Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study

A machine learning framework for short-term prediction of chronic obstructive pulmonary disease exacerbations using personal air quality monitors and lifestyle data

Chronic Obstructive Pulmonary Disease (COPD) is a heterogeneous disease with a variety of symptoms including, persistent coughing and mucus production, shortness of breath, wheezing, and chest tightness. As the disease advances, exacerbations, i.e. acute worsening of respiratory symptoms, may increase in frequency, leading to potentially life-threatening complications. Exposure to air pollutants may trigger COPD exacerbations. Literature predictive models for COPD exacerbations, while promising, may be constrained by their reliance on fixed air quality sensor data that may not fully capture individuals' dynamic exposure to air pollution. To address this, we designed a machine learning (ML) framework that leverages data from personal air quality monitors, health records, lifestyle, and living condition information to build models that perform short-term prediction of COPD exacerbations. The framework employs (i) k-means clustering to uncover potentially distinct patient sub-types, (ii) supervised ML techniques (Logistic Regression, Random Forest, and eXtreme Gradient Boosting) to train and test predictive models for each patient sub-type and (iii) an explainable artificial intelligence technique (SHAP) to interpret the final models. The framework was tested on data collected in 101 COPD patients monitored for up to 6 months with occurrence of exacerbation in 10.7% of total samples. Two different patient sub-types have been identified, characterised by different disease severity. The best performing models were Random Forest in cluster 1, with area under the receiver operating characteristic curve (AUC) of 0.90, and area under the precision/recall curve (AUPRC) of 0.7; and Random Forest model in cluster 2, with AUC of 0.82 and AUPRC of 0.56. The model interpretability analysis identified previous symptoms and cumulative pollutant exposure as key predictors of exacerbations. The results of our study set a premise for a predictive framework in COPD exacerbations, particularly investigating the potential influence of environmental features. The SHAP analysis revealed that the contribution of environmental features is not uniform across all subjects. For instance, cumulative exposure to pollutants demonstrated greater predictive power in cluster 1. The SHAP analysis also shown that overall clinical factors and individual symptomatology play the most significant role in this setup to determine exacerbation risk.

Development, evaluation and comparison of machine learning algorithms for predicting in-hospital patient charges for congestive heart failure exacerbations, chronic obstructive pulmonary disease exacerbations and diabetic ketoacidosis

BACKGROUND

Hospitalizations for exacerbations of congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD) and diabetic ketoacidosis (DKA) are costly in the United States. The purpose of this study was to predict in-hospital charges for each condition using machine learning (ML) models.

RESULTS

We conducted a retrospective cohort study on national discharge records of hospitalized adult patients from January 1st, 2016, to December 31st, 2019. We constructed six ML models (linear regression, ridge regression, support vector machine, random forest, gradient boosting and extreme gradient boosting) to predict total in-hospital cost for admission for each condition. Our models had good predictive performance, with testing R-squared values of 0.701-0.750 (mean of 0.713) for CHF; 0.694-0.724 (mean 0.709) for COPD; and 0.615-0.729 (mean 0.694) for DKA. We identified important key features driving costs, including patient age, length of stay, number of procedures, and elective/nonelective admission.

CONCLUSIONS

ML methods may be used to accurately predict costs and identify drivers of high cost for COPD exacerbations, CHF exacerbations and DKA. Overall, our findings may inform future studies that seek to decrease the underlying high patient costs for these conditions.

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.

Development and validation of a nomogram for assessing survival in acute exacerbation of chronic obstructive pulmonary disease patients

BACKGROUND

Early prediction of survival of hospitalized acute exacerbations of chronic obstructive pulmonary disease (AECOPD) patients is vital. We aimed to establish a nomogram to predict the survival probability of AECOPD patients.

METHODS

Retrospectively collected data of 4601 patients hospitalized for AECOPD. These patients were randomly divided into a training and a validation cohort at a 6:4 ratio. In the training cohort, LASSO-Cox regression analysis and multivariate Cox regression analysis were utilized to identify prognostic factors for in-hospital survival of AECOPD patients. A model was established based on 3 variables and visualized by nomogram. The performance of the model was assesed by AUC, C-index, calibration curve, decision curve analysis in both cohorts.

RESULTS

Coexisting arrhythmia, invasive mechanical ventilation (IMV) usage and lower serum albumin values were found to be significantly associated with lower survival probability of AECOPD patients, and these 3 predictors were further used to establish a prediction nomogram. The C-indexes of the nomogram were 0.816 in the training cohort and 0.814 in the validation cohort. The AUC in the training cohort was 0.825 for 7-day, 0.807 for 14-day and 0.825 for 21-day survival probability, in the validation cohort this were 0.796 for 7-day, 0.831 for 14-day and 0.841 for 21-day. The calibration of the nomogram showed a good goodness-of-fit and decision curve analysis showed the net clinical benefits achievable at different risk thresholds were excellent.

CONCLUSION

We established a nomogram based on 3 variables for predicting the survival probability of AECOPD patients. The nomogram showed good performance and was clinically useful.

Development and Optimization of Machine Learning Algorithms for Predicting In-hospital Patient Charges for Congestive Heart Failure Exacerbations, Chronic Obstructive Pulmonary Disease Exacerbations and Diabetic Ketoacidosis

Background

Hospitalizations for exacerbations of congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD) and diabetic ketoacidosis (DKA) are costly in the United States. The purpose of this study was to predict in-hospital charges for each condition using machine learning (ML) models.

Results

We conducted a retrospective cohort study on national discharge records of hospitalized adult patients from January 1st, 2016, to December 31st, 2019. We used numerous ML techniques to predict in-hospital total cost. We found that linear regression (LM), gradient boosting (GBM) and extreme gradient boosting (XGB) models had good predictive performance and were statistically equivalent, with training R-square values ranging from 0.49-0.95 for CHF, 0.56-0.95 for COPD, and 0.32-0.99 for DKA. We identified important key features driving costs, including patient age, length of stay, number of procedures. and elective/nonelective admission.

Conclusions

ML methods may be used to accurately predict costs and identify drivers of high cost for COPD exacerbations, CHF exacerbations and DKA. Overall, our findings may inform future studies that seek to decrease the underlying high patient costs for these conditions.

Acute exacerbation prediction of COPD based on Auto-metric graph neural network with inspiratory and expiratory chest CT images

Chronic obstructive pulmonary disease (COPD) is a widely prevalent disease with significant mortality and disability rates and has become the third leading cause of death globally. Patients with acute exacerbation of COPD (AECOPD) often substantially suffer deterioration and death. Therefore, COPD patients deserve special consideration regarding treatment in this fragile population for pre-clinical health management. Based on the above, this paper proposes an AECOPD prediction model based on the Auto-Metric Graph Neural Network (AMGNN) using inspiratory and expiratory chest low-dose CT images. This study was approved by the ethics committee in the First Affiliated Hospital of Guangzhou Medical University. Subsequently, 202 COPD patients with inspiratory and expiratory chest CT Images and their annual number of AECOPD were collected after the exclusion. First, the inspiratory and expiratory lung parenchyma images of the 202 COPD patients are extracted using a trained ResU-Net. Then, inspiratory and expiratory lung Radiomics and CNN features are extracted from the 202 inspiratory and expiratory lung parenchyma images by Pyradiomics and pre-trained Med3D (a heterogeneous 3D network), respectively. Last, Radiomics and CNN features are combined and then further selected by the Lasso algorithm and generalized linear model for determining node features and risk factors of AMGNN, and then the AECOPD prediction model is established. Compared to related models, the proposed model performs best, achieving an accuracy of 0.944, precision of 0.950, F1-score of 0.944, ad area under the curve of 0.965. Therefore, it is concluded that our model may become an effective tool for AECOPD prediction.

Artificial intelligence in respiratory care: Current scenario and future perspective

BACKGROUND

This narrative review aims to explore the current state and future perspective of artificial intelligence (AI) in respiratory care. The objective is to provide insights into the potential impact of AI in this field.

METHODS

A comprehensive analysis of relevant literature and research studies was conducted to examine the applications of AI in respiratory care and identify areas of advancement. The analysis included studies on remote monitoring, early detection, smart ventilation systems, and collaborative decision-making.

RESULTS

The obtained results highlight the transformative potential of AI in respiratory care. AI algorithms have shown promising capabilities in enabling tailored treatment plans based on patient-specific data. Remote monitoring using AI-powered devices allows for real-time feedback to health-care providers, enhancing patient care. AI algorithms have also demonstrated the ability to detect respiratory conditions at an early stage, leading to timely interventions and improved outcomes. Moreover, AI can optimize mechanical ventilation through continuous monitoring, enhancing patient comfort and reducing complications. Collaborative AI systems have the potential to augment the expertise of health-care professionals, leading to more accurate diagnoses and effective treatment strategies.

CONCLUSION

By improving diagnosis, AI has the potential to revolutionize respiratory care, treatment planning, and patient monitoring. While challenges and ethical considerations remain, the transformative impact of AI in this domain cannot be overstated. By leveraging the advancements and insights from this narrative review, health-care professionals and researchers can continue to harness the power of AI to improve patient outcomes and enhance respiratory care practices.

IMPROVEMENTS

Based on the findings, future research should focus on refining AI algorithms to enhance their accuracy, reliability, and interpretability. In addition, attention should be given to addressing ethical considerations, ensuring data privacy, and establishing regulatory frameworks to govern the responsible implementation of AI in respiratory care.

Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis

BACKGROUND

Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps.

METHODS

We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV1). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I2>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052).

FINDINGS

We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I2 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I2 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias.

INTERPRETATION

There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility.

FUNDING

None.

Identification of non-small cell lung cancer with chronic obstructive pulmonary disease using clinical symptoms and routine examination: a retrospective study

Background

Patients with non-small cell lung cancer (NSCLC) and patients with NSCLC combined with chronic obstructive pulmonary disease (COPD) have similar physiological conditions in early stages, and the latter have shorter survival times and higher mortality rates. The purpose of this study was to develop and compare machine learning models to identify future diagnoses of COPD combined with NSCLC patients based on the patient's disease and routine clinical data.

Methods

Data were obtained from 237 patients with COPD combined with NSCLC as well as NSCLC admitted to Ningxia Hui Autonomous Region People's Hospital from October 2013 to July 2022. Six machine learning algorithms (K-nearest neighbor, logistic regression, eXtreme gradient boosting, support vector machine, naïve Bayes, and artificial neural network) were used to develop prediction models for NSCLC combined with COPD. Sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, Mathews correlation coefficient (MCC), Kappa, area under the receiver operating characteristic curve (AUROC)and area under the precision-recall curve (AUPRC) were used as performance indicators to evaluate the performance of the models.

Results

135 patients with NSCLC combined with COPD, 102 patients with NSCLC were included in the study. The results showed that pulmonary function and emphysema were important risk factors and that the support vector machine-based identification model showed optimal performance with accuracy:0.946, recall:0.940, specificity:0.955, precision:0.972, npv:0.920, F1 score:0.954, MCC:0.893, Kappa:0.888, AUROC:0.975, AUPRC:0.987.

Conclusion

The use of machine learning tools combining clinical symptoms and routine examination data features is suitable for identifying the risk of concurrent NSCLC in COPD patients.

Unleashing the Power of Very Small Data to Predict Acute Exacerbations of Chronic Obstructive Pulmonary Disease

Introduction

In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD).

Methods

We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed.

Results

We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data.

Discussion

To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is "maintenance medication changes by HBHC". This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs.

Conclusion

The experiments return useful insights about the use of small data for ML.

A machine-learning approach for predicting the effect of carnitine supplementation on body weight in patients with polycystic ovary syndrome

The present study aimed to explore the effect of carnitine supplementation on body weight in patients with polycystic ovary syndrome (PCOS) and predict an appropriate dosage schedule using a machine-learning approach. Data were obtained from literature mining and the rates of body weight change from the initial values were selected as the therapeutic index. The maximal effect (E_max) model was built up as the machine-learning model. A total of 242 patients with PCOS were included for analysis. In the machine-learning model, the E_max of carnitine supplementation on body weight was -3.92%, the ET₅₀ was 3.6 weeks, and the treatment times to realize 25%, 50%, 75%, and 80% (plateau) E_max of carnitine supplementation on body weight were 1.2, 3.6, 10.8, and 14.4 weeks, respectively. In addition, no significant relationship of dose-response was found in the dosage range of carnitine supplementation used in the present study, indicating the lower limit of carnitine supplementation dosage, 250 mg/day, could be used as a suitable dosage. The present study first explored the effect of carnitine supplementation on body weight in patients with PCOS, and in order to realize the optimal therapeutic effect, carnitine supplementation needs 250 mg/day for at least 14.4 weeks.

Health-Screening-Based Chronic Obstructive Pulmonary Disease and Its Effect on Cardiovascular Disease Risk

Chronic obstructive pulmonary disease (COPD) is considered a major cause of death worldwide, and various studies have been conducted for its early diagnosis. Our work developed a scoring system by predicting and validating COPD and performed predictive model implementations. Participants who underwent a health screening between 2017 and 2020 were extracted from the Korea National Health and Nutrition Examination Survey (KNHANES) database. COPD individuals were defined as aged 40 years or older with prebronchodilator forced expiratory volume in 1 s/forced vital capacity (FEV1/FVC < 0.7). The logistic regression model was performed, and the C-index was used for variable selection. Receiver operating characteristic (ROC) curves with area under the curve (AUC) values were generated for evaluation. Age, sex, waist circumference and diastolic blood pressure were used to predict COPD and to develop a COPD score based on a multivariable model. A simplified model for COPD was validated with an AUC value of 0.780 from the ROC curves. In addition, we evaluated the association of the derived score with cardiovascular disease (CVD). COPD scores showed significant performance in COPD prediction. The developed score also showed a good effect on the diagnostic ability for CVD risk. In the future, studies comparing the diagnostic accuracy of the derived scores with standard diagnostic tests are needed.

Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study

Background

Chronic obstructive pulmonary disease (COPD) is a major cause of death and places a heavy burden on health care. To optimize the allocation of precious preventive care management resources and improve the outcomes for high-risk patients with COPD, we recently built the most accurate model to date to predict severe COPD exacerbations, which need inpatient stays or emergency department visits, in the following 12 months. Our model is a machine learning model. As is the case with most machine learning models, our model does not explain its predictions, forming a barrier for clinical use. Previously, we designed a method to automatically provide rule-type explanations for machine learning predictions and suggest tailored interventions with no loss of model performance. This method has been tested before for asthma outcome prediction but not for COPD outcome prediction.

Objective

This study aims to assess the generalizability of our automatic explanation method for predicting severe COPD exacerbations.

Methods

The patient cohort included all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019. In a secondary analysis of 43,576 data instances, we used our formerly developed automatic explanation method to automatically explain our model’s predictions and suggest tailored interventions.

Results

Our method explained the predictions for 97.1% (100/103) of the patients with COPD whom our model correctly predicted to have severe COPD exacerbations in the following 12 months and the predictions for 73.6% (134/182) of the patients with COPD who had ≥1 severe COPD exacerbation in the following 12 months.

Conclusions

Our automatic explanation method worked well for predicting severe COPD exacerbations. After further improving our method, we hope to use it to facilitate future clinical use of our model.

International Registered Report Identifier (IRRID)

RR2-10.2196/13783