Use of artificial intelligence-powered ECG to differentiate between cardiac and pulmonary pathologies in patients with acute dyspnoea in the emergency department.

BACKGROUND: Acute dyspnoea is common in acute care settings. However, identifying the origin of dyspnoea in the emergency department (ED) is often challenging. We aimed to investigate whether our artificial intelligence (AI)-powered ECG analysis reliably distinguishes between the causes of dyspnoea and evaluate its potential as a clinical triage tool for comparing conventional heart failure diagnostic processes using natriuretic peptides. METHODS: A retrospective analysis was conducted using an AI-based ECG algorithm on patients ≥18 years old presenting with dyspnoea at the ED from February 2006 to September 2023. Patients were categorised into cardiac or pulmonary origin groups based on initial admission. The performance of an AI-ECG using a transformer neural network algorithm was assessed to analyse standard 12-lead ECGs for accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AUC). Additionally, we compared the diagnostic efficacy of AI-ECG models with N-terminal probrain natriuretic peptide (NT-proBNP) levels to identify cardiac origins. RESULTS: Among the 3105 patients included in the study, 1197 had cardiac-origin dyspnoea. The AI-ECG model demonstrated an AUC of 0.938 and 88.1% accuracy for cardiac-origin dyspnoea. The sensitivity, specificity and positive and negative predictive values were 93.0%, 79.5%, 89.0% and 86.4%, respectively. The F1 score was 0.828. AI-ECG demonstrated superior diagnostic performance in identifying cardiac-origin dyspnoea compared with NT-proBNP. True cardiac origin was confirmed in 96 patients in a sensitivity analysis of 129 patients with a high probability of cardiac origin initially misdiagnosed as pulmonary origin predicted by AI-ECG. CONCLUSIONS: AI-ECG demonstrated superior diagnostic accuracy over NT-proBNP and showed promise as a clinical triage tool. It is a potentially valuable tool for identifying the origin of dyspnoea in emergency settings and supporting decision-making.

Impaired lung function and associated risk factors in children born prematurely: a systematic review and meta-analysis.

BACKGROUND: Immature lung development and respiratory morbidity place preterm-born children at high risk of long-term pulmonary sequelae. This systematic review and meta-analysis aims to quantify lung function in preterm-born children and identify risk factors for a compromised lung function. METHODS: We searched MEDLINE, Embase, Cochrane Library, Web of Science and Scopus for relevant studies published on preterm cohorts born since 1990. Studies comparing forced expiratory volume in 1 s (FEV1) in preterm-born children aged ≥5 years to term-born controls or normative data were included. Study quality was assessed using the Newcastle-Ottawa Scale for cohort studies. Standardised mean differences in FEV1 and secondary spirometry outcomes per study were pooled using meta-analysis. The impact of different demographic and neonatal variables on studies' FEV1 effect sizes was investigated by meta-regression analyses. Certainty of evidence was assessed using the Grading of Recommendations, Assessment, Development, and Evaluations framework. RESULTS: We identified 42 studies with unique cohorts including 4743 preterm children and 9843 controls. Median gestational age in the studies was 28.0 weeks and age at assessment ranged from 6.7 to 16.7 years. Preterm children had lower FEV1 than controls (-0.58 sd, 95% CI -0.69- -0.47 sd, p<0.001) resulting in a relative risk of 2.9 (95% CI 2.4-3.4) for abnormal outcome, with high certainty of evidence. FEV1 was significantly associated with gestational age, birthweight, bronchopulmonary dysplasia and invasive mechanical ventilation in univariate meta-regression analyses (R2=36-96%). CONCLUSION: This systematic review shows robust evidence of impaired lung function in preterm-born children with a high certainty of evidence.

Implementation of spirometry screening for post-tuberculosis lung disease (PTLD) among adolescents and adults enrolled within the National Tuberculosis Control Program of Carmelo Hospital in Chókwè District, Mozambique: A hybrid type III effectiveness-implementation study protocol.

BACKGROUND: Despite receiving adequate treatment, many tuberculosis (TB) survivors are left with post-tuberculosis complications, possibly due to lung tissue damage incurred during the active period of the disease. Current TB programs worldwide deliver quality care throughout the course of active TB treatment, yet often fail to provide organized follow-up once treatment ends. Post-tuberculosis lung disease (PTLD) is a prominent, yet underrecognized cause of chronic lung disease, managed similarly to chronic respiratory diseases with pharmacotherapy and/or personalized pulmonary rehabilitation interventions. Basic pulmonary rehabilitation packages for people finishing TB treatment are still lacking in low- and middle-income countries (LMICs). We offer a study protocol to evaluate the implementation of spirometry and symptom screening for PTLD among people who have completed TB treatment in a rural district in Mozambique. METHODS: The overall objective of this study is to evaluate the introduction of a new screening program that utilizes symptom screening and spirometry for diagnosing PTLD among adolescents and adults that have completed TB treatment. This research protocol consists of three complementary components: 1) assessing the prevalence of PTLD among patients enrolled in the National TB Control Program (NTCP) at Carmelo Hospital (CHC) in Chókwè District, Mozambique; 2) evaluating anticipated implementation outcomes through the identification of the site-, provider-, and individual-level determinants that either facilitate or hinder the successful adoption, implementation, and maintenance of the spirometry screening program, and 3) evaluating the real-time implementation outcomes/processes in order to provide practical evidence-based key indicators of successful implementation of the spirometry screening program. DISCUSSION: Providing well-organized, evidence-based care for individuals with a history of TB who are experiencing symptoms of PTLD can relieve chronic respiratory issues, enhance quality of life, and potentially lower the risk of further pulmonary infections, including recurrent TB. However, there is a significant gap in the literature regarding the implementation of best practices of HIV and TB health services delivery. Addressing this gap could assist Mozambique in improving diagnosis, treatment, and continuity of care for people formerly living with TB. The insights from this study will help decision-makers improve spirometry screening coverage, enhance intervention effectiveness, and translate our findings to evidence-based programming. TRIAL REGISTRATION: ISRCTN92021748 retrospectively registered.

Nontuberculous Mycobacterial Pulmonary Disease: Patients, Principles, and Prospects.

Nontuberculous mycobacterial pulmonary disease (NTM-PD) is increasing in incidence globally and challenging to manage. The 2020 multisociety treatment guideline and the 2022 consensus recommendations provide comprehensive evidence-based guides to manage pulmonary diseases caused by the most common NTM. However, with >190 different NTM species that may require different multidrug regimens for treatment, the breadth and complexity of NTM-PD remain daunting for both patients and clinicians. In this narrative review, we aim to distill this broad, complex field into principles applicable to most NTM species and highlight important nuances, specifically elaborating on the presentation, diagnosis, principles of patient-centered care, principles of pathogen-directed therapy, and prospects of NTM-PD.

Evaluation and Management of Perioperative Pulmonary Complications.

Pulmonary complications are very common after noncardiac surgery and can be easily overlooked. If not properly screened for or evaluated these can in many instances lead to postoperative respiratory failure or even death. Decisions regarding ambulatory versus inpatient surgery, modality of anesthesia, protective ventilation and method of weaning, type of analgesia, and postoperative monitoring can be crucial to avoid such complications.

Effect of perioperative sigh ventilation on postoperative hypoxemia and pulmonary complications after on-pump cardiac surgery (E-SIGHT): study protocol for a randomized controlled trial.

BACKGROUND: Postoperative hypoxemia and pulmonary complications remain a frequent event after on-pump cardiac surgery and mostly characterized by pulmonary atelectasis. Surfactant dysfunction or hyposecretion happens prior to atelectasis formation, and sigh represents the strongest stimulus for surfactant secretion. The role of sigh breaths added to conventional lung protective ventilation in reducing postoperative hypoxemia and pulmonary complications among cardiac surgery is unknown. METHODS: The perioperative sigh ventilation in cardiac surgery (E-SIGHT) trial is a single-center, two-arm, randomized controlled trial. In total, 192 patients scheduled for elective cardiac surgery with cardiopulmonary bypass (CPB) and aortic cross-clamp will be randomized into one of the two treatment arms. In the experimental group, besides conventional lung protective ventilation, sigh volumes producing plateau pressures of 35 cmH2O (or 40 cmH2O for patients with body mass index > 35 kg/m2) delivered once every 6 min from intubation to extubation. In the control group, conventional lung protective ventilation without preplanned recruitment maneuvers is used. Lung protective ventilation (LPV) consists of low tidal volumes (6-8 mL/kg of predicted body weight) and positive end-expiratory pressure (PEEP) setting according to low PEEP/FiO2 table for acute respiratory distress syndrome (ARDS). The primary endpoint is time-weighted average SpO2/FiO2 ratio during the initial post-extubation hour. Main secondary endpoint is the severity of postoperative pulmonary complications (PPCs) computed by postoperative day 7. DISCUSSION: The E-SIGHT trial will be the first randomized controlled trial to evaluate the impact of perioperative sigh ventilation on the postoperative outcomes after on-pump cardiac surgery. The trial will introduce and assess a novel perioperative ventilation approach to mitigate the risk of postoperative hypoxemia and PPCs in patients undergoing cardiac surgery. Also provide the basis for a future larger trial aiming at verifying the impact of sigh ventilation on postoperative pulmonary complications. TRIAL REGISTRATION: ClinicalTrials.gov NCT06248320. Registered on January 30, 2024. Last updated February 26, 2024.

Pulmonary Crystal-Storing Histiocytosis Misdiagnosed as Lung Cancer.

BACKGROUND: Crystalloid storage histiocytosis (CSH) is a rare clinical condition characterized by abnormally high numbers of histiocytes with a large accumulation of crystalline immunoglobulins. Due to its relative rarity, clinical diagnosis of it is frequently incomplete or incorrect. We report a case with pulmonary crystal-storing histiocytosis that was mistakenly identified as lung carcinoma. METHODS: Percutaneous lung biopsy, bronchoscopy. RESULTS: Percutaneous lung biopsy pathology shows granulomatous inflammation with massive eosinophilic infiltration, immunohistochemistry shows CD68, kappa positive, S-100, desmin, myogenin, lambda negative. The final diagnosis is pulmonary crystal-storing histiocytosis. CONCLUSIONS: To get pathology tissue for a definitive diagnosis, patients with pulmonary nodules who have changes in tumor markers or nodule size should have bronchoscopy or percutaneous lung biopsy done as soon as possible.

Mitochondrial Extracellular Vesicles: A Promising Avenue for Diagnosing and Treating Lung Diseases.

Mitochondria, pivotal organelles governing cellular biosynthesis, energy metabolism, and signal transduction, maintain dynamic equilibrium through processes such as biogenesis, fusion, fission, and mitophagy. Growing evidence implicates mitochondrial dysfunction in a spectrum of respiratory diseases including acute lung injury/acute respiratory distress syndrome, bronchial asthma, pulmonary fibrosis, chronic obstructive pulmonary disease, and lung cancer. Consequently, identifying methods capable of ameliorating damaged mitochondrial function is crucial for the treatment of pulmonary diseases. Extracellular vesicles (EVs), nanosized membrane vesicles released by cells into the extracellular space, facilitate intercellular communication by transferring bioactive substances or signals between cells or organs. Recent studies have identified abundant mitochondrial components within specific subsets of EVs, termed mitochondrial extracellular vesicles (mitoEVs), whose contents and compositions vary with disease progression. Moreover, mitoEVs have demonstrated reparative mitochondrial functions in injured recipient cells. However, a comprehensive understanding of mitoEVs is currently lacking, limiting their clinical translation prospects. This Review explores the biogenesis, classification, functional mitochondrial cargo, and biological effects of mitoEVs, with a focus on their role in pulmonary diseases. Emphasis is placed on their potential as biological markers and innovative therapeutic strategies in pulmonary diseases, offering fresh insights for mechanistic studies and drug development in various pulmonary disorders.

Discriminating Benign from Malignant Lung Diseases Using Plasma Glycosaminoglycans and Cell-Free DNA.

We aimed to investigate the use of free glycosaminoglycan profiles (GAGomes) and cfDNA in plasma to differentiate between lung cancer and benign lung disease, in a cohort of 113 patients initially suspected of lung cancer. GAGomes were analyzed in all samples using the MIRAM® Free Glycosaminoglycan Kit with ultra-high-performance liquid chromatography and electrospray ionization triple quadrupole mass spectrometry. In a subset of samples, cfDNA concentration and NGS-data was available. We detected two GAGome features, 0S chondroitin sulfate (CS), and 4S CS, with cancer-specific changes. Based on the observed GAGome changes, we devised a model to predict lung cancer. The model, named the GAGome score, could detect lung cancer with 41.2% sensitivity (95% CI: 9.2-54.2%) at 96.4% specificity (95% CI: 95.2-100.0%, n = 113). When we combined the GAGome score with a cfDNA-based model, the sensitivity increased from 42.6% (95% CI: 31.7-60.6%, cfDNA alone) to 70.5% (95% CI: 57.4-81.5%) at 95% specificity (95% CI: 75.1-100%, n = 74). Notably, the combined GAGome and cfDNA testing improved the sensitivity, compared to cfDNA alone, especially in ASCL stage I (55.6% vs 11.1%). Our findings show that plasma GAGome profiles can enhance cfDNA testing performance, highlighting the applicability of a multiomics approach in lung cancer diagnostics.

In vivo detection of pulmonary mucociliary clearance: present challenges and future directions.

Pulmonary mucociliary clearance (MCC) is an important defence mechanism of the respiratory system and clears pathogens and foreign particles from the airways. Understanding the effect of disease states, drugs, toxins and airway manipulations on MCC could be beneficial in preventing early pulmonary disease and developing new pulmonary therapeutics. This review summarises the current methods and future efforts to detect pulmonary MCC in vivo.

Assessing the accuracy of the revised Cardiac Risk Index compared to the American Society of Anaesthesiologists physical status classification in predicting Pulmonary and Cardiac complications among non-cardiothoracic surgery patients at Muhimbili National Hospital: a prospective cohort study.

BACKGROUND: The Revised Cardiac Risk Index (RCRI) and the American Society of Anaesthesiologists (ASA-PS) classification system are two commonly used tools for preoperative risk assessment. This study aimed to assess the accuracy of RCRI compared to the ASA-PS classification system in preoperative risk assessment for pulmonary and cardiac problems among non-cardiothoracic surgery patients admitted at Muhimbili National Hospital (MNH). METHODS: This was a prospective cohort study design conducted from August 2022 to April 2023 among 184 patients of 18 years and above admitted at MNH for elective non-cardiothoracic surgery. Data Analysis was conducted using STATA software version 16. Means and standard deviations were used to summarize continuous data. Frequencies and percentages were used to summarize categorical data. The logistic regression and ROC curve analysis were used to determine the correlation between variables. RESULTS: The majority of patients (43.3%) had an RCRI score of 1 point, and 39.9% were classified as ASA class 1. Patients in ASA classes 3 and 4 had higher odds of developing cardiac and pulmonary complications (AUC = 0.75 and 0.77, respectively). Patients with an RCRI score of 2 or ≥ 3 points were also more likely to experience cardiac and pulmonary complications (AUC = 0.73 and 0.72, respectively). There was no significant difference in the predictive ability of the two tools. Both RCRI and ASA-PS classification systems were equally effective in predicting these complications. CONCLUSION: Both the RCRI and the ASA-PS classification system demonstrated good predictive ability for cardiac and pulmonary complications among patients undergoing non-cardiothoracic surgery.

Pulmonary actinomycosis misdiagnosed as lung cancer: a case report.

Pulmonary actinomycosis is a rare pulmonary infectious disease that is often challenging to diagnose early and has a high misdiagnosis rate. In some cases, it can be particularly difficult to distinguish pulmonary actinomycosis from lung cancer. We herein report a rare case of pulmonary actinomycosis in which the preoperative examinations strongly suggested lung cancer, leading to the patient undergoing right upper lung resection and bronchoplasty. The patient had a good postoperative recovery; however, the postoperative pathology report indicated pulmonary actinomycosis. In this report, we summarize the key aspects of the diagnosis and treatment of pulmonary actinomycosis to aid clinicians in reducing the likelihood of misdiagnosis.

Recomendaciones para el manejo de la enfermedad pulmonar post tuberculosis / Recommendations for the Management of Post Tuberculosis Lung Disease

Introducción: Los esfuerzos de la lucha contra la tuberculosis (TB) se centran habitualmente en un diagnóstico precoz y un tratamiento eficaz y oportuno para romper la cadena de transmisión de Mycobacterium tuberculosis. Sin embargo, en los últimos años, coincidiendo con la asociación sindémica TB/COVID-19, han aparecido cada vez más evidencias sobre las graves secuelas clínicas, funcionales y psicosociales que puede ocasionar la TB, condición que se ha definido como enfermedad pulmonar post-tuberculosis (PTLD). Aproximadamente, un tercio de los pacientes que sobreviven a la TB se enfrentan a esto, incluyendo síntomas respiratorios persistentes con exacerbaciones episódicas, insuficiencia respiratoria crónica, trastornos emocionales y desafíos psico-sociales que impactan negativamente en la calidad de vida y enfrentan un alto costo catastrófico. Objetivo: Proporcionar un modelo compartido, orientador y científicamente válido para diagnosticar, evaluar y tratar en forma oportuna a los pacientes con PTLD (prevención, diagnóstico, tratamiento y posible rehabilitación). Metodología: Es una investigación documental que incluye revisiones sistemáticas, meta-análisis, estudios observacionales y de las directrices existentes en los últimos años al respecto, sumado a una evaluación por expertos en el tema, con el propósito de adaptarlas a las condiciones locales de cada país latinoamericano. Conclusiones: Considerando la carga mundial, particularmente, latinoamericana de TB, y la carga estimada de la PTLD, se considera urgente el desarrollo de un consenso sobre este tema. Creemos que las recomendaciones de ALAT proporcionarán la base para la formulación y adopción de directrices nacionales para el manejo del PTLD en Amé- rica Latina.

Introduction: Efforts to combat tuberculosis (TB) usually focus on early, rapid diagnosis and effective treatment to break the chain of transmission of Mycobacterium tuberculosis. However, in the last few years, coinciding with the syndemic TB/COVID-19 association, more and more evidence has proved the serious clinical, functional and psycho-social sequelae that TB can cause. This condition has been defined as Post-Pulmonary Disease Tuberculosis (PTLD) and it affects approximately one-third of the patients who survive TB, facing persistent respiratory symptoms with episodic exacerbations, chronic respiratory failure, emotional disorders and psychosocial challenges that negatively impact their life quality, meaning a high catastrophic cost. Objective: Provide a shared, guiding and scientifically valid model to promptly diagnose, evaluate and treat patients with PTLD (prevention, diagnosis, treatment and possible rehabilitation). Methodology: It is documentary research that includes systematic reviews, meta-analysis, observational studies and the guidelines that have existed in recent years in this regard, added to an evaluation by experts, with the purpose of adapting them to local conditions of each Latin American country. Conclusions: Considering the global and, particularly, the Latin American burden of TB, and the estimated burden of PTLD, the development of a consensus document on this topic is urgent. Therefore, we think ALAT recommendations will provide the basis for the formulation and adoption of national specific guidelines for the management of PTLD in Latin America.

Assessment and monitoring of lung disease in patients with severe alpha 1 antitrypsin deficiency: a european delphi consensus of the EARCO group.

BACKGROUND: Currently, there is conflicting information and guidance on the effective management of Alpha 1 Antitrypsin Deficiency (AATD). Establishing a consensus of assessment and disease management specific to AATD is important for achieving a standardized treatment pathway and for improving patient outcomes. Here, we aim to utilize the Delphi method to establish a European consensus for the assessment and management of patients with severe AATD. METHODS: Two rounds of a Delphi survey were completed online by members of the European Alpha-1 Research Collaboration (EARCO). Respondents were asked to indicate their agreement with proposed statements for patients with no respiratory symptoms, stable respiratory disease, and worsening respiratory disease using a Likert scale of 1-7. Levels of agreement between respondents were calculated using a weighted average. RESULTS: Round 1 of the Delphi survey was sent to 103 members of EARCO and 38/103 (36.9%) pulmonologists from across 15 countries completed all 109 questions. Round 2 was sent to all who completed Round 1 and 36/38 (94.7%) completed all 79 questions. Responses regarding spirometry, body plethysmography, high-resolution computed tomography, and the initiation of augmentation therapy showed little variability among physicians, but there was discordance among other aspects, such as the use of low-dose computed tomography in both a research setting and routine clinical care. CONCLUSIONS: These results provide expert opinions for the assessment and monitoring of patients with severe AATD, which could be used to provide updated recommendations and standardized treatment pathways for patients across Europe.

The PROgnostic ModEl for chronic lung disease (PRO-MEL): development and temporal validation.

BACKGROUND: Patients with chronic lung diseases (CLDs), defined as progressive and life-limiting respiratory conditions, experience a heavy symptom burden as the conditions become more advanced, but palliative referral rates are low and late. Prognostic tools can help clinicians identify CLD patients at high risk of deterioration for needs assessments and referral to palliative care. As current prognostic tools may not generalize well across all CLD conditions, we aim to develop and validate a general model to predict one-year mortality in patients presenting with any CLD. METHODS: A retrospective cohort study of patients with a CLD diagnosis at a public hospital from July 2016 to October 2017 was conducted. The outcome of interest was all-cause mortality within one-year of diagnosis. Potential prognostic factors were identified from reviews of prognostic studies in CLD, and data was extracted from electronic medical records. Missing data was imputed using multiple imputation by chained equations. Logistic regression models were developed using variable selection methods and validated in patients seen from January 2018 to December 2019. Discriminative ability, calibration and clinical usefulness of the model was assessed. Model coefficients and performance were pooled across all imputed datasets and reported. RESULTS: Of the 1000 patients, 122 (12.2%) died within one year. Patients had chronic obstructive pulmonary disease or emphysema (55%), bronchiectasis (38%), interstitial lung diseases (12%), or multiple diagnoses (6%). The model selected through forward stepwise variable selection had the highest AUC (0.77 (0.72-0.82)) and consisted of ten prognostic factors. The model AUC for the validation cohort was 0.75 (0.70, 0.81), and the calibration intercept and slope were - 0.14 (-0.54, 0.26) and 0.74 (0.53, 0.95) respectively. Classifying patients with a predicted risk of death exceeding 0.30 as high risk, the model would correctly identify 3 out 10 decedents and 9 of 10 survivors. CONCLUSIONS: We developed and validated a prognostic model for one-year mortality in patients with CLD using routinely available administrative data. The model will support clinicians in identifying patients across various CLD etiologies who are at risk of deterioration for a basic palliative care assessment to identify unmet needs and trigger an early referral to palliative medicine. TRIAL REGISTRATION: Not applicable (retrospective study).

Improving diagnostic strategies in bronchoscopy for peripheral pulmonary lesions.

INTRODUCTION: In the past two decades, bronchoscopy of peripheral pulmonary lesions (PPLs) has improved its diagnostic yield due to the combination of various instruments and devices. Meanwhile, the application is complex and intertwined. AREAS COVERED: This review article outlines strategies in diagnostic bronchoscopy for PPLs. We summarize the utility and evidence of key instruments and devices based on the results of clinical trials. Future perspectives of bronchoscopy for PPLs are also discussed. EXPERT OPINION: The accuracy of reaching PPLs by bronchoscopy has improved significantly with the introduction of combined instruments such as navigation, radial endobronchial ultrasound, digital tomosynthesis, and cone-beam computed tomography. It has been accelerated with the advent of approach tools such as newer ultrathin bronchoscopes and robotic-assisted bronchoscopy. In addition, needle aspiration and cryobiopsy provide further diagnostic opportunities beyond forceps biopsy. Rapid on-site evaluation may also play an important role in decision making during the procedures. As a result, the diagnostic yield of bronchoscopy for PPLs has improved to a level comparable to that of transthoracic needle biopsy. The techniques and technologies developed in the diagnosis will be carried over to the next step in the transbronchial treatment of PPLs in the future.