Strengthening the use of artificial intelligence within healthcare delivery organizations: balancing regulatory compliance and patient safety.

OBJECTIVES: Surface the urgent dilemma that healthcare delivery organizations (HDOs) face navigating the US Food and Drug Administration (FDA) final guidance on the use of clinical decision support (CDS) software. MATERIALS AND METHODS: We use sepsis as a case study to highlight the patient safety and regulatory compliance tradeoffs that 6129 hospitals in the United States must navigate. RESULTS: Sepsis CDS remains in broad, routine use. There is no commercially available sepsis CDS system that is FDA cleared as a medical device. There is no public disclosure of an HDO turning off sepsis CDS due to regulatory compliance concerns. And there is no public disclosure of FDA enforcement action against an HDO for using sepsis CDS that is not cleared as a medical device. DISCUSSION AND CONCLUSION: We present multiple policy interventions that would relieve the current tension to enable HDOs to utilize artificial intelligence to improve patient care while also addressing FDA concerns about product safety, efficacy, and equity.

Artificial Intelligence in Cardiovascular Care - Part 2: Applications: JACC Review Topic of the Week.

Recent Artificial Intelligence (AI) advancements in cardiovascular care offer potential enhancements in effective diagnosis, treatment, and outcomes. Over 600 Food and Drug Administration (FDA)-approved clinical AI algorithms now exist, with 10% focusing on cardiovascular applications, highlighting the growing opportunities for AI to augment care. This review discusses the latest advancements in the field of AI, with a particular focus on the utilization of multimodal inputs and the field of generative AI. Further discussions in this review involve an approach to understanding the larger context in which AI-augmented care may exist, and include a discussion of the need for rigorous evaluation, appropriate infrastructure for deployment, ethics and equity assessments, regulatory oversight, and viable business cases for deployment. Embracing this rapidly evolving technology while setting an appropriately high evaluation benchmark with careful and patient-centered implementation will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Artificial Intelligence for Cardiovascular Care - Part 1: Advances: JACC Review Topic of the Week.

Recent AI advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and outcomes. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms, echocardiography, angiography, genetics, and more. AI models detect diseases from electrocardiograms at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies. However, AI's unique characteristics necessitates rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Preparing for the bedside-optimizing a postpartum depression risk prediction model for clinical implementation in a health system.

OBJECTIVE: We developed and externally validated a machine-learning model to predict postpartum depression (PPD) using data from electronic health records (EHRs). Effort is under way to implement the PPD prediction model within the EHR system for clinical decision support. We describe the pre-implementation evaluation process that considered model performance, fairness, and clinical appropriateness. MATERIALS AND METHODS: We used EHR data from an academic medical center (AMC) and a clinical research network database from 2014 to 2020 to evaluate the predictive performance and net benefit of the PPD risk model. We used area under the curve and sensitivity as predictive performance and conducted a decision curve analysis. In assessing model fairness, we employed metrics such as disparate impact, equal opportunity, and predictive parity with the White race being the privileged value. The model was also reviewed by multidisciplinary experts for clinical appropriateness. Lastly, we debiased the model by comparing 5 different debiasing approaches of fairness through blindness and reweighing. RESULTS: We determined the classification threshold through a performance evaluation that prioritized sensitivity and decision curve analysis. The baseline PPD model exhibited some unfairness in the AMC data but had a fair performance in the clinical research network data. We revised the model by fairness through blindness, a debiasing approach that yielded the best overall performance and fairness, while considering clinical appropriateness suggested by the expert reviewers. DISCUSSION AND CONCLUSION: The findings emphasize the need for a thorough evaluation of intervention-specific models, considering predictive performance, fairness, and appropriateness before clinical implementation.

Implications of Bias in Artificial Intelligence: Considerations for Cardiovascular Imaging.

PURPOSE OF REVIEW: Bias in artificial intelligence (AI) models can result in unintended consequences. In cardiovascular imaging, biased AI models used in clinical practice can negatively affect patient outcomes. Biased AI models result from decisions made when training and evaluating a model. This paper is a comprehensive guide for AI development teams to understand assumptions in datasets and chosen metrics for outcome/ground truth, and how this translates to real-world performance for cardiovascular disease (CVD). RECENT FINDINGS: CVDs are the number one cause of mortality worldwide; however, the prevalence, burden, and outcomes of CVD vary across gender and race. Several biomarkers are also shown to vary among different populations and ethnic/racial groups. Inequalities in clinical trial inclusion, clinical presentation, diagnosis, and treatment are preserved in health data that is ultimately used to train AI algorithms, leading to potential biases in model performance. Despite the notion that AI models themselves are biased, AI can also help to mitigate bias (e.g., bias auditing tools). In this review paper, we describe in detail implicit and explicit biases in the care of cardiovascular disease that may be present in existing datasets but are not obvious to model developers. We review disparities in CVD outcomes across different genders and race groups, differences in treatment of historically marginalized groups, and disparities in clinical trials for various cardiovascular diseases and outcomes. Thereafter, we summarize some CVD AI literature that shows bias in CVD AI as well as approaches that AI is being used to mitigate CVD bias.

Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality.

Utilizing clinical texts in survival analysis is difficult because they are largely unstructured. Current automatic extraction models fail to capture textual information comprehensively since their labels are limited in scope. Furthermore, they typically require a large amount of data and high-quality expert annotations for training. In this work, we present a novel method of using BERT-based hidden layer representations of clinical texts as covariates for proportional hazards models to predict patient survival outcomes. We show that hidden layers yield notably more accurate predictions than predefined features, outperforming the previous baseline model by 5.7% on average across C-index and time-dependent AUC. We make our work publicly available at https://github.com/bionlplab/heart_failure_mortality.

Using electronic health records for population health sciences: a case study to evaluate the associations between changes in left ventricular ejection fraction and the built environment.

OBJECTIVE: Electronic health record (EHR) data linked with address-based metrics using geographic information systems (GIS) are emerging data sources in population health studies. This study examined this approach through a case study on the associations between changes in ejection fraction (EF) and the built environment among heart failure (HF) patients. MATERIALS AND METHODS: We identified 1287 HF patients with at least 2 left ventricular EF measurements that are minimally 1 year apart. EHR data were obtained at an academic medical center in New York for patients who visited between 2012 and 2017. Longitudinal clinical information was linked with address-based built environment metrics related to transportation, air quality, land use, and accessibility by GIS. The primary outcome is the increase in the severity of EF categories. Statistical analyses were performed using mixed-effects models, including a subgroup analysis of patients who initially had normal EF measurements. RESULTS: Previously reported effects from the built environment among HF patients were identified. Increased daily nitrogen dioxide concentration was associated with the outcome while controlling for known HF risk factors including sex, comorbidities, and medication usage. In the subgroup analysis, the outcome was significantly associated with decreased distance to subway stops and increased distance to parks. CONCLUSIONS: Population health studies using EHR data may drive efficient hypothesis generation and enable novel information technology-based interventions. The availability of more precise outcome measurements and home locations, and frequent collection of individual-level social determinants of health may further drive the use of EHR data in population health studies.

Development of novel machine learning model for right ventricular quantification on echocardiography-A multimodality validation study.

PURPOSE: Echocardiography (echo) is widely used for right ventricular (RV) assessment. Current techniques for RV evaluation require additional imaging and manual analysis; machine learning (ML) approaches have the potential to provide efficient, fully automated quantification of RV function. METHODS: An automated ML model was developed to track the tricuspid annulus on echo using a convolutional neural network approach. The model was trained using 7791 image frames, and automated linear and circumferential indices quantifying annular displacement were generated. Automated indices were compared to an independent reference of cardiac magnetic resonance (CMR) defined RV dysfunction (RVEF < 50%). RESULTS: A total of 101 patients prospectively underwent echo and CMR: Fully automated annular tracking was uniformly successful; analyses entailed minimal processing time (<1 second for all) and no user editing. Findings demonstrate all automated annular shortening indices to be lower among patients with CMR-quantified RV dysfunction (all P < .001). Magnitude of ML annular displacement decreased stepwise in relation to population-based tertiles of TAPSE, with similar results when ML analyses were localized to the septal or lateral annulus (all P ≤ .001). Automated segmentation techniques provided good diagnostic performance (AUC 0.69-0.73) in relation to CMR reference and compared to conventional RV indices (TAPSE and S') with high negative predictive value (NPV 84%-87% vs 83%-88%). Reproducibility was higher for ML algorithm as compared to manual segmentation with zero inter- and intra-observer variability and ICC 1.0 (manual ICC: 0.87-0.91). CONCLUSIONS: This study provides an initial validation of a deep learning system for RV assessment using automated tracking of the tricuspid annulus.

Utilizing electronic health data and machine learning for the prediction of 30-day unplanned readmission or all-cause mortality in heart failure.

Background: Existing risk assessment tools for heart failure (HF) outcomes use structured databases with static, single-timepoint clinical data and have limited accuracy. Objective: The purpose of this study was to develop a comprehensive approach for accurate prediction of 30-day unplanned readmission and all-cause mortality (ACM) that integrates clinical and physiological data available in the electronic health record system. Methods: Three predictive models for 30-day unplanned readmissions or ACM were created using an extreme gradient boosting approach: (1) index admission model; (2) index discharge model; and (3) feature-aggregated model. Performance was assessed by the area under the curve (AUC) metric and compared with that of the HOSPITAL score, a widely used predictive model for hospital readmission. Results: A total of 3774 patients with a primary billing diagnosis of HF were included (614 experienced the primary outcome), with 796 variables used in the admission and discharge models, and 2032 in the feature-aggregated model. The index admission model had AUC = 0.723, the index discharge model had AUC = 0.754, and the feature-aggregated model had AUC = 0.756 for prediction of 30-day unplanned readmission or ACM. For comparison, the HOSPITAL score had AUC = 0.666 (admission model: P = .093; discharge model: P = .022; feature aggregated: P = .012). Conclusion: These models predict risk of HF hospitalizations and ACM in patients admitted with HF and emphasize the importance of incorporating large numbers of variables in machine learning models to identify predictors for future investigation.

Risk Reclassification With Coronary Computed Tomography Angiography-Visualized Nonobstructive Coronary Artery Disease According to 2018 American College of Cardiology/American Heart Association Cholesterol Guidelines (from the Coronary Computed Tomography Angiography Evaluation for Clinical Outcomes : An International Multicenter Registry [CONFIRM]).

The 2018 American College of Cardiology (ACC)/American Heart Association (AHA) cholesterol management guideline recommends risk enhancers in the borderline-risk and statin recommended/intermediate-risk groups. We determined the risk reclassification by the presence and severity of coronary computed tomography angiography (CCTA)-visualized coronary artery disease (CAD) according to statin eligibility groups. Of 35,281 individuals who underwent CCTA, 1,303 asymptomatic patients (age 59, 65% male) were identified. Patients were categorized as low risk, borderline risk, statin recommended/intermediate risk or statin recommended/high risk according to the guideline. CCTA-visualized CAD was categorized as no CAD, nonobstructive, or obstructive. Major adverse cardiovascular events (MACE) were defined as a composite outcome of all-cause mortality, nonfatal myocardial infarction, and late coronary revascularization (>90 days). We tested a reclassification wherein no CAD reclassifies downward, and the presence of any CAD reclassifies upward. During a median follow-up of 2.9 years, 93 MACE events (7.1%) were observed. Among the borderline-risk and statin-recommended/intermediate-risk groups eligible for risk enhancers, the presence or absence of any CCTA-visualized CAD led to a net increase of 2.3% of cases and 22.4% of controls correctly classified (net reclassification index [NRI] 0.27, 95% CI 0.13 to 0.41, p = 0.0002). The NRI was not significant among low- or statin-recommended/high-risk patients (all p >0.05). The presence or absence of CCTA-visualized CAD, including both obstructive and nonobstructive CAD, significantly improves reclassification in patients eligible for risk enhancers in 2018 ACC/AHA guidelines. Patients in low- and high-risk groups derive no significant improvement in risk reclassification from CCTA.

Clinical and Socioeconomic Predictors of Heart Failure Readmissions: A Review of Contemporary Literature.

Heart failure represents a clinical syndrome that results from a constellation of disease processes affecting myocardial function. Although recent studies have suggested a declining or stable incidence of heart failure, patients with heart failure continue to have high hospitalization and readmission rates, resulting in a substantial economic and public health burden. We searched PubMed and Google Scholar to identify published literature from 1998 through 2018 using the following keywords: heart failure, readmissions, predictors, prediction models, and interventions. Cited references were also used to identify relevant literature. Developments in the diagnosis and management of patients with heart failure have improved hospitalization and readmission rates in the past few decades. However, heart failure remains the most common cause of hospitalization in persons older than 65 years. As a result, given the enormous clinical and financial burden associated with heart failure readmissions on health care, there has been growing interest in the investigation of mechanisms aimed at improving outcomes and curtailing associated costs of care. Herein, we review the current literature on clinical and socioeconomic predictors of heart failure readmissions, briefly discussing limitations of existing strategies and providing an overview of current technology aimed at reducing hospitalizations.

Machine learning derived segmentation of phase velocity encoded cardiovascular magnetic resonance for fully automated aortic flow quantification.

BACKGROUND: Phase contrast (PC) cardiovascular magnetic resonance (CMR) is widely employed for flow quantification, but analysis typically requires time consuming manual segmentation which can require human correction. Advances in machine learning have markedly improved automated processing, but have yet to be applied to PC-CMR. This study tested a novel machine learning model for fully automated analysis of PC-CMR aortic flow. METHODS: A machine learning model was designed to track aortic valve borders based on neural network approaches. The model was trained in a derivation cohort encompassing 150 patients who underwent clinical PC-CMR then compared to manual and commercially-available automated segmentation in a prospective validation cohort. Further validation testing was performed in an external cohort acquired from a different site/CMR vendor. RESULTS: Among 190 coronary artery disease patients prospectively undergoing CMR on commercial scanners (84% 1.5T, 16% 3T), machine learning segmentation was uniformly successful, requiring no human intervention: Segmentation time was < 0.01 min/case (1.2 min for entire dataset); manual segmentation required 3.96 ± 0.36 min/case (12.5 h for entire dataset). Correlations between machine learning and manual segmentation-derived flow approached unity (r = 0.99, p < 0.001). Machine learning yielded smaller absolute differences with manual segmentation than did commercial automation (1.85 ± 1.80 vs. 3.33 ± 3.18 mL, p < 0.01): Nearly all (98%) of cases differed by ≤5 mL between machine learning and manual methods. Among patients without advanced mitral regurgitation, machine learning correlated well (r = 0.63, p < 0.001) and yielded small differences with cine-CMR stroke volume (∆ 1.3 ± 17.7 mL, p = 0.36). Among advanced mitral regurgitation patients, machine learning yielded lower stroke volume than did volumetric cine-CMR (∆ 12.6 ± 20.9 mL, p = 0.005), further supporting validity of this method. Among the external validation cohort (n = 80) acquired using a different CMR vendor, the algorithm yielded equivalently small differences (∆ 1.39 ± 1.77 mL, p = 0.4) and high correlations (r = 0.99, p < 0.001) with manual segmentation, including similar results in 20 patients with bicuspid or stenotic aortic valve pathology (∆ 1.71 ± 2.25 mL, p = 0.25). CONCLUSION: Fully automated machine learning PC-CMR segmentation performs robustly for aortic flow quantification - yielding rapid segmentation, small differences with manual segmentation, and identification of differential forward/left ventricular volumetric stroke volume in context of concomitant mitral regurgitation. Findings support use of machine learning for analysis of large scale CMR datasets.

Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging.

Artificial intelligence (AI) has transformed key aspects of human life. Machine learning (ML), which is a subset of AI wherein machines autonomously acquire information by extracting patterns from large databases, has been increasingly used within the medical community, and specifically within the domain of cardiovascular diseases. In this review, we present a brief overview of ML methodologies that are used for the construction of inferential and predictive data-driven models. We highlight several domains of ML application such as echocardiography, electrocardiography, and recently developed non-invasive imaging modalities such as coronary artery calcium scoring and coronary computed tomography angiography. We conclude by reviewing the limitations associated with contemporary application of ML algorithms within the cardiovascular disease field.

Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry.

INTRODUCTION: Machine learning (ML) is a field in computer science that demonstrated to effectively integrate clinical and imaging data for the creation of prognostic scores. The current study investigated whether a ML score, incorporating only the 16 segment coronary tree information derived from coronary computed tomography angiography (CCTA), provides enhanced risk stratification compared with current CCTA based risk scores. METHODS: From the multi-center CONFIRM registry, patients were included with complete CCTA risk score information and ≥3 year follow-up for myocardial infarction and death (primary endpoint). Patients with prior coronary artery disease were excluded. Conventional CCTA risk scores (conventional CCTA approach, segment involvement score, duke prognostic index, segment stenosis score, and the Leaman risk score) and a score created using ML were compared for the area under the receiver operating characteristic curve (AUC). Only 16 segment based coronary stenosis (0%, 1-24%, 25-49%, 50-69%, 70-99% and 100%) and composition (calcified, mixed and non-calcified plaque) were provided to the ML model. A boosted ensemble algorithm (extreme gradient boosting; XGBoost) was used and the entire data was randomly split into a training set (80%) and testing set (20%). First, tuned hyperparameters were used to generate a trained model from the training data set (80% of data). Second, the performance of this trained model was independently tested on the unseen test set (20% of data). RESULTS: In total, 8844 patients (mean age 58.0 ±â€¯11.5 years, 57.7% male) were included. During a mean follow-up time of 4.6 ±â€¯1.5 years, 609 events occurred (6.9%). No CAD was observed in 48.7% (3.5% event), non-obstructive CAD in 31.8% (6.8% event), and obstructive CAD in 19.5% (15.6% event). Discrimination of events as expressed by AUC was significantly better for the ML based approach (0.771) vs the other scores (ranging from 0.685 to 0.701), P < 0.001. Net reclassification improvement analysis showed that the improved risk stratification was the result of down-classification of risk among patients that did not experience events (non-events). CONCLUSION: A risk score created by a ML based algorithm, that utilizes standard 16 coronary segment stenosis and composition information derived from detailed CCTA reading, has greater prognostic accuracy than current CCTA integrated risk scores. These findings indicate that a ML based algorithm can improve the integration of CCTA derived plaque information to improve risk stratification.

Discharge Processes and 30-Day Readmission Rates of Patients Hospitalized for Heart Failure on General Medicine and Cardiology Services.

Given high rates of heart failure (HF) hospitalizations and widespread adoption of the hospitalist model, patients with HF are often cared for on General Medicine (GM) services. Differences in discharge processes and 30-day readmission rates between patients on GM and those on Cardiology during the contemporary hospitalist era are unknown. The present study compared discharge processes and 30-day readmission rates of patients with HF admitted on GM services and those on Cardiology services. We retrospectively studied 926 patients discharged home after HF hospitalization. The primary outcome was 30-day all-cause readmission after discharge from index hospitalization. Although 60% of patients with HF were admitted to Cardiology services, 40% were admitted to GM services. Prevalence of cardiovascular and noncardiovascular co-morbidities were similar between patients admitted to GM services and Cardiology services. Discharge summaries for patients on GM services were less likely to have reassessments of ejection fraction, new study results, weights, discharge vital signs, discharge physical examinations, and scheduled follow-up cardiologist appointments. In a multivariable regression analysis, patients on GM services were more likely to experience 30-day readmissions compared with those on Cardiology services (odds ratio 1.43 95% confidence interval [1.05 to 1.96], p = 0.02). In conclusion, outcomes are better among those admitted to Cardiology services, signaling the need for studies and interventions focusing on noncardiology hospital providers that care for patients with HF.

Association between epicardial fat volume and fractional flow reserve: An analysis of the determination of fractional flow reserve (DeFACTO) study.

BACKGROUND: This study examines the relationship between epicardial fat volume (EFV) and lesion-specific ischemia by fractional flow reserve (FFR). METHODS: In a study of 173 patients (63.0 ±â€¯8.3 years) undergoing FFR, EFV was determined using cardiac computed tomography. Relationships between EFV and FFR were assessed using multivariable linear and logistic regression. RESULTS: Using multivariable linear and logistic regression, no association between EFV and FFR was observed (ß [SE] = -0.001 [0.003], P = 0.6, OR [95% CI]: 1.02 [0.94-1.11], P = 0.64, respectively). CONCLUSION: In patients with suspected or known coronary artery disease undergoing invasive angiography, EFV was not associated with FFR.

Patterns of scheduled follow-up appointments following hospitalization for heart failure: insights from an urban medical center in the United States.

OBJECTIVES: Although postdischarge outpatient follow-up appointments after a hospitalization for heart failure represent a potentially effective strategy to prevent heart failure readmissions, patterns of scheduled follow-up appointments upon discharge are poorly described. We aimed to characterize real-world patterns of scheduled follow-up appointments among adult patients with heart failure upon hospital discharge. PATIENTS AND METHODS: This was a retrospective cohort study performed at a large urban academic center in the United States among adults hospitalized with a principal diagnosis of congestive heart failure between January 1, 2013, and December 31, 2014. Patient demographics, administrative data, clinical parameters, echocardiographic indices, and scheduled postdischarge outpatient follow-up appointments were collected. RESULTS: Of the 796 patients hospitalized for heart failure, just over half of the cohort had a scheduled follow-up appointment upon discharge. Follow-up appointments were less likely among patients who were white and had heart failure with preserved ejection fraction and more likely among patients with Medicaid and chronic obstructive pulmonary disease. In an adjusted multivariable regression model, age ≥65 years was inversely associated with a scheduled follow-up appointment upon hospital discharge, despite higher rates of several cardiovascular and noncardiovascular comorbidities. CONCLUSION: Just half of the patients discharged home following a hospitalization for heart failure had a follow-up appointment scheduled, representing a missed opportunity to provide a recommended care transition intervention. Despite a greater burden of both cardiovascular and noncardiovascular comorbidities, older adults (age ≥65 years) were less likely to have a follow-up appointment scheduled upon discharge compared with younger adults, revealing a disparity that warrants further investigation.