Machine Learning Algorithms Utilizing Functional Respiratory Imaging May Predict COPD Exacerbations

Rapid deposition analysis of inhaled aerosols in human airways

A rapid data-driven method for determining regional deposition of inhaled medication aerosols in human airways is presented, which is patient specific. Inhalation patterns, device characteristics, and aerodynamic particle size distribution of medications are considered. The method is developed using dimensional analysis and Buckingham Pi theorem, and provides total, regional, and lobar distributions of aerosol deposition. 34 dimensionless quantities are selected, of which 22 encode features of the airway trees and segmented lobes, 14 pertain to the device and the drug formulation, and 13 the inhalation profile of the subject. The dimensionless correlations are obtained using a large database of computational fluid dynamics results on patient specific airways. The intraclass correlation coefficient between the current method and its training dataset is 0.92. The difference between the predicted average lobar deposition in the six asthma patients and the in-vivo data is 1.3%. The model has the potential to offer insights into the effectiveness of personalized drug delivery in clinical settings and can aid in drug development cycles.

Classifying Future Healthcare Utilization in COPD Using Quantitative CT Lung Imaging and Two-Step Feature Selection via Sparse Subspace Learning with the CanCOLD Study

RATIONALE

Although numerous candidate features exist for predicting risk of higher risk of healthcare utilization in patients with chronic obstructive pulmonary disease (COPD), the process for selecting the most discriminative features remains unclear.

OBJECTIVE

The objective of this study was to develop a robust feature selection method to identify the most discriminative candidate features for predicting healthcare utilization in COPD, and compare the model performance with other common feature selection methods.

MATERIALS AND METHODS

In this retrospective study, demographic, lung function measurements and CT images were collected from 454 COPD participants from the Canadian Cohort Obstructive Lung Disease study from 2010-2017. A follow-up visit was completed approximately 1.5 years later and participants reported healthcare utilization. CT analysis was performed for feature extraction. A two-step hybrid feature selection method was proposed that utilized: (1) sparse subspace learning with nonnegative matrix factorization, and, (2) genetic algorithm. Seven commonly used feature selection methods were also implemented that reported the top 10 or 20 features for comparison. Performance was evaluated using accuracy.

RESULTS

Of the 454 COPD participants evaluated, 161 (35%) utilized healthcare services at follow-up. The accuracy for predicting subsequent healthcare utilization for the seven commonly used feature selection methods ranged from 72%-76% with the top 10 features, and 77%-80% with the top 20 features. Relative to these methods, hybrid feature selection obtained significantly higher accuracy for predicting subsequent healthcare utilization at 82% ± 3% (p < 0.05). Selected features with the proposed method included: DLCO, FEV1, RV, FVC, TAC, LAA950, Pi-10, LAA856, LAC total hole count, outer area RB1, wall area RB1, wall area and Jacobian.

CONCLUSION

The hybrid feature selection method identified the most discriminative features for classifying individuals with and without future healthcare utilization, and increased the accuracy compared to other state-of-the-art approaches.

Artificial intelligence in COPD CT images: identification, staging, and quantitation

Chronic obstructive pulmonary disease (COPD) stands as a significant global health challenge, with its intricate pathophysiological manifestations often demanding advanced diagnostic strategies. The recent applications of artificial intelligence (AI) within the realm of medical imaging, especially in computed tomography, present a promising avenue for transformative changes in COPD diagnosis and management. This review delves deep into the capabilities and advancements of AI, particularly focusing on machine learning and deep learning, and their applications in COPD identification, staging, and imaging phenotypes. Emphasis is laid on the AI-powered insights into emphysema, airway dynamics, and vascular structures. The challenges linked with data intricacies and the integration of AI in the clinical landscape are discussed. Lastly, the review casts a forward-looking perspective, highlighting emerging innovations in AI for COPD imaging and the potential of interdisciplinary collaborations, hinting at a future where AI doesn't just support but pioneers breakthroughs in COPD care. Through this review, we aim to provide a comprehensive understanding of the current state and future potential of AI in shaping the landscape of COPD diagnosis and management.

Quantitative CT Lung Imaging and Machine Learning Improves Prediction of Emergency Room Visits and Hospitalizations in COPD

RATIONALE

Predicting increased risk of future healthcare utilization in chronic obstructive pulmonary disease (COPD) patients is an important goal for improving patient management.

OBJECTIVE

Our objective was to determine the importance of computed tomography (CT) lung imaging measurements relative to other demographic and clinical measurements for predicting future health services use with machine learning in COPD.

MATERIALS AND METHODS

In this retrospective study, lung function measurements and chest CT images were acquired from Canadian Cohort of Obstructive Lung Disease study participants from 2010 to 2017 (https://clinicaltrials.gov, NCT00920348). Up to two follow-up visits (1.5- and 3-year follow-up) were performed and participants were asked for details related to healthcare utilization. Healthcare utilization was defined as any COPD hospitalization or emergency room visit due to respiratory problems in the 12 months prior to the follow-up visits. CT analysis was performed (VIDA Diagnostics Inc.); a total of 108 CT quantitative emphysema, airway and vascular measurements were investigated. A hybrid feature selection method with support vector machine classifier was used to predict healthcare utilization. Performance was determined using accuracy, F1-measure and area under the receiver operating characteristic curve (AUC) and Matthews's correlation coefficient (MC).

RESULTS

Of the 527 COPD participants evaluated, 179 (35%) used healthcare services at follow-up. There were no significant differences between the participants with or without healthcare utilization at follow-up for age (p = 0.50), sex (p = 0.44), BMI (p = 0.05) or pack-years (p = 0.76). The accuracy for predicting subsequent healthcare utilization was 80% ± 3% (F1-measure = 74%, AUC = 0.80, MC = 0.6) when all measurements were considered, 76% ± 6% (F1-measure = 72%, AUC = 0.77, MC = 0.55) for CT measurements alone and 65% ± 5% (F1-measure = 60%, AUC = 0.67, MC = 0.34) for demographic and lung function measurements alone.

CONCLUSION

The combination of CT lung imaging and conventional measurements leads to greater prediction accuracy of subsequent health services use than conventional measurements alone, and may provide needed prognostic information for patients suffering from COPD.

CT-Based Commercial Software Applications: Improving Patient Care Through Accurate COPD Subtyping

Chronic obstructive pulmonary disease (COPD) is heterogenous in its clinical manifestations and disease progression. Patients often have disease courses that are difficult to predict with readily available data, such as lung function testing. The ability to better classify COPD into well-defined groups will allow researchers and clinicians to tailor novel therapies, monitor their effects, and improve patient-centered outcomes. Different modalities of assessing these COPD phenotypes are actively being studied, and an area of great promise includes the use of quantitative computed tomography (QCT) techniques focused on key features such as airway anatomy, lung density, and vascular morphology. Over the last few decades, companies around the world have commercialized automated CT software packages that have proven immensely useful in these endeavors. This article reviews the key features of several commercial platforms, including the technologies they are based on, the metrics they can generate, and their clinical correlations and applications. While such tools are increasingly being used in research and clinical settings, they have yet to be consistently adopted for diagnostic work-up and treatment planning, and their full potential remains to be explored.

Dynamic Quantitative Magnetic Resonance Imaging Assessment of Areas of the Lung During Free-Breathing of Patients with Chronic Obstructive Pulmonary Disease

RATIONALE AND OBJECTIVES

Changes in the geometry of the chest wall due to lung hyperinflation occur in COPD. However, the quantitative assessment of impaired lung motions and its association with the clinical characteristics of COPD patients are unclear. This study aimed to investigate the respiratory kinetics of COPD patients by dynamic MRI.

MATERIALS AND METHODS

This study enrolled 22 COPD patients and 10 normal participants who underwent dynamic MRI and pulmonary function testing (PFT). Changes in the areas of the lung and mediastinum during respiration were compared between the COPD patients and the normal controls. Relationships between MRI, CT parameters, and clinical measures that included PFT results also were evaluated.

RESULTS

Asynchronous movements and decreased diaphragmatic motion were found in COPD patients. COPD patients had a larger ratio of MRI-measured lung areas at expiration to inspiration, a smaller magnitude of the peak area change ratio, and a smaller mediastinal-thoracic area ratio than the normal participants. The lung area ratio was associated with FEV₁/FVC, predicted RV%, and CT lung volume/predicted total lung capacity (pTLC). The lung area ratio of the right lower and left lower lungs was significantly correlated with emphysema of each lower lobe. The expiratory mediastinal-thoracic area ratio was associated with FEV₁% predicted and RV/TLC.

CONCLUSION

Changes in the lung areas of COPD patients as shown on MRI reflected the severity of airflow limitation, hyperinflation, and the extent of emphysema. Dynamic MRI provides essential information about respiratory kinetics in COPD.

Digital healthcare in COPD management: a narrative review on the advantages, pitfalls, and need for further research

Chronic obstructive pulmonary disease (COPD) remains a leading cause of morbidity and mortality despite current treatment strategies which focus on smoking cessation, pulmonary rehabilitation, and symptomatic relief. A focus of COPD care is to encourage self-management, particularly during COVID-19, where much face-to-face care has been reduced or ceased. Digital health solutions may offer affordable and scalable solutions to support COPD patient education and self-management, such solutions could improve clinical outcomes and expand service reach for limited additional cost. However, optimal ways to deliver digital medicine are still in development, and there are a number of important considerations for clinicians, commissioners, and patients to ensure successful implementation of digitally augmented care. In this narrative review, we discuss advantages, pitfalls, and future prospects of digital healthcare, which offer a variety of tools including self-management plans, education videos, inhaler training videos, feedback to patients and healthcare professionals (HCPs), exacerbation monitoring, and pulmonary rehabilitation. We discuss the key issues with sustaining patient and HCP engagement and limiting attrition of use, interoperability with devices, integration into healthcare systems, and ensuring inclusivity and accessibility. We explore the essential areas of research beyond determining safety and efficacy to understand the acceptability of digital healthcare solutions to patients, clinicians, and healthcare systems, and hence ways to improve this and sustain engagement. Finally, we explore the regulatory challenges to ensure quality and engagement and effective integration into current healthcare systems and care pathways, while maintaining patients' autonomy and privacy. Understanding and addressing these issues and successful incorporation of an acceptable, simple, scalable, affordable, and future-proof digital solution into healthcare systems could help remodel global chronic disease management and fractured healthcare systems to provide best patient care and optimisation of healthcare resources to meet the global burden and unmet clinical need of COPD.

Value of refined care in patients with acute exacerbation of chronic obstructive pulmonary disease

BACKGROUND

Under physiological conditions, sputum produced during acute exacerbation of chronic obstructive pulmonary disease (AECOPD) can move passively with the cilia in the airway; the sputum is gradually excreted from the depth of the airways through the stimulation of the coughing reflex on the sensory nerve on the surface of the airway. However, when the sputum is thick, the cough is weak, or the tracheal cilia are abnormal, sputum accumulation may occur and affect the exchange of oxygen and carbon dioxide in the lung. Furthermore, the presence of pathogenic microorganisms in sputum may cause or aggravate the symptoms of pulmonary infection in patients, which is the main factor leading to AECOPD. Therefore, promoting effective drainage of sputum and maintaining airway opening are key points requiring clinical attention.

AIM

To explore the effect of refined nursing strategies in patients with AECOPD and dysphagia.

METHODS

We selected 126 patients with AECOPD and difficulty of expectoration at our hospital, and divided them into a refined care group and a routine care group, with 63 cases each, using a random number table. The two groups of patients were treated with expectorant, anti-infection, oxygen inhalation, and other basic treatment measures; patients in the refined care group were given refined nursing intervention during hospitalization, and the routine care group received conventional nursing intervention. The differences in sputum expectoration, negative pressure suction rate, blood gas parameters, dyspnea score measured through the tool developed by the Medical Research Council (MRC), and quality of life were compared between the two groups.

RESULTS

After 7 d of intervention, the sputum expectoration effect of the refined care group was 62.30%, the effective rate was 31.15%, and the inefficiency rate was 6.56%. The sputum expectoration effect of the routine care group was 44.07%, the effective rate was 42.37%, and the inefficiency rate was 13.56%. The refined care group had better sputum expectoration than the routine care group (P < 0.05). The negative pressure suction rate in the refined care group was significantly lower than that of the routine care group during the treatment (22.95% vs 44.07%, P < 0.05). Before the intervention, the arterial oxygen saturation (PaO₂) and arterial carbon dioxide saturation (PaCO₂) values were not significantly different between the two groups (P > 0.05); the PaO₂ and PaCO₂ values in the refined care group were comparable to those in the routine care group after 7 d of intervention (P > 0.05). Before the intervention, there was no significant difference in the MRC score between the two groups (P > 0.05); the MRC score of the refined care group was lower than that of the routine care group after 7 d of intervention, but the difference was not statistically significant (P > 0.05). Before intervention, there was no significant difference in the symptoms, activities, disease impact, or St. George’s Respiratory questionnaire (SGRQ) total scores between the two groups (P> 0.05). After 7 days of intervention, the symptoms, activities, and total score of SGRQ of the refined care group were higher than those of the routine care group, but the difference was not statistically significant (P > 0.05).

CONCLUSION

AECOPD with thick sputum, weak coughing reflex, and abnormal tracheal cilia function will lead to sputum accumulation and affect the exchange of oxygen and carbon dioxide in the lung. Patients with AECOPD who have difficulty expectorating sputum may undergo refined nursing strategies that will promote expectoration, alleviate clinical symptoms, and improve the quality of life.

An Inhaled PI3Kδ Inhibitor Improves Recovery in Acutely Exacerbating COPD Patients: A Randomized Trial

Purpose

This study evaluated the safety and efficacy of inhaled nemiralisib, a phosphoinositide 3-kinase δ (PI3Kδ) inhibitor, in patients with an acute exacerbation of chronic obstructive pulmonary disease (COPD).

Methods

In this double-blind, placebo-controlled study, 126 patients (40–80 years with a post-bronchodilator forced expiratory volume in 1 sec (FEV₁) ≤80% of predicted (previously documented)) were randomized 1:1 to once daily inhaled nemiralisib (1 mg) or placebo for 84 days, added to standard of care. The primary endpoint was specific imaging airway volume (siVaw) after 28 treatment days and was analyzed using a Bayesian repeated measures model (clintrials.gov: NCT02294734).

Results

A total of 126 patients were randomized to treatment; 55 on active treatment and 49 on placebo completed the study. When comparing nemiralisib and placebo-treated patients, an 18% placebo-corrected increase from baseline in distal siVaw (95% credible intervals (Cr I) (−1%, 42%)) was observed on Day 28. The probability that the true treatment ratio was >0% (Pr(θ>0)) was 96%, suggestive of a real treatment effect. Improvements were observed across all lung lobes. Patients treated with nemiralisib experienced a 107.3 mL improvement in posterior median FEV₁ (change from baseline, 95% Cr I (−2.1, 215.5)) at day 84, compared with placebo. Adverse events were reported by 41 patients on placebo and 49 on nemiralisib, the most common being post-inhalation cough on nemiralisib (35%) vs placebo (3%).

Conclusion

These data show that addition of nemiralisib to usual care delivers more effective recovery from an acute exacerbation and improves lung function parameters including siVaw and FEV₁. Although post-inhalation cough was identified, nemiralisib was otherwise well tolerated, providing a promising novel therapy for this acutely ill patient group.

Multilevel threshold image segmentation with diffusion association slime mould algorithm and Renyi's entropy for chronic obstructive pulmonary disease

Image segmentation is an essential pre-processing step and is an indispensable part of image analysis. This paper proposes Renyi's entropy multi-threshold image segmentation based on an improved Slime Mould Algorithm (DASMA). First, we introduce the diffusion mechanism (DM) into the original SMA to increase the population's diversity so that the variants can better avoid falling into local optima. The association strategy (AS) is then added to help the algorithm find the optimal solution faster. Finally, the proposed algorithm is applied to Renyi's entropy multilevel threshold image segmentation based on non-local means 2D histogram. The proposed method's effectiveness is demonstrated on the Berkeley segmentation dataset and benchmark (BSD) by comparing it with some well-known algorithms. The DASMA-based multilevel threshold segmentation technique is also successfully applied to the CT image segmentation of chronic obstructive pulmonary disease (COPD). The experimental results are evaluated by image quality metrics, which show the proposed algorithm's extraordinary performance. This means that it can help doctors analyze the lesion tissue qualitatively and quantitatively, improve its diagnostic accuracy and make the right treatment plan. The supplementary material and info about this article will be available at https://aliasgharheidari.com.

Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary Disease

Chronic airway diseases are characterized by airway inflammation, obstruction, and remodeling and show high prevalence, especially in developing countries. Among them, asthma and chronic obstructive pulmonary disease (COPD) show the highest morbidity and socioeconomic burden worldwide. Although there are extensive guidelines for the prevention, early diagnosis, and rational treatment of these lifelong diseases, their value in precision medicine is very limited. Artificial intelligence (AI) and machine learning (ML) techniques have emerged as effective methods for mining and integrating large-scale, heterogeneous medical data for clinical practice, and several AI and ML methods have recently been applied to asthma and COPD. However, very few methods have significantly contributed to clinical practice. Here, we review four aspects of AI and ML implementation in asthma and COPD to summarize existing knowledge and indicate future steps required for the safe and effective application of AI and ML tools by clinicians.

Remote Patient Monitoring for the Detection of COPD Exacerbations

Background

COPD exacerbations occur more frequently with disease progression and are associated with worse prognosis and higher healthcare expenditure.

Purpose

To utilize a networked system, optimized with statistical process control (SPC), for remote patient monitoring (RPM) and to identify potential predictors of COPD exacerbations.

Methods

Seventeen subjects, mean (SD) age of 69.7 (7.2) years, with moderate to severe COPD received RPM. Over 2618 patient-days (7.17 patient-years) of monitoring, we obtained daily symptom scores, treatment adherence, self-reported activity levels, daily spirometry (SVC, FEV₁, FVC, PEF), inspiratory capacity (IC), and oxygenation (SpO₂). These data were used to identify predictors of exacerbations defined using Anthonisen and other criteria.

Results

After implementation of SPC, concordance analysis showed substantial agreement between FVC (decrease below the 7-day rolling average minus 1.645 SD) and self-reported healthcare utilization events (κ=0.747, P<0.001) as well as between increased use of inhaled short-acting bronchodilators and exacerbations defined by two Anthonisen criteria (κ=0.611, P<0.001) or modified Anthonisen criteria (κ=0.622, P<0.001). There was a moderate agreement between FEV₁ (decrease >1.645 SD below the 7-day rolling average) and self-reported healthcare utilization events (κ=0.475, P<0.001) and between SpO₂ less than 90% and exacerbations defined by two Anthonisen criteria (κ=0.474, P<0.001) or modified Anthonisen criteria (κ=0.564, P<0.001).

Conclusion

Exacerbations were best predicted by FVC and FEV₁ below the one-sided 95% confidence interval derived from SPC but also by increased use of inhaled short-acting bronchodilators and fall in oxygen saturation. An RPM program that captures these parameters may be used to guide appropriate interventions aimed at reducing healthcare utilization in COPD patients.

Targeted lung denervation in sheep: durability of denervation and long-term histologic effects on bronchial wall and peribronchial structures

BACKGROUND

Targeted lung denervation (TLD), a novel bronchoscopic procedure which attenuates pulmonary nerve input to the lung to reduce the clinical consequences of neural hyperactivity, may be an important emerging treatment for COPD. While procedural safety and impact on clinical outcomes have recently been reported, the mechanism of action has not been reported. We explored the long-term pathologic and histopathologic effects in a sheep model of ablation of bronchial branches of the vagus nerve using a novel dual-cooled radiofrequency ablation catheter.

METHODS

Nineteen sheep underwent circumferential ablation of both main bronchi with simultaneous balloon surface cooling using a targeted lung denervation system (Nuvaira, Inc., USA). Animals were followed over an extended time course (30, 365, and 640 days post procedure). At each time point, lung denervation (axonal staining in bronchial nerves), and effect on peribronchial structures near the treatment site (histopathology of bronchial epithelium, bronchial cartilage, smooth muscle, alveolar parenchyma, and esophagus) were quantified. One way analysis of variance (ANOVA) was performed to reveal differences between group means on normal data. Non-parametric analysis using Kruskal-Wallis Test was employed on non-normal data sets.

RESULTS

No adverse clinical effects were observed in any sheep. Nerve axon staining distal to the ablation site was decreased by 60% at 30 days after TLD and efferent axon staining was decreased by >70% at 365 and 640 days. All treated airways exhibited 100% epithelial integrity. Effect on peribronchial structures was strictly limited to lung tissue immediately adjacent to the ablation site. Tissue structure 1 cm proximal and distal to the treatment area remained normal, and the pulmonary veins, pulmonary arteries, and esophagus were unaffected.

CONCLUSIONS

The denervation of efferent axons induced by TLD therapy is durable and likely a contributing mechanism through which targeted lung denervation impacts clinical outcomes. Further, long term lung denervation did not alter the anatomy of the bronchioles or lung, as evaluated from both a gross and histologic perspective.