Faraz S. Ahmad

Validity of Cardiovascular Data From Electronic Sources: The Multi-Ethnic Study of Atherosclerosis and HealthLNK

Background: Understanding the validity of data from electronic data research networks is critical to national research initiatives and learning healthcare systems for cardiovascular care. Our goal was to evaluate the degree of agreement of electronic data research networks in comparison with data collected by standardized research approaches in a cohort study. Methods: We linked individual-level data from MESA (Multi-Ethnic Study of Atherosclerosis), a community-based cohort, with HealthLNK, a 2006 to 2012 database of electronic health records from 6 Chicago health systems. To evaluate the correlation and agreement of blood pressure in HealthLNK in comparison with in-person MESA examinations, and body mass index in HealthLNK in comparison with MESA, we used Pearson correlation coefficients and Bland-Altman plots. Using diagnoses in MESA as the criterion standard, we calculated the performance of HealthLNK for hypertension, obesity, and diabetes mellitus diagnosis by using International Classification of Diseases, Ninth Revision codes and clinical data. We also identified potential myocardial infarctions, strokes, and heart failure events in HealthLNK and compared them with adjudicated events in MESA. Results: Of the 1164 MESA participants enrolled at the Chicago Field Center, 802 (68.9%) participants had data in HealthLNK. The correlation was low for systolic blood pressure (0.39; P<0.0001). In comparison with MESA, HealthLNK overestimated systolic blood pressure by 6.5 mm Hg (95% confidence interval, 4.2–7.8). There was a high correlation between body mass index in MESA and HealthLNK (0.94; P<0.0001). HealthLNK underestimated body mass index by 0.3 kg/m2 (95% confidence interval, –0.4 to –0.1). With the use of International Classification of Diseases, Ninth Revision codes and clinical data, the sensitivity and specificity of HealthLNK queries for hypertension were 82.4% and 59.4%, for obesity were 73.0% and 89.8%, and for diabetes mellitus were 79.8% and 93.3%. In comparison with adjudicated cardiovascular events in MESA, the concordance rates for myocardial infarction, stroke, and heart failure were, respectively, 41.7% (5/12), 61.5% (8/13), and 62.5% (10/16). Conclusions: These findings illustrate the limitations and strengths of electronic data repositories in comparison with information collected by traditional standardized epidemiological approaches for the ascertainment of cardiovascular risk factors and events.

Tensor Factorization for Precision Medicine in Heart Failure with Preserved Ejection Fraction

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous clinical syndrome that may benefit from improved subtyping in order to better characterize its pathophysiology and to develop novel targeted therapies. The United States Precision Medicine Initiative comes amid the rapid growth in quantity and modality of clinical data for HFpEF patients ranging from deep phenotypic to trans-omic data. Tensor factorization, a form of machine learning, allows for the integration of multiple data modalities to derive clinically relevant HFpEF subtypes that may have significant differences in underlying pathophysiology and differential response to therapies. Tensor factorization also allows for better interpretability by supporting dimensionality reduction and identifying latent groups of data for meaningful summarization of both features and disease outcomes. In this narrative review, we analyze the modest literature on the application of tensor factorization to related biomedical fields including genotyping and phenotyping. Based on the cited work including work of our own, we suggest multiple tensor factorization formulations capable of integrating the deep phenotypic and trans-omic modalities of data for HFpEF, or accounting for interactions between genetic variants at different omic hierarchies. We encourage extensive experimental studies to tackle challenges in applying tensor factorization for precision medicine in HFpEF, including effectively incorporating existing medical knowledge, properly accounting for uncertainty, and efficiently enforcing sparsity for better interpretability.

Characterizing Teamwork in Cardiovascular Care Outcomes: A Network Analytics Approach

Background—The nature of teamwork in healthcare is complex and interdisciplinary, and provider collaboration based on shared patient encounters is crucial to its success. Characterizing the intensity of working relationships with risk-adjusted patient outcomes supplies insight into provider interactions in a hospital environment. Methods and Results—We extracted 4 years of patient, provider, and activity data for encounters in an inpatient cardiology unit from Northwestern Medicine’s Enterprise Data Warehouse. We then created a provider–patient network to identify healthcare providers who jointly participated in patient encounters and calculated satisfaction rates for provider–provider pairs. We demonstrated the application of a novel parameter, the shared positive outcome ratio, a measure that assesses the strength of a patient-sharing relationship between 2 providers based on risk-adjusted encounter outcomes. We compared an observed collaboration network of 334 providers and 3453 relationships to 1000 networks with shared positive outcome ratio scores based on randomized outcomes and found 188 collaborative relationships between pairs of providers that showed significantly higher than expected patient satisfaction ratings. A group of 22 providers performed exceptionally in terms of patient satisfaction. Our results indicate high variability in collaboration scores across the network and highlight our ability to identify relationships with both higher and lower than expected scores across a set of shared patient encounters. Conclusions—Satisfaction rates seem to vary across different teams of providers. Team collaboration can be quantified using a composite measure of collaboration across provider pairs. Tracking provider pair outcomes over a sufficient set of shared encounters may inform quality improvement strategies such as optimizing team staffing, identifying characteristics and practices of high-performing teams, developing evidence-based team guidelines, and redesigning inpatient care processes.

Endovascular repair of ventricular assist device outflow cannula stenosis

This report describes a case of endovascular repair of an outflow cannula obstruction in a heart failure patient with biventricular assist devices. The patient presented with cardiogenic shock and was diagnosed via multimodality imaging with outflow cannula obstruction of the left ventricular assist device, likely from a hematoma. A transesophageal echocardiogram‐guided endovascular approach was undertaken. A 10.0 mm × 38 mm covered stent was successfully deployed and post‐dilated. Normal flow in the outflow cannula was restored. Hemodynamic and left ventricular flow parameters returned close to baseline post‐procedure. The growth in ventricular assist device implantation and associated complications will create new opportunities for endovascular repair.

Racial/Ethnic Differences in Left Ventricular Structure and Function in Chronic Kidney Disease: The Chronic Renal Insufficiency Cohort

BACKGROUND Chronic kidney disease (CKD) is associated with increased risk of cardiovascular disease (CVD) and it is especially common among Blacks. Left ventricular hypertrophy (LVH) is an important subclinical marker of CVD, but there are limited data on racial variation in left ventricular structure and function among persons with CKD. METHODS In a cross-sectional analysis of the Chronic Renal Insufficiency Cohort Study, we compared the prevalence of different types of left ventricular remodeling (concentric hypertrophy, eccentric hypertrophy, and concentric remodeling) by race/ethnicity. We used multinomial logistic regression to test whether race/ethnicity associated with different types of left ventricular remodeling independently of potential confounding factors. RESULTS We identified 1,164 non-Hispanic Black and 1,155 non-Hispanic White participants who completed Year 1 visits with echocardiograms that had sufficient data to categorize left ventricular geometry type. Compared to non-Hispanic Whites, non-Hispanic Blacks had higher mean left ventricular mass index (54.7 ± 14.6 vs. 47.4 ± 12.2 g/m2.7; P < 0.0001) and prevalence of concentric LVH (45.8% vs. 24.9%). In addition to higher systolic blood pressure and treatment with >3 antihypertensive medications, Black race/ethnicity was independently associated with higher odds of concentric LVH compared to White race/ethnicity (odds ratio: 2.73; 95% confidence interval: 2.02, 3.69). CONCLUSION In a large, diverse cohort with CKD, we found significant differences in left ventricular mass and hypertrophic morphology between non-Hispanic Blacks and Whites. Future studies will evaluate whether higher prevalence of LVH contribute to racial/ethnic disparities in cardiovascular outcomes among CKD patients.

Using a Post-Intubation Checklist and Time Out to Expedite Mechanical Ventilation Monitoring: Observational Study of a Quality Improvement Intervention

BACKGROUND: Delayed mechanical ventilation monitoring may impede recognition of life-threatening acidemia. Coordination of multidisciplinary processes can be improved by using a checklist and time-out procedure. The study objective was to evaluate process-related outcomes after implementation of a post-intubation checklist and time out. METHODS: An observational study of a 24-bed medical ICU in Philadelphia, Pennsylvania, was conducted from January to December 2011. A random sample of mechanically ventilated adults was selected from the pre-intervention (n = 80) and post-intervention (n = 144) periods. The primary outcome was the proportion of subjects with an arterial blood gas (ABG) result within 60 min of mechanical ventilation initiation. Secondary outcomes included rates of respiratory acidosis, moderate-severe acidemia (pH <7.25), checklist initiation, and project sustainability. Chi-square analysis was used to evaluate differences in outcomes between time periods. RESULTS: After the intervention, the proportion of subjects with an ABG result within 60 min increased (56% vs 37%, P = .01), and time to ABG result improved (58 min vs 79 min, P = .004). Adjusting for illness severity, the proportion with an ABG result within 60 min remained significantly higher in the post-intervention period (odds ratio 2.42, 95% CI 1.25–4.68, P = .009). Checklist adherence was higher with ICU intubations than for intubations performed outside the ICU (71% vs 27% checklist initiation rate, P < .001). Transfer from referring institutions (23% checklist initiation rate, P = .006) negatively impacted checklist use. Implementation challenges included frequent stakeholder turnover, undefined process ownership, and lack of real-time performance feedback. CONCLUSIONS: A post-intubation checklist and time out improved the timeliness of mechanical ventilation monitoring through more rapid assessment of arterial blood gases. Implementing this peri-intubation procedure may reduce the risks associated with transitioning to full mechanical ventilatory support. Optimal implementation necessitates strategies to surmount organizational and behavioral barriers to change.

Leveraging electronic health record documentation for Failure Mode and Effects Analysis team identification

Objective: Using Failure Mode and Effects Analysis (FMEA) as an example quality improvement approach, our objective was to evaluate whether secondary use of orders, forms, and notes recorded by the electronic health record (EHR) during daily practice can enhance the accuracy of process maps used to guide improvement. We examined discrepancies between expected and observed activities and individuals involved in a high-risk process and devised diagnostic measures for understanding discrepancies that may be used to inform quality improvement planning. Methods: Inpatient cardiology unit staff developed a process map of discharge from the unit. We matched activities and providers identified on the process map to EHR data. Using four diagnostic measures, we analyzed discrepancies between expectation and observation. Results: EHR data showed that 35% of activities were completed by unexpected providers, including providers from 12 categories not identified as part of the discharge workflow. The EHR also revealed sub-components of process activities not identified on the process map. Additional information from the EHR was used to revise the process map and show differences between expectation and observation. Conclusion: Findings suggest EHR data may reveal gaps in process maps used for quality improvement and identify characteristics about workflow activities that can identify perspectives for inclusion in an FMEA. Organizations with access to EHR data may be able to leverage clinical documentation to enhance process maps used for quality improvement. While focused on FMEA protocols, findings from this study may be applicable to other quality activities that require process maps.

Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization

Motivation Hypertension is a heterogeneous syndrome in need of improved subtyping using phenotypic and genetic measurements with the goal of identifying subtypes of patients who share similar pathophysiologic mechanisms and may respond more uniformly to targeted treatments. Existing machine learning approaches often face challenges in integrating phenotype and genotype information and presenting to clinicians an interpretable model. We aim to provide informed patient stratification based on phenotype and genotype features. Results In this article, we present a hybrid non‐negative matrix factorization (HNMF) method to integrate phenotype and genotype information for patient stratification. HNMF simultaneously approximates the phenotypic and genetic feature matrices using different appropriate loss functions, and generates patient subtypes, phenotypic groups and genetic groups. Unlike previous methods, HNMF approximates phenotypic matrix under Frobenius loss, and genetic matrix under Kullback‐Leibler (KL) loss. We propose an alternating projected gradient method to solve the approximation problem. Simulation shows HNMF converges fast and accurately to the true factor matrices. On a real‐world clinical dataset, we used the patient factor matrix as features and examined the association of these features with indices of cardiac mechanics. We compared HNMF with six different models using phenotype or genotype features alone, with or without NMF, or using joint NMF with only one type of loss We also compared HNMF with 3 recently published methods for integrative clustering analysis, including iClusterBayes, Bayesian joint analysis and JIVE. HNMF significantly outperforms all comparison models. HNMF also reveals intuitive phenotype‐genotype interactions that characterize cardiac abnormalities. Availability and implementation Our code is publicly available on github at https://github.com/yuanluo/hnmf. Supplementary information Supplementary data are available at Bioinformatics online.

A Novel Patient Recruitment Strategy: Patient Selection Directly from the Community through Linkage to Clinical Data

OBJECTIVE This article presents and describes our methods in developing a novel strategy for recruitment of underrepresented, community-based participants, for pragmatic research studies leveraging routinely collected electronic health record (EHR) data. METHODS We designed a new approach for recruiting eligible patients from the community, while also leveraging affiliated health systems to extract clinical data for community participants. The strategy involves methods for data collection, linkage, and tracking. In this workflow, potential participants are identified in the community and surveyed regarding eligibility. These data are then encrypted and deidentified via a hashing algorithm for linkage of the community participant back to a record at a clinical site. The linkage allows for eligibility verification and automated follow-up. Longitudinal data are collected by querying the EHR data and surveying the community participant directly. We discuss this strategy within the context of two national research projects, a clinical trial and an observational cohort study. CONCLUSION The community-based recruitment strategy is a novel, low-touch, clinical trial enrollment method to engage a diverse set of participants. Direct outreach to community participants, while utilizing EHR data for clinical information and follow-up, allows for efficient recruitment and follow-up strategies. This new strategy for recruitment links data reported from community participants to clinical data in the EHR and allows for eligibility verification and automated follow-up. The workflow has the potential to improve recruitment efficiency and engage traditionally underrepresented individuals in research.

Incorporating patient-centered factors into heart failure readmission risk prediction: A mixed-methods study

Background: Capturing and incorporating patient‐centered factors into 30‐day readmission risk prediction after hospitalized heart failure (HF) could improve the modest performance of current models. Methods: Using a mixed‐methods approach, we developed a patient‐centered survey and evaluated the additional predictive utility of the survey compared to a traditional readmission risk model (the Krumholz et al. model). Area under the receiver operating characteristic curve (AUC) and the Hosmer‐Lemeshow goodness‐of‐fit statistic quantified the performance of both models. We measured the amount of model improvement with the addition of patient‐centered factors to the Krumholz et al. model with the integrated discrimination improvement (IDI). In an exploratory analysis, we used hierarchical clustering algorithms to identify groups with similar survey responses and tested for differences between clusters using standard descriptive statistics. Results: From 3/24/2014 to 3/12/2015, 183 patients hospitalized with HF were enrolled from an urban, academic health system and followed for 30 days after discharge. The Krumholz et al. plus patient‐centered factors model had similar‐to‐slightly lower performance (AUC [95%CI]:0.62 [0.52, 0.71]; goodness‐of‐fit P = .10) than the Krumholz et al. model (AUC [95%CI]:0.66 [0.57, 0.76]; goodness‐of‐fit P = .19). The IDI (95%CI) was 0.003 (−0.014,0.020). We identified three patient clusters based on patient‐centered survey responses. The clusters differed with respect to gender, self‐rated health, employment status, and prior hospitalization frequency (all P < .05). Conclusions: The addition of patient‐centered factors did not improve 30‐day readmission model performance. Rather than designing interventions based on predicted readmission risk, tailoring interventions to all patients, based on their characteristics, could inform the design of targeted, readmission reduction strategies.