Artificial intelligence predictive analytics in heart failure: results of the pilot phase of a pragmatic randomized clinical trial.

OBJECTIVES: We conducted an implementation planning process during the pilot phase of a pragmatic trial, which tests an intervention guided by artificial intelligence (AI) analytics sourced from noninvasive monitoring data in heart failure patients (LINK-HF2). MATERIALS AND METHODS: A mixed-method analysis was conducted at 2 pilot sites. Interviews were conducted with 12 of 27 enrolled patients and with 13 participating clinicians. iPARIHS constructs were used for interview construction to identify workflow, communication patterns, and clinician's beliefs. Interviews were transcribed and analyzed using inductive coding protocols to identify key themes. Behavioral response data from the AI-generated notifications were collected. RESULTS: Clinicians responded to notifications within 24 hours in 95% of instances, with 26.7% resulting in clinical action. Four implementation themes emerged: (1) High anticipatory expectations for reliable patient communications, reduced patient burden, and less proactive provider monitoring. (2) The AI notifications required a differential and tailored balance of trust and action advice related to role. (3) Clinic experience with other home-based programs influenced utilization. (4) Responding to notifications involved significant effort, including electronic health record (EHR) review, patient contact, and consultation with other clinicians. DISCUSSION: Clinician's use of AI data is a function of beliefs regarding the trustworthiness and usefulness of the data, the degree of autonomy in professional roles, and the cognitive effort involved. CONCLUSION: The implementation planning analysis guided development of strategies that addressed communication technology, patient education, and EHR integration to reduce clinician and patient burden in the subsequent main randomized phase of the trial. Our results provide important insights into the unique implications of implementing AI analytics into clinical workflow.

Longitudinal changes in cardiac function in Duchenne muscular dystrophy population as measured by magnetic resonance imaging.

BACKGROUND: The lack of dystrophin in cardiomyocytes in Duchenne muscular dystrophy (DMD) is associated with progressive decline in cardiac function eventually leading to death by 20-40 years of age. The aim of this prospective study was to determine rate of progressive decline in left ventricular (LV) function in Duchenne muscular dystrophy (DMD) over 5 years. METHODS: Short axis cine and grid tagged images of the LV were acquired in individuals with DMD (n = 59; age = 5.3-18.0 years) yearly, and healthy controls at baseline (n = 16, age = 6.0-18.3 years) on a 3 T MRI scanner. Grid-tagged images were analyzed for composite circumferential strain (ℇcc%) and ℇcc% in six mid LV segments. Cine images were analyzed for left ventricular ejection fraction (LVEF), LV mass (LVM), end-diastolic volume (EDV), end-systolic volume (ESV), LV atrioventricular plane displacement (LVAPD), and circumferential uniformity ratio estimate (CURE). LVM, EDV, and ESV were normalized to body surface area for a normalized index of LVM (LVMI), EDV (EDVI) and ESV (ESVI). RESULTS: At baseline, LV ℇcc% was significantly worse in DMD compared to controls and five of the six mid LV segments demonstrated abnormal strain in DMD. Longitudinal measurements revealed that ℇcc% consistently declined in individuals with DMD with the inferior segments being more affected. LVEF progressively declined between 3 to 5 years post baseline visit. In a multivariate analysis, the use of cardioprotective drugs trended towards positively impacting cardiac measures while loss of ambulation and baseline age were associated with negative impact. Eight out of 17 cardiac parameters reached a minimal clinically important difference with a threshold of 1/3 standard deviation. CONCLUSION: The study shows a worsening of circumferential strain in dystrophic myocardium. The findings emphasize the significance of early and longitudinal assessment of cardiac function in DMD and identify early biomarkers of cardiac dysfunction to help design clinical trials to mitigate cardiac pathology. This study provides valuable non-invasive and non-contrast based natural history data of cardiac changes which can be used to design clinical trials or interpret the results of current trials aimed at mitigating the effects of decreased cardiac function in DMD.

Continuous Wearable Monitoring Analytics Predict Heart Failure Hospitalization: The LINK-HF Multicenter Study.

BACKGROUND: Implantable cardiac sensors have shown promise in reducing rehospitalization for heart failure (HF), but the efficacy of noninvasive approaches has not been determined. The objective of this study was to determine the accuracy of noninvasive remote monitoring in predicting HF rehospitalization. METHODS: The LINK-HF study (Multisensor Non-invasive Remote Monitoring for Prediction of Heart Failure Exacerbation) examined the performance of a personalized analytical platform using continuous data streams to predict rehospitalization after HF admission. Study subjects were monitored for up to 3 months using a disposable multisensor patch placed on the chest that recorded physiological data. Data were uploaded continuously via smartphone to a cloud analytics platform. Machine learning was used to design a prognostic algorithm to detect HF exacerbation. Clinical events were formally adjudicated. RESULTS: One hundred subjects aged 68.4±10.2 years (98% male) were enrolled. After discharge, the analytical platform derived a personalized baseline model of expected physiological values. Differences between baseline model estimated vital signs and actual monitored values were used to trigger a clinical alert. There were 35 unplanned nontrauma hospitalization events, including 24 worsening HF events. The platform was able to detect precursors of hospitalization for HF exacerbation with 76% to 88% sensitivity and 85% specificity. Median time between initial alert and readmission was 6.5 (4.2-13.7) days. CONCLUSIONS: Multivariate physiological telemetry from a wearable sensor can provide accurate early detection of impending rehospitalization with a predictive accuracy comparable to implanted devices. The clinical efficacy and generalizability of this low-cost noninvasive approach to rehospitalization mitigation should be further tested. Registration: URL: https://www.clinicaltrials.gov. Unique Identifier: NCT03037710.

Electronic consults for improving specialty care access for veterans.

OBJECTIVES: We adopted e-consults within an active referral management (ARM) process for our Veterans Health Administration (VHA) outpatient cardiology clinic to reduce clinic wait times. STUDY DESIGN: Prospective multiphase cohort study. METHODS: Our ARM process consisted of reviewing all incoming consult requests for our outpatient clinic and triaging the requests to either an e-consult or a clinic visit. The primary outcome was wait time for an appointment in our clinic. RESULTS: Median wait time prior to the ARM process was 24 days. After implementation of the ARM process, wait times decreased to 13 days (46% reduction). Approximately 60% of incoming consults could be triaged into e-consults, predominantly by managing stable diseases or minor symptoms. CONCLUSIONS: E-consults and ARM of clinical referrals were effective at reducing wait times for our outpatient VHA cardiology clinic. The majority of clinical referrals could be handled through an e-consult and did not require an in-person clinic visit.

A specialty-specific, multimodality educational quality improvement initiative to deimplement rarely appropriate myocardial perfusion imaging.

OBJECTIVE: Investigations of Appropriate Use Criteria (AUC) education have shown a mixed effect on changing provider behaviour. At our facility, rarely appropriate myocardial perfusion imaging (MPI) differs by specialty; awareness of AUC is low. Our objective is to investigate if specialty-specific, multimodality education could reduce rarely appropriate MPI. METHODS: We designed education focused on the rarely appropriate MPI ordered most often by each specialty. We tracked appropriateness of MPI in three cohorts: pre, post (immediately after) and late-post (4 months after) intervention. RESULTS: A total of 889 MPI were evaluated (n=287 pre, n=313 post, n=289 late-post), 95.3% were men. Chest pain was the most common symptom (n=530, 59.6%), while 14.1% (n=125) had no symptoms. Rarely appropriate testing decreased from 4.9% to 1.3% and remained at 1.4% in the late-post cohort (p<0.0001). In logistic regression, lack of symptoms (OR 31.3, 95% CI 10.3 to 94.8, p≤0.0001) and being in the post or late-post cohorts (OR 0.27, 95% CI 0.11 to 0.68, p=0.006) were associated with rarely appropriate MPI. Preoperative MPI in patients with good exercise capacity was a common rarely appropriate indication. Ischaemia was not observed among patients with rarely appropriate indication for MPI. CONCLUSIONS: In certain clinical settings, education may be an effective approach for deimplementing rarely appropriate MPI. The effect of education may be enhanced when focused on improving patient care, delivered by a peer, and needs assessment indicates low awareness of guidelines. Lack of symptoms and preoperative MPI continue to be the predominant rarely appropriate MPI ordered.

Baseline Hemodynamics and Response to Contrast Media During Diagnostic Cardiac Catheterization Predict Adverse Events in Heart Failure Patients.

BACKGROUND: Contrast media administered during cardiac catheterization can affect hemodynamic variables. However, little is documented about the effects of contrast on hemodynamics in heart failure patients or the prognostic value of baseline and changes in hemodynamics for predicting subsequent adverse events. METHODS AND RESULTS: In this prospective study of 150 heart failure patients, we measured hemodynamics at baseline and after administration of iodixanol or iopamidol contrast. One-year Kaplan-Meier estimates of adverse event-free survival (death, heart failure hospitalization, and rehospitalization) were generated, grouping patients by baseline measures of pulmonary capillary wedge pressure (PCWP) and cardiac index (CI), and by changes in those measures after contrast administration. We used Cox proportional hazards modeling to assess sequentially adding baseline PCWP and change in CI to 5 validated risk models (Seattle Heart Failure Score, ESCAPE [Evaluation Study of Congestive Heart Failure and Pulmonary Artery Catheterization Effectiveness], CHARM [Candesartan in Heart Failure: Assessment of Reduction in Mortality and Morbidity], CORONA [Controlled Rosuvastatin Multinational Trial in Heart Failure], and MAGGIC [Meta-Analysis Global Group in Chronic Heart Failure]). Median contrast volume was 109 mL. Both contrast media caused similarly small but statistically significant changes in most hemodynamic variables. There were 39 adverse events (26.0%). Adverse event rates increased using the composite metric of baseline PCWP and change in CI (P<0.01); elevated baseline PCWP and decreased CI after contrast correlated with the poorest prognosis. Adding both baseline PCWP and change in CI to the 5 risk models universally improved their predictive value (P≤0.02). CONCLUSIONS: In heart failure patients, the administration of contrast causes small but significant changes in hemodynamics. Calculating baseline PCWP with change in CI after contrast predicts adverse events and increases the predictive value of existing models. Patients with elevated baseline PCWP and decreased CI after contrast merit greatest concern.

Physician-level variation in the diagnosis of myocardial infarction and the use of angiography among Veterans with elevated troponin.

BACKGROUND: Cardiac troponin assays have improved the ability to detect myocardial damage. However, ascertaining whether troponin elevation is due to myocardial infarction (MI) or secondary to another process can be challenging. Our aim is to evaluate provider-level variation in the diagnosis of MI and the use of invasive coronary angiography (ICA) among patients with undifferentiated elevations in cardiac troponin. METHODS: We analyzed data from all patients with elevated troponin levels in a single Veterans Affairs (VA) Medical Center between 2006 and 2007. One of several cardiologists prospectively evaluated each patient's presentation and course of care. We compared the frequency of MI diagnosis and ICA use between physicians using univariate odds ratios (OR). RESULTS: Among 761 patients, 34.0 % were diagnosed with MI and 25.9 % underwent ICA. The unadjusted rates of MI (23.9 to 56.7 %, P = 0.02) and ICA (17.3 to 73.3 %, P < 0.001) differed between physicians. Comparing the patient cohorts for each physician, baseline characteristics were similar except for chest pain. In multivariate regression, factors associated with the use of cardiac ICA included an abnormal electrocardiograph (ECG) (OR = 1.89, P = 0.014), level of troponin (OR = 1.71, P = 0.004), chest pain (OR = 8.60, P < 0.001), and care by non-VA physicians (OR = 4.45, P = 0.006). One physician had a lower ICA use (OR = 0.56, P = 0.017). In multivariate regression of MI, no physician-level variation was observed. CONCLUSION: Among patients with elevated troponin, the likelihood of being diagnosed with MI and undergoing ICA is dependent on their clinical presentation. After adjustment, physician-level variation in care was observed for the use of ICA, but not for the diagnosis of MI.

Predictors of short- and long-term mortality in hospitalized veterans with elevated troponin.

BACKGROUND: Cardiac troponin elevation is associated with mortality. We compared the mortality risk related to elevated troponin from acute coronary syndrome (ACS) and non-ACS causes in a hospitalized elderly veteran population. METHODS AND RESULTS: As part of a quality initiative at our Veterans Affairs hospital, all patients with elevated troponin were evaluated by a cardiologist to determine if ACS was present and to recommend management. We selected a sample (n = 761) of consecutive patients studied between February 2006 and February 2007 and examined all-cause mortality over extended follow-up. Nearly all were men (99.1%), and about half had coronary disease (n = 385, 50.5%) and diabetes (n = 339, 44.4%). ACS patients had lower mortality that non-ACS patients. Mortality began to diverge at 30 days; at 1 year it was 42.0% versus 29.0% (odds ratio [OR]: 0.56, 95% confidence interval [CI]: 0.41-0.78) and at 6 years 77.7% versus 58.7% (OR: 0.41, 95% CI: 0.30-0.56). Cox regression models for mortality at multiple time points yielded several independent factors associated with mortality; however, the distribution of the factors was not sufficient to explain the observed difference in mortality. CONCLUSIONS: In this elderly, male veteran population, mortality related to an elevated troponin was higher at 1 and 6 years for non-ACS patients compared with ACS patients. Factors independently associated with a higher mortality risk were predominantly markers of general systemic illness, but did not elucidate the reasons why troponin elevation secondary to non-ACS causes carries this higher risk. A better understanding of these cardiac troponin elevations and implications for future mortality requires additional investigation. Journal of Hospital Medicine 2016;11:773-777. © 2016 Society of Hospital Medicine.

Association of diurnal blood pressure pattern with risk of hospitalization or death in men with heart failure.

BACKGROUND: An altered diurnal blood pressure (BP) pattern has been linked to the risk of developing heart failure (HF). We tested whether an altered diurnal BP pattern is associated with adverse outcomes (death or hospitalization for HF exacerbation) in patients with HF. METHODS AND RESULTS: A total of 118 patients with HF were enrolled from a tertiary care HF clinic and followed for death or HF hospitalization for up to 4 years; 24-hour ambulatory BP was monitored. Forty patients (34%) had a normal BP dipping pattern (night-day ambulatory BP ratio < 0.9), 44 patients (37%) had a nondipping pattern (0.9 < or = night-day ambulatory BP ratio < 1.0), and 34 patients (29%) had a reverse dipping BP pattern (night-day ambulatory BP ratio > or = 1.0). A total of 39 patients had an adverse outcome. Adverse outcome rates were the lowest in dippers and the highest in reverse dippers (log rank P = .052). Predictors of adverse outcomes, selected on the basis of log likelihood contrast, were as follows: New York Heart Association functional class (hazard ratio [HR] 1.96, 95% confidence interval [CI] 1.11-3.44), anemia (HR 2.50, 95% CI 1.23-5.08), and dipping status (HR 1.65, 95% CI 1.08-2.50). CONCLUSION: In addition to other traditional predictors, BP dipping status may be an important prognostic factor in HF.

Mental stress provokes ischemia in coronary artery disease subjects without exercise- or adenosine-induced ischemia.

OBJECTIVES: The purpose of this study was to investigate the possibility that some patients with coronary artery disease (CAD) but negative exercise or chemical stress test results might have mental stress-induced ischemia. The study population consisted solely of those with negative test results. BACKGROUND: Mental stress-induced ischemia has been reported in 20% to 70% of CAD subjects with exercise-induced ischemia. Because mechanisms of exercise and mental stress-induced ischemia may differ, we studied whether mental stress would produce ischemia in a proportion of subjects with CAD who have no inducible ischemia with exercise or pharmacologic tests. METHODS: Twenty-one subjects (14 men, 7 women) with a mean age of 67 years and with a documented history of CAD were studied. All subjects had a recent negative nuclear stress test result (exercise or chemical). Subjects completed a speaking task involving role playing a difficult interpersonal situation. A total of 30 mCi 99mTc-sestamibi was injected at one minute into the speech, and imaging was started 40 min later. A resting image obtained within one week was compared with the stress image. Images were analyzed for number and severity of perfusion defects. The summed difference score based on the difference between summed stress and rest scores was calculated. Severity was assessed using a semiquantitative scoring method from zero to four. RESULTS: Six of 21 (29%) subjects demonstrated reversible ischemia (summed difference score > or =3) with mental stress. No subject had chest pain or electrocardiographic changes during the stressor. Mean systolic and diastolic blood pressure and heart rate all increased between resting and times of peak stress. CONCLUSIONS: Mental stress may produce ischemia in some subjects with CAD and negative exercise or chemical nuclear stress test results.

Early outcomes of a care coordination-enhanced telehome care program for elderly veterans with chronic heart failure.

Veterans with chronic heart failure (HF) are frequently elderly, have numerous comorbid chronic medical illnesses, frequent hospitalizations, and have high rates of cardiovascular events. Within the Veterans Health Administration (VHA), primary care providers are required to manage the majority of HF patients because access to cardiac specialty care within the VHA may be limited. We designed and implemented a care-coordinated, nurse-directed home telehealth management program for veterans with difficult-to-manage or new onset chronic systolic HF. An in-home telehealth message device was provided to the patient at enrollment, and patients received daily HF-specific education via the nurse coordinator and/or the device throughout their continuum of care. We collected demographic characteristics, clinical characteristics, and outcome data at the time of enrollment and at nearly 6 months after enrollment. A total of 92 patients were enrolled, with complete data available on 73. The mean patient age was 67 years, the mean left ventricular ejection fraction (LVEF) was 23%, and nearly all patients (99%) were men. After enrollment, significant improvements were found in blood pressure (129/73 to 119/69 mm Hg, p < 0.05), weight (196 to 192 pounds, p < 0.01), and shortness of breath rating (0-10 scale, 4.0 to 2.7, p = 0.02). Average daily doses of fosinopril (24 to 35 mg/d, p < 0.01) and metoprolol (84 to 94 mg/d, p = 0.05) were also improved. The total number of inpatient hospital days were reduced while on the home telehealth program (from 630 for the previous year to 122 for the duration of the program) with only 31% of the hospitalizations related to HF while on the program. Our nurse-directed, care coordinated home telehealth management program was associated with improved early outcomes in a group of elderly male veterans with chronic HF.

Pharmacological treatment of patients with peripheral arterial disease.

Atherosclerosis is a disease process that affects the coronary, cerebral and peripheral arterial circulation. While great emphasis has been placed on the aggressive pharmacological management of coronary artery disease, less attention has been paid to the pharmacological management of peripheral vascular disease, despite its significant morbidity and mortality. The purpose of medical management in peripheral arterial disease is to relieve symptoms of claudication and to prevent thrombotic vascular events. These goals are best achieved through aggressive risk factor modification and pharmacotherapy. Risk factor modification includes smoking cessation, adequate control of blood pressure and cholesterol, as well as aggressive glycaemic control in patients with diabetes mellitus. Antiplatelet therapy and relief of claudication is also achieved through pharmacotherapy. With aggressive risk factor modification and adequate pharmacotherapy, patients with peripheral arterial disease can have an improved quality of life as well as prolonged survival.

Systolic compression of the left anterior descending coronary artery: a case series, review of the literature, and therapeutic options including stenting.

Six cases in our institution of various presentations of left anterior descending (LAD) myocardial bridging were found on coronary angiography. Generally a benign condition, this finding can result in ischemia or infarction as seen in some of our cases. We found one case in which the bridge resulted in an anterior myocardial infarction in an elderly patient, one case with fixed stenoses at the entry and exit point of the bridge causing ischemia, another with vasospasm within the bridged segment, one case in which the patient was referred for intervention of a fixed stenosis which after intracoronary nitroglycerin (NTG) was found to be an LAD bridge, another case in which the thallium myocardial perfusion scan revealed a reversible anterior defect, and finally one case with anginal chest pain despite a normal coronary flow reserve proximal and distal to the bridged segment. Our treatments varied from stenting in three patients to medical therapy in the remaining patients. We concluded that a thorough evaluation in this population should include functional testing for ischemia, intravascular ultrasound to assess wall thickness, and coronary flow reserve measurements in order to determine the significance of the these bridges. Stenting may have a role in select patients. However, additional studies are needed.