Current Opinion in Pulmonary Medicine最新文献

Purpose of review: To explore the current applications of artificial intelligence and machine learning in lung transplantation, including outcome prediction, drug dosing, and the potential future uses and risks as the technology continues to evolve.

Recent findings: While the use of artificial intelligence (AI) and machine learning (ML) in lung transplantation is relatively new, several groups have developed models to predict short-term outcomes, such as primary graft dysfunction and time-to-extubation, as well as long-term outcomes related to survival and chronic lung allograft dysfunction. Additionally, drug dosing models for Tacrolimus levels have been designed, demonstrating proof of concept for modelling treatment as a time-series problem.

Summary: The integration of ML models with clinical decision-making has shown promise in improving post-transplant survival and optimizing donor lung utilization. As technology advances, the field will continue to evolve, with enhanced datasets supporting more sophisticated ML models, particularly through real-time monitoring of biological, biochemical, and physiological data.

Purpose of review: Chronic lung allograft dysfunction (CLAD) is a recognized complication after lung transplantation, with a clear definition, although some pitfalls in phenotyping still exist. Recently, new terminologies, such as acute lung allograft dysfunction (ALAD) and baseline lung allograft dysfunction (BLAD) were introduced, but their definitions and real significance are not yet fully established.

Recent findings: Based on the existing literature and ongoing discussions within two expert groups of the Advanced Lung Failure & Transplantation Interdisciplinary Network (ALFTx IDN) of the International Society for Heart and Lung Transplantation (ISHLT), we will describe current definitions, prevalence and outcome of these rather new entities, keeping in mind that a lot of uncertainties still exist.

Summary: ALAD and BLAD will be defined, and the currently accepted outcome of these conditions will be summarized. Existing pitfalls in the phenotyping of CLAD will also be discussed.

Purpose of review: Relative to other lung tumors, pulmonary carcinoid tumors are rare and have unique histopathological and clinical features. The purpose of this review is to summarize the presentation and management of pulmonary carcinoid tumors, with a particular focus on recent clinical trials in the management of advanced and metastatic disease.

Recent findings: Surgical resection remains a central tenet in the management of pulmonary carcinoid tumors that are localized and even those that have locoregional spread. However, in recent years, the treatment of pulmonary carcinoid has expanded to include several systemic hormonal and cytotoxic therapies as well as radiation and endobronchial strategies. The decision to initiate any of these therapies as either primary or adjuvant treatment after resection depends upon several factors including tumor stage, disease burden, patient's functional status, and whether they will tolerate surgery.

Summary: The treatment of pulmonary carcinoid tumors has expanded beyond just surgical resection. Novel regimens of systemic hormonal and cytotoxic therapies as well as radiation and endobronchial intervention should be customized for each patient by a multidisciplinary team of surgeons, medical and radiation oncologists, pulmonologists, and pathologists.

Purpose of review: Evaluation of a candidate's risk profile for lung transplant includes understanding which patient factors can be addressed to minimize transplant risk. Some risk factors can be modified, while others cannot. This review explores current understanding of modifiable and nonmodifiable risk factors for lung transplantation.

Recent findings: Several risk factors for lung transplant can be resolved entirely, thereby minimizing a candidate's transplant risk. Some features cannot be eliminated, though can be optimized to minimize risk. Others cannot be altered and inherently bring risk to transplant, while a subset of nonmodifiable risk factors are considered absolute barriers to transplant.

Summary: Robust research and novel therapies have led to increased ability to modify certain risk factors and thus decrease lung transplant risk. Further studies are needed to better understand how to estimate risk profiles when assessing candidacy and timing for lung transplant.

Purpose of review: The purpose of this review is to provide clinicians a comprehensive overview of the epidemiology, clinical symptoms, radiological features, pathological features, and management recommendations for the vast majority of benign lung tumors. Benign lung tumors are very rare with incidence ranging from 1 in 1000 to 1 in 1 million. Despite not being malignant, certain benign tumors carry significant morbidity and mortality along with diagnostic challenges.

Recent findings: Advancements in genomic sequencing have led to discovery of mutations in particular benign lung tumors. Improved genotyping have aided the diagnosis of certain tumors and the identification of lung lesions with malignant transformation potential. Genomic understanding has also led to targeted therapy for tumors with significant morbidity.

Summary: Despite radiographic and pathologic advances in understanding benign lung tumors, the paucity of cases continues to impact management recommendations and early detection. Global collaborative initiatives in compiling and analyzing cases are essential for stronger evidence based management recommendations.

Purpose of review: This review evaluates the role of artificial intelligence (AI) in diagnosing solitary pulmonary nodules (SPNs), focusing on clinical applications and limitations in pulmonary medicine. It explores AI's utility in imaging and blood/tissue-based diagnostics, emphasizing practical challenges over technical details of deep learning methods.

Recent findings: AI enhances computed tomography (CT)-based computer-aided diagnosis (CAD) through steps like nodule detection, false positive reduction, segmentation, and classification, leveraging convolutional neural networks and machine learning. Segmentation achieves Dice similarity coefficients of 0.70-0.92, while malignancy classification yields areas under the curve of 0.86-0.97. AI-driven blood tests, incorporating RNA sequencing and clinical data, report AUCs up to 0.907 for distinguishing benign from malignant nodules. However, most models lack prospective, multiinstitutional validation, risking overfitting and limited generalizability. The "black box" nature of AI, coupled with overlapping inputs (e.g., nodule size, smoking history) with physician assessments, complicates integration into clinical workflows and precludes standard Bayesian analysis.

Summary: AI shows promise for SPN diagnosis but requires rigorous validation in diverse populations and better clinician training for effective use. Rather than replacing judgment, AI should serve as a second opinion, with its reported performance metrics understood as study-specific, not directly applicable at the bedside due to double-counting issues.

Purpose of review: The management of thoracic empyema is often complicated by diagnostic delays, recurrence, treatment failures and infections with antibiotic resistant bacteria. The emergence of artificial intelligence (AI) in healthcare, particularly in clinical decision support, imaging, and diagnostic microbiology raises great expectations in addressing these challenges.

Recent findings: Machine learning (ML) and AI models have been applied to CT scans and chest X-rays to identify and classify pleural effusions and empyema with greater accuracy. AI-based analyses can identify complex imaging features that are often missed by the human eye, improving diagnostic precision. AI-driven decision-support algorithms could reduce time to diagnosis, improve antibiotic stewardship, and enhance more precise and less invasive surgical therapy, significantly improving clinical outcomes and reducing inpatient hospital stays.

Summary: ML and AI can analyse large datasets and recognize complex patterns and thus have the potential to enhance diagnostic accuracy, preop planning for thoracic surgery, and optimize surgical treatment strategies, antibiotic therapy, antibiotic stewardship, monitoring complications, and long-term patient management outcomes.

Purpose of review: To describe the recent advances in the pathobiology and treatment of mucus hypersecretion in asthma, a critical factor contributing to airway obstruction, inflammation, and impaired lung function.

Recent findings: Significant progress has been made in understanding how mucin protein regulation, mucus viscosity, and adhesion are affected by cytokine-driven inflammation, especially interleukin-13, and defects in ion transport mechanisms. Advances in imaging techniques, such as multidetector computed tomography (MDCT) and hyperpolarized gas MRI, allow for a more precise assessment of mucus plugging and associated ventilation defects. Emerging therapies, including biologicals targeting type-2 (T2) inflammation, and novel mucolytics aimed at modifying mucus properties and secretion, offer promising effects in reducing mucus in severe asthmatics.

Summary: The growing understanding of mucus biology and the development of advanced imaging and therapeutic strategies could significantly improve the management of mucus-related complications in asthma. By targeting mucus characteristics, these findings support future approaches to reduce airway obstruction, enhance lung function, and improve clinical outcomes in patients with severe asthma. A deeper understanding of the glycobiology of mucus is critical to develop new therapies.

Purpose of review: This review addresses the growing understanding that a specific subset of patients with a respiratory disease, including asthma, chronic obstructive pulmonary disease (COPD), or bronchiectasis may have one thing in common: type 2 inflammation. In the era of personalized medicine, we need to refine clinical markers combined with molecular and cellular endotyping to improve patient outcomes.

Recent findings: Recent literature reveals that type 2 markers such as blood eosinophils, fractional exhaled nitric oxide (FeNO), and immunglobulin E (IgE), can provide valuable insights into disease progression, exacerbation risk, and treatment response, but their stability remains to be investigated. Treating asthma and COPD patients with biologics to target IL-4/IL-13, IL-5, and alarmins have shown potential, although efficacy varied. In bronchiectasis, a subset of patients with type 2 inflammation may benefit from corticosteroid therapy, despite broader concerns regarding its use.

Summary: This underscores the importance of improved disease endotyping to better characterize patients who may benefit from targeted therapies. In clinical practice, personalized treatment based on inflammatory profiles has been shown to improve outcomes in heterogeneous lung diseases. Future research needs to focus on validating reliable biomarkers and optimizing clinical trial designs to advance therapeutic strategies in respiratory diseases.

Purpose of review: Adherence to medication is essential for asthma control and reducing the risk of exacerbations. Research has accumulated in recent years on causes and consequences of adherence and effective interventions. This review highlights current advances in adherence research and their potential for clinical practice.

Findings: Optimizing adherence to medication can be achieved through interventions that identify individual barriers and train the care team in offering tailored support. Digital technologies that facilitate remote monitoring, patient-provider communication and care coordination are increasingly being integrated into asthma care.

Summary: Adherence determinants reported cover individual, social and health service-related factors. Age and attitudes toward adherence are crucial determinants. Patients' and caregivers' mental health is relevant for adherence and clinical outcomes, highlighting the importance of integrating this aspect into holistic asthma management. Single-site care arrangements are beneficial for adherence. Tailoring adherence interventions to individual needs, using brief questionnaires to assess barriers and recommending evidence-based strategies to address them, have been found useful and feasible across care settings. Digital technologies such as smart inhaler systems and telemedicine-enhanced care have been shown to be effective in randomized controlled trials, yet implementation research highlights challenges to sustaining support on the long-term.