Development and External Validation of a Machine Learning Model to Predict Restriction from Spirometry.

Background: Though European Respiratory Society and American Thoracic Society (ERS/ATS) guidelines for pulmonary function test (PFT) interpretation recommend the use of the forced vital capacity (FVC) lower limit of normal (LLN) to exclude restriction, recent data suggest that the negative predictive value (NPV) of the FVC LLN is lower than has been accepted, particularly among non-Hispanic Black patients. We sought to develop and externally validate a machine learning (ML) model to predict restriction from spirometry and determine whether its use may improve the accuracy and equity of PFT interpretation.

Methods: We included PFTs with both static and dynamic lung volume measurements for patients between 18 and 80 years of age who were tested at pulmonary diagnostic labs within two health systems.

An Explanatory Mixed-methods Study of "ICU net benefit": Triage and Trajectory for Sepsis and Acute Respiratory Failure.

Rationale: Patients with sepsis and/or acute respiratory failure are at high risk for death or long hospital stays, yet limited evidence exists to guide triage to intensive care units (ICUs) or general medical wards for the majority of these patients who do not initially require life support.

Objectives: To identify factors that influence how hospitals triage patients with capacity-sensitive conditions and those factors that may account for observed ICU relative to ward, or ward relative to ICU, benefits for such patients.

Methods: We conducted an explanatory sequential mixed-methods study.

Integrating Out-of-Pocket Costs Into Shared Decision-Making for Heart Failure With Reduced Ejection Fraction: A Stepped-Wedge Trial (POCKET-COST-HF).

Background: Guideline-directed medical therapy for heart failure (HF) with reduced ejection fraction can entail high out-of-pocket (OOP) costs, prompting concerns about financial toxicity and access. OOP costs are generally unavailable during encounters. This trial assessed the impact of providing patient-specific OOP costs to patients and clinicians.

A Normal Forced Vital Capacity Does Not Reliably or Equitably Exclude Restriction.

Background: European Respiratory Society and American Thoracic Society (ERS/ATS) guidelines for pulmonary function test (PFT) interpretation recommend the use of a normal forced vital capacity (FVC) to exclude restriction. However, this recommendation is based upon a single study from 1999, which was limited to White patients, and used race-specific reference equations that are no longer recommended by ERS/ATS. We sought to reassess the support for this recommendation by calculating the negative predictive value (NPV) of a normal FVC in a diverse, multicenter cohort using race-neutral reference equations.

The Effect of a Post-Bronchodilator FEV/FVC < 0.7 on COPD Diagnosis and Treatment: A Regression Discontinuity Design.

Background: Global Initiative for Chronic Obstructive Lung Disease (GOLD) guidelines recommend the diagnosis of chronic obstructive pulmonary disease (COPD) only in patients with a post-bronchodilator forced expiratory volume in 1 second to forced vital capacity ratio (FEV/FVC) less than 0.7. However the impact of this recommendation on clinical practice is unknown.

A randomized trial of behavioral interventions yielding sustained reductions in distracted driving.

Distracted driving is responsible for nearly 1 million crashes each year in the United States alone, and a major source of driver distraction is handheld phone use. We conducted a randomized, controlled trial to compare the effectiveness of interventions designed to create sustained reductions in handheld use while driving (NCT04587609). Participants were 1,653 consenting Progressive® Snapshot® usage-based auto insurance customers ages 18 to 77 who averaged at least 2 min/h of handheld use while driving in the month prior to study invitation.

Gender Differences in the Diagnosis of Chronic Obstructive Pulmonary Disease after Spirometry.

Background: Women are more likely than men to report delays in the diagnosis of chronic obstructive pulmonary disease (COPD), though the etiology of these delays is unknown. We sought to test whether delays in COPD diagnosis persist after the performance of spirometry.

Methods: We used the Optum Labs Data Warehouse to identify patients 18 years of age and older without a prior diagnosis of COPD, with a post-bronchodilator forced expiratory volume in 1 second (FEV) to forced vital capacity (FVC) ratio of less than 0.

Feedback and Financial Incentives for Reducing Cell Phone Use While Driving: A Randomized Clinical Trial.

Importance: Handheld phone use while driving is a major factor in vehicle crashes. Scalable interventions are needed to encourage drivers not to use their phones.

Objective: To test whether interventions involving social comparison feedback and/or financial incentives can reduce drivers' handheld phone use.

Exploring the impact of missingness on racial disparities in predictive performance of a machine learning model for emergency department triage.

Objective: To investigate how missing data in the patient problem list may impact racial disparities in the predictive performance of a machine learning (ML) model for emergency department (ED) triage.

Materials And Methods: Racial disparities may exist in the missingness of EHR data (eg, systematic differences in access, testing, and/or treatment) that can impact model predictions across racialized patient groups. We use an ML model that predicts patients' risk for adverse events to produce triage-level recommendations, patterned after a clinical decision support tool deployed at multiple EDs.

Assessing treatment effect heterogeneity in the presence of missing effect modifier data in cluster-randomized trials.

Understanding whether and how treatment effects vary across subgroups is crucial to inform clinical practice and recommendations. Accordingly, the assessment of heterogeneous treatment effects based on pre-specified potential effect modifiers has become a common goal in modern randomized trials. However, when one or more potential effect modifiers are missing, complete-case analysis may lead to bias and under-coverage.

Measuring Quality-weighted Hospital-Free Days in Acute Respiratory Failure: A Modified Delphi Study.

Hospital-free days (HFDs), a measure of the number of days alive spent outside the hospital, is increasingly used as an endpoint in studies of patients with acute respiratory failure (ARF) or other critical and serious illnesses. Current approaches to measuring HFDs do not account for decrements in functional status or quality of life that ARF survivors and family members value. To develop an acceptable approach to measure quality-weighted HFDs using patient-reported outcomes.

How do surrogates make treatment decisions for patients with dementia: An experimental survey study.

Despite the growing need for surrogate decision-making for older adults, little is known about how surrogates make decisions and whether advance directives would change decision-making. We conducted a nationally representative experimental survey that cross-randomized cognitive impairment, gender, and characteristics of advance care planning among hospitalized older adults through a series of vignettes. Our study yielded three main findings: first, respondents were much less likely to recommend life-sustaining treatments for patients with dementia, especially after personal exposure.

Default Palliative Care Consultation for Seriously Ill Hospitalized Patients: A Pragmatic Cluster Randomized Trial.

Importance: Increasing inpatient palliative care delivery is prioritized, but large-scale, experimental evidence of its effectiveness is lacking.

Objective: To determine whether ordering palliative care consultation by default for seriously ill hospitalized patients without requiring greater palliative care staffing increased consultations and improved outcomes.

Design, Setting, And Participants: A pragmatic, stepped-wedge, cluster randomized trial was conducted among patients 65 years or older with advanced chronic obstructive pulmonary disease, dementia, or kidney failure admitted from March 21, 2016, through November 14, 2018, to 11 US hospitals.

Integrating Cost into Shared Decision-Making for Heart Failure with Reduced Ejection Fraction (POCKET-COST-HF): A Trial Providing Out-of-Pocket Costs for Heart Failure Medications during Clinical Encounters.

Background: Evidence-based medical therapy for heart failure with reduced ejection fraction (HFrEF) often entails substantial out-of-pocket costs that can vary appreciably between patients. This has raised concerns regarding financial toxicity, equity, and adherence to medical therapy. In spite of these concerns, cost discussions in the HFrEF population appear to be rare, partly because out-of-pocket costs are generally unavailable during clinical encounters.

A mixed model approach to estimate the survivor average causal effect in cluster-randomized trials.

In many medical studies, the outcome measure (such as quality of life, QOL) for some study participants becomes informatively truncated (censored, missing, or unobserved) due to death or other forms of dropout, creating a nonignorable missing data problem. In such cases, the use of a composite outcome or imputation methods that fill in unmeasurable QOL values for those who died rely on strong and untestable assumptions and may be conceptually unappealing to certain stakeholders when estimating a treatment effect. The survivor average causal effect (SACE) is an alternative causal estimand that surmounts some of these issues.

A vignette-based evaluation of ChatGPT's ability to provide appropriate and equitable medical advice across care contexts.

ChatGPT is a large language model trained on text corpora and reinforced with human supervision. Because ChatGPT can provide human-like responses to complex questions, it could become an easily accessible source of medical advice for patients. However, its ability to answer medical questions appropriately and equitably remains unknown.

Decision Making for Patients With Severe Dementia Versus Normal Cognition Near the End of Life.

Background And Objectives: The clinical progression of severe dementia frequently leads to situations where surrogate decision makers must quickly make choices about potentially burdensome treatments that offer limited clinical benefit. We examined whether the number of decision makers and their access to advance directives were related to treatment choice for patients with severe dementia in comparison to those with normal cognition.

Research Design And Methods: We retrospectively linked survey responses about end-of-life treatment decisions to Medicare claims for Health and Retirement Study respondents dying between 2002 and 2015 whose next-of-kin reported a need for surrogate decision making.