Chest
-
Predictive analytic models leveraging machine learning methods increasingly have become vital to health care organizations hoping to improve clinical outcomes and the efficiency of care delivery for all patients. Unfortunately, predictive models could harm populations that have experienced interpersonal, institutional, and structural biases. Models learn from historically collected data that could be biased. ⋯ This strategy follows the lifecycle of machine learning models in health care, namely, identifying the clinical problem, model design, data collection, model training, model validation, model deployment, and monitoring after deployment. To illustrate this approach, we use a hypothetical case of a health system developing and deploying a machine learning model to predict the risk of mortality in 6 months for patients admitted to the hospital to target a hospital's delivery of palliative care services to those with the highest mortality risk. The core ethical concepts of equity and transparency guide our proposed framework to help ensure the safe and effective use of predictive algorithms in health care to help everyone achieve their best possible health.
-
Patients with non-small cell lung cancer (NSCLC) and preexisting interstitial lung disease (ILD) are often excluded from clinical trials of immune checkpoint inhibitors (ICIs), leaving a gap in knowledge. ⋯ Programmed cell death protein 1/programmed cell death ligand 1 inhibitors had favorable efficacy in NSCLC with preexisting ILD. CIP is frequent in patients with preexisting ILD who receive ICI therapy but is often mild and easily manageable. Clinicians should be cautious when using ICIs in patients with preexisting ILD.
-
Lung cancer screening is slowly but steadily entering the realm of preventive health maintenance. Standardization of reporting of positive findings identified on screening low-dose CT (LDCT) scans, specifically lung nodules, is a key element of high-quality lung cancer screening. The American College of Radiology developed the Lung CT Screening Reporting and Data System (Lung-RADS) system for this purpose. ⋯ In contrast to the highly structured reporting for nodules, category S findings are reported at the discretion of individual readers, with the potential for high variability of reporting. Incidental findings on lung cancer screening studies are common, may trigger unwarranted evaluation with potential harm and cost, and may precipitate patient distress. In response to these concerns, our multidisciplinary lung cancer screening program developed a structured system for standardized reporting of category S findings based on recommendations of the American College of Radiology and relevant specialty societies.
-
The characteristics and outcomes of adult patients with respiratory syncytial virus (RSV) infection who require ICU admission are poorly defined. Although several studies in adults with RSV infection have been published in recent years, they did not focus specifically on patients with critical illness. ⋯ Adult patients in the ICU with RSV infection differ from adult patients in the ICU with influenza in terms of comorbidities and characteristics at diagnosis. RSV infection was associated with high in-hospital mortality, approaching 25%. In multivariate analysis, RSV infection was associated with a similar odds of in-hospital death compared with influenza infection.
-
Brazil has been disproportionately affected by COVID-19, placing a high burden on ICUs. ⋯ During the COVID-19 pandemic, ICU HCPs in Brazil experienced substantial resource shortages, health care disparities between regions, changes in end-of-life care associated with resource shortages, and high proportions of burnout.