Classification of usual interstitial pneumonia in patients with interstitial lung disease: assessment of a machine learning approach using high-dimensional transcriptional data

Interpretable mortality prediction model for ICU patients with pneumonia: using shapley additive explanation method

BACKGROUND

Pneumonia, a leading cause of morbidity and mortality worldwide, often necessitates Intensive Care Unit (ICU) admission. Accurate prediction of pneumonia mortality is crucial for tailored prevention and treatment plans. However, existing mortality prediction models face limited adoption in clinical practice due to their lack of interpretability.

OBJECTIVE

This study aimed to develop an interpretable model for predicting pneumonia mortality in ICUs. Leveraging the Shapley Additive Explanation (SHAP) method, we sought to elucidate the Extreme Gradient Boosting (XGBoost) model and identify prognostic factors for pneumonia.

METHODS

Conducted as a retrospective cohort study, we utilized electronic health records from the eICU-CRD (2014-2015) for all adult pneumonia patients. The first 24 h of each ICU admission records were considered, with 70% of the dataset allocated for model training and 30% for validation. The XGBoost model was employed, and performance was assessed using the area under the receiver operating characteristic curve (AUC). The SHAP method provided insights into the XGBoost model.

RESULTS

Among 10,962 pneumonia patients, in-hospital mortality was 16.33%. The XGBoost model demonstrated superior predictive performance (AUC: 0.778 ± 0.016)) compared to traditional scoring systems and other machine learning method, which achieved an improvement of 10% points. SHAP analysis identified Aspartate Aminotransferase (AST) as the most crucial predictor.

CONCLUSIONS

Interpretable predictive models enhance mortality risk assessment for pneumonia patients in the ICU, fostering transparency. AST emerged as the foremost predictor, followed by patient age, albumin, BMI et al. These insights, rooted in strong correlations with mortality, facilitate improved clinical decision-making and resource allocation.

Multidisciplinary Approach to the Diagnosis of Idiopathic Interstitial Pneumonias: Focus on the Pathologist's Key Role

Idiopathic Interstitial Pneumonias (IIPs) are a heterogeneous group of the broader category of Interstitial Lung Diseases (ILDs), pathologically characterized by the distortion of lung parenchyma by interstitial inflammation and/or fibrosis. The American Thoracic Society (ATS)/European Respiratory Society (ERS) international multidisciplinary consensus classification of the IIPs was published in 2002 and then updated in 2013, with the authors emphasizing the need for a multidisciplinary approach to the diagnosis of IIPs. The histological evaluation of IIPs is challenging, and different types of IIPs are classically associated with specific histopathological patterns. However, morphological overlaps can be observed, and the same histopathological features can be seen in totally different clinical settings. Therefore, the pathologist's aim is to recognize the pathologic-morphologic pattern of disease in this clinical setting, and only after multi-disciplinary evaluation, if there is concordance between clinical and radiological findings, a definitive diagnosis of specific IIP can be established, allowing the optimal clinical-therapeutic management of the patient.

Pulmonary Pathology Society Survey on Practice Approaches in the Histologic Diagnosis of Fibrotic Interstitial Lung Disease: Consensus and Opportunities

CONTEXT.—

The pathologic diagnosis of usual interstitial pneumonia (UIP) remains a challenging area, and application of histologic UIP guidelines has proved difficult.

OBJECTIVE.—

To understand current practice approaches by pulmonary pathologists for the histologic diagnosis of UIP and other fibrotic interstitial lung diseases (ILDs).

DESIGN.—

The Pulmonary Pathology Society (PPS) ILD Working Group developed and sent a 5-part survey on fibrotic ILD electronically to the PPS membership.

RESULTS.—

One hundred sixty-one completed surveys were analyzed. Of the respondents, 89% reported using published histologic features in clinical guidelines for idiopathic pulmonary fibrosis (IPF) in their pathologic diagnosis; however, there was variability in reporting terminology, quantity and quality of histologic features, and the use of guideline categorization. Respondents were very likely to have access to pulmonary pathology colleagues (79%), pulmonologists (98%), and radiologists (94%) to discuss cases. Half of respondents reported they may alter their pathologic diagnosis based on additional clinical and radiologic history if it is pertinent. Airway-centered fibrosis, granulomas, and types of inflammatory infiltrates were considered important, but there was poor agreement on how these features are defined.

CONCLUSIONS.—

There is significant consensus among the PPS membership on the importance of histologic guidelines/features of UIP. There are unmet needs for (1) consensus and standardization of diagnostic terminology and incorporation of recommended histopathologic categories from the clinical IPF guidelines into pathology reports, (2) agreement on how to incorporate into the report relevant clinical and radiographic information, and (3) defining the quantity and quality of features needed to suggest alternative diagnoses.

Diagnosis of interstitial lung diseases: from Averill A. Liebow to artificial intelligence

Histopathologic criteria of usual interstitial pneumonia (UIP)/idiopathic pulmonary fibrosis (IPF) were defined over the years and endorsed by leading organizations decades after Dr. Averill A. Liebow first coined the term UIP in the 1960s as a distinct pathologic pattern of fibrotic interstitial lung disease. Novel technology and recent research on interstitial lung diseases with genetic component shed light on molecular pathogenesis of UIP/IPF. Two antifibrotic agents introduced in the mid-2010s opened a new era of therapeutic approaches to UIP/IPF, albeit contentious issues regarding their efficacy, side effects, and costs. Recently, the concept of progressive pulmonary fibrosis was introduced to acknowledge additional types of progressive fibrosing interstitial lung diseases with the clinical and pathologic phenotypes comparable to those of UIP/IPF. Likewise, some authors have proposed a paradigm shift by considering UIP as a stand-alone diagnostic entity to encompass other fibrosing interstitial lung diseases that manifest a relentless progression as in IPF. These trends signal a pendulum moving toward the tendency of lumping diagnoses, which poses a risk of obscuring potentially important information crucial to both clinical and research purposes. Recent advances in whole slide imaging for digital pathology and artificial intelligence technology could offer an unprecedented opportunity to enhance histopathologic evaluation of interstitial lung diseases. However, current clinical practice trends of moving away from surgical lung biopsies in interstitial lung disease patients may become a limiting factor in this endeavor as it would be difficult to build a large histopathologic database with correlative clinical data required for artificial intelligence models.

Walking the path of treatable traits in interstitial lung diseases

Interstitial lung diseases (ILDs) are complex and heterogeneous diseases. The use of traditional diagnostic classification in ILD can lead to suboptimal management, which is worsened by not considering the molecular pathways, biological complexity, and disease phenotypes. The identification of specific "treatable traits" in ILDs, which are clinically relevant and modifiable disease characteristics, may improve patient's outcomes. Treatable traits in ILDs may be classified into four different domains (pulmonary, aetiological, comorbidities, and lifestyle), which will facilitate identification of related assessment tools, treatment options, and expected benefits. A multidisciplinary care team model is a potential way to implement a "treatable traits" strategy into clinical practice with the aim of improving patients' outcomes. Multidisciplinary models of care, international registries, and the use of artificial intelligence may facilitate the implementation of the "treatable traits" approach into clinical practice. Prospective studies are needed to test potential therapies for a variety of treatable traits to further advance care of patients with ILD.

Application of Deep Learning Techniques for Detection of Pneumothorax in Chest Radiographs

With the advent of Artificial Intelligence (AI) and even more so recently in the field of Machine Learning (ML), there has been rapid progress across the field. One of the prominent examples is image recognition in the medical category, such as X-ray imaging, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). It has the potential to alleviate a doctor's heavy workload of sifting through large quantities of images. Due to the rising attention to lung-related diseases, such as pneumothorax and nodules, ML is being incorporated into the field in the hope of alleviating the already strained medical resources. In this study, we proposed a system that can detect pneumothorax diseases reliably. By comparing multiple models and hyperparameter configurations, we recommend a model for hospitals, as its focus on minimizing false positives aligns with the precision required by medical professionals. Through our cooperation with Poh-Ai Hospital, we acquired a total of over 8000 X-ray images, with more than 1000 of them from pneumothorax patients. We hope that by integrating AI systems into the automated process of scanning chest X-ray images with various diseases, more resources will be available in the already strained medical systems. Our proposed system showed that the best model that is used for transfer learning from our dataset performed with an AP of 51.57 and an AP75 of 61.40, with accuracy at 93.89%, a false positive of 1.12%, and a false negative of 4.99%. Based on the feedback from practicing doctors, they are more wary of false positives. For their use case, we recommend another model due to the lower false positive rate and higher accuracy compared with other models, which in our test shows a rate of only 0.88% and 95.68%, demonstrating the feasibility of the research. This promising result showed that it could be utilized in other types of diseases and expand to more hospitals and medical organizations, potentially benefitting more people.

Deep learning diagnostic and severity-stratification for interstitial lung diseases and chronic obstructive pulmonary disease in digital lung auscultations and ultrasonography: clinical protocol for an observational case-control study

BACKGROUND

Interstitial lung diseases (ILD), such as idiopathic pulmonary fibrosis (IPF) and non-specific interstitial pneumonia (NSIP), and chronic obstructive pulmonary disease (COPD) are severe, progressive pulmonary disorders with a poor prognosis. Prompt and accurate diagnosis is important to enable patients to receive appropriate care at the earliest possible stage to delay disease progression and prolong survival. Artificial intelligence-assisted lung auscultation and ultrasound (LUS) could constitute an alternative to conventional, subjective, operator-related methods for the accurate and earlier diagnosis of these diseases. This protocol describes the standardised collection of digitally-acquired lung sounds and LUS images of adult outpatients with IPF, NSIP or COPD and a deep learning diagnostic and severity-stratification approach.

METHODS

A total of 120 consecutive patients (≥ 18 years) meeting international criteria for IPF, NSIP or COPD and 40 age-matched controls will be recruited in a Swiss pulmonology outpatient clinic, starting from August 2022. At inclusion, demographic and clinical data will be collected. Lung auscultation will be recorded with a digital stethoscope at 10 thoracic sites in each patient and LUS images using a standard point-of-care device will be acquired at the same sites. A deep learning algorithm (DeepBreath) using convolutional neural networks, long short-term memory models, and transformer architectures will be trained on these audio recordings and LUS images to derive an automated diagnostic tool. The primary outcome is the diagnosis of ILD versus control subjects or COPD. Secondary outcomes are the clinical, functional and radiological characteristics of IPF, NSIP and COPD diagnosis. Quality of life will be measured with dedicated questionnaires. Based on previous work to distinguish normal and pathological lung sounds, we estimate to achieve convergence with an area under the receiver operating characteristic curve of > 80% using 40 patients in each category, yielding a sample size calculation of 80 ILD (40 IPF, 40 NSIP), 40 COPD, and 40 controls.

DISCUSSION

This approach has a broad potential to better guide care management by exploring the synergistic value of several point-of-care-tests for the automated detection and differential diagnosis of ILD and COPD and to estimate severity. Trial registration Registration: August 8, 2022.

CLINICALTRIALS

gov Identifier: NCT05318599.

An explainable machine learning-driven proposal of pulmonary fibrosis biomarkers

Pulmonary fibrosing diseases are in the very epicenter of biomedical research both due to their increasing prevalence and their association with SARS-CoV-2 infections. Research of idiopathic pulmonary fibrosis, the most lethal among the interstitial lung diseases, is in need for new biomarkers and potential disease targets, a goal that could be accelerated using machine learning techniques. In this study, we have used Shapley values to explain the decisions made by an ensemble learning model trained to classify samples to an either pulmonary fibrosis or steady state based on the expression values of deregulated genes. This process resulted in a full and a laconic set of features capable of separating phenotypes to an at least equal degree as previously published marker sets. Indicatively, a maximum increase of 6% in specificity and 5% in Mathew's correlation coefficient was achieved. Evaluation with an additional independent dataset showed our feature set having a greater generalization potential than the rest. Ultimately, the proposed gene lists are expected not only to serve as new sets of diagnostic marker elements, but also as a target pool for future research initiatives.

Diagnosis and Pharmacologic Management of Fibrotic Interstitial Lung Disease

Interstitial lung disease is an umbrella term that encompasses a spectrum of parenchymal lung pathologies affecting the gas exchanging part of the lung. While many of these disease entities are not fibrotic in nature, a number can lead to pulmonary fibrosis which may or may not progress over time. Idiopathic pulmonary fibrosis is the prototypical, progressive fibrotic interstitial lung disease, which can lead to worsening hypoxemic respiratory failure and mortality within a number of years from the time of diagnosis. The importance of an accurate and timely diagnosis of interstitial lung diseases, which is needed to inform prognosis and guide clinical management, cannot be overemphasized. Developing a consensus diagnosis requires the incorporation of a variety of factors by a multidisciplinary team, which then may or may not determine a need for tissue sampling. Clinical management can be challenging given the heterogeneity of disease behavior and the paucity of controlled trials to guide decision making. This review addresses current paradigms and recent updates in the diagnosis and pharmacologic management of these fibrotic interstitial lung diseases.

Novel diagnostic techniques in interstitial lung disease

Research into novel diagnostic techniques and targeted therapeutics in interstitial lung disease (ILD) is moving the field toward increased precision and improved patient outcomes. An array of molecular techniques, machine learning approaches and other innovative methods including electronic nose technology and endobronchial optical coherence tomography are promising tools with potential to increase diagnostic accuracy. This review provides a comprehensive overview of the current evidence regarding evolving diagnostic methods in ILD and to consider their future role in routine clinical care.

Immune cell profiles and patient clustering in complex cases of interstitial lung disease

Interstitial lung disease comprises numerous clinical entities posing significant challenges towards a prompt and accurate diagnosis. Amongst the contributing factors are intricate pathophysiological mechanisms, an overlap between conditions, and interobserver disagreement. We developed a model for patient clustering offering an additional approach to such complex clinical cases. The model is based on surface phenotyping of over 40 markers on immune cells isolated from bronchoalveolar lavage in combination with clinical data. Based on the marker expression pattern we constructed an individual immune cell profile, then merged these to create a global profile encompassing various pathologies. The contribution of each participant to the global profile was assessed through dimensionality reduction tools and the ensuing similarity between samples was calculated. Our model enables two approaches. First, assessing the immune cell population landscape similarity between patients within a diagnostic group allows rapid identification of divergent profiles, which is particularly helpful for cases with uncertain diagnoses. Second, sample clustering is based exclusively on the calculated similarity of the immune cell profiles, thereby removing physician bias and relying on cellular nearest neighbors.

Diagnosing interstitial lung disease by multidisciplinary discussion: A review

The multidisciplinary meeting (MDM) has been endorsed in current international consensus guidelines as the gold standard method for diagnosis of interstitial lung disease (ILD). In the absence of an accurate and reliable diagnostic test, the agreement between multidisciplinary meetings has been used as a surrogate marker for diagnostic accuracy. Although the ILD MDM has been shown to improve inter-clinician agreement on ILD diagnosis, result in a change in diagnosis in a significant proportion of patients and reduce unclassifiable diagnoses, the ideal form for an ILD MDM remains unclear, with constitution and processes of ILD MDMs varying greatly around the world. It is likely that this variation of practice contributes to the lack of agreement seen between MDMs, as well as suboptimal diagnostic accuracy. A recent Delphi study has confirmed the essential components required for the operation of an ILD MDM. The ILD MDM is a changing entity, as it incorporates new diagnostic tests and genetic markers, while also adapting in its form in response to the obstacles of the COVID-19 pandemic. The aim of this review was to evaluate the current evidence regarding ILD MDM and their role in the diagnosis of ILD, the practice of ILD MDM around the world, approaches to ILD MDM standardization and future directions to improve diagnostic accuracy in ILD.

[French practical guidelines for the diagnosis and management of IPF - 2021 update, full version]

BACKGROUND

Since the previous French guidelines were published in 2017, substantial additional knowledge about idiopathic pulmonary fibrosis has accumulated.

METHODS

Under the auspices of the French-speaking Learned Society of Pulmonology and at the initiative of the coordinating reference center, practical guidelines for treatment of rare pulmonary diseases have been established. They were elaborated by groups of writers, reviewers and coordinators with the help of the OrphaLung network, as well as pulmonologists with varying practice modalities, radiologists, pathologists, a general practitioner, a head nurse, and a patients' association. The method was developed according to rules entitled "Good clinical practice" in the overall framework of the "Guidelines for clinical practice" of the official French health authority (HAS), taking into account the results of an online vote using a Likert scale.

RESULTS

After analysis of the literature, 54 recommendations were formulated, improved, and validated by the working groups. The recommendations covered a wide-ranging aspects of the disease and its treatment: epidemiology, diagnostic modalities, quality criteria and interpretation of chest CT, indication and modalities of lung biopsy, etiologic workup, approach to familial disease entailing indications and modalities of genetic testing, evaluation of possible functional impairments and prognosis, indications for and use of antifibrotic therapy, lung transplantation, symptom management, comorbidities and complications, treatment of chronic respiratory failure, diagnosis and management of acute exacerbations of fibrosis.

CONCLUSION

These evidence-based guidelines are aimed at guiding the diagnosis and the management in clinical practice of idiopathic pulmonary fibrosis.

French practical guidelines for the diagnosis and management of idiopathic pulmonary fibrosis - 2021 update. Full-length version

BACKGROUND

Since the latest 2017 French guidelines, knowledge about idiopathic pulmonary fibrosis has evolved considerably.

METHODS

Practical guidelines were drafted on the initiative of the Coordinating Reference Center for Rare Pulmonary Diseases, led by the French Language Pulmonology Society (SPLF), by a coordinating group, a writing group, and a review group, with the involvement of the entire OrphaLung network, pulmonologists practicing in various settings, radiologists, pathologists, a general practitioner, a health manager, and a patient association. The method followed the "Clinical Practice Guidelines" process of the French National Authority for Health (HAS), including an online vote using a Likert scale.

RESULTS

After a literature review, 54 guidelines were formulated, improved, and then validated by the working groups. These guidelines addressed multiple aspects of the disease: epidemiology, diagnostic procedures, quality criteria and interpretation of chest CT scans, lung biopsy indication and procedures, etiological workup, methods and indications for family screening and genetic testing, assessment of the functional impairment and prognosis, indication and use of antifibrotic agents, lung transplantation, management of symptoms, comorbidities and complications, treatment of chronic respiratory failure, diagnosis and management of acute exacerbations of fibrosis.

CONCLUSION

These evidence-based guidelines are intended to guide the diagnosis and practical management of idiopathic pulmonary fibrosis.

La fibrose pulmonaire idiopathique

La fibrose pulmonaire idiopathique (FPI) est une maladie pulmonaire chronique, évolutive et mortelle dont l’origine est inconnue. Elle se caractérise par une cicatrisation aberrante de l’épithélium alvéolaire aboutissant à une accumulation de matrice extracellulaire (MEC). Les foyers fibroblastiques, constitués de fibroblastes et de myofibroblastes, sont responsables de la production excessive de MEC. Les deux seules molécules thérapeutiques disponibles sur le marché permettent seulement de ralentir l’évolution de la maladie. Dans cette revue, nous présentons les mécanismes impliqués dans la progression de la maladie, ses traitements et les modèles d’étude.

Usual interstitial pneumonia: a clinically significant pattern, but not the final word

Usual interstitial pneumonia (UIP) is a concept that is deeply entrenched in clinical practice and the prognostic significance of UIP is well established, but the field continues to suffer from the lack of a true gold standard for diagnosing fibrotic interstitial lung disease (ILD). The meaning and usage of UIP have shifted over time and this term is prone to misinterpretation and poor diagnostic agreement. For pathologists, it is worth reflecting on the limitations of UIP and our true role in the care of patients with ILD, a controversial topic explored in two point-counterpoint editorials published simultaneously in this journal. Current diagnostic guidelines are ambiguous and difficult to apply in clinical practice. Further complicating matters for the pathologist is the paradigm shift that occurred with the advent of anti-fibrotic agents, necessitating increased focus on the most likely etiology of fibrosis rather than simply the pattern of fibrosis when pulmonologists select appropriate therapy. Despite the wealth of information locked in tissue samples that could provide novel insights into fibrotic ILDs, pulmonologists increasingly shy away from obtaining biopsies, likely because pathologists no longer provide sufficient value to offset the risks of a biopsy procedure, and pathologic assessment is insufficiently reliable to meaningfully inform therapeutic decisionmaking. To increase the value of biopsies, pathologists must first recognize the problems with UIP as a diagnostic term. Second, pathologists must realize that the primary goal of a biopsy is to determine the most likely etiology to target with therapy, requiring a shift in diagnostic focus. Third, pathologists must devise and validate new classifications and criteria that are evidence-based, biologically relevant, easy to use, and predictive of outcome and treatment response. Only after the limitations of UIP are understood will pathologists provide maximum diagnostic value from biopsies to clinicians today and advance the field forward.

Usual interstitial pneumonia (UIP): a clinically significant pathologic diagnosis

This editorial focuses on common issues that surround the diagnosis of usual interstitial pneumonia (UIP), a clinically significant pathologic diagnosis. Most of these issues stem from conflation of the pathologically defined entity UIP with the clinically defined entity IPF. A pathologic or radiologic diagnosis of UIP is required for the clinical/multidisciplinary diagnosis of idiopathic pulmonary fibrosis (IPF) but it has also been described in several other clinical settings. I offer my viewpoint on 5 important questions. 1. Is UIP a diagnosis or a "pattern"?

ANSWER

UIP is a pathologic diagnosis and is better conceptualized as a "pattern" than as a specific clinical entity. Since all cases of UIP require pattern recognition, adding the word "pattern" to UIP is redundant. 2. Is pathology the gold standard for UIP?

ANSWER

Yes. 3. How do you "prove" etiology of a given case of UIP?

ANSWER

"Soft" histologic features can raise the possibility of certain etiologies but the final determination of etiology comes from the multidisciplinary team. With few exceptions, there are no findings pathognomonic for any etiology in UIP. 4. Does UIP imply IPF?

ANSWER

No. 5. What should we do when pathology and HRCT are discordant?

ANSWER

This depends on the specifics of the discrepancy. When HRCT suggests a non-UIP diagnosis such as NSIP and histology shows UIP, histology has been shown to predict prognosis in multiple studies. In other settings, the radiologic impression based on HRCT is often proven to be incorrect by the histologic findings.

Idiopathic Pulmonary Fibrosis (an Update) and Progressive Pulmonary Fibrosis in Adults: An Official ATS/ERS/JRS/ALAT Clinical Practice Guideline

Background: This American Thoracic Society, European Respiratory Society, Japanese Respiratory Society, and Asociación Latinoamericana de Tórax guideline updates prior idiopathic pulmonary fibrosis (IPF) guidelines and addresses the progression of pulmonary fibrosis in patients with interstitial lung diseases (ILDs) other than IPF. Methods: A committee was composed of multidisciplinary experts in ILD, methodologists, and patient representatives. 1) Update of IPF: Radiological and histopathological criteria for IPF were updated by consensus. Questions about transbronchial lung cryobiopsy, genomic classifier testing, antacid medication, and antireflux surgery were informed by systematic reviews and answered with evidence-based recommendations using the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) approach. 2) Progressive pulmonary fibrosis (PPF): PPF was defined, and then radiological and physiological criteria for PPF were determined by consensus. Questions about pirfenidone and nintedanib were informed by systematic reviews and answered with evidence-based recommendations using the GRADE approach. Results:1) Update of IPF: A conditional recommendation was made to regard transbronchial lung cryobiopsy as an acceptable alternative to surgical lung biopsy in centers with appropriate expertise. No recommendation was made for or against genomic classifier testing. Conditional recommendations were made against antacid medication and antireflux surgery for the treatment of IPF. 2) PPF: PPF was defined as at least two of three criteria (worsening symptoms, radiological progression, and physiological progression) occurring within the past year with no alternative explanation in a patient with an ILD other than IPF. A conditional recommendation was made for nintedanib, and additional research into pirfenidone was recommended. Conclusions: The conditional recommendations in this guideline are intended to provide the basis for rational, informed decisions by clinicians.

Transbronchial lung cryobiopsy for the diagnosis of interstitial lung diseases

PURPOSE OF REVIEW

Transbronchial lung cryobiopsy has shown promise in several studies in providing meaningful histological information in the multidisciplinary team diagnosis of fibrotic interstitial lung diseases. The purpose of this review is to describe recent literature providing support for the formal integration of cryobiopsy into the algorithm for interstitial lung disease diagnosis.

RECENT FINDINGS

Histopathological concordance between cryobiopsy and surgical biopsy and diagnostic agreement at multidisciplinary discussion have been reported good; furthermore, cryobiopsy may provide an increased diagnostic confidence to a level likely to influence management. Finally, although cryobiopsy is more likely to provide a probable usual interstitial pneumonia (UIP) pattern than a definite UIP pattern, given the limited sampling of sub-pleural lung parenchyma in most cases, finding of a probable UIP pattern at cryobiopsy samples is strongly predictive of a definite UIP pattern in the corresponding surgical biopsy and when a UIP pattern is found on cryobiopsy sample, this is associated with higher mortality compared with other histological patterns.

SUMMARY

Cryobiopsy is becoming a valid alternative to surgical lung biopsy for making histopathological diagnosis in patients with interstitial lung diseases of undetermined type in experienced centres, with standardized protocols, in order to have the best risks/diagnostic yields ratio.

The Impact of the Envisia Genomic Classifier in the Diagnosis and Management of Patients with Idiopathic Pulmonary Fibrosis

RATIONALE

The diagnosis of idiopathic pulmonary fibrosis (IPF) remains challenging and can result in delayed or misdiagnosis. IPF diagnosis is based upon the presence of either a radiographic or histologic usual interstitial pneumonia (UIP) pattern in the absence of an identifiable etiology. The Envisia Genomic Classifier is a clinically validated molecular diagnostic test that identifies UIP in transbronchial biopsies.

OBJECTIVE

To determine the impact of the Envisia Genomic Classifier on physician's clinical decision making in the diagnosis and management of IPF.

METHODS

This prospective randomized decision impact survey was designed to test the hypothesis that including an Envisia UIP positive (UIP+) result will increase IPF diagnoses, diagnostic confidence levels, and the recommendation for antifibrotic therapy. The survey included patients from the BRAVE study who had an HRCT scan without a typical UIP pattern, an Envisia UIP+ result, and a final diagnosis of IPF by multidisciplinary team discussion. Each case was presented in three different formats: a pre-post cohort where each case is presented initially without and then with Envisia, and two independent cohorts where each case is presented without and with Envisia, respectively.

RESULTS

U.S. based pulmonologists from community and academic centers in geographically diverse practices were approached for inclusion in this study. 103 (65%) US-based pulmonologists met the inclusion criteria and provided 605 case reviews of 11 patient cases. The number of IPF diagnoses increased with Envisia by an absolute difference of 39% from 47 (30%) pre-Envisia to 107 (69%) post-Envisia in the pre-post cohort and by 13% in the independent cohorts. High confidence (> 90%) of ILD diagnoses was more commonly seen with Envisia in both the pre-post cohort and in the independent cohorts. Recommendation for antifibrotic treatment increased with Envisia by an absolute difference of 36% from 15 (10%) pre-Envisia to 72 (46.4%) post-Envisia in the pre-post cohort and by 11% in the independent cohorts.

CONCLUSIONS

This decision impact survey suggests the clinical utility of the Envisia Classifier by demonstrating a significant increase in IPF diagnoses, diagnostic confidence, and recommendation for antifibrotic therapies to assist physicians to effectively manage patients to improve outcomes of patients with IPF.

A Soft Voting Ensemble-Based Model for the Early Prediction of Idiopathic Pulmonary Fibrosis (IPF) Disease Severity in Lungs Disease Patients

Idiopathic pulmonary fibrosis, which is one of the lung diseases, is quite rare but fatal in nature. The disease is progressive, and detection of severity takes a long time as well as being quite tedious. With the advent of intelligent machine learning techniques, and also the effectiveness of these techniques, it was possible to detect many lung diseases. So, in this paper, we have proposed a model that could be able to detect the severity of IPF at the early stage so that fatal situations can be controlled. For the development of this model, we used the IPF dataset of the Korean interstitial lung disease cohort data. First, we preprocessed the data while applying different preprocessing techniques and selected 26 highly relevant features from a total of 502 features for 2424 subjects. Second, we split the data into 80% training and 20% testing sets and applied oversampling on the training dataset. Third, we trained three state-of-the-art machine learning models and combined the results to develop a new soft voting ensemble-based model for the prediction of severity of IPF disease in patients with this chronic lung disease. Hyperparameter tuning was also performed to get the optimal performance of the model. Fourth, the performance of the proposed model was evaluated by calculating the accuracy, AUC, confusion matrix, precision, recall, and F1-score. Lastly, our proposed soft voting ensemble-based model achieved the accuracy of 0.7100, precision 0.6400, recall 0.7100, and F1-scores 0.6600. This proposed model will help the doctors, IPF patients, and physicians to diagnose the severity of the IPF disease in its early stages and assist them to take proactive measures to overcome this disease by enabling the doctors to take necessary decisions pertaining to the treatment of IPF disease.

Cellular Senescence in Idiopathic Pulmonary Fibrosis

Cellular senescence (CS) is increasingly implicated in the etiology of age-related diseases. While CS can facilitate physiological processes such as tissue repair and wound healing, senescent cells also contribute to pathophysiological processes involving macromolecular damage and metabolic dysregulation that characterize multiple morbid and prevalent diseases, including Alzheimer's disease, osteoarthritis, atherosclerotic vascular disease, diabetes mellitus, and idiopathic pulmonary fibrosis (IPF). Preclinical studies targeting senescent cells and the senescence-associated secretory phenotype (SASP) with "senotherapeutics" have demonstrated improvement in age-related morbidity associated with these disease states. Despite promising results from these preclinical trials, few human clinical trials have been conducted. A first-in-human, open-label, pilot study of the senolytic combination of dasatinib and quercetin (DQ) in patients with IPF showed improved physical function and mobility. In this review, we will discuss our current understanding of cellular senescence, its role in age-associated diseases, with a specific focus on IPF, and potential for senotherapeutics in the treatment of fibrotic lung diseases.

Molecular Markers and the Promise of Precision Medicine for Interstitial Lung Disease

Management of patients with interstitial lung disease (ILD) requires accurate classification. However, this process relies on subjective interpretation of nonspecific and overlapping clinical features that could hamper clinical care. The development and implementation of objective biomarkers reflective of specific disease states could facilitate precision-based approaches based on patient-level biology to improve the health of ILD patients. Omics-based studies allow for the seemingly unbiased and highly efficient screening of candidate biomarkers and offer unprecedented opportunities for discovery. This review outlines representative major omics-based discoveries in a well-studied condition, idiopathic pulmonary fibrosis, to develop a roadmap to personalized medicine in ILD.

Biopsy in interstitial lung disease: specific diagnosis and the identification of the progressive fibrotic phenotype

PURPOSE OF REVIEW

The evaluation of progression in fibrotic interstitial lung diseases (ILDs) may require a multidimensional approach. This review will cover the role and usefulness of lung biopsy in diagnosis and assessment of the progressive fibrotic phenotype.

RECENT FINDINGS

The identification of specific findings and the balance between inflammation and fibrosis on lung biopsy may help distinguishing different disease entities and may likely determine the effect of treatment and possibly prognosis. The fibrotic morphological patterns potentially associated with a progressive phenotype include usual interstitial pneumonia (UIP), fibrotic nonspecific interstitial pneumonia, pleuroparenchymal fibroelastosis, desquamative interstitial pneumonia, fibrotic hypersensitivity pneumonitis and other less common fibrotic variants, with histopathological findings of UIP at the time of diagnosis being predictive of worse outcome compared with other patterns. The prognostic significance of lung biopsy findings has been assessed after both surgical lung biopsy (SLB) and transbronchial lung cryobiopsy (TBLC), the latter becoming a valid alternative to SLB, if performed in experienced centres, due to significantly lower morbidity and mortality.

SUMMARY

Lung biopsy plays an important role in diagnosis and identification of the progressive fibrotic phenotype. The introduction of less invasive procedures could potentially expand the role of lung sampling, including for example patients with a known diagnosis of ILD or at an earlier stage of the disease.

Unclassifiable, or simply unclassified interstitial lung disease?

PURPOSE OF REVIEW

Unclassifiable interstitial lung disease (ILD) comprises a subset of ILDs which cannot be classified according to the current diagnostic framework. This is a likely a heterogeneous group of diseases rather than a single entity and it is poorly defined and hence problematic for prognosis and therapy.

RECENT FINDINGS

With increased treatment options for progressive fibrosing ILD it is increasingly relevant to correctly categorise ILD.

SUMMARY

This review article will summarise the definition and reasons for a diagnosis of unclassifiable ILD, the current management options and possible future approaches to improve diagnosis and differentiation within this broad subset. Finally, we will describe the implications of the labelling of unclassifiable ILD in clinical practice and research and whether the term 'unclassified' should be used, implying a less definitive diagnosis.

A contemporary practical approach to the multidisciplinary management of unclassifiable interstitial lung disease

Fibrotic interstitial lung diseases (ILDs) frequently have nonspecific and overlapping clinical and radiological features, resulting in approximately 10-20% of patients with ILD lacking a clear diagnosis and thus being labelled with unclassifiable ILD. The objective of this review is to describe how patients with unclassifiable ILD should be evaluated and what impact specific clinical, radiological, and histopathological features may have on management decisions, focusing on patients with a predominantly fibrotic phenotype. We highlight recent data that have suggested an increasing role for antifibrotic medications in a variety of fibrotic ILDs, but justify the ongoing importance of making an accurate ILD diagnosis given the benefit of immunomodulatory therapies in many patient populations. We provide a practical approach to support management decisions that can be used by clinicians and tested by clinical researchers, and further identify the need for additional research to support a rational and standardised approach to the management of patients with unclassifiable ILD.

Use of a Genomic Classifier in Patients with Interstitial Lung Disease: A Systematic Review

This ahead-of-print article has been temporarily removed from the AnnalsATS journal website in anticipation of the publication of a forthcoming official ATS/ERS/JRS/ALAT clinical practice guideline on idiopathic pulmonary fibrosis and progressive pulmonary fibrosis to be published in a future issue of the American Journal of Respiratory and Critical Care Medicine (AJRCCM). This article was posted prematurely and will be published in the Annals of the American Thoracic Society after the official clinical practice guideline has been published in AJRCCM.

Idiopathic pulmonary fibrosis: Disease mechanisms and drug development

Idiopathic pulmonary fibrosis (IPF) is a chronic progressive disease of unknown cause characterized by relentless scarring of the lung parenchyma leading to reduced quality of life and earlier mortality. IPF is an age-related disorder, and with the population aging worldwide, the economic burden of IPF is expected to steadily increase in the future. The mechanisms of fibrosis in IPF remain elusive, with favored concepts of disease pathogenesis involving recurrent microinjuries to a genetically predisposed alveolar epithelium, followed by an aberrant reparative response characterized by excessive collagen deposition. Pirfenidone and nintedanib are approved for treatment of IPF based on their ability to slow functional decline and disease progression; however, they do not offer a cure and are associated with tolerability issues. In this review, we critically discuss how cutting-edge research in disease pathogenesis may translate into identification of new therapeutic targets, thus facilitate drug discovery. There is a growing portfolio of treatment options for IPF. However, targeting the multitude of profibrotic cytokines and growth factors involved in disease pathogenesis may require a combination of therapeutic strategies with different mechanisms of action.

The Role of Surgical Lung Biopsy in the Diagnosis of Fibrotic Interstitial Lung Disease: Perspective from the Pulmonary Fibrosis Foundation

Diagnosis of interstitial lung disease (ILD) requires a multidisciplinary diagnosis (MDD) approach that includes clinicians, radiologists, and pathologists. Surgical lung biopsy (SLB) is currently the recommended standard in obtaining pathological specimens for patients with ILD requiring a tissue diagnosis. The increased diagnostic confidence and accuracy provided by microscopic pathology assessment of SLB specimens must be balanced with the associated risks in ILD patients. This document was developed by the Surgical Lung Biopsy Working Group of the Pulmonary Fibrosis Foundation, composed of a multidisciplinary group of ILD physicians including pulmonologists, radiologists, pathologists, and thoracic surgeons. In this document, we present an up-to-date literature review of the indications, contraindications, risks, and alternatives to SLB in the diagnosis of fibrotic ILD, outline an integrated approach to the decision-making around SLB in the diagnosis of fibrotic ILD, and provide practical information to maximize the yield and safety of SLB.

Chest Imaging of Patients with Sarcoidosis and SARS-CoV-2 Infection. Current Evidence and Clinical Perspectives

The recent COVID-19 pandemic has dramatically changed the world in the last months, leading to a serious global emergency related to a novel coronavirus infection that affects both sexes of all ages ubiquitously. Advanced age, cardiovascular comorbidity, and viral load have been hypothesized as some of the risk factors for severity, but their role in patients affected with other diseases, in particular immune disorders, such as sarcoidosis, and the specific interaction between these two diseases remains unclear. The two conditions might share similar imaging findings but have distinctive features that are here described. The recent development of complex imaging softwares, called deep learning techniques, opens new scenarios for the diagnosis and management.

S2K Guideline for Diagnosis of Idiopathic Pulmonary Fibrosis

Idiopathic pulmonary fibrosis (IPF) is a severe and often fatal disease. Diagnosis of IPF requires considerable expertise and experience. Since the publication of the international IPF guideline in the year 2011 and the update 2018 several studies and technical advances have occurred, which made a new assessment of the diagnostic process mandatory. The goal of this guideline is to foster early, confident, and effective diagnosis of IPF. The guideline focusses on the typical clinical context of an IPF patient and provides tools to exclude known causes of interstitial lung disease including standardized questionnaires, serologic testing, and cellular analysis of bronchoalveolar lavage. High-resolution computed tomography remains crucial in the diagnostic workup. If it is necessary to obtain specimens for histology, transbronchial lung cryobiopsy is the primary approach, while surgical lung biopsy is reserved for patients who are fit for it and in whom a bronchoscopic diagnosis did not provide the information needed. After all, IPF is a diagnosis of exclusion and multidisciplinary discussion remains the golden standard of diagnosis.

Updates in using a molecular classifier to identify usual interstitial pneumonia in conventional transbronchial lung biopsy samples

The most common fibrosing interstitial lung disease (ILD) is idiopathic pulmonary fibrosis (IPF), with an incidence of 14–60 cases per 100 000 inhabitants per year in North America [1] and 3–9 cases per 100 000 per year in Europe [2]. IPF is a chronic, progressive fibrosing interstitial lung disease characterised by continued scarring of the lung parenchyma and associated with a steady worsening of respiratory symptoms, quality of life and pulmonary function, ultimately leading to death [1, 3], and a median survival of 3–5 years from the time of diagnosis [4, 5]. A precise diagnosis of the underlying ILD entity is essential for prognostication and choice of therapy as treatments differ between ILD subtypes, including that some drugs may be detrimental to an IPF patient. However, the diagnosis of ILD is sometimes difficult, partly imprecise, and frequently characterised by delay, misdiagnosis, use of costly and invasive procedures, and high use of healthcare resources.

A molecular classifier using a machine-learning algorithm based on genomic data could provide an objective method to aid clinicians and multidisciplinary teams to establish the diagnosis of IPF in less-invasive transbronchial lung biopsy sampleshttps://bit.ly/2QLdWim

Molecular approach to the classification of chronic fibrosing lung disease-there and back again

Chronic diffuse parenchymal lung disease (DPLD) is an umbrella term for a very heterogeneous group of lung diseases. Over the last decades, clinical, radiological and histopathological criteria have been established to define and separate these entities. More recently the clinical utility of this approach has been challenged as a unifying concept of pathophysiological mechanisms and a shared response to therapy across the disease spectrum have been described. In this review, we discuss molecular motifs for subtyping and the prediction of prognosis focusing on genetics and markers found in the blood, lavage and tissue. As a purely molecular classification so far lacks sufficient sensitivity and specificity for subtyping, it is not routinely used and not implemented in international guidelines. However, a better molecular characterization of lung disease with a more precise identification of patients with, for example, a risk for rapid disease progression would facilitate more accurate treatment decisions and hopefully contribute to better patients' outcomes.

Artificial intelligence identifies inflammation and confirms fibroblast foci as prognostic tissue biomarkers in idiopathic pulmonary fibrosis

A large number of fibroblast foci (FF) predict mortality in idiopathic pulmonary fibrosis (IPF). Other prognostic histological markers have not been identified. Artificial intelligence (AI) offers a possibility to quantitate possible prognostic histological features in IPF. We aimed to test the use of AI in IPF lung tissue samples by quantitating FF, interstitial mononuclear inflammation, and intra-alveolar macrophages with a deep convolutional neural network (CNN). Lung tissue samples of 71 patients with IPF from the FinnishIPF registry were analyzed by an AI model developed in the Aiforia® platform. The model was trained to detect tissue, air spaces, FF, interstitial mononuclear inflammation, and intra-alveolar macrophages with 20 samples. For survival analysis, cut-point values for high and low values of histological parameters were determined with maximally selected rank statistics. Survival was analyzed using the Kaplan-Meier method. A large area of FF predicted poor prognosis in IPF (p = 0.01). High numbers of interstitial mononuclear inflammatory cells and intra-alveolar macrophages were associated with prolonged survival (p = 0.01 and p = 0.01, respectively). Of lung function values, low diffusing capacity for carbon monoxide was connected to a high density of FF (p = 0.03) and a high forced vital capacity of predicted was associated with a high intra-alveolar macrophage density (p = 0.03). The deep CNN detected histological features that are difficult to quantitate manually. Interstitial mononuclear inflammation and intra-alveolar macrophages were novel prognostic histological biomarkers in IPF. Evaluating histological features with AI provides novel information on the prognostic estimation of IPF.

Artificial intelligence in pulmonary medicine: computer vision, predictive model and COVID-19

Artificial intelligence (AI) is transforming healthcare delivery. The digital revolution in medicine and healthcare information is prompting a staggering growth of data intertwined with elements from many digital sources such as genomics, medical imaging and electronic health records. Such massive growth has sparked the development of an increasing number of AI-based applications that can be deployed in clinical practice. Pulmonary specialists who are familiar with the principles of AI and its applications will be empowered and prepared to seize future practice and research opportunities. The goal of this review is to provide pulmonary specialists and other readers with information pertinent to the use of AI in pulmonary medicine. First, we describe the concept of AI and some of the requisites of machine learning and deep learning. Next, we review some of the literature relevant to the use of computer vision in medical imaging, predictive modelling with machine learning, and the use of AI for battling the novel severe acute respiratory syndrome-coronavirus-2 pandemic. We close our review with a discussion of limitations and challenges pertaining to the further incorporation of AI into clinical pulmonary practice.

Artificial intelligence (AI) is changing the landscape in medicine. AI-based applications will empower pulmonary specialists to seize modern practice and research opportunities. Data-driven precision medicine is already here.https://bit.ly/324tl2m

CT Findings in Pulmonary and Abdominal Sarcoidosis. Implications for Diagnosis and Classification

Sarcoidosis is a granulomatous disorder of unknown etiology characterized by noncaseating granulomas virtually in every organ and tissue. This finding represents the most important diagnostic clue to reach a correct definition of sarcoidosis, although the biopsy is invasive and has several risk procedures. Several efforts are made to suspect the diagnosis of sarcoidosis by combining noninvasive elements, in particular from imaging, though these findings are often nonspecific and reflect the wide multifactorial pathogenesis. Every effort should be made to obtain a detailed radiological picture that, if associated with a suggestive clinical picture, could avoid the need of biopsy in some specific cases. In this narrative review, we aim to describe main computed tomography (CT) features of pulmonary and abdominal sarcoidosis, by reporting strengths and limits of this technique, in particular for the identification of extrapulmonary, isolated disease.

Breathing fresh air into respiratory research with single-cell RNA sequencing

The complex cellular heterogeneity of the lung poses a unique challenge to researchers in the field. While the use of bulk RNA sequencing has become a ubiquitous technology in systems biology, the technique necessarily averages out individual contributions to the overall transcriptional landscape of a tissue. Single-cell RNA sequencing (scRNA-seq) provides a robust, unbiased survey of the transcriptome comparable to bulk RNA sequencing while preserving information on cellular heterogeneity. In just a few years since this technology was developed, scRNA-seq has already been adopted widely in respiratory research and has contributed to impressive advancements such as the discoveries of the pulmonary ionocyte and of a profibrotic macrophage population in pulmonary fibrosis. In this review, we discuss general technical considerations when considering the use of scRNA-seq and examine how leading investigators have applied the technology to gain novel insights into respiratory biology, from development to disease. In addition, we discuss the evolution of single-cell technologies with a focus on spatial and multi-omics approaches that promise to drive continued innovation in respiratory research.

Management of interstitial lung diseases: A consensus statement of the Indian Chest Society (ICS) and National College of Chest Physicians (NCCP)

BACKGROUND

Interstitial lung disease (ILD) is a complex and heterogeneous group of acute and chronic lung diseases of several known and unknown causes. While clinical practice guidelines (CPG) for idiopathic pulmonary fibrosis (IPF) have been recently updated, CPG for ILD other than IPF are needed.

METHODS

A working group of multidisciplinary clinicians familiar with clinical management of ILD (pulmonologists, radiologist, pathologist, and rheumatologist) and three epidemiologists selected by the leaderships of Indian Chest Society and National College of Chest Physicians, India, posed questions to address the clinically relevant situation. A systematic search was performed on PubMed, Embase, and Cochrane databases. A modified GRADE approach was used to grade the evidence. The working group discussed the evidence and reached a consensus of opinions for each question following face-to-face discussions.

RESULTS

Statements have been made for each specific question and the grade of evidence has been provided after performing a systematic review of literature. For most of the questions addressed, the available evidence was insufficient and of low to very low quality. The consensus of the opinions of the working group has been presented as statements for the questions and not as an evidence-based CPG for the management of ILD.

CONCLUSION

This document provides the guidelines made by consensus of opinions among experts following discussion of systematic review of evidence pertaining to the specific questions for management of ILD other than IPF. It is hoped that this document will help the clinician understand the accumulated evidence and help better management of idiopathic and nonidiopathic interstitial pneumonias.

Single-cell RNA sequencing reveals profibrotic roles of distinct epithelial and mesenchymal lineages in pulmonary fibrosis

Pulmonary fibrosis (PF) is a form of chronic lung disease characterized by pathologic epithelial remodeling and accumulation of extracellular matrix (ECM). To comprehensively define the cell types, mechanisms, and mediators driving fibrotic remodeling in lungs with PF, we performed single-cell RNA sequencing of single-cell suspensions from 10 nonfibrotic control and 20 PF lungs. Analysis of 114,396 cells identified 31 distinct cell subsets/states. We report that a remarkable shift in epithelial cell phenotypes occurs in the peripheral lung in PF and identify several previously unrecognized epithelial cell phenotypes, including a KRT5- /KRT17 + pathologic, ECM-producing epithelial cell population that was highly enriched in PF lungs. Multiple fibroblast subtypes were observed to contribute to ECM expansion in a spatially discrete manner. Together, these data provide high-resolution insights into the complexity and plasticity of the distal lung epithelium in human disease and indicate a diversity of epithelial and mesenchymal cells contribute to pathologic lung fibrosis.

Towards the Essence of Progressiveness: Bringing Progressive Fibrosing Interstitial Lung Disease (PF-ILD) to the Next Stage

Although only recently introduced in the ILD community, the concept of progressive fibrosing interstitial lung disease (PF-ILD) has rapidly acquired an important place in the management of non-idiopathic pulmonary fibrosis fibrosing ILD (nonIPF fILD) patients. It confirms a clinical gut feeling that an important subgroup of nonIPF fILD portends a dismal prognosis despite therapeutically addressing the alleged triggering event. Due to several recently published landmark papers showing a treatment benefit with currently available antifibrotic drugs in PF-ILD patients, endorsing a PF-ILD phenotype has vital therapeutic consequences. Importantly, defining progressiveness is based on former progression, which has proven to be a rather moderate predictor of future progression. As fibrosis extent >20% and the presence of honeycombing have superior predictive properties regarding future progression, we advocate immediate initiation of antifibrotic treatment in the presence of these risk factors. In this perspective, we describe the historical context wherein PF-ILD has emerged, determine the currently employed PF-ILD criteria and their inherent limitations and propose new directions to mature its definition. Finally, while ascertaining progression in a nonIPF fILD patient clearly demonstrates the need for (additional) therapy, in the future, therapeutic decisions should be taken after assessing which pathway is ultimately driving the progression. Although not readily available, pathophysiological insight and diagnostic means are emergent to go full steam ahead in this novel direction.

Traction Bronchiectasis/Bronchiolectasis is Associated with Interstitial Lung Abnormality Mortality

PURPOSE

To investigate if the presence and severity of traction bronchiectasis/bronchiolectasis are associated with poorer survival in subjects with ILA.

METHOD

The study included 3,594 subjects (378 subjects with ILA and 3,216 subjects without ILA) in AGES-Reykjavik Study. Chest CT scans of 378 subjects with ILA were evaluated for traction bronchiectasis/bronchiolectasis, defined as dilatation of bronchi/bronchioles within areas demonstrating ILA. Traction bronchiectasis/bronchiolectasis Index (TBI) was assigned as: TBI = 0, ILA without traction bronchiectasis/bronchiolectasis: TBI = 1, ILA with bronchiolectasis but without bronchiectasis or architectural distortion: TBI = 2, ILA with mild to moderate traction bronchiectasis: TBI = 3, ILA and severe traction bronchiectasis and/or honeycombing. Overall survival (OS) was compared among the subjects in different TBI groups and those without ILA.

RESULTS

The median OS was 12.93 years (95%CI; 12.67 - 13.43) in the subjects without ILA; 11.95 years (10.03 - not reached) in TBI-0 group; 8.52 years (7.57 - 9.30) in TBI-1 group; 7.63 years (6.09 - 9.10) in TBI-2 group; 5.40 years (1.85 - 5.98) in TBI-3 group. The multivariable Cox models demonstrated significantly shorter OS of TBI-1, TBI-2, and TBI-3 groups compared to subjects without ILA (P < 0.0001), whereas TBI-0 group had no significant OS difference compared to subjects without ILA, after adjusting for age, sex, and smoking status.

CONCLUSIONS

The presence and severity of traction bronchiectasis/bronchiolectasis are associated with shorter survival. The traction bronchiectasis/bronchiolectasis is an important contributor to increased mortality among subjects with ILA.

Applications of artificial intelligence and machine learning in respiratory medicine

The past 5 years have seen an explosion of interest in the use of artificial intelligence (AI) and machine learning techniques in medicine. This has been driven by the development of deep neural networks (DNNs)-complex networks residing in silico but loosely modelled on the human brain-that can process complex input data such as a chest radiograph image and output a classification such as 'normal' or 'abnormal'. DNNs are 'trained' using large banks of images or other input data that have been assigned the correct labels. DNNs have shown the potential to equal or even surpass the accuracy of human experts in pattern recognition tasks such as interpreting medical images or biosignals. Within respiratory medicine, the main applications of AI and machine learning thus far have been the interpretation of thoracic imaging, lung pathology slides and physiological data such as pulmonary function tests. This article surveys progress in this area over the past 5 years, as well as highlighting the current limitations of AI and machine learning and the potential for future developments.

Diagnostic approach of fibrosing interstitial lung diseases of unknown origin

Interstitial lung diseases encompass a broad range of numerous individual conditions, some of them characterized histologically by fibrosis, especially idiopathic pulmonary fibrosis, nonspecific interstitial pneumonia, chronic hypersensitivity pneumonia, interstitial lung disease associated with connective tissue diseases, and unclassifiable interstitial lung disease. The diagnostic approach relies mainly on the clinical evaluation, especially assessment of the patient's demographics, history, smoking habits, occupational or domestic exposures, use of drugs, and on interpretation of high-quality HRCT of the chest. Imaging is key to the initial diagnostic approach, and often can confirm a definite diagnosis, particularly a diagnosis of idiopathic pulmonary fibrosis when showing a pattern of usual interstitial pneumonia in the appropriate context. In other cases, chest HRCT may orientate toward an alternative diagnosis and appropriate investigations to confirm the suspected diagnosis. Autoimmune serology helps diagnosing connective disease. Indications for bronchoalveolar lavage and for lung biopsy progressively become more restrictive, with better considerations for their discriminate value, of the potential risk associated with the procedure, and of the anticipated impact on management. Innovative techniques and genetics are beginning to contribute to diagnosing interstitial lung disease and to be implemented routinely in the clinic. Multidisciplinary discussion, enabling interaction between pulmonologists, chest radiologists, pathologists and often other healthcare providers, allows integration of all information available. It increases the accuracy of diagnosis and prognosis prediction, proposes a first-choice diagnosis, may suggest additional investigations, and often informs the management. The concept of working diagnosis, which can be revised upon additional information being made available especially longitudinal disease behaviour, helps dealing with diagnostic uncertainty inherent to interstitial lung diseases and facilitates management decisions. Above all, the clinical approach and how thoroughly the patient's history and possible exposures are assessed determine the possibility of an accurate diagnosis.

Morphological and molecular motifs of fibrosing pulmonary injury patterns

Interstitial lung diseases encompass a large number of entities, which are characterised by a small number of partially overlapping fibrosing injury patterns, either alone or in combination. Thus, the presently applied morphological diagnostic criteria do not reliably discriminate different interstitial lung diseases. We therefore analysed critical regulatory pathways and signalling molecules involved in pulmonary remodelling with regard to their diagnostic suitability. Using laser‐microdissection and microarray techniques, we examined the expression patterns of 45 tissue‐remodelling associated target genes in remodelled and non‐remodelled tissue samples from patients with idiopathic pulmonary fibrosis/usual interstitial pneumonia (IPF/UIP), non‐specific interstitial pneumonia (NSIP), organising pneumonia (OP) and alveolar fibroelastosis (AFE), as well as controls (81 patients in total). We found a shared usage of pivotal pathways in AFE, NSIP, OP and UIP, but also individual molecular traits, which set the fibrosing injury patterns apart from each other and correlate well with their specific morphological aspects. Comparison of the aberrant gene expression patterns demonstrated that (1) molecular profiling in fibrosing lung diseases is feasible, (2) pulmonary injury patterns can be discriminated with very high confidence on a molecular level (86–100% specificity) using individual gene subsets and (3) these findings can be adapted as suitable diagnostic adjuncts.