Faculty Bibliography

BACKGROUND:Potential of the electronic health records (EHR) and clinical decision support (CDS) systems to improve the practice of medicine has been tempered by poor design and the resulting burden they place on providers. CDS is rarely tested in the real clinical environment. As a result, many tools are hard to use, placing strain on providers and resulting in low adoption rates. The existing CDS usability literature relies primarily on expert opinion and provider feedback via survey. This is the first study to evaluate CDS usability and the provider-computer-patient interaction with complex CDS in the real clinical environment. OBJECTIVE:This study aimed to further understand the barriers and facilitators of meaningful CDS usage within a real clinical context. METHODS:This qualitative observational study was conducted with 3 primary care providers during 6 patient care sessions. In patients with the chief complaint of sore throat, a CDS tool built with the Centor Score was used to stratify the risk of group A Streptococcus pharyngitis. In patients with a chief complaint of cough or upper respiratory tract infection, a CDS tool built with the Heckerling Rule was used to stratify the risk of pneumonia. During usability testing, all human-computer interactions, including audio and continuous screen capture, were recorded using the Camtasia software. Participants' comments and interactions with the tool during clinical sessions and participant comments during a postsession brief interview were placed into coding categories and analyzed for generalizable themes. RESULTS:In the 6 encounters observed, primary care providers toggled between addressing either the computer or the patient during the visit. Minimal time was spent listening to the patient without engaging the EHR. Participants mostly used the CDS tool with the patient, asking questions to populate the calculator and discussing the results of the risk assessment; they reported the ability to do this as the major benefit of the tool. All providers were interrupted during their use of the CDS tool by the need to refer to other sections of the chart. In half of the visits, patients' clinical symptoms challenged the applicability of the tool to calculate the risk of bacterial infection. Primary care providers rarely used the incorporated incentives for CDS usage, including progress notes and patient instructions. CONCLUSIONS:Live usability testing of these CDS tools generated insights about their role in the patient-provider interaction. CDS may contribute to the interaction by being simultaneously viewed by the provider and patient. CDS can improve usability and lessen the strain it places on providers by being short, flexible, and customizable to unique provider workflow. A useful component of CDS is being as widely applicable as possible and ensuring that its functions represent the fastest way to perform a particular task.

Costly signaling theory was developed in both economics and biology and has been used to explain a wide range of phenomena. However, the theory's prediction that signal cost can enforce information quality in the design of new communication systems has never been put to an empirical test. Here we show that imposing time costs on reporting extreme scores can improve crowd wisdom in a previously cost-free rating system. We developed an online game where individuals interacted repeatedly with simulated services and rated them for satisfaction. We associated ratings with differential time costs by endowing the graphical user interface that solicited ratings from the users with "physics," including an initial (default) slider position and friction. When ratings were not associated with differential cost (all scores from 0 to 100 could be given by an equally low-cost click on the screen), scores correlated only weakly with objective service quality. However, introducing differential time costs, proportional to the deviation from the mean score, improved correlations between subjective rating scores and objective service performance and lowered the sample size required for obtaining reliable, averaged crowd estimates. Boosting time costs for reporting extreme scores further facilitated the detection of top performances. Thus, human collective online behavior, which is typically cost-free, can be made more informative by applying costly signaling via the virtual physics of rating devices.

INTRODUCTION/BACKGROUND:Obesity is a major public health challenge and exacerbates economic disparities through employment discrimination and increased personal health expenditures. Financial incentives for weight management may intensify individuals' utilisation of evidence-based behavioural strategies while addressing obesity-related economic disparities in low-income populations. Trials have focused on testing incentives contingent on achieving weight loss outcomes. However, based on social cognitive and self-determination theories, providing incentives for achieving intermediate behavioural goals may be more sustainable than incentivising outcomes if they enhance an individual's skills and self-efficacy for maintaining long-term weight loss. The objective of this paper is to describe the rationale and design of the Financial Incentives foR Weight Reduction study, a randomised controlled trial to test the comparative effectiveness and cost-effectiveness of two financial incentive strategies for weight loss (goal directed vs outcome based) among low-income adults with obesity, as well as compared with the provision of health behaviour change resources alone. METHODS AND ANALYSIS/UNASSIGNED:, from three primary care clinics serving residents of socioeconomically disadvantaged neighbourhoods in New York City and Los Angeles. All participants receive a 1-year commercial weight loss programme membership, self-monitoring tools (bathroom scale, food journal and Fitbit Alta HR), health education and monthly check-in visits. In addition to these resources, those in the two intervention groups can earn up to $750 over 6 months for: (1) participating in an intensive weight management programme, self-monitoring weight and diet and meeting physical activity guidelines (goal-directed arm); or (2) a ≥1.5% to ≥5% reduction in baseline weight (outcome-based arm). To maximise incentive efficacy, we incorporate concepts from behavioural economics, including immediacy of payments and framing feedback to elicit regret aversion. We will use generalised mixed effect models for repeated measures to examine intervention effects on weight at 6, 9 and 12 months. ETHICS AND DISSEMINATION/UNASSIGNED:Human research protection committees at New York University School of Medicine, University of California Los Angeles (UCLA) David Geffen School of Medicine and Olive-View-UCLA Medical Center granted ethics approval. We will disseminate the results of this research via peer-reviewed publications, conference presentations and meetings with stakeholders. TRIAL REGISTRATION NUMBER/BACKGROUND:NCT03157713.

OBJECTIVE:The aim of this study was to identify and test whether AKI sub-phenotypes have prognostic and therapeutic implications. METHODS:First, latent class analysis methodology was applied independently in two critically ill populations (Discovery: n=794 and Replication: n=425) with AKI. Second, a parsimonious classification model was developed to identify AKI sub-phenotypes. Third, the classification model was applied to patients with AKI in the Vasopressin in Septic Shock (VASST: n=271) clinical trial and differences in treatment response were determined. In all three populations, AKI was defined using serum creatinine and urine output. RESULTS:A two-sub-phenotype LCA model had the best fit in both the Discovery (p = 0.004) and Replication (p= 0.004) AKI groups. The risk of 7-day renal non-recovery and 28-day mortality was greater with AKI sub-phenotype 2 (AKI-SP2) relative to AKI sub-phenotype 1 (AKI-SP1). The AKI sub-phenotypes discriminated risk for poor clinical outcomes better than the Kidney Disease Improving Global Outcomes (KDIGO) Stages of AKI. A three-variable model that included markers of endothelial dysfunction and inflammation accurately determined sub-phenotype membership (C-statistic 0.92). In VASST, vasopressin compared to norepinephrine was associated with improved 90-day mortality in AKI-SP1 (46% vs 27%, respectively; p=0.02), but no significant difference in AKI-SP2 (49% vs 45%, respectively; p=0.54) and the p-value for interaction was 0.05. CONCLUSION/CONCLUSIONS:This analysis identified two molecularly distinct AKI sub-phenotypes with different clinical outcomes and response to vasopressin therapy. Identification of AKI sub-phenotypes could improve risk prognostication and may be useful for predictive enrichment in clinical trials.

BACKGROUND:While an expanding armamentarium of pharmacologic therapies has contributed to improved outcomes among adults with heart failure (HF) over the past two decades, this has also been accompanied by an increase in the number of medications taken by adults with HF. The use of at least 10 medications, defined as hyperpolypharmacy, is particularly notable given its association with adverse outcomes. We aimed to assess the prevalence and identify determinants of hyperpolypharmacy among adults with HF. METHODS:We studied adults aged ≥50 years with self-reported HF from the National Health And Nutrition Examination Survey (NHANES) in 2003-2014. We calculated weighted means and percentages to describe patient characteristics. We conducted a multivariable Poisson regression analysis to identify factors independently associated with hyperpolypharmacy; we adjusted for survey sampling, socio-demographics, comorbidity, geriatric conditions, and health care utilization. We examined 947 participants, representing 4.6 million adults with HF. RESULTS:The prevalence of hyperpolypharmacy was 26%. In a multivariable regression analysis, comorbidity count, ≥10 ambulatory contacts, and ≥ 3 hospitalizations were independently associated with hyperpolypharmacy. Interestingly, functional impairment and cognitive impairment were not independently associated with hyperpolypharmacy; while low annual household income and low educational status were each associated with an almost 2-fold increase in hyperpolypharmacy. CONCLUSION:Hyperpolypharmacy is a common condition among adults with HF. We additionally found that low household income and low educational status are independently associated with hyperpolypharmacy, suggesting that non-medical factors may be contributing to this potentially harmful condition.

AIMS:Coronary artery calcium (CAC) is the strongest predictor of cardiovascular disease (CVD), yet is also associated with chronic non-CVD such as cancer. We performed this analysis in order to describe the association of CAC with CVD vs. cancer mortality. METHODS AND RESULTS:The CAC Consortium is comprised of 66 636 scans performed in asymptomatic patients without known CVD. The mean age was 54 ± 11 years and 67% of participants were men. Cause of death was ascertained from death certificates. The association of CAC with cause-specific mortality was calculated using Fine and Gray sub-distribution hazard ratio (SHR) models, which account for competing causes of death. There were 3158 deaths over a median 12 ± 4 years follow-up (37% cancer and 32% CVD). Cancer was the leading cause of death when CAC = 0 (50%) with CVD overtaking cancer when baseline CAC >300. Compared to participants with CAC = 0, the SHR for CVD mortality was 1.44 [95% confidence interval (CI) 1.14-1.81], 2.26 (95% CI 1.76-2.90), and 3.68 (95% CI 2.90-4.67) for patients with CAC 1-99, 100-299, and ≥300, and the SHR for cancer was 1.04 (95% CI 0.88-1.23), 1.19 (95% CI 0.98-1.46), and 1.30 (95% CI 1.07-1.58). CONCLUSION:Cancer was the leading cause of death for patients with baseline CAC = 0, whereas CVD overtook cancer above a threshold of CAC >300. These results argue for a focused approach for patients at the extremes of CAC scoring while suggesting that combined CVD and cancer primary prevention strategies for patients with intermediate CAC scores may significantly decrease mortality from the two leading causes of death.

PURPOSE/OBJECTIVE:Peptide receptor radionuclide therapy (PRRT) with the radiolabeled somatostatin analogue [Lutetium-177-DOTA0-Tyr3]octreotate (177Lu-DOTATATE) is widely applied for inoperable metastatic small intestinal and nonfunctioning pancreatic neuroendocrine tumors (pNETs). The aim of this study is to describe the safety and efficacy of the treatment of functioning pNETs. METHODS:Patients were treated with up to four cycles of 177Lu-DOTATATE with an intended dose of 7.4 Gbq per cycle. Radiological (Response Evaluation Criteria in Solid Tumors 1.1), symptomatic, and biochemical response were analyzed retrospectively for all patients with a functioning pNET (insulinoma, gastrinoma, VIPoma, and glucagonoma) treated with 177Lu-DOTATATE. Quality of life (QOL) was assessed with the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-Core Module questionnaire. RESULTS:Thirty-four patients with a metastatic functioning pNET (European Neuroendocrine Tumor Society grade 1 or 2) were included: 14 insulinomas, 5 VIPomas, 7 gastrinomas, and 8 glucagonomas. Subacute hematological toxicity, grade 3 or 4 occurred in 4 patients (12%) and a hormonal crisis in 3 patients (9%). PRRT resulted in partial or complete response in 59% of patients and the disease control rate was 78% in patients with baseline progression. 71% of patients with uncontrolled symptoms had a reduction of symptoms and a more than 80% decrease of circulating hormone levels was measured during follow-up. After PRRT, median progression-free survival was 18.1 months (interquartile range: 3.3 to 35.7) with a concurrent increase in QOL. CONCLUSION/CONCLUSIONS:Treatment with 177Lu-DOTATATE is a safe and effective therapy resulting in radiological, symptomatic and biochemical response in a high percentage of patients with metastatic functioning pNETs. Hormonal crises occur relatively frequent and preventive therapy should be considered before and/or during PRRT.