Augmented Intelligence to Identify Patients With Advanced Heart Failure in an Integrated Health System

BACKGROUND

Timely referral for specialist evaluation in patients with advanced heart failure (HF) is a Class 1 recommendation. However, the transition from stage C HF to advanced or stage D HF often goes undetected in routine care, resulting in delayed referral and higher mortality rates.

OBJECTIVES

The authors sought to develop an augmented intelligence-enabled workflow using machine learning to identify patients with stage D HF and streamline referral.

METHODS

We extracted data on HF patients with encounters from January 1, 2007, to November 30, 2020, from a HF registry within a regional, integrated health system. We created an ensemble machine learning model to predict stage C or stage D HF and integrated the results within the electronic health record.

RESULTS

In a retrospective data set of 14,846 patients, the model had a good positive predictive value (60%) and low sensitivity (25%) for identifying stage D HF in a 100-person, physician-reviewed, holdout test set. During prospective implementation of the workflow from April 1, 2021, to February 15, 2022, 416 patients were reviewed by a clinical coordinator, with agreement between the model and the coordinator in 50.3% of stage D predictions. Twenty-four patients have been scheduled for evaluation in a HF clinic, 4 patients started an evaluation for advanced therapies, and 1 patient received a left ventricular assist device.

CONCLUSIONS

An augmented intelligence-enabled workflow was integrated into clinical operations to identify patients with advanced HF. Endeavors such as this require a multidisciplinary team with experience in design thinking, informatics, quality improvement, operations, and health information technology, as well as dedicated resources to monitor and improve performance over time.

Strain echocardiography to describe left ventricular function pre- and postexercise in elite basketball athletes: A feasibility study

BACKGROUND

Elite athletes show structural cardiac changes as an adaptation to exercise. Studies examining strain in athletes have largely analyzed images at rest only. There is little data available regarding the change in strain with exercise. Our objectives were: to investigate the feasibility of strain analysis in athletes at peak exercise, to determine the normal range of left ventricular (LV) global longitudinal strain (GLS) within this population postexercise, to describe how LV GLS changes with exercise, and to determine whether any clinical characteristics correlate with the change in GLS that occurs with exercise.

METHODS

We conducted a cross-sectional study on elite athletes who participated in the 2016-2018 National Basketball Association Draft Combines. Echocardiograms were obtained at rest and after completing a treadmill stress test to maximal exertion or completion of Bruce protocol. Primary outcomes included GLS obtained at rest and peak exercise. Secondary outcome was the change in GLS between rest and exercise. Univariate relationships between various clinical characteristics and our secondary outcome were analyzed.

RESULTS

Our final cohort (n = 111) was all male and 92/111 (82.9%) were African American. Mean GLS magnitude increased in response to exercise (-17.6 ± 1.8 vs -19.2 ± 2.6, P < .0001). Lower resting heart rates (r = .22, P = .02) and lower heart rates at peak exercise (r = .21, P = .03) correlated with the increase in LV GLS from exercise.

CONCLUSIONS

Strain imaging is technically feasible to obtain among elite basketball athletes at peak exercise. Normative strain response to exercise from this study may help identify abnormal responses to exercise in athletes.

Vasospastic Arrest

Vasospastic angina is an uncommon cause of cardiac arrest. We describe a patient who presented with sudden cardiac arrest due to severe coronary vasospasm. Telemetry during the event revealed ventricular arrhythmias and asystole followed by spontaneous self-conversion back to normal sinus rhythm. The patient underwent implantable cardioverter-defibrillator therapy. (Level of Difficulty: Beginner.)

Expanded algorithm for managing patients with acute decompensated heart failure

Heart failure is a complex disease process, the manifestation of various cardiac and noncardiac abnormalities. General treatment approaches for heart failure have remained the same over the past decades despite the advent of novel therapies and monitoring modalities. In the same vein, the readmission rates for heart failure patients remain high and portend a poor prognosis for morbidity and mortality. In this context, development and implementation of improved algorithms for assessing and treating HF patients during hospitalization remains an unmet need. We propose an expanded algorithm for both monitoring and treating patients admitted for acute decompensated heart failure with the goal to improve post-discharge outcomes and decrease rates of rehospitalizations.

Plasma renin activity, response to aliskiren, and clinical outcomes in patients hospitalized for heart failure: the ASTRONAUT trial

AIMS

The direct renin inhibitor, aliskiren, is known to reduce plasma renin activity (PRA), but whether the efficacy of aliskiren varies based on an individual's baseline PRA in patients hospitalized for heart failure (HF) is presently unknown. We characterized the prognostic value of PRA and determined if this risk is modifiable with use of aliskiren.

METHODS AND RESULTS

This pre-specified neurohormonal substudy of ASTRONAUT analysed all patients hospitalized for HF with ejection fraction (EF) ≤40% with available baseline PRA data (n = 1306, 80.9%). Risk associated with baseline PRA and short-term changes in PRA from baseline to 1 month was modelled with respect to 12-month clinical events. Median baseline PRA was 3.0 (interquartile range 0.6-16.4) ng/mL/h. Aliskiren significantly reduced PRA early after treatment initiation through 12-month follow-up compared with placebo (P < 0.001). The lowest baseline PRA quartile (<0.6 ng/mL/h) was independently predictive of lower all-cause mortality [adjusted hazard ratio (HR) 0.50, 95% confidence interval (CI) 0.31-0.81] and the composite of cardiovascular mortality and HF hospitalization (adjusted HR 0.57, 95% CI 0.40-0.79). Delta log-normalized PRA (from baseline to 1 month) was not predictive of either primary endpoint at 12 months (P ≥ 0.43). The prognostic value of baseline PRA and short-term changes in PRA did not vary by randomization to aliskiren or placebo (interaction P ≥ 0.13).

CONCLUSIONS

Plasma renin activity is reduced early and durably by aliskiren, but this did not translate into improved clinical outcomes in ASTRONAUT. Baseline PRA or short-term reduction in PRA do not identify a subgroup who may preferentially benefit from direct renin inhibition. Clinical Trial Registration ClinicalTrials.gov Unique Identifier: NCT00894387.

Lessons learned in acute heart failure

Acute heart failure (HF) is a global pandemic with more than one million admissions to hospital annually in the US and millions more worldwide. Post-discharge mortality and readmission rates remain unchanged and unacceptably high. Although recent drug development programmes have failed to deliver novel therapies capable of reducing cardiovascular morbidity and mortality in patients hospitalized for worsening chronic HF, hospitalized HF registries and clinical trial databases have generated a wealth of information improving our collective understanding of the HF syndrome. This review will summarize key insights from clinical trials in acute HF and hospitalized HF registries over the last several decades, focusing on improving the management of patients with HF and reduced ejection fraction.

The natural product phyllanthusmin C enhances IFN-γ production by human NK cells through upregulation of TLR-mediated NF-κB signaling

Natural products are a major source for cancer drug development. NK cells are a critical component of innate immunity with the capacity to destroy cancer cells, cancer-initiating cells, and clear viral infections. However, few reports describe a natural product that stimulates NK cell IFN-γ production and unravel a mechanism of action. In this study, through screening, we found that a natural product, phyllanthusmin C (PL-C), alone enhanced IFN-γ production by human NK cells. PL-C also synergized with IL-12, even at the low cytokine concentration of 0.1 ng/ml, and stimulated IFN-γ production in both human CD56(bright) and CD56(dim) NK cell subsets. Mechanistically, TLR1 and/or TLR6 mediated PL-C's activation of the NF-κB p65 subunit that in turn bound to the proximal promoter of IFNG and subsequently resulted in increased IFN-γ production in NK cells. However, IL-12 and IL-15Rs and their related STAT signaling pathways were not responsible for the enhanced IFN-γ secretion by PL-C. PL-C induced little or no T cell IFN-γ production or NK cell cytotoxicity. Collectively, we identify a natural product with the capacity to selectively enhance human NK cell IFN-γ production. Given the role of IFN-γ in immune surveillance, additional studies to understand the role of this natural product in prevention of cancer or infection in select populations are warranted.