ICU outcomes following a Central Line Associated Blood Stream Infections (CLABSI) reduction quality improvement project.

BACKGROUND: Central Line Associated Blood Stream Infections (CLABSI) are significant complications for hospitalized patients. Several different approaches have been used to reduce CLABSI. OBJECTIVE: This study aimed to (1) describe a systematic approach used to analyze and reduce CLABSI rates in a surgical ICU (SICU) at a quaternary care medical facility (CLABSI reduction bundle) and (2) examine the association of the bundle on CLABSI rates in the SICU, compared to six unexposed health system ICUs. METHODS: Retrospective analysis of 14,022 adult patients with > 0 central line days within a single health system in the southeastern United States. The CLABSI intervention bundle was created and implemented in July 2021. Single and multiple interrupted time series analyses were performed to assess the impact of the CLABSI bundle on CLABSI rate in SICU (compared to control ICUs) pre- and post-intervention. Secondary analyses examined the association of the bundle with ICU mortality and length of stay. RESULTS: The CLABSI bundle was associated with a significant immediate effect in reducing the CLABSI rate in the SICU compared with control ICUs. There was no significant change in the slope of CLABSI rate post-intervention, compared to control ICUs. There was no significant association of the CLABSI reduction bundle on ICU length of stay or mortality in the SICU. CONCLUSION: The CLABSI bundle was associated with an immediate reduction in CLABSI incidence in the SICU compared to unexposed ICUs. A simple, bundled intervention can be effective in reducing CLABSI incidence in a surgical ICU population.

When in the intensive care unit (ICU), many patients have different lines, drains, catheters, and other devices inserted into the body to help care for them. Each device has a risk of getting infected and can make a patient's hospital stay more complicated, longer, and require more intense treatments. One ICU at our health system performed a long-term quality improvement intervention to reduce and prevent these kinds of infections. Over the course of 4­6 months, multiple changes to daily patient care related to central lines were implemented. Our study examined the effects of this QI intervention. Using data from our ICU database, we determined that these changes decreased the number infections immediately after implementing them, but not over the long term. They also did not impact how long patients stayed in the hospital nor their risk of dying (mortality). These new protocols offer a way to reduce infections, and more work needs to be done to continue reducing them for patients in the ICU.

A Clinician's Guide to Understanding Bias in Critical Clinical Prediction Models.

This narrative review focuses on the role of clinical prediction models in supporting informed decision-making in critical care, emphasizing their 2 forms: traditional scores and artificial intelligence (AI)-based models. Acknowledging the potential for both types to embed biases, the authors underscore the importance of critical appraisal to increase our trust in models. The authors outline recommendations and critical care examples to manage risk of bias in AI models. The authors advocate for enhanced interdisciplinary training for clinicians, who are encouraged to explore various resources (books, journals, news Web sites, and social media) and events (Datathons) to deepen their understanding of risk of bias.

Value-Based Care for Chest Physicians.

Value-based care aims to improve the health outcomes of patients, eliminate waste and unwarranted clinical variation, and reduce the total cost of care. Professional medical societies have put forward guidelines to raise awareness on unproven practice patterns (Choosing Wisely Campaign), and payers have sought to replace the traditional fee-for-service payment models with value-based contracts that share financial gains or losses based on achieving high-quality outcomes and lowering the cost of care. Regardless of whether their practices are engaged in value-based arrangements, chest physicians should seek understanding of these principles, participate in designing and implementing practical and impactful high-value initiatives in their practices, and have a national voice on the path forward.

Application of Machine Learning in Pulmonary Function Assessment Where Are We Now and Where Are We Going?

Analysis of pulmonary function tests (PFTs) is an area where machine learning (ML) may benefit clinicians, researchers, and the patients. PFT measures spirometry, lung volumes, and carbon monoxide diffusion capacity of the lung (DLCO). The results are usually interpreted by the clinicians using discrete numeric data according to published guidelines. PFT interpretations by clinicians, however, are known to have inter-rater variability and the inaccuracy can impact patient care. This variability may be caused by unfamiliarity of the guidelines, lack of training, inadequate understanding of lung physiology, or simply mental lapses. A rules-based automated interpretation system can recapitulate expert's pattern recognition capability and decrease errors. ML can also be used to analyze continuous data or the graphics, including the flow-volume loop, the DLCO and the nitrogen washout curves. These analyses can discover novel physiological biomarkers. In the era of wearables and telehealth, particularly with the COVID-19 pandemic restricting PFTs to be done in the clinical laboratories, ML can also be used to combine mobile spirometry results with an individual's clinical profile to deliver precision medicine. There are, however, hurdles in the development and commercialization of the ML-assisted PFT interpretation programs, including the need for high quality representative data, the existence of different formats for data acquisition and sharing in PFT software by different vendors, and the need for collaboration amongst clinicians, biomedical engineers, and information technologists. Hurdles notwithstanding, the new developments would represent significant advances that could be the future of PFT, the oldest test still in use in clinical medicine.