectional study employed questionnaires to assess lifetime exercise exposure and utilized the PedsQL QOL Inventory. We developed an Exercise Exposure Score (EES) to quantify lifetime exercise exposure. Questionnaires were completed via telephone with complimentary medical record review. RESULTS: Forty patients were enrolled. Mean age was 26 years. The diagnosis was MFS in 83%. Despite 88% of patients being restricted by their provider, 65% reported competitive sports participation and 93% reported recreational exercise. Participants with an EES greater than the median had significantly better total QOL scores compared to those below the median (78 vs 65, p = 0.03). There were significant positive correlations between current frequency of exercise and psychosocial QOL (slope = 3.9, 95% CI: (1.2, 6.6), p = 0.005), physical QOL (slope = 8.1, 95% CI: (4.1, 12), p < 0.001), and total QOL score (slope = 6.0, 95% CI: (3.1, 9.0), p < 0.001). We found no difference in aortic size or need for surgical intervention between those above and below the median EES, or between those who did and did not participate in competitive sports. CONCLUSIONS: Despite exercise restrictions, young HTAD patients are physically active. Increased lifetime exercise and current physical activity levels were associated with improved QOL in HTAD patients.

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.

A novel predictive analytics score reflecting accumulating disease burden-an investigation of the cumulative CoMET score.

OBJECTIVE: Predictive analytics tools variably take into account data from the electronic medical record, lab tests, nursing charted vital signs and continuous cardiorespiratory monitoring to deliver an instantaneous prediction of patient risk or instability. Few, if any, of these tools reflect the risk to a patient accumulated over the course of an entire hospital stay. APPROACH: We have expanded on our instantaneous CoMET predictive analytics score to generate the cumulative CoMET score (cCoMET), which sums all of the instantaneous CoMET scores throughout a hospital admission relative to a baseline expected risk unique to that patient. MAIN RESULTS: We have shown that higher cCoMET scores predict mortality, but not length of stay, and that higher baseline CoMET scores predict higher cCoMET scores at discharge/death. cCoMET scores were higher in males in our cohort, and added information to the final CoMET when it came to the prediction of death. SIGNIFICANCE: We have shown that the inclusion of all repeated measures of risk estimation performed throughout a patients hospital stay adds information to instantaneous predictive analytics, and could improve the ability of clinicians to predict deterioration, and improve patient outcomes in so doing.

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.

Noninvasive Electrical Mapping Compared with the Paced QRS Complex for Optimizing CRT Programmed Settings and Predicting Multidimensional Response.

The aim was to test the hypothesis that left ventricular (LV) and right ventricular (RV) activation from body surface electrical mapping (CardioInsight 252-electrode vest, Medtronic) identifies optimal cardiac resynchronization therapy (CRT) pacing strategies and outcomes in 30 patients. The LV80, RV80, and BIV80 were defined as the times to 80% LV, RV, or biventricular electrical activation. Smaller differences in the LV80 and RV80 (|LV80-RV80|) with synchronized LV pacing predicted better LV function post-CRT (p = 0.0004) than the LV-paced QRS duration (p = 0.32). Likewise, a lower RV80 was associated with a better pre-CRT RV ejection fraction by CMR (r = - 0.40, p = 0.04) and predicted post-CRT improvements in myocardial oxygen uptake (p = 0.01) better than the biventricular-paced QRS (p = 0.38), while a lower LV80 with BIV pacing predicted lower post-CRT B-type natriuretic peptide (BNP) (p = 0.02). RV pacing improved LV function with smaller |LV80-RV80| (p = 0.009). In conclusion, 3-D electrical mapping predicted favorable post-CRT outcomes and informed effective pacing strategies.

First-in-human noninvasive left ventricular ultrasound pacing: A potential screening tool for cardiac resynchronization therapy.

Background: A screening tool to predict response to cardiac resynchronization therapy (CRT) could improve patient selection and outcomes. Objective: The purpose of this study was to investigate the feasibility and safety of noninvasive CRT via transcutaneous ultrasonic left ventricular (LV) pacing applied as a screening test before CRT implants. Methods: P-wave-triggered ultrasound stimuli were delivered during bolus dosing of an echocardiographic contrast agent to simulate CRT noninvasively. Ultrasound pacing was delivered at a variety of LV locations with a range of atrioventricular delays to achieve fusion with intrinsic ventricular activation. Three-dimensional cardiac activation maps were acquired via the Medtronic CardioInsight 252-electrode mapping vest during baseline, ultrasound pacing, and after CRT implantation. A separate control group received only the CRT implants. Results: Ultrasound pacing was achieved in 10 patients with a mean of 81.2 ± 50.8 ultrasound paced beats per patient and up to 20 consecutive beats of ultrasound pacing. QRS width at baseline (168.2 ± 17.8 ms) decreased significantly to 117.3 ± 21.5 ms (P <.001) in the best ultrasound paced beat and to 125.8 ± 13.3 ms (P <.001) in the best CRT beat. Electrical activation patterns were similar between CRT pacing and ultrasound pacing with stimulation from the same area of the LV. Troponin results were similar between the ultrasound pacing and the control groups (P = .96), confirming safety. Conclusion: Noninvasive ultrasound pacing before CRT is safe and feasible, and it estimates the degree of electrical resynchronization achievable with CRT. Further study of this promising technique to guide CRT patient selection is warranted.

Cardiac Magnetic Resonance, Electromechanical Activation, Kidney Function, and Natriuretic Peptides in Cardiac Resynchronization Therapy Upgrades.

As the mechanism for worse prognosis after cardiac resynchronization therapy (CRT) upgrades in heart failure patients with RVP dependence (RVP-HF) has clinical implications for patient selection and CRT implementation approaches, this study's objective was to evaluate prognostic implications of cardiac magnetic resonance (CMR) findings and clinical factors in 102 HF patients (23.5% female, median age 66.5 years old, median follow-up 4.8 years) with and without RVP dependence undergoing upgrade and de novo CRT implants. Compared with other CRT groups, RVP-HF patients had decreased survival (p = 0.02), more anterior late-activated LV pacing sites (p = 0.002) by CMR, more atrial fibrillation (p = 0.0006), and higher creatinine (0.002). CMR activation timing at the LV pacing site predicted post-CRT LV functional improvement (p < 0.05), and mechanical activation onset < 34 ms by CMR at the LVP site was associated with decreased post-CRT survival in a model with higher pre-CRT creatinine and B-type natriuretic peptide (AUC 0.89; p < 0.0001); however, only the higher pre-CRT creatinine partially mediated (37%) the decreased survival in RVP-HF patients. In conclusion, RVP-HF had a distinct CMR phenotype, which has important implications for the selection of LV pacing sites in CRT upgrades, and only chronic kidney disease mediated the decreased survival after CRT in RVP-HF.

Exercise in the Genetic Arrhythmia Syndromes - A Review.

Provide a brief summary of your article (100-150 words; no references or figures/tables). The synopsis appears only in the table of contents and is often used by indexing services such as PubMed. Genetic arrhythmia syndromes are rare, yet harbor the potential for highly consequential, often unpredictable arrhythmias or sudden death events. There has been historical uncertainty regarding the correct advice to offer to affected patients who are reasonably wanting to participate in sporting and athletic endeavors. In some cases, this had led to abundantly cautious disqualifications, depriving individuals from participation unnecessarily. Societal guidance and expert opinion has evolved significantly over the last decade or 2, along with our understanding of the genetics and natural history of these conditions, and the emphasis has switched toward shared decision making with respect to the decision to participate or not, with patients and families becoming better informed, and willing participants in the decision making process. This review aims to give a brief update of the salient issues for the busy physician concerning these syndromes and to provide a framework for approaching their management in the otherwise aspirational or keen sports participant.

Machine learning for multidimensional response and survival after cardiac resynchronization therapy using features from cardiac magnetic resonance.

Background: Cardiac resynchronization therapy (CRT) response is complex, and better approaches are required to predict survival and need for advanced therapies. Objective: The objective was to use machine learning to characterize multidimensional CRT response and its relationship with long-term survival. Methods: Associations of 39 baseline features (including cardiac magnetic resonance [CMR] findings and clinical parameters such as glomerular filtration rate [GFR]) with a multidimensional CRT response vector (consisting of post-CRT left ventricular end-systolic volume index [LVESVI] fractional change, post-CRT B-type natriuretic peptide, and change in peak VO2) were evaluated. Machine learning generated response clusters, and cross-validation assessed associations of clusters with 4-year survival. Results: Among 200 patients (median age 67.4 years, 27.0% women) with CRT and CMR, associations with more than 1 response parameter were noted for the CMR CURE-SVD dyssynchrony parameter (associated with post-CRT brain natriuretic peptide [BNP] and LVESVI fractional change) and GFR (associated with peak VO2 and post-CRT BNP). Machine learning defined 3 response clusters: cluster 1 (n = 123, 90.2% survival [best]), cluster 2 (n = 45, 60.0% survival [intermediate]), and cluster 3 (n = 32, 34.4% survival [worst]). Adding the 6-month response cluster to baseline features improved the area under the receiver operating characteristic curve for 4-year survival from 0.78 to 0.86 (P = .02). A web-based application was developed for cluster determination in future patients. Conclusion: Machine learning characterizes distinct CRT response clusters influenced by CMR features, kidney function, and other factors. These clusters have a strong and additive influence on long-term survival relative to baseline features.

Cardiac magnetic resonance defines mechanisms of sex-based differences in outcomes following cardiac resynchronization therapy.

Background: Mechanisms of sex-based differences in outcomes following cardiac resynchronization therapy (CRT) are poorly understood. Objective: To use cardiac magnetic resonance (CMR) to define mechanisms of sex-based differences in outcomes after CRT and describe distinct CMR-based phenotypes of CRT candidates based on sex and non-ischemic/ischemic cardiomyopathy type. Materials and methods: In a prospective study, sex-based differences in three short-term CRT response measures [fractional change in left ventricular end-systolic volume index 6 months after CRT (LVESVI-FC), B-type natriuretic peptide (BNP) 6 months after CRT, change in peak VO2 6 months after CRT], and long-term survival were evaluated with respect to 39 baseline parameters from CMR, exercise testing, laboratory testing, electrocardiograms, comorbid conditions, and other sources. CMR was also used to quantify the degree of left-ventricular mechanical dyssynchrony by deriving the circumferential uniformity ratio estimate (CURE-SVD) parameter from displacement encoding with stimulated echoes (DENSE) strain imaging. Statistical methods included multivariable linear regression with evaluation of interaction effects associated with sex and cardiomyopathy type (ischemic and non-ischemic cardiomyopathy) and survival analysis. Results: Among 200 patients, the 54 female patients (27%) pre-CRT had a smaller CMR-based LVEDVI (p = 0.04), more mechanical dyssynchrony based on the validated CMR CURE-SVD parameter (p = 0.04), a lower frequency of both late gadolinium enhancement (LGE) and ischemic cardiomyopathy (p < 0.0001), a greater RVEF (p = 0.02), and a greater frequency of LBBB (p = 0.01). After categorization of patients into four groups based on cardiomyopathy type (ischemic/non-ischemic cardiomyopathy) and sex, female patients with non-ischemic cardiomyopathy had the lowest CURE-SVD (p = 0.003), the lowest pre-CRT BNP levels (p = 0.01), the lowest post-CRT BNP levels (p = 0.05), and the most favorable LVESVI-FC (p = 0.001). Overall, female patients had better 3-year survival before adjustment for cardiomyopathy type (p = 0.007, HR = 0.45) and after adjustment for cardiomyopathy type (p = 0.009, HR = 0.67). Conclusion: CMR identifies distinct phenotypes of female CRT patients with non-ischemic and ischemic cardiomyopathy relative to male patients stratified by cardiomyopathy type. The more favorable short-term response and long-term survival outcomes in female heart failure patients with CRT were associated with lower indexed CMR-based LV volumes, decreased presence of scar associated with prior myocardial infarction and ICM, and greater CMR-based dyssynchrony with the CURE-SVD.

Changes in the expression of ion channels, connexins and Ca2+-handling proteins in the sino-atrial node during postnatal development.

There are important postnatal changes in the sino-atrial node (SAN), the pacemaker of the heart. Compared with the neonate, the adult has a slower intrinsic heart rate and a longer SAN action potential. These changes may be due to differences in ion channel expression. Consequently, we investigated postnatal developmental changes in the expression of ion channels and Ca(2+)-handling proteins in the SAN to see whether this is indeed the case. Using quantitative PCR, in situ hybridization and immunohistochemistry, we investigated the expression of ion channels, Ca(2+)-handling proteins and connexins in the SAN from neonatal (2-7 days of age) and adult (∼6 months of age) New Zealand White rabbits. The spontaneous beating rate of adult SAN preparations was 21% slower than that of neonatal preparations. During postnatal development, quantitative PCR revealed a significant decline in the SAN of the following mRNAs: HCN4 (major isoform responsible for I(f)), Na(V)1.5 (responsible for I(Na)), Ca(V)1.3 (in part responsible for I(Ca,L)) and NCX1 (responsible for inward I(NaCa)). These declines could be responsible for the slowing of the pacemaker during postnatal development. There was a significant decline during development in mRNA for delayed rectifier K(+) channel subunits (K(V)1.5, responsible for I(K,ur), K(V)LQT1 and minK, responsible for I(K,s), and ERG, responsible for I(K,r)) and this could explain the prolongation of the action potential. In situ hybridization confirmed the changes observed by quantitative PCR. In addition, immunohistochemistry revealed hypertrophy of nodal cells during postnatal development. Moreover, there were complex changes in the expression of Ca(2+)-handling proteins with age. In summary, there are significant postnatal changes in the expression of ion channels and Ca(2+)-handling proteins in the SAN that could explain the established changes in heart rate and action potential duration that occur during normal development.

Continuous cardiorespiratory monitoring is a dominant source of predictive signal in machine learning for risk stratification and clinical decision support.

Beaulieu-Jones and coworkers propose a litmus test for the field of predictive analytics-performance improvements must be demonstrated to be the result of non-clinician-initiated data, otherwise, there should be caution in assuming that predictive models could improve clinical decision-making (Beaulieu-Joneset al2021). They demonstrate substantial prognostic information in unsorted physician orders made before the first midnight of hospital admission, and we are persuaded that it is fair to ask-if the physician thought of it first, what exactly is machine learning for in-patient risk stratification learning about? While we want predictive analytics to represent the leading indicators of a patient's illness, does it instead merely reflect the lagging indicators of clinicians' actions? We propose that continuous cardiorespiratory monitoring-'routine telemetry data,' in Beaulieu-Jones' terms-represents the most valuable non-clinician-initiated predictive signal present in patient data, and the value added to patient care justifies the efforts and expense required. Here, we present a clinical and a physiological point of view to support our contention.