Applications of artificial intelligence and machine learning in respiratory medicine

Early prediction of pediatric asthma in the Canadian Healthy Infant Longitudinal Development (CHILD) birth cohort using machine learning

BACKGROUND

Early identification of children at risk of asthma can have significant clinical implications for effective intervention and treatment. This study aims to disentangle the relative timing and importance of early markers of asthma.

METHODS

Using the CHILD Cohort Study, 132 variables measured in 1754 multi-ethnic children were included in the analysis for asthma prediction. Data up to 4 years of age was used in multiple machine learning models to predict physician-diagnosed asthma at age 5 years. Both predictive performance and variable importance was assessed in these models.

RESULTS

Early-life data (≤1 year) has limited predictive ability for physician-diagnosed asthma at age 5 years (area under the precision-recall curve (AUPRC) < 0.35). The earliest reliable prediction of asthma is achieved at age 3 years, (area under the receiver-operator curve (AUROC) > 0.90) and (AUPRC > 0.80). Maternal asthma, antibiotic exposure, and lower respiratory tract infections remained highly predictive throughout childhood. Wheezing status and atopy are the most important predictors of early childhood asthma from among the factors included in this study.

CONCLUSIONS

Childhood asthma is predictable from non-biological measurements from the age of 3 years, primarily using parental asthma and patient history of wheezing, atopy, antibiotic exposure, and lower respiratory tract infections.

IMPACT

Machine learning models can predict physician-diagnosed asthma in early childhood (AUROC > 0.90 and AUPRC > 0.80) using ≥3 years of non-biological and non-genetic information, whereas prediction with the same patient information available before 1 year of age is challenging. Wheezing, atopy, antibiotic exposure, lower respiratory tract infections, and the child's mother having asthma were the strongest early markers of 5-year asthma diagnosis, suggesting an opportunity for earlier diagnosis and intervention and focused assessment of patients at risk for asthma, with an evolving risk stratification over time.

Supervised training models with or without manual lesion delineation outperform clinicians in distinguishing pulmonary cryptococcosis from lung adenocarcinoma on chest CT

BACKGROUND

The role of artificial intelligence (AI) in the discrimination between pulmonary cryptococcosis (PC) and lung adenocarcinoma (LA) warrants further research.

OBJECTIVES

To compare the performances of AI models with clinicians in distinguishing PC from LA on chest CT.

METHODS

Patients diagnosed with confirmed PC or LA were retrospectively recruited from three tertiary hospitals in Guangzhou. A deep learning framework was employed to develop two models: an undelineated supervised training (UST) model utilising original CT images, and a delineated supervised training (DST) model utilising CT images with manual lesion annotations provided by physicians. A subset of 20 cases was randomly selected from the entire dataset and reviewed by clinicians through a network questionnaire. The sensitivity, specificity and accuracy of the models and the clinicians were calculated.

RESULTS

A total of 395 PC cases and 249 LA cases were included in the final analysis. The internal validation results for the UST model showed a sensitivity of 85.3%, specificity of 81.0%, accuracy of 83.6% and an area under the curve (AUC) of 0.93. Similarly, the DST model exhibited a sensitivity of 88.2%, specificity of 88.1%, accuracy of 88.2% and an AUC of 0.94. The external validation of the two models yielded AUC values of 0.74 and 0.77, respectively. The average sensitivity, specificity and accuracy of 102 clinicians were determined to be 63.1%, 53.7% and 59.3%, respectively.

CONCLUSIONS

Both models outperformed the clinicians in distinguishing between PC and LA on chest CT, with the UST model exhibiting comparable performance to the DST model.

Computer-aided diagnostic accuracy of pulmonary tuberculosis on chest radiography among lower respiratory tract symptoms patients

Even though the Gaza Strip is a low pulmonary tuberculosis (TB) burden region, it is well-known that TB is primarily a socioeconomic problem associated with overcrowding, poor hygiene, a lack of fresh water, and limited access to healthcare, which is the typical case in the Gaza Strip. Therefore, this study aimed at assessing the accuracy of the automatic software computer-aided detection for tuberculosis (CAD4TB) in diagnosing pulmonary TB on chest radiography and compare the CAD4TB software reading with the results of geneXpert. Using a census sampling method, the study was conducted in radiology departments in the Gaza Strip hospitals between 1 December 2022 and 31 March 2023. A digital X-ray, printer, and online X-ray system backed by CAD4TBv6 software were used to screen patients with lower respiratory tract symptoms. GeneXpert analysis was performed for all patients having a score > 40. A total of 1,237 patients presenting with lower respiratory tract symptoms participated in this current study. Chest X-ray readings showed that 7.8% (n = 96) were presumptive for TB. The CAD4TBv6 scores showed that 11.8% (n = 146) of recruited patients were presumptive for TB. GeneXpert testing on sputum samples showed that 6.2% (n = 77) of those with a score > 40 on CAD4TB were positive for pulmonary TB. Significant differences were found in chest X-ray readings, CAD4TBv6 scores, and GeneXpert results among sociodemographic and health status variables (P-value < 0.05). The study showed that the incidence rate of TB in the Gaza Strip is 3.5 per 100,000 population in the Gaza strip. The sensitivity of the CAD4TBv6 score and the symptomatic review for tuberculosis with a threshold score of >40 is 80.2%, and the specificity is 94.0%. The positive Likelihood Ratio is 13.3%, Negative Likelihood Ratio is 0.2 with 7.8% prevalence. Positive Predictive Value is 52.7%, Negative Predictive Value is 98.3%, and accuracy is 92.9%. In a resource-limited country with a high burden of neglected disease, combining chest X-ray readings by CAD4TB and symptomatology is extremely valuable for screening a population at risk. CAD4TB is noticeably more efficient than other methods for TB screening and early diagnosis in people who would otherwise go undetected.

Remote patient monitoring strategies and wearable technology in chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease (COPD) is highly prevalent and is associated with a heavy burden on patients and health systems alike. Exacerbations of COPD (ECOPDs) are a leading cause of acute hospitalization among all adult chronic diseases. There is currently a paradigm shift in the way that ECOPDs are conceptualized. For the first time, objective physiological parameters are being used to define/classify what an ECOPD is (including heart rate, respiratory rate, and oxygen saturation criteria) and therefore a mechanism to monitor and measure their changes, particularly in an outpatient ambulatory setting, are now of great value. In addition to pre-existing challenges on traditional 'in-person' health models such as geography and seasonal (ex. winter) impacts on the ability to deliver in-person visit-based care, the COVID-19 pandemic imposed additional stressors including lockdowns, social distancing, and the closure of pulmonary function labs. These health system stressors, combined with the new conceptualization of ECOPDs, rapid advances in sophistication of hardware and software, and a general openness by stakeholders to embrace this technology, have all influenced the propulsion of remote patient monitoring (RPM) and wearable technology in the modern care of COPD. The present article reviews the use of RPM and wearable technology in COPD. Context on the influences, factors and forces which have helped shape this health system innovation is provided. A focused summary of the literature of RPM in COPD is presented. Finally, the practical and ethical principles which must guide the transition of RPM in COPD into real-world clinical use are reviewed.

Exploring the Intersection of Artificial Intelligence and Clinical Healthcare: A Multidisciplinary Review

Artificial intelligence (AI) plays a more and more important role in our everyday life due to the advantages that it brings when used, such as 24/7 availability, a very low percentage of errors, ability to provide real time insights, or performing a fast analysis. AI is increasingly being used in clinical medical and dental healthcare analyses, with valuable applications, which include disease diagnosis, risk assessment, treatment planning, and drug discovery. This paper presents a narrative literature review of AI use in healthcare from a multi-disciplinary perspective, specifically in the cardiology, allergology, endocrinology, and dental fields. The paper highlights data from recent research and development efforts in AI for healthcare, as well as challenges and limitations associated with AI implementation, such as data privacy and security considerations, along with ethical and legal concerns. The regulation of responsible design, development, and use of AI in healthcare is still in early stages due to the rapid evolution of the field. However, it is our duty to carefully consider the ethical implications of implementing AI and to respond appropriately. With the potential to reshape healthcare delivery and enhance patient outcomes, AI systems continue to reveal their capabilities.

Predicting total lung capacity from spirometry: a machine learning approach

Background and objective

Spirometry patterns can suggest that a patient has a restrictive ventilatory impairment; however, lung volume measurements such as total lung capacity (TLC) are required to confirm the diagnosis. The aim of the study was to train a supervised machine learning model that can accurately estimate TLC values from spirometry and subsequently identify which patients would most benefit from undergoing a complete pulmonary function test.

Methods

We trained three tree-based machine learning models on 51,761 spirometry data points with corresponding TLC measurements. We then compared model performance using an independent test set consisting of 1,402 patients. The best-performing model was used to retrospectively identify restrictive ventilatory impairment in the same test set. The algorithm was compared against different spirometry patterns commonly used to predict restriction.

Results

The prevalence of restrictive ventilatory impairment in the test set is 16.7% (234/1402). CatBoost was the best-performing machine learning model. It predicted TLC with a mean squared error (MSE) of 560.1 mL. The sensitivity, specificity, and F1-score of the optimal algorithm for predicting restrictive ventilatory impairment was 83, 92, and 75%, respectively.

Conclusion

A machine learning model trained on spirometry data can estimate TLC to a high degree of accuracy. This approach could be used to develop future smart home-based spirometry solutions, which could aid decision making and self-monitoring in patients with restrictive lung diseases.

Human-guided deep learning with ante-hoc explainability by convolutional network from non-image data for pregnancy prognostication

BACKGROUND AND OBJECTIVE

Deep learning is applied in medicine mostly due to its state-of-the-art performance for diagnostic imaging. Supervisory authorities also require the model to be explainable, but most explain the model after development (post hoc) instead of incorporating explanation into the design (ante hoc). This study aimed to demonstrate a human-guided deep learning with ante-hoc explainability by convolutional network from non-image data to develop, validate, and deploy a prognostic prediction model for PROM and an estimator of time of delivery using a nationwide health insurance database.

METHODS

To guide modeling, we constructed and verified association diagrams respectively from literatures and electronic health records. Non-image data were transformed into meaningful images utilizing predictor-to-predictor similarities, harnessing the power of convolutional neural network mostly used for diagnostic imaging. The network architecture was also inferred from the similarities.

RESULTS

This resulted the best model for prelabor rupture of membranes (n=883, 376) with the area under curves 0.73 (95% CI 0.72 to 0.75) and 0.70 (95% CI 0.69 to 0.71) respectively by internal and external validations, and outperformed previous models found by systematic review. It was explainable by knowledge-based diagrams and model representation.

CONCLUSIONS

This allows prognostication with actionable insights for preventive medicine.

Machine-Learning Model for Mortality Prediction in Patients With Community-Acquired Pneumonia: Development and Validation Study

BACKGROUND

Artificial intelligence tools and techniques such as machine learning (ML) are increasingly seen as a suitable manner in which to increase the prediction capacity of currently available clinical tools, including prognostic scores. However, studies evaluating the efficacy of ML methods in enhancing the predictive capacity of existing scores for community-acquired pneumonia (CAP) are limited. We aimed to apply and validate a causal probabilistic network (CPN) model to predict mortality in patients with CAP.

RESEARCH QUESTION

Is a CPN model able to predict mortality in patients with CAP better than the commonly used severity scores?

STUDY DESIGN AND METHODS

This was a derivation-validation retrospective study conducted in two Spanish university hospitals. The ability of a CPN designed to predict mortality in sepsis (SepsisFinder [SeF]), and adapted for CAP (SeF-ML), to predict 30-day mortality was assessed and compared with other scoring systems (Pneumonia Severity Index [PSI], Sequential Organ Failure Assessment [SOFA], quick Sequential Organ Failure Assessment [qSOFA], and CURB-65 criteria [confusion, urea, respiratory rate, BP, age ≥ 65 years]). The SeF models are proprietary software. Differences between receiver operating characteristic curves were assessed by the DeLong method for correlated receiver operating characteristic curves.

RESULTS

The derivation cohort comprised 4,531 patients, and the validation cohort consisted of 1,034 patients. In the derivation cohort, the areas under the curve (AUCs) of SeF-ML, CURB-65, SOFA, PSI, and qSOFA were 0.801, 0.759, 0.671, 0.799, and 0.642, respectively, for 30-day mortality prediction. In the validation study, the AUC of SeF-ML was 0.826, concordant with the AUC (0.801) in the derivation data (P = .51). The AUC of SeF-ML was significantly higher than those of CURB-65 (0.764; P = .03) and qSOFA (0.729, P = .005). However, it did not differ significantly from those of PSI (0.830; P = .92) and SOFA (0.771; P = .14).

INTERPRETATION

SeF-ML shows potential for improving mortality prediction among patients with CAP, using structured health data. Additional external validation studies should be conducted to support generalizability.

Development and application of survey-based artificial intelligence for clinical decision support in managing infectious diseases: A pilot study on a hospital in central Vietnam

Introduction

In this study, we developed a simplified artificial intelligence to support the clinical decision-making of medical personnel in a resource-limited setting.

Methods

We selected seven infectious disease categories that impose a heavy disease burden in the central Vietnam region: mosquito-borne disease, acute gastroenteritis, respiratory tract infection, pulmonary tuberculosis, sepsis, primary nervous system infection, and viral hepatitis. We developed a set of questionnaires to collect information on the current symptoms and history of patients suspected to have infectious diseases. We used data collected from 1,129 patients to develop and test a diagnostic model. We used XGBoost, LightGBM, and CatBoost algorithms to create artificial intelligence for clinical decision support. We used a 4-fold cross-validation method to validate the artificial intelligence model. After 4-fold cross-validation, we tested artificial intelligence models on a separate test dataset and estimated diagnostic accuracy for each model.

Results

We recruited 1,129 patients for final analyses. Artificial intelligence developed by the CatBoost algorithm showed the best performance, with 87.61% accuracy and an F1-score of 87.71. The F1-score of the CatBoost model by disease entity ranged from 0.80 to 0.97. Diagnostic accuracy was the lowest for sepsis and the highest for central nervous system infection.

Conclusion

Simplified artificial intelligence could be helpful in clinical decision support in settings with limited resources.

Where Is the Artificial Intelligence Applied in Dentistry? Systematic Review and Literature Analysis

This literature research had two main objectives. The first objective was to quantify how frequently artificial intelligence (AI) was utilized in dental literature from 2011 until 2021. The second objective was to distinguish the focus of such publications; in particular, dental field and topic. The main inclusion criterium was an original article or review in English focused on dental utilization of AI. All other types of publications or non-dental or non-AI-focused were excluded. The information sources were Web of Science, PubMed, Scopus, and Google Scholar, queried on 19 April 2022. The search string was “artificial intelligence” AND (dental OR dentistry OR tooth OR teeth OR dentofacial OR maxillofacial OR orofacial OR orthodontics OR endodontics OR periodontics OR prosthodontics). Following the removal of duplicates, all remaining publications were returned by searches and were screened by three independent operators to minimize the risk of bias. The analysis of 2011–2021 publications identified 4413 records, from which 1497 were finally selected and calculated according to the year of publication. The results confirmed a historically unprecedented boom in AI dental publications, with an average increase of 21.6% per year over the last decade and a 34.9% increase per year over the last 5 years. In the achievement of the second objective, qualitative assessment of dental AI publications since 2021 identified 1717 records, with 497 papers finally selected. The results of this assessment indicated the relative proportions of focal topics, as follows: radiology 26.36%, orthodontics 18.31%, general scope 17.10%, restorative 12.09%, surgery 11.87% and education 5.63%. The review confirms that the current use of artificial intelligence in dentistry is concentrated mainly around the evaluation of digital diagnostic methods, especially radiology; however, its implementation is expected to gradually penetrate all parts of the profession.

Additive manufacturing in respiratory sciences - Current applications and future prospects

Additive Manufacturing (AM) comprises a variety of techniques that enable fabrication of customised objects with specific attributes. The versatility of AM procedures and constant technological improvements allow for their application in the development of medicinal products and medical devices. This review provides an overview of AM applications related to respiratory sciences. For this purpose, both fields of research are briefly introduced and the potential benefits of integrating AM to respiratory sciences at different levels of pharmaceutical development are highlighted. Tailored manufacturing of microstructures as a particle design approach in respiratory drug delivery will be discussed. At the dosage form level, we exemplify AM as an important link in the iterative loop of data driven inhaler design, rapid prototyping and in vitro testing. This review also presents the application of bioprinting in the respiratory field for design of biorelevant in vitro cellular models, followed by an overview of AM-related processes in preventive and therapeutic care. Finally, this review discusses future prospects of AM as a component in a digital health environment.

A narrative review of deep learning applications in lung cancer research: from screening to prognostication

Background and Objective

Deep learning (DL) algorithms have been developed for various tasks, including lung nodule detection on chest radiographs or lung cancer computed tomography screening, potential candidate selection in lung cancer screening, malignancy prediction for indeterminate pulmonary nodules, lung cancer staging, treatment response prediction, prognostication, and prediction of genetic mutations in lung cancer. Furthermore, these DL algorithms have been applied in various clinical settings in order for them to be generalized in real-world clinical practice. Multiple DL algorithms have been corroborated to be on par with experts or current clinical prediction models for several specific tasks. However, no article has yet comprehensively reviewed DL algorithms dedicated to lung cancer research. This narrative review presents an overview of the literature dealing with DL techniques applied in lung cancer research and briefly summarizes the results according to the DL algorithms’ clinical use cases.

Methods

we performed a narrative review by searching the Embase and OVID-MEDLINE databases for articles published in English from October, 2016 until September, 2021 and reviewing the bibliographies of key references to identify important literature related to DL in lung cancer research. The background, development, results, and clinical implications of each DL algorithm are briefly discussed. Lastly, we end this review article by highlighting future directions in lung cancer research using DL techniques.

Key Content and Findings

DL algorithms have been introduced to show comparable or higher performance than human experts in various clinical settings. Specifically, they have been actively applied to detect lung nodules in chest radiographs or computed tomography (CT) examinations, optimize candidate selection for lung cancer screening (LCS), predict the malignancy of lung nodules, stage lung cancer, and predict treatment response, patients’ prognoses, and genetic mutations in lung cancers.

Conclusions

DL algorithms have corroborated their potential value for various tasks, ranging from lung cancer screening to prognostication of lung cancer patients. Future research is warranted for the clinical application of these algorithms in daily clinical practice and verification of their real-world clinical usefulness.

Efficient screening for severe aortic valve stenosis using understandable artificial intelligence: a prospective diagnostic accuracy study

Aims

The medical need for screening of aortic valve stenosis (AS), which leads to timely and appropriate medical intervention, is rapidly increasing because of the high prevalence of AS in elderly population. This study aimed to establish a screening method using understandable artificial intelligence (AI) to detect severe AS based on heart sounds and to package the built AI into a smartphone application.

Methods and results

In this diagnostic accuracy study, we developed multiple convolutional neural networks (CNNs) using a modified stratified five-fold cross-validation to detect severe AS in electronic heart sound data recorded at three auscultation locations. Clinical validation was performed with the developed smartphone application in an independent cohort (model establishment: n = 556, clinical validation: n = 132). Our ensemble technique integrating the heart sounds from multiple auscultation locations increased the detection accuracy of CNN model by compensating detection errors. The established smartphone application achieved a sensitivity, specificity, accuracy, and F1 value of 97.6% (41/42), 94.4% (85/90), 95.7% (126/132), and 0.93, respectively, which were higher compared with the consensus of cardiologists (81.0%, 93.3%, 89.4%, and 0.829, respectively), implying a good utility for severe AS screening. The Gradient-based Class Activation Map demonstrated that the built AIs could focus on specific heart sounds to differentiate the severity of AS.

Conclusions

Our CNN model combining multiple auscultation locations and exported on smartphone application could efficiently identify severe AS based on heart sounds. The visual explanation of AI decisions for heart sounds was interpretable. These technologies may support medical training and remote consultations.

The Current and Future Role of Technology in Respiratory Care

Over the past few decades, technology and improvements in artificial intelligence have dramatically changed major sectors of our day-to-day lives, including the field of healthcare. E-health includes a wide range of subdomains, such as wearables, smart-inhalers, portable electronic spirometers, digital stethoscopes, and clinical decision support systems. E-health has been consistently shown to enhance the quality of care, improve adherence to therapy, and allow early detection of worsening in chronic pulmonary diseases. The present review addresses the current and potential future role of major e-health tools and approaches in respiratory medicine, with the aim of providing readers with trustful and updated evidence to increase their awareness of the topic, and to allow them to optimally benefit from the latest innovation technology. Collected literature evidence shows that the potential of technology tools in respiratory medicine mainly relies on three fundamental interactions: between clinicians, between clinician and patient, and between patient and health technology. However, it would be desirable to establish widely agreed and adopted standards for conducting trials and reporting results in this area, as well as to take into proper consideration potentially relevant pitfalls related to privacy protection and compliance with regulatory procedures.

Implementation of prognostic machine learning algorithms in paediatric chronic respiratory conditions: a scoping review

Machine learning (ML) holds great potential for predicting clinical outcomes in heterogeneous chronic respiratory diseases (CRD) affecting children, where timely individualised treatments offer opportunities for health optimisation. This paper identifies rate-limiting steps in ML prediction model development that impair clinical translation and discusses regulatory, clinical and ethical considerations for ML implementation. A scoping review of ML prediction models in paediatric CRDs was undertaken using the PRISMA extension scoping review guidelines. From 1209 results, 25 articles published between 2013 and 2021 were evaluated for features of a good clinical prediction model using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines.

Most of the studies were in asthma (80%), with few in cystic fibrosis (12%), bronchiolitis (4%) and childhood wheeze (4%). There were inconsistencies in model reporting and studies were limited by a lack of validation, and absence of equations or code for replication. Clinician involvement during ML model development is essential and diversity, equity and inclusion should be assessed at each step of the ML pipeline to ensure algorithms do not promote or amplify health disparities among marginalised groups. As ML prediction studies become more frequent, it is important that models are rigorously developed using published guidelines and take account of regulatory frameworks which depend on model complexity, patient safety, accountability and liability.

Artificial Intelligence for Interstitial Lung Disease Analysis on Chest Computed Tomography: A Systematic Review

RATIONALE AND OBJECTIVES

High-resolution computed tomography (HRCT) is paramount in the assessment of interstitial lung disease (ILD). Yet, HRCT interpretation of ILDs may be hampered by inter- and intra-observer variability. Recently, artificial intelligence (AI) has revolutionized medical image analysis. This technology has the potential to advance patient care in ILD. We aimed to systematically evaluate the application of AI for the analysis of ILD in HRCT.

MATERIALS AND METHODS

We searched MEDLINE/PubMed databases for original publications of deep learning for ILD analysis on chest CT. The search included studies published up to March 1, 2021. The risk of bias evaluation included tailored Quality Assessment of Diagnostic Accuracy Studies and the modified Joanna Briggs Institute Critical Appraisal checklist.

RESULTS

Data was extracted from 19 retrospective studies. Deep learning techniques included detection, segmentation, and classification of ILD on HRCT. Most studies focused on the classification of ILD into different morphological patterns. Accuracies of 78%-91% were achieved. Two studies demonstrated near-expert performance for the diagnosis of idiopathic pulmonary fibrosis (IPF). The Quality Assessment of Diagnostic Accuracy Studies tool identified a high risk of bias in 15/19 (78.9%) of the studies.

CONCLUSION

AI has the potential to contribute to the radiologic diagnosis and classification of ILD. However, the accuracy performance is still not satisfactory, and research is limited by a small number of retrospective studies. Hence, the existing published data may not be sufficiently reliable. Only well-designed prospective controlled studies can accurately assess the value of existing AI tools for ILD evaluation.

Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology

Objective

This review will focus on how AI—and, specifically, deep learning—can be applied to complement aspects of the current healthcare system. We describe how AI-based tools can augment existing clinical workflows by discussing the applications of AI to worklist prioritization and patient triage, the performance-boosting effects of AI as a second reader, and the use of AI to facilitate complex quantifications. We also introduce prominent examples of recent AI applications, such as tuberculosis screening in resource-constrained environments, the detection of lung cancer with screening CT, and the diagnosis of COVID-19. We also provide examples of prognostic predictions and new discoveries beyond existing clinical practices.

Background

Artificial intelligence (AI) has shown promising performance for thoracic diseases, particularly in the field of thoracic radiology. However, it has not yet been established how AI-based image analysis systems can help physicians in clinical practice.

Methods

This review included peer-reviewed research articles on AI in the thorax published in English between 2015 and 2021.

Conclusions

With advances in technology and appropriate preparation of physicians, AI could address various clinical problems that have not been solved due to a lack of clinical resources or technological limitations.

Keywords

Artificial intelligence (AI); deep learning (DL); computer aided diagnosis (CAD); thoracic radiology; pulmonary medicine

Rationale and design of the Early Chronic Obstructive Pulmonary Disease (ECOPD) study in Guangdong, China: a prospective observational cohort study

Background

Chronic obstructive pulmonary disease (COPD) is a heterogeneous disease and its clinically relevant subtypes are not well understood. Which clinical characteristics are more likely to be present among individuals who develop COPD remains to be studied in depth. Therefore, we designed a prospective observational cohort study, entitled the Early Chronic Obstructive Pulmonary Disease (ECOPD) study, to fill this evidence gap. The ECOPD study has four specific aims: (I) identification of characteristics, parameters, and biomarkers that may predict the development of airflow obstruction and annual decline in lung function with normal spirometry; (II) identification of clinically relevant early COPD subtypes; (III) identification of characteristics, parameters, and biomarkers that may predict disease progression in these early COPD subtypes; (IV) development and validation of machine learning models to predict development of airflow obstruction and disease progression.

Methods

We will recruit approximately 2,000 participants aged 40–80 years, including approximately 1,000 with COPD [post-bronchodilator forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC) <0.7] and approximately 1,000 without COPD, using a population-based survey for COPD. We will assess all participants using standard respiratory epidemiological questionnaires, pulmonary function tests [pre-bronchodilator and post-bronchodilator spirometry, and impulse oscillometry (IOS)], health outcomes [modified British Medical Research Council (mMRC) dyspnea scale, COPD assessment test (CAT), COPD clinical questionnaire (CCQ)], inspiratory and expiratory chest computed tomography (CT), and biomarker measurements (blood and urine), as well as satellite remote sensing pollutant exposure measures. Subgroup will additionally complete induced sputum, exercise capacity tests [6-minute walk test (6MWT) and cardiopulmonary exercise testing (CPET)] and home monitoring/personal sampling as pollutant exposure measures. Study procedures will be performed at baseline and every 1 year thereafter.

Discussion

The ECOPD study will provide insight into many aspects of early COPD and improve our understanding of COPD development, which may facilitate therapeutic interventions with the potential to modify the course of disease.

Trial Registration

Chinese Clinical Trial Registry, ChiCTR1900024643. Registered on 19 July, 2019.

Machine Learning Approaches for Predicting Acute Respiratory Failure, Ventilator Dependence, and Mortality in Chronic Obstructive Pulmonary Disease

Chronic obstructive pulmonary disease (COPD) is one of the leading causes of mortality and contributes to high morbidity worldwide. Patients with COPD have a higher risk for acute respiratory failure, ventilator dependence, and mortality after hospitalization compared with the general population. Accurate and early risk detection will provide more information for early management and better decision making. This study aimed to build prediction models using patients’ characteristics, laboratory data, and comorbidities for early detection of acute respiratory failure, ventilator dependence, and mortality in patients with COPD after hospitalization. We retrospectively collected the electronic medical records of 5061 patients with COPD in three hospitals of the Chi Mei Medical Group, Taiwan. After data cleaning, we built three prediction models for acute respiratory failure, ventilator dependence, and mortality using seven machine learning algorithms. Based on the AUC value, the best model for mortality was built by the XGBoost algorithm (AUC = 0.817), the best model for acute respiratory failure was built by random forest algorithm (AUC = 0.804), while the best model for ventilator dependence was built by LightGBM algorithm (AUC = 0.809). A web service application was implemented with the best models and integrated into the existing hospital information system for physician’s trials and evaluations. Our machine learning models exhibit excellent predictive quality and can therefore provide physicians with a useful decision-making reference for the adverse prognosis of COPD patients.

Requirement of artificial intelligence technology awareness for thoracic surgeons

Background

We have recently witnessed incredible interest in computer-based, internet web-dependent mechanisms and artificial intelligence (AI)-dependent technique emergence in our day-to-day lives. In the recent era of COVID-19 pandemic, this nonhuman, machine-based technology has gained a lot of momentum.

Main body of the abstract

The supercomputers and robotics with AI technology have shown the potential to equal or even surpass human experts' accuracy in some tasks in the future. Artificial intelligence (AI) is prompting massive data interweaving with elements from many digital sources such as medical imaging sorting, electronic health records, and transforming healthcare delivery. But in thoracic surgical and our counterpart pulmonary medical field, AI's main applications are still for interpretation of thoracic imaging, lung histopathological slide evaluation, physiological data interpretation, and biosignal testing only. The query arises whether AI-enabled technology-based or autonomous robots could ever do or provide better thoracic surgical procedures than current surgeons but it seems like an impossibility now.

Short conclusion

This review article aims to provide information pertinent to the use of AI to thoracic surgical specialists. In this review article, we described AI and related terminologies, current utilisation, challenges, potential, and current need for awareness of this technology.

Imaging diagnosis of bronchogenic carcinoma (the forgotten disease) during times of COVID-19 pandemic: Current and future perspectives

Patients with bronchogenic carcinoma comprise a high-risk group for coronavirus disease 2019 (COVID-19), pneumonia and related complications. Symptoms of COVID-19 related pulmonary syndrome may be similar to deteriorating symptoms encountered during bronchogenic carcinoma progression. These resemblances add further complexity for imaging assessment of bronchogenic carcinoma. Similarities between clinical and imaging findings can pose a major challenge to clinicians in distinguishing COVID-19 super-infection from evolving bronchogenic carcinoma, as the above-mentioned entities require very different therapeutic approaches. However, the goal of bronchogenic carcinoma management during the pandemic is to minimize the risk of exposing patients to COVID-19, whilst still managing all life-threatening events related to bronchogenic carcinoma. The current pandemic has forced all healthcare stakeholders to prioritize per value resources and reorganize therapeutic strategies for timely management of patients with COVID-19 related pulmonary syndrome. Processing of radiographic and computed tomography images by means of artificial intelligence techniques can facilitate triage of patients. Modified and newer therapeutic strategies for patients with bronchogenic carcinoma have been adopted by oncologists around the world for providing uncompromised care within the accepted standards and new guidelines.

Artificial Intelligence/Machine Learning in Respiratory Medicine and Potential Role in Asthma and COPD Diagnosis

Artificial intelligence (AI) and machine learning, a subset of AI, are increasingly used in medicine. AI excels at performing well-defined tasks, such as image recognition; for example, classifying skin biopsy lesions, determining diabetic retinopathy severity, and detecting brain tumors. This article provides an overview of the use of AI in medicine and particularly in respiratory medicine, where it is used to evaluate lung cancer images, diagnose fibrotic lung disease, and more recently is being developed to aid the interpretation of pulmonary function tests and the diagnosis of a range of obstructive and restrictive lung diseases. The development and validation of AI algorithms requires large volumes of well-structured data, and the algorithms must work with variable levels of data quality. It is important that clinicians understand how AI can function in the context of heterogeneous conditions such as asthma and chronic obstructive pulmonary disease where diagnostic criteria overlap, how AI use fits into everyday clinical practice, and how issues of patient safety should be addressed. AI has a clear role in providing support for doctors in the clinical workplace, but its relatively recent introduction means that confidence in its use still has to be fully established. Overall, AI is expected to play a key role in aiding clinicians in the diagnosis and management of respiratory diseases in the future, and it will be exciting to see the benefits that arise for patients and doctors from its use in everyday clinical practice.

Challenges and advances in clinical applications of mesenchymal stromal cells

Mesenchymal stromal cells (MSCs), also known as mesenchymal stem cells, have been intensely investigated for clinical applications within the last decades. However, the majority of registered clinical trials applying MSC therapy for diverse human diseases have fallen short of expectations, despite the encouraging pre-clinical outcomes in varied animal disease models. This can be attributable to inconsistent criteria for MSCs identity across studies and their inherited heterogeneity. Nowadays, with the emergence of advanced biological techniques and substantial improvements in bio-engineered materials, strategies have been developed to overcome clinical challenges in MSC application. Here in this review, we will discuss the major challenges of MSC therapies in clinical application, the factors impacting the diversity of MSCs, the potential approaches that modify MSC products with the highest therapeutic potential, and finally the usage of MSCs for COVID-19 pandemic disease.

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

Artificial intelligence accuracy in detecting pathological breath sounds in children using digital stethoscopes

Background

Manual auscultation to detect abnormal breath sounds has poor inter-observer reliability. Digital stethoscopes with artificial intelligence (AI) could improve reliable detection of these sounds. We aimed to independently test the abilities of AI developed for this purpose.

Methods

One hundred and ninety two auscultation recordings collected from children using two different digital stethoscopes (Clinicloud™ and Littman™) were each tagged as containing wheezes, crackles or neither by a pediatric respiratory physician, based on audio playback and careful spectrogram and waveform analysis, with a subset validated by a blinded second clinician. These recordings were submitted for analysis by a blinded AI algorithm (StethoMe AI) specifically trained to detect pathologic pediatric breath sounds.

Results

With optimized AI detection thresholds, crackle detection positive percent agreement (PPA) was 0.95 and negative percent agreement (NPA) was 0.99 for Clinicloud recordings; for Littman-collected sounds PPA was 0.82 and NPA was 0.96. Wheeze detection PPA and NPA were 0.90 and 0.97 respectively (Clinicloud auscultation), with PPA 0.80 and NPA 0.95 for Littman recordings.

Conclusions

AI can detect crackles and wheeze with a reasonably high degree of accuracy from breath sounds obtained from different digital stethoscope devices, although some device-dependent differences do exist.

Detecting asthma exacerbations using daily home monitoring and machine learning

OBJECTIVE

Acute exacerbations contribute significantly to the morbidity of asthma. Recent studies have shown that early detection and treatment of asthma exacerbations leads to improved outcomes. We aimed to develop a machine learning algorithm to detect severe asthma exacerbations using easily available daily monitoring data.

METHODS

We analyzed daily peak expiratory flow and symptom scores recorded by participants in the SAKURA study (NCT00839800), an international multicentre randomized controlled trial comparing budesonide/formoterol as maintenance and reliever therapy versus budesonide/formoterol maintenance plus terbutaline as reliever, in adults with persistent asthma. The dataset consisted of 728,535 records of daily monitoring data in 2010 patients, with 576 severe exacerbation events. Data post-processing techniques included normalization, standardization, calculation of differences or slopes over time and the use of smoothing filters. Principal components analysis was used to reduce the large number of derived variables to a smaller number of linearly independent components. Logistic regression, decision tree, naïve Bayes, and perceptron algorithms were evaluated. Model accuracy was assessed using stratified cross-validation. The primary outcome was the detection of exacerbations on the same day or up to three days in the future.

RESULTS

The best model used logistic regression with input variables derived from post-processed data using principal components analysis. This had an area under the receiver operating characteristic curve of 0.85, with a sensitivity of 90% and specificity of 83% for severe asthma exacerbations.

CONCLUSION

Asthma exacerbations may be detected using machine learning algorithms applied to daily self-monitoring of peak expiratory flow and asthma symptoms.

Deep Learning for the Classification of Small-Cell and Non-Small-Cell Lung Cancer

Reliable entity subtyping is paramount for therapy stratification in lung cancer. Morphological evaluation remains the basis for entity subtyping and directs the application of additional methods such as immunohistochemistry (IHC). The decision of whether to perform IHC for subtyping is subjective, and access to IHC is not available worldwide. Thus, the application of additional methods to support morphological entity subtyping is desirable. Therefore, the ability of convolutional neuronal networks (CNNs) to classify the most common lung cancer subtypes, pulmonary adenocarcinoma (ADC), pulmonary squamous cell carcinoma (SqCC), and small-cell lung cancer (SCLC), was evaluated. A cohort of 80 ADC, 80 SqCC, 80 SCLC, and 30 skeletal muscle specimens was assembled; slides were scanned; tumor areas were annotated; image patches were extracted; and cases were randomly assigned to a training, validation or test set. Multiple CNN architectures (VGG16, InceptionV3, and InceptionResNetV2) were trained and optimized to classify the four entities. A quality control (QC) metric was established. An optimized InceptionV3 CNN architecture yielded the highest classification accuracy and was used for the classification of the test set. Image patch and patient-based CNN classification results were 95% and 100% in the test set after the application of strict QC. Misclassified cases mainly included ADC and SqCC. The QC metric identified cases that needed further IHC for definite entity subtyping. The study highlights the potential and limitations of CNN image classification models for tumor differentiation.