Brooks T. Kuhn

Balloon dilation atrial septostomy for advanced pulmonary hypertension in patients on prostanoid therapy

Background: Prostanoid therapy improves quality of life and may increase survival in patients with advanced pulmonary hypertension (PH). Balloon dilated atrial septostomy (BDAS) can palliate or bridge to transplantation for patients resistant to medical therapy. The safety and efficacy of BDAS in the prostanoid era has not previously been reported. Methods: All patients had progressive symptoms despite prostanoid therapy at the time of their first BDAS. Sixteen patients who underwent a total of 23 septostomies between 2004 and 2014 were included in this retrospective case series. Results: Patients were aged 47.6 years ± 11.3 with 12/16 women. Etiologies included idiopathic (7), methamphetamine (6), scleroderma (1), and anorexigen (2). One patient died within 24 hr post‐procedure. Thirty‐day and 1‐year survival were 75% and 64%, respectively. Six of the septostomies were revisions, including two which were ultimately stented. Three subjects were successfully bridged to transplant. Pulmonary capillary wedge pressure (PCWP) increased from a mean of 13 to 17 mm Hg, cardiac index increased from 2.1 to 2.4 L/min/m2, and arterial saturation decreased from 90.7 ± 4.3 to 82.5 ± 5.6%. All non‐survivors at 30 days were male and had higher baseline serum creatinine, mean RAP, right ventricular end diastolic pressure (RVEDP), and left ventricle (LV) filling pressures, and lower right ventricle (RV) ejection fraction. Mortality was associated with unchanged post‐septostomy cardiac output despite an increase in left ventricular end diastolic pressure (LVEDP). Conclusions: BDAS may be an alternate therapy for select PH patients who have symptomatic progression despite prostanoid therapy. Survival is comparable to prior reports of BDAS in the pre‐prostanoid era.

Development and Validation of a Multi-Algorithm Analytic Platform to Detect Off-Target Mechanical Ventilation

Healthcare-specific analytic software is needed to process the large volumes of streaming physiologic waveform data increasingly available from life support devices such as mechanical ventilators. Detection of clinically relevant events from these data streams will advance understanding of critical illness, enable real-time clinical decision support, and improve both clinical outcomes and patient experience. We used mechanical ventilation waveform data (VWD) as a use case to address broader issues of data access and analysis including discrimination between true events and waveform artifacts. We developed an open source data acquisition platform to acquire VWD, and a modular, multi-algorithm analytic platform (ventMAP) to enable automated detection of off-target ventilation (OTV) delivery in critically-ill patients. We tested the hypothesis that use of artifact correction logic would improve the specificity of clinical event detection without compromising sensitivity. We showed that ventMAP could accurately detect harmful forms of OTV including excessive tidal volumes and common forms of patient-ventilator asynchrony, and that artifact correction significantly improved the specificity of event detection without decreasing sensitivity. Our multi-disciplinary approach has enabled automated analysis of high-volume streaming patient waveform data for clinical and translational research, and will advance the study and management of critically ill patients requiring mechanical ventilation.

Paradigms in chronic obstructive pulmonary disease: phenotypes, immunobiology, and therapy with a focus on vascular disease

Chronic obstructive pulmonary disease (COPD) is a complex and heterogeneous syndrome that represents a major global health burden. COPD phenotypes have recently emerged based on large cohort studies addressing the need to better characterize the syndrome. Though comprehensive phenotyping is still at an early stage, factors such as ethnicity and radiographic, serum, and exhaled breath biomarkers have shown promise. COPD is also an immunological disease where innate and adaptive immune responses to the environment and tobacco smoke are altered. The frequent overlap between COPD and other systemic diseases, such as cardiovascular disease, has influenced COPD therapy, and treatments for both conditions may lead to improved patient outcomes. Here, we discuss current paradigms that center on improving the definition of COPD, understanding the immunological overlap between COPD and vascular inflammation, and the treatment of COPD—with a focus on comorbid cardiovascular disease.

Management of Mechanical Ventilation in Decompensated Heart Failure

Mechanical ventilation (MV) is a life-saving intervention for respiratory failure, including decompensated congestive heart failure. MV can reduce ventricular preload and afterload, decrease extra-vascular lung water, and decrease the work of breathing in heart failure. The advantages of positive pressure ventilation must be balanced with potential harm from MV: volutrauma, hyperoxia-induced injury, and difficulty assessing readiness for liberation. In this review, we will focus on cardiac, pulmonary, and broader effects of MV on patients with decompensated HF, focusing on practical considerations for management and supporting evidence.

Creation of a Robust and Generalizable Machine Learning Classifier for Patient Ventilator Asynchrony

BACKGROUNDnAs healthcare increasingly digitizes, streaming waveform data is being made available from an variety of sources, but there still remains a paucity of performant clinical decision support systems. For example, in the intensive care unit (ICU) existing automated alarm systems typically rely on simple thresholding that result in frequent false positives. Recurrent false positive alerts create distrust of alarm mechanisms that can be directly detrimental to patient health. To improve patient care in the ICU, we need alert systems that are both pervasive, and accurate so as to be informative and trusted by providers.nnnOBJECTIVEnWe aimed to develop a machine learning-based classifier to detect abnormal waveform events using the use case of mechanical ventilation waveform analysis, and the detection of harmful forms of ventilation delivery to patients. We specifically focused on detecting injurious subtypes of patient-ventilator asynchrony (PVA).nnnMETHODSnUsing a dataset of breaths recorded from 35 different patients, we used machine learning to create computational models to automatically detect, and classify two types of injurious PVA, double trigger asynchrony (DTA), breath stacking asynchrony (BSA). We examined the use of synthetic minority over-sampling technique (SMOTE) to overcome class imbalance problems, varied methods for feature selection, and use of ensemble methods to optimize the performance of our model.nnnRESULTSnWe created an ensemble classifier that is able to accurately detect DTA at a sensitivity/specificity of 0.960/0.975, BSA at sensitivity/specificity of 0.944/0.987, and non-PVA events at sensitivity/specificity of .967/.980.nnnCONCLUSIONSnOur results suggest that it is possible to create a high-performing machine learning-based model for detecting PVA in mechanical ventilator waveform data in spite of both intra-patient, and inter-patient variability in waveform patterns, and the presence of clinical artifacts like cough and suction procedures. Our work highlights the importance of addressing class imbalance in clinical data sets, and the combined use of statistical methods and expert knowledge in feature selection.

Development of a research-oriented system for collecting mechanical ventilator waveform data

Lack of access to high-frequency, high-volume patient-derived data, such as mechanical ventilator waveform data, has limited the secondary use of these data for research, quality improvement, and decision support. Existing methods for collecting these data are obtrusive, require high levels of technical expertise, and are often cost-prohibitive, limiting their use and scalability for research applications. We describe here the development of an unobtrusive, open-source, scalable, and user-friendly architecture for collecting, transmitting, and storing mechanical ventilator waveform data that is generalizable to other patient care devices. The system implements a software framework that automates and enforces end-to-end data collection and transmission. A web-based data management application facilitates nontechnical end users abilities to manage data acquisition devices, mitigates data loss and misattribution, and automates data storage. Using this integrated system, we have been able to collect ventilator waveform data fromu2009>450 patients as part of an ongoing clinical study.

Cosmetic Talc–Related Pulmonary Granulomatosis

Inhalation of cosmetic talc can lead to pulmonary foreign-body granulomatosis, though fewer than 10 cases of inhaled cosmetic talc–related pulmonary granulomatosis have been reported in adults. We report the case of a 64-year-old man with diffuse, bilateral pulmonary nodules and ground glass opacities associated with chronic inhalation of cosmetic talc. Transbronchial biopsy showed peribronchiolar foreign-body granulomas. After cessation of talc exposure, the patient demonstrated clinical and radiographic improvement without the use of corticosteroids. This case demonstrates that a conservative approach with cessation of exposure alone, without the use of corticosteroids, can be an effective therapy in cosmetic talc–related pulmonary granulomatosis.