Predicting Hospitalization Due to COPD Exacerbations in Swedish Primary Care Patients Using Machine Learning - Based on the ARCTIC Study

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.

Using an electronic diary and wristband accelerometer to detect exacerbations and activity levels in COPD: a feasibility study

Background

Early and accurate identification of acute exacerbations of COPD may lead to earlier treatment and prevent hospital admission. Electronic diaries have been developed for symptom monitoring and accelerometers to monitor activity. However, it is unclear whether this technology is usable in the COPD population. This study aimed to assess the feasibility of an electronic diary (eDiary) for symptom reporting using the MoreCare app and activity monitoring with the Garmin Vivofit 2 in COPD.

Methods

Participants were recruited from the London COPD Cohort. Participants were provided a Garmin Vivofit 2 activity monitor and an android tablet with the MoreCare app for a period of 3 months.

Results

25 COPD patients were recruited (mean±sd age 70.8±7.1 years, forced expiratory volume in 1 s (FEV1) 49.8±14.8% predicted). Age, gender, disease severity and exacerbation frequency had no impact on eDiary compliance. There was a moderate positive correlation between median daily very active minutes and FEV1 % pred (ρ=0.62, p=0.005). Daily step counts decreased during the initial 7 days of exacerbation and recovery compared to a pre-exacerbation baseline. A decision-tree model identified change in sputum colour, change in step count, severity of cold, exacerbation history and use of rescue medication as the most important predictors of acute exacerbations of COPD in this cohort.

Conclusions

Symptom and activity monitoring using digital technology is feasible in COPD. Further large-scale digital health studies are needed to assess whether eDiaries can be used to identify patients at risk of exacerbation and guide early intervention.

A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.

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.

Machine learning reveals sex differences in clinical features of acute exacerbation of chronic obstructive pulmonary disease: A multicenter cross-sectional study

Introduction

Intrinsically, chronic obstructive pulmonary disease (COPD) is a highly heterogonous disease. Several sex differences in COPD, such as risk factors and prevalence, were identified. However, sex differences in clinical features of acute exacerbation chronic obstructive pulmonary disease (AECOPD) were not well explored. Machine learning showed a promising role in medical practice, including diagnosis prediction and classification. Then, sex differences in clinical manifestations of AECOPD were explored by machine learning approaches in this study.

Methods

In this cross-sectional study, 278 male patients and 81 female patients hospitalized with AECOPD were included. Baseline characteristics, clinical symptoms, and laboratory parameters were analyzed. The K-prototype algorithm was used to explore the degree of sex differences. Binary logistic regression, random forest, and XGBoost models were performed to identify sex-associated clinical manifestations in AECOPD. Nomogram and its associated curves were established to visualize and validate binary logistic regression.

Results

The predictive accuracy of sex was 83.930% using the k-prototype algorithm. Binary logistic regression revealed that eight variables were independently associated with sex in AECOPD, which was visualized by using a nomogram. The AUC of the ROC curve was 0.945. The DCA curve showed that the nomogram had more clinical benefits, with thresholds from 0.02 to 0.99. The top 15 sex-associated important variables were identified by random forest and XGBoost, respectively. Subsequently, seven clinical features, including smoking, biomass fuel exposure, GOLD stages, PaO2, serum potassium, serum calcium, and blood urea nitrogen (BUN), were concurrently identified by three models. However, CAD was not identified by machine learning models.

Conclusions

Overall, our results support that the clinical features differ markedly by sex in AECOPD. Male patients presented worse lung function and oxygenation, less biomass fuel exposure, more smoking, renal dysfunction, and hyperkalemia than female patients with AECOPD. Furthermore, our results also suggest that machine learning is a promising and powerful tool in clinical decision-making.

Hospital Frailty Risk Score Predicts Outcomes in Chronic Obstructive Pulmonary Disease Exacerbations

INTRODUCTION

Patients with chronic obstructive pulmonary disease (COPD) are at high risk for frailty and prone to complications after admission for an acute exacerbation. We aim to investigate the association between frailty risk and functional outcomes in patients with acute exacerbations of COPD, using a nationwide database.

METHODS

This retrospective cohort study included patients with acute exacerbations of COPD who were admitted by ambulance. We assessed frailty using the Hospital Frailty Risk Score (HFRS) and compared the outcomes between low frailty risk (HFRS < 5) and frailty at risk (HFRS ≥ 5) groups. The primary outcome was prolonged hospitalization (≥30 days). The secondary outcomes were in-hospital mortality, readmission (≤90 days), poor activities of daily living (ADL) at discharge, and difficulty in returning home.

RESULTS

There were 3,396 eligible patients (mean age, 75.9 ± 11.2 years; 20.4% female). The rate of frailty at risk patients was 14.0%. Frailty at risk patients were significantly higher rates of prolonged hospitalization (32.9% vs. 17.5%), more in-hospital mortality (16.4% vs. 12.5%), more difficulty in returning home (34.6% vs. 22.9%), and poorer ADL at discharge (8.7% vs. 12.4%) than those of low frailty risk. Multivariate analysis with adjusted covariates showed that HFRS was independently associated with prolonged hospitalization (odds ratio, 2.0; 95% confidence interval, 1.4-2.9).

CONCLUSIONS

HFRS can be used to predict the outcome of patients with acute exacerbations of COPD. This finding supports the validity of using the HFRS in clinical practice with patients with acute exacerbations of COPD.

Evaluating Triple Therapy Treatment Pathways in Chronic Obstructive Pulmonary Disease (COPD): A Machine-Learning Predictive Model

Purpose

Inhaled triple therapy (TT) comprising a long-acting muscarinic antagonist, long-acting β₂ agonist, and inhaled corticosteroid is recommended for symptomatic chronic obstructive pulmonary disease (COPD) patients, or those at risk of exacerbation. However, it is not well understood which patient characteristics contribute most to future exacerbation risk. This study assessed patient predictors associated with future exacerbation time following initiation of TT.

Patients and Methods

This retrospective cohort study used data from the Optum™ Clinformatics™ Data Mart, a large health claims database in the United States. COPD patients who initiated TT between January 2008 and March 2018 (index) were eligible. Patients were required to be aged ≥18 years at index and have continuous enrollment for the 12 months prior to index (baseline) and the 12 months following index (follow-up). Patients who had received TT during baseline were excluded. Data from eligible patients were analyzed using a reverse engineering forward simulation machine learning platform to predict future COPD exacerbation time.

Results

Data from 73,625 patients were included. The model found that prior exacerbation was largely correlated with post-index exacerbation time; patients who had ≥4 exacerbation episodes during baseline had an average increase of 32.4 days post-index exacerbation, compared with patients with no exacerbations during baseline. Likewise, ≥2 inpatient visits (effect size 27.1 days), the use of xanthines (effect size 11.5 days), or rheumatoid arthritis (effect size 6.4 days) during baseline were associated with increased exacerbation time. Conversely, diagnosis of anemia (effect size –5.68 days), or oral corticosteroids in the past month (effect size –3.43 days) were associated with reduced exacerbation time.

Conclusion

Frequent prior exacerbations, healthcare resource utilization, xanthine use, and rheumatoid arthritis were the strongest factors predicting the future increase of exacerbations. These results improve our understanding of exacerbation risk among COPD patients initiating triple therapy.

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

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

Background

Chronic obstructive pulmonary disease (COPD) poses a large burden on health care. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause an irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target patients at high risk for preventive care management to reduce severe COPD exacerbations and improve outcomes.

Objective

The aim of this study is to develop a more accurate model to predict severe COPD exacerbations.

Methods

We examined all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019 and identified 278 candidate features. By performing secondary analysis on 43,576 University of Washington Medicine data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD.

Results

The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 9.99% (752/7529) of the patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6801/7529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6698/7347).

Conclusions

Our model provided a more accurate prediction of severe COPD exacerbations in the next year compared with prior published models. After further improvement of its performance measures (eg, by adding features extracted from clinical notes), our model could be used in a decision support tool to guide the identification of patients with COPD and at high risk for care management to improve outcomes.

International Registered Report Identifier (IRRID)

RR2-10.2196/13783

Predictive modeling of COPD exacerbation rates using baseline risk factors

Background:

Demographic and disease characteristics have been associated with the risk of chronic obstructive pulmonary disease (COPD) exacerbations. Using previously collected multinational clinical trial data, we developed models that use baseline risk factors to predict an individual’s rate of moderate/severe exacerbations in the next year on various pharmacological treatments for COPD.

Methods:

Exacerbation data from 20,054 patients in the ETHOS, KRONOS, TELOS, SOPHOS, and PINNACLE-1, PINNACLE-2, and PINNACLE-4 studies were pooled. Machine learning was used to identify predictors of moderate/severe exacerbation rates. Important factors were selected for generalized linear modeling, further informed by backward variable selection. An independent test set was held back for validation.

Results:

Prior exacerbations, eosinophil count, forced expiratory volume in 1 s percent predicted, prior maintenance treatments, reliever medication use, sex, COPD Assessment Test score, smoking status, and region were significant predictors of exacerbation risk, with response to inhaled corticosteroids (ICSs) increasing with higher eosinophil counts, more prior exacerbations, or additional prior treatments. Model fit was similar in the training and test set. Prediction metrics were ~10% better in the full model than in a simplified model based only on eosinophil count, prior exacerbations, and ICS use.

Conclusion:

These models predicting rates of moderate/severe exacerbations can be applied to a broad range of patients with COPD in terms of airway obstruction, eosinophil counts, exacerbation history, symptoms, and treatment history. Understanding the relative and absolute risks related to these factors may be useful for clinicians in evaluating the benefit: risk ratio of various treatment decisions for individual patients.

Clinical trials registered with www.clinicaltrials.gov (NCT02465567, NCT02497001, NCT02766608, NCT02727660, NCT01854645, NCT01854658, NCT02343458, NCT03262012, NCT02536508, and NCT01970878)

Analyzing the use of artificial intelligence for the management of chronic obstructive pulmonary disease (COPD)

OBJECTIVE

Chronic obstructive pulmonary disease (COPD) is a disease that causes airflow limitation to the lungs and has a high morbidity around the world. The objective of this study was to evaluate how artificial intelligence (AI) is being applied for the management of the disease, analyzing the objectives that are raised, the algorithms that are used and what results they offer.

METHODS

We conducted a scoping review following the Arksey and O'Malley (2005) and Levac et al. (2010) guidelines. Two reviewers independently searched, analyzed and extracted data from papers of five databases: Web of Science, PubMed, Scopus, Cinahl and Cochrane. To be included, the studies had to apply some AI techniques for the management of at least one stage of the COPD clinical process. In the event of any discrepancy between both reviewers, the criterion of a third reviewer prevailed.

RESULTS

380 papers were identified through database searches. After applying the exclusion criteria, 67 papers were included in the study. The studies were of a different nature and pursued a wide range of objectives, highlighting mainly those focused on the identification, classification and prevention of the disease. Neural nets, support vector machines and decision trees were the AI algorithms most commonly used. The mean and median values of all the performance metrics evaluated were between 80% and 90%.

CONCLUSIONS

The results obtained show a growing interest in the development of medical applications that manage the different phases of the COPD clinical process, especially predictive models. According to the performance shown, these models could be a useful complementary tool in the decision-making by health specialists, although more high-quality ML studies are needed to endorse the findings of this study.

Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis

Background

Asthma and chronic obstructive pulmonary disease (COPD) impose a heavy burden on health care. Approximately one-fourth of patients with asthma and patients with COPD are prone to exacerbations, which can be greatly reduced by preventive care via integrated disease management that has a limited service capacity. To do this well, a predictive model for proneness to exacerbation is required, but no such model exists. It would be suboptimal to build such models using the current model building approach for asthma and COPD, which has 2 gaps due to rarely factoring in temporal features showing early health changes and general directions. First, existing models for other asthma and COPD outcomes rarely use more advanced temporal features, such as the slope of the number of days to albuterol refill, and are inaccurate. Second, existing models seldom show the reason a patient is deemed high risk and the potential interventions to reduce the risk, making already occupied clinicians expend more time on chart review and overlook suitable interventions. Regular automatic explanation methods cannot deal with temporal data and address this issue well.

Objective

To enable more patients with asthma and patients with COPD to obtain suitable and timely care to avoid exacerbations, we aim to implement comprehensible computational methods to accurately predict proneness to exacerbation and recommend customized interventions.

Methods

We will use temporal features to accurately predict proneness to exacerbation, automatically find modifiable temporal risk factors for every high-risk patient, and assess the impact of actionable warnings on clinicians’ decisions to use integrated disease management to prevent proneness to exacerbation.

Results

We have obtained most of the clinical and administrative data of patients with asthma from 3 prominent American health care systems. We are retrieving other clinical and administrative data, mostly of patients with COPD, needed for the study. We intend to complete the study in 6 years.

Conclusions

Our results will help make asthma and COPD care more proactive, effective, and efficient, improving outcomes and saving resources.

International Registered Report Identifier (IRRID)

PRR1-10.2196/27065