Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data

Exacerbation predictive modelling using real-world data from the myCOPD app

Background

Acute exacerbations of COPD (AECOPD) are episodes of breathlessness, cough and sputum which are associated with the risk of hospitalisation, progressive lung function decline and death. They are often missed or diagnosed late. Accurate timely intervention can improve these poor outcomes. Digital tools can be used to capture symptoms and other clinical data in COPD. This study aims to apply machine learning to the largest available real-world digital dataset to develop AECOPD Prediction tools which could be used to support early intervention and improve clinical outcomes.

Objective

To create and validate a machine learning predictive model that forecasts exacerbations of COPD 1-8 days in advance. The model is based on routine patient-entered data from myCOPD self-management app.

Method

Adaptations of the AdaBoost algorithm were employed as machine learning approaches. The dataset included 506 patients users between 2017 and 2021. 55,066 app records were available for stable COPD event labels and 1263 records of AECOPD event labels. The data used for training the model included COPD assessment test (CAT) scores, symptom scores, smoking history, and previous exacerbation frequency. All exacerbation records used in the model were confined to the 1-8 days preceding a self-reported exacerbation event.

Results

TheEasyEnsemble Classifier resulted in a Sensitivity of 67.0 % and a Specificity of 65 % with a positive predictive value (PPV) of 5.0 % and a negative predictive value (NPV) of 98.9 %. An AdaBoost model with a cost-sensitive decision tree resulted in a a Sensitivity of 35.0 % and a Specificity of 89.0 % with a PPV of 7.08 % and NPV of 98.3 %.

Conclusion

This preliminary analysis demonstrates that machine learning approaches to real-world data from a widely deployed digital therapeutic has the potential to predict AECOPD and can be used to confidently exclude the risk of exacerbations of COPD within the next 8 days.

The Exacerbation of Chronic Obstructive Pulmonary Disease: Which Symptom is Most Important to Monitor?

Background

GOLD 2023 defines an exacerbation of COPD (ECOPD) by a deterioration of breathlessness at rest (BaR), mucus and cough. The severity of an ECOPD is determined by the degree of BaR, ranging from 0 to 10. However, it is not known which symptom is the most important one to detect early of an ECOPD, and which symptom that predicts future ECOPDs best. Thus, the purpose of the present study was to find out which symptom is the most important one to monitor.

Methods

We analysed data on COPD symptoms from the telehealth study The eHealth Diary. Frequent exacerbators (n = 27) were asked to daily monitor BaR and breathlessness at physical activity (BaPA), mucus and cough, employing a digital pen and symptom scales (0-10). Twenty-seven patients with 105 ECOPDs were analysed. The association between symptom development and the occurrence of exacerbations was evaluated using the Andersen-Gill formulation of the Cox proportional hazards model for the analysis of recurrent time-to-event data with time-varying predictors.

Results

According to the criteria proposed by GOLD 2023, 42% ECOPDs were mild, 48% were moderate and 5% were severe, while 6% were undefinable. Mucus and cough improved over study time, while BaR and BaPA deteriorated. Mucus appeared earliest, which was the most prominent feature of the average exacerbation, and worsening of mucus increased the risk for a future ECOPD. There was a 58% increase in the risk of exacerbation per unit increase in mucus score.

Conclusion

This study suggests that mucus worsening is the most important COPD symptom to monitor to detect ECOPDs early and to predict future risk för ECOPDs. In the present study, we also noticed a pronounced difference between GOLD 2022 and 2023. Hence, GOLD 2023 defined the ECOPD severity much lower than GOLD 2022 did.

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.

Early detection of COPD patients' symptoms with personal environmental sensors: a remote sensing framework using probabilistic latent component analysis with linear dynamic systems

In this study, we present a cohort study involving 106 COPD patients using portable environmental sensor nodes with attached air pollution sensors and activity-related sensors, as well as daily symptom records and peak flow measurements to monitor patients' activity and personal exposure to air pollution. This is the first study which attempts to predict COPD symptoms based on personal air pollution exposure. We developed a system that can detect COPD patients' symptoms one day in advance of symptoms appearing. We proposed using the Probabilistic Latent Component Analysis (PLCA) model based on 3-dimensional and 4-dimensional spectral dictionary tensors for personalised and population monitoring, respectively. The model is combined with Linear Dynamic Systems (LDS) to track the patients' symptoms. We compared the performance of PLCA and PLCA-LDS models against Random Forest models in the identification of COPD patients' symptoms, since tree-based classifiers were used for remote monitoring of COPD patients in the literature. We found that there was a significant difference between the classifiers, symptoms and the personalised versus population factors. Our results show that the proposed PLCA-LDS-3D model outperformed the PLCA and the RF models between 4 and 20% on average. When we used only air pollutants as input, the PLCA-LDS-3D forecasting results in personalised and population models were 48.67 and 36.33% accuracy for worsening of lung capacity and 38.67 and 19% accuracy for exacerbation of COPD patients' symptoms, respectively. We have shown that indicators of the quality of an individual's environment, specifically air pollutants, are as good predictors of the worsening of respiratory symptoms in COPD patients as a direct measurement.

Effect of Long-Term Oxygen Therapy on Reducing Rehospitalization of Patients with Chronic Obstructive Pulmonary Disease: A Systematic Review and Meta-Analysis

INTRODUCTION

The aim of this work is to evaluate whether the addition of home oxygen therapy (HOT) would reduce readmission in chronic obstructive pulmonary disease (COPD) patients.

METHODS

PubMed, ScopeMed, Cochrane, Scopus, and Google Scholar databases were searched. The search strategy used the following keywords "chronic obstructive pulmonary disease", the intervention "long-term oxygen therapy", and the outcome "readmission" combined with the AND operator. The Newcastle-Ottawa Scale and Jadad Scale were used for assessing the quality of cohort studies and clinical trials, respectively. A random-effects model was employed in this study after calculating the standard errors by 95% confidence intervals. The I2 statistic and Cochran's Q-test were used to measure heterogeneity. To address heterogeneity, subgroup analyses were carried out according to the length of LTOT, which was classified as "over 8 months" and "under 8 months".

RESULTS

Seven studies were included in the analysis. In the pooled analysis, the RR [CI95%, p value], heterogeneity criteria for readmission reduced by 1.542 [1.284-1.851, < 0.001], I² = 60%, and 1.693 [1.645-1.744, < 0.001], I² = 60% for patients with a length of LTOT treatment under and above 8 months, respectively. A sensitivity analysis was conducted by systematically omitting each study, and it showed no influential studies. Egger's test indicated no publication bias (p = 0.64).

CONCLUSIONS

Based on our results in this systematic review, long-tern oxygen therapy (LTOT) at home was associated with a significantly lower risk ratio of hospital readmission. However, the sample sizes in the studies necessitate larger RCTs to evaluate the effect of LTOT on readmission in COPD patients.

Artificial intelligence to differentiate asthma from COPD in medico-administrative databases

INTRODUCTION

Discriminating asthma from chronic obstructive pulmonary disease (COPD) using medico-administrative databases is challenging but necessary for medico-economic analyses focusing on respiratory diseases. Artificial intelligence (AI) may improve dedicated algorithms.

OBJECTIVES

To assess performance of different AI-based approaches to distinguish asthmatics from COPD patients in medico-administrative databases where the clinical diagnosis is absent. An "Asthma COPD Overlap" category was defined to further test whether AI can detect complexity.

METHODS

This study included 178,962 patients treated by two "R03" treatment prescriptions at least from January 2016 to December 2018 and managed by either a general practitioner and/or a pulmonologist participating in a permanent longitudinal observatory of prescription in ambulatory medicine (LPD). Clinical diagnoses are available in this database and were used as gold standards to develop diagnostic rules. Three types of AI approaches were explored using data restricted to demographics and treatment dispensations: multinomial regression, gradient boosting and recurrent neural networks (RNN). The best performing model (based on metric properties) was then applied to estimate the size of asthma and COPD populations based on a database (LRx) of treatment dispensations between July, 2018 and June, 2019.

RESULTS

The best models were obtained with the boosting approach and RNN, with an overall accuracy of 68%. Performance metrics were better for asthma than COPD. Based on LRx data, the extrapolated numbers of patients treated for asthma and COPD in France were 3.7 and 1.2 million, respectively. Asthma patients were younger than COPD patients (mean, 49.9 vs. 72.1 years); COPD occurred mostly in men (68%) compared to asthma (33%).

CONCLUSION

AI can provide models with acceptable accuracy to distinguish between asthma, ACO and COPD in medico-administrative databases where the clinical diagnosis is absent. Deep learning and machine learning (RNN) had similar performances in this regard.

Multi-disciplinary community respiratory team management of patients with chronic respiratory illness during the COVID-19 pandemic

The Greater Glasgow & Clyde NHS Trust Community Respiratory Response Team was established to manage patients with chronic respiratory disease at home during the COVID-19 pandemic. The team aimed to avert hospital admission while maximally utilising remote consultations. This observational study analysed outcomes of the triage pathway used, use of remote consultations, hospital admissions and mortality among patients managed by the team. Patients’ electronic health records were retrospectively reviewed. Rates of emergency department attendance, hospital admission and death within 28 days of referral were compared across triage pathways. Segmented linear regression was carried out for emergency admissions in Greater Glasgow and Clyde pre- and post- Community Respiratory Response Team implementation, using emergency admissions for chronic obstructive pulmonary disease in the rest of Scotland as control and adjusting for all-cause emergency admissions. The triage category correlated with hospital admission and death. The red pathway had the highest proportion attending the emergency department (21%), significantly higher than the amber and green pathways (p = 0.03 and p = 0.004, respectively). The highest number of deaths were in the blue “end-of-life” pathway (p < 0.001). 87% of interactions were undertaken remotely. Triage severity appropriately led to targeted home visits. No nosocomial COVID-19 infections occurred among patients or staff. The Community Respiratory Response Team was associated with a significant decrease in emergency admissions (RR = 0.96 for each additional month under the Poisson model) compared to the counterfactual if the service had not been in place, suggesting a benefit in reducing secondary care pressures. The Community Respiratory Response Team effectively managed patients with chronic respiratory disease in the community, with an associated reduction in secondary care pressures during the COVID-19 pandemic.

Remote patient monitoring in the management of chronic obstructive pulmonary disease

Remote patient monitoring allows monitoring high-risk patients through implementation of an expanding number of technologies in coordination with a healthcare team to augment care, with the potential to provide early detection of exacerbation, prompt access to therapy and clinical services, and ultimately improved patient outcomes and decreased healthcare utilization.In this review, we describe the application of remote patient monitoring in chronic obstructive pulmonary disease including the potential benefits and possible barriers to implementation both for the individual and the healthcare system.

A proof of concept for continuous, non-invasive, free-living vital signs monitoring to predict readmission following an acute exacerbation of COPD: a prospective cohort study

Background

The use of vital signs monitoring in the early recognition of an acute exacerbation of chronic obstructive pulmonary disease (AECOPD) post-hospital discharge is limited. This study investigated whether continuous vital signs monitoring could predict an AECOPD and readmission.

Methods

35 people were recruited at discharge following hospitalisation for an AECOPD. Participants were asked to wear an Equivital LifeMonitor during waking hours for 6 weeks and to complete the Exacerbations of Chronic Pulmonary Disease Tool (EXACT), a 14-item symptom diary, daily. The Equivital LifeMonitor recorded respiratory rate (RR), heart rate (HR), skin temperature (ST) and physical activity (PA) every 15-s. An AECOPD was classified as mild (by EXACT score), moderate (prescribed oral steroids/antibiotics) or severe (hospitalisation).

Results

Over the 6-week period, 31 participants provided vital signs and symptom data and 14 participants experienced an exacerbation, of which, 11 had sufficient data to predict an AECOPD. HR and PA were associated with EXACT score (p < 0.001). Three days prior to an exacerbation, RR increased by mean ± SD 2.0 ± 0.2 breaths/min for seven out of 11 exacerbations and HR increased by 8.1 ± 0.7 bpm for nine of these 11 exacerbations.

Conclusions

Increased heart rate and reduced physical activity were associated with worsening symptoms. Even with high-resolution data, the variation in vital signs data remains a challenge for predicting AECOPDs. Respiratory rate and heart rate should be further explored as potential predictors of an impending AECOPD.

Trial registration: ISRCTN registry; ISRCTN12855961. Registered 07 November 2018—Retrospectively registered, https://www.isrctn.com/ISRCTN12855961

Supplementary Information

The online version contains supplementary material available at 10.1186/s12931-022-02018-5.

Deep learning for spirometry quality assurance with spirometric indices and curves

Background

Spirometry quality assurance is a challenging task across levels of healthcare tiers, especially in primary care. Deep learning may serve as a support tool for enhancing spirometry quality. We aimed to develop a high accuracy and sensitive deep learning-based model aiming at assisting high-quality spirometry assurance.

Methods

Spirometry PDF files retrieved from one hospital between October 2017 and October 2020 were labeled according to ATS/ERS 2019 criteria and divided into training and internal test sets. Additional files from three hospitals were used for external testing. A deep learning-based model was constructed and assessed to determine acceptability, usability, and quality rating for FEV₁ and FVC. System warning messages and patient instructions were also generated for general practitioners (GPs).

Results

A total of 16,502 files were labeled. Of these, 4592 curves were assigned to the internal test set, the remaining constituted the training set. In the internal test set, the model generated 95.1%, 92.4%, and 94.3% accuracy for FEV₁ acceptability, usability, and rating. The accuracy for FVC acceptability, usability, and rating were 93.6%, 94.3%, and 92.2%. With the assistance of the model, the performance of GPs in terms of monthly percentages of good quality (A, B, or C grades) tests for FEV₁ and FVC was higher by ~ 21% and ~ 36%, respectively.

Conclusion

The proposed model assisted GPs in spirometry quality assurance, resulting in enhancing the performance of GPs in quality control of spirometry.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12931-022-02014-9.

Predictive performance and impact of algorithms in remote monitoring of chronic conditions: A systematic review and meta-analysis

BACKGROUND

The use of telehealth interventions, such as the remote monitoring of patient clinical data (e.g. blood pressure, blood glucose, heart rate, medication use), has been proposed as a strategy to better manage chronic conditions and to reduce the impact on patients and healthcare systems. The use of algorithms for data acquisition, analysis, transmission, communication and visualisation are now common in remote patient monitoring. However, their use and impact on chronic disease management has not been systematically investigated.

OBJECTIVES

To investigate the use, impact, and performance of remote monitoring algorithms across various types of chronic conditions.

METHODS

A literature search of MEDLINE complete, CINHAL complete, and EMBASE was performed using search terms relating to the concepts of remote monitoring, chronic conditions, and data processing algorithms. Comparable outcomes from studies describing the impact on process measures and clinical and patient-reported outcomes were pooled for a summary effect and meta-analyses. A comparison of studies reporting the predictive performance of algorithms was also conducted using the Youden Index.

RESULTS

A total of 89 articles were included in the review. There was no evidence of a positive impact on healthcare utilisation [OR 1.09 (0.90 to 1.31); P = .35] and mortality [OR 0.83 (0.63 to 1.10); P = .208], but there was a positive effect on generic health status [SDM 0.2912 (0.06 to 0.51); P = .010] and diabetes control [SDM -0.53 (-0.74 to -0.33); P < .001; I² = 15.71] (with two of the three diabetes studies being identified as having a high risk of bias). While the majority of impact studies made use of heuristic threshold-based algorithms (n = 27,87%), most performance studies (n = 36, 62%) analysed non-sequential machine learning methods. There was considerable variance in the quality, sample size and performance amongst these studies. Overall, algorithms involved in diagnosis (n = 22, 47%) had superior performance to those involved in predicting a future event (n = 25, 53%). Detection of arrythmia and ischaemia utilising ECG data showed particularly promising results.

CONCLUSION

The performance of data processing algorithms for the diagnosis of a current condition, particularly those related to the detection of arrythmia and ischaemia, is promising. However, there appears to exist minimal testing in experimental studies, with only two included impact studies citing a performance study as support for the intervention algorithm used. Because of the disconnect between performance and impact studies, there is currently limited evidence of the effect of integrating advanced inference algorithms in remote monitoring interventions. If the field of remote patient monitoring is to progress, future impact studies should address this disconnect by evaluating high performance validated algorithms in robust clinical trials.

Machine-learning based feature selection for a non-invasive breathing change detection

Background

Chronic Obstructive Pulmonary Disease (COPD) is one of the top 10 causes of death worldwide, representing a major public health problem. Researchers have been looking for new technologies and methods for patient monitoring with the intention of an early identification of acute exacerbation events. Many of these works have been focusing in breathing rate variation, while achieving unsatisfactory sensitivity and/or specificity. This study aims to identify breathing features that better describe respiratory pattern changes in a short-term adjustment of the load-capacity-drive balance, using exercising data.

Results

Under any tested circumstances, breathing rate alone leads to poor capability of classifying rest and effort periods. The best performances were achieved when using Fourier coefficients or when combining breathing rate with the signal amplitude and/or ARIMA coefficients.

Conclusions

Breathing rate alone is a quite poor feature in terms of prediction of breathing change and the addition of any of the other proposed features improves the classification power. Thus, the combination of features may be considered for enhancing exacerbation prediction methods based in the breathing signal.Trial Registration : ClinicalTrials NCT03753386. Registered 27 November 2018, https://clinicaltrials.gov/show/NCT03753386

The role of clinical signs and spirometry in the diagnosis of obstructive airway diseases: a systematic analysis adapted to general practice settings

Background

In general practice (GP), the diagnosis of obstructive airway diseases much relies on diagnostic questions, in view of the limited availability of lung function. We systematically assessed the relative importance of such questions for diagnosing asthma and chronic obstructive pulmonary disease (COPD), either without or with information from spirometry.

Methods

We used data obtained in a pulmonary practice to ensure the validity of diagnoses and assessments. Subjects with a diagnosis of COPD (n=260), or asthma (n=433), or other respiratory diseases (n=230), and subjects without respiratory diseases (n=364, controls) were included. The diagnostic questions comprised eight items, covering smoking history, self-attributed allergic rhinitis, dyspnea, cough, phlegm and wheeze. Optionally standard parameters of the flow-volume-curve were included. Decision trees for the diagnosis of COPD and asthma were constructed, moreover a probabilistic diagnostic network based on the results of path analyses describing the relationship between variables.

Results

In the decision trees, age, sex, current smoking, wheezing, dyspnea upon mild exertion, self-attributed allergic rhinitis, phlegm, forced expiratory volume in one second (FEV₁), and expiratory flow rates were relevant, depending on the diagnostic comparison, while cough, dyspnea upon strong exertion and ex-smoker status were not relevant. In contrast, the probabilistic network for the diagnosis of COPD and asthma versus controls incorporated all diagnostic questions, i.e., dyspnea upon mild or strong exertion, current smoking, ex-smoking, wheezing, cough and phlegm but from spirometry only FEV₁. Depending on the individual pattern, the probability for COPD could raise from 25% to 81%, while the diagnostic gain for asthma was lower.

Conclusions

The study developed simple diagnostic algorithms for asthma and COPD that take into account the relative importance of clinical signs and history, as well as spirometric data if available. The diagnostic accuracy was especially high for COPD. These algorithms may be helpful as a starting point in the standardisation of diagnostic strategies in GP practices.

Trial registration

The study is registered under DRKS00013935 at German Clinical Trials Register (DRKS, Date of registration 01/03/2018).

Semi-automated tracking of pain in critical care patients using artificial intelligence: a retrospective observational study

Monitoring the pain intensity in critically ill patients is crucial because intense pain can cause adverse events, including poor survival rates; however, continuous pain evaluation is difficult. Vital signs have traditionally been considered ineffective in pain assessment; nevertheless, the use of machine learning may automate pain assessment using vital signs. This retrospective observational study was performed at a university hospital in Sendai, Japan. Objective pain assessments were performed in eligible patients using the Critical-Care Pain Observation Tool (CPOT). Three machine-learning methods—random forest (RF), support vector machine (SVM), and logistic regression (LR)—were employed to predict pain using parameters, such as vital signs, age group, and sedation levels. Prediction accuracy was calculated as the harmonic mean of sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC). Furthermore, 117,190 CPOT assessments were performed in 11,507 eligible patients (median age: 65 years; 58.0% males). We found that pain prediction was possible with all three machine-learning methods. RF demonstrated the highest AUROC for the test data (RF: 0.853, SVM: 0.823, and LR: 0.787). With this method, pain can be objectively, continuously, and semi-automatically evaluated in critically ill patients.

Length of hospital stay prediction with an integrated approach of statistical-based fuzzy cognitive maps and artificial neural networks

Chronic obstructive pulmonary disease (COPD) is a global burden, which is estimated to be the third leading cause of death worldwide by 2030. The economic burden of COPD grows continuously because it is not a curable disease. These conditions make COPD an important research field of artificial intelligence (AI) techniques in medicine. In this study, an integrated approach of the statistical-based fuzzy cognitive maps (SBFCM) and artificial neural networks (ANN) is proposed for predicting length of hospital stay of patients with COPD, who admitted to the hospital with an acute exacerbation. The SBFCM method is developed to determine the input variables of the ANN model. The SBFCM conducts statistical analysis to prepare preliminary information for the experts and then collects expert opinions accordingly, to define a conceptual map of the system. The integration of SBFCM and ANN methods provides both statistical data and expert opinion in the prediction model. In the numerical application, the proposed approach outperformed the conventional approach and other machine learning algorithms with 79.95% accuracy, revealing the power of expert opinion involvement in medical decisions. A medical decision support framework is constructed for better prediction of length of hospital stay and more effective hospital management.

Using an Extended Technology Acceptance Model to Understand the Factors Influencing Telehealth Utilization After Flattening the COVID-19 Curve in South Korea: Cross-sectional Survey Study

BACKGROUND

Although telehealth is considered a key component in combating the worldwide crisis caused by COVID-19, the factors that influence its acceptance by the general population after the flattening of the COVID-19 curve remain unclear.

OBJECTIVE

We aimed to identify factors affecting telehealth acceptance, including anxiety related to COVID-19, after the initial rapid spread of the disease in South Korea.

METHODS

We proposed an extended technology acceptance model (TAM) and performed a cross-sectional survey of individuals aged ≥30 years. In total, 471 usable responses were collected. Confirmatory factor analysis was used to examine the validity of measurements, and the partial least squares (PLS) method was used to investigate factors influencing telehealth acceptance and the impacts of COVID-19.

RESULTS

PLS analysis showed that increased accessibility, enhanced care, and ease of telehealth use had positive effects on its perceived usefulness (P=.002, P<.001, and P<.001, respectively). Furthermore, perceived usefulness, ease, and privacy/discomfort significantly impacted the acceptance of telehealth (P<.001, P<.001, and P<.001, respectively). However, anxiety toward COVID-19 was not associated with telehealth acceptance (P=.112), and this insignificant relationship was consistent in the cluster (n=216, 46%) of respondents with chronic diseases (P=.185).

CONCLUSIONS

Increased accessibility, enhanced care, usefulness, ease of use, and privacy/discomfort are decisive variables affecting telehealth acceptance in the Korean general population, whereas anxiety about COVID-19 is not. This study may lead to a tailored promotion of telehealth after the pandemic subsides.

A two-layer probabilistic model to predict COPD exacerbations for patients in telehealth

Conventional one-layer models have yet to achieve clinically relevant classification rates in predicting exacerbations for patients with COPD. The present study investigates whether a two-layer probabilistic model can increase classification rates compared to a one-layer model. Continuous measurements of oxygen saturation, pulse rate, and blood pressure from nine patients with COPD were structured into 17 prodromal exacerbation periods and 398 control periods. A one-layer model was compared to a two-layer model based on prior probabilities using double cross-validation. The two models were compared by the area under the receiver operating characteristics curve and sensitivity at an arbitrarily set specificity of 0.95. This comparison was carried out across nine different classification algorithms. The area under the receiver operating characteristics curve was increased across all nine classification algorithms and by a mean value of 0.11. Sensitivity at an arbitrarily set specificity of 0.95 was also increased by a mean value of 0.13. In conclusion, a two-layer probabilistic model for predicting COPD exacerbations can increase classification rates compared to a one-layer model, and to a level of clinical relevance, for patients in telehealth.

How stable is lung function in patients with stable chronic obstructive pulmonary disease when monitored using a telehealth system? A longitudinal and home-based study

Background

Many telehealth systems have been designed to identify signs of exacerbations in patients with chronic obstructive pulmonary disease (COPD), but few previous studies have reported the nature of recorded lung function data and what variations to expect in this group of individuals. The aim of the study was to evaluate the nature of individual diurnal, day-to-day and long-term variation in important prognostic markers of COPD exacerbations by employing a telehealth system developed in-house.

Methods

Eight women and five men with COPD performed measurements (spirometry, pulse oximetry and the COPD assessment test (CAT)) three times per week for 4–6 months using the telehealth system. Short-term and long-term individual variations were assessed using the relative density and weekly means respectively. Quality of the spirometry measurements (forced expiratory volume in one second (FEV₁) and inspiratory capacity (IC)) was assessed employing the criteria of American Thoracic Society (ATS)/European Respiratory Society (ERS) guidelines.

Results

Close to 1100 measurements of both FEV₁ and IC were performed during a total of 240 patient weeks. The two standard deviation ranges for intra-individual short-term variation were approximately ±210 mL and ± 350 mL for FEV₁ and IC respectively. In long-term, spirometry values increased and decreased without notable changes in symptoms as reported by CAT, although it was unusual with a decrease of more than 50 mL per measurement of FEV₁ between three consecutive measurement days. No exacerbation occurred. There was a moderate to strong positive correlation between FEV₁ and IC, but weak or absent correlation with the other prognostic markers in the majority of the participants.

Conclusions

Although FEV₁ and IC varied within a noticeable range, no corresponding change in symptoms occurred. Therefore, this study reveals important and, to our knowledge, previously not reported information about short and long-term variability in prognostic markers in stable patients with COPD. The present data are of significance when defining criteria for detecting exacerbations using telehealth strategies.

Comparison of machine learning algorithms for the identification of acute exacerbations in chronic obstructive pulmonary disease

OBJECTIVES

Identifying acute exacerbations in chronic obstructive pulmonary disease (AECOPDs) is of utmost importance for reducing the associated mortality and financial burden. In this research, the authors aimed to develop identification models for AECOPDs and to compare the relative performance of different modeling paradigms to find the best model for this task.

METHODS

Data were extracted from electronic medical records (EMRs) of patients with chronic obstructive pulmonary disease who admitted to the China-Japan Friendship Hospital between February 2011 and March 2017. Five machine learning algorithms (random forest, support vector machine, logistic regression, K-nearest neighbor and naïve Bayes) were used to develop the AECOPDs identification models. Feature selection was performed to find an optimal feature subset. 10-folds cross-validation was used to find the best hyperparameters for each model. The following metrics:  area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were used to evaluate the performance of these models.

RESULTS

A total of 303 EMRs (AECOPDs patients:135; None AECOPDs patients: 168) were included in the study. The SVM model obtained the best performance (sensitivity: 0.80, specificity: 0.83, positive predictive value:0.81, negative predictive value:0.85 and area under the receiver operating characteristic curve: 0.90) after performing feature selection.

CONCLUSIONS

Our research confirms that the proposed model based on the support vector machine is a powerful tool to identify AECOPDs patients, and it is promising to provide decision support for clinicians when they are struggling to give a confirmed clinical diagnosis.

Evaluating Mobile Apps and Biosensing Devices to Monitor Physical Activity and Respiratory Function in Smokers With and Without Respiratory Symptoms or Chronic Obstructive Pulmonary Disease: Protocol for a Proof-of-Concept, Open-Label, Feasibility Study

BACKGROUND

Chronic obstructive pulmonary disease (COPD) is a global public health problem, and continuous monitoring is essential for both its management as well as the management of other chronic diseases. Telemonitoring using mobile health (mHealth) devices has the potential to promote self-management, improve control, increase quality of life, and prevent hospital admissions.

OBJECTIVE

This study aims to demonstrate whether a large-scale study assessing the use of mHealth devices to improve the treatment, assessment, compliance, and outcomes of chronic diseases, particularly COPD and cardio-metabolic syndrome, is feasible. This will allow our team to select the appropriate design and characteristics for our large-scale study.

METHODS

A total of 3 cohorts, with 9 participants in each, will use mHealth devices for 90 days while undergoing the current standard of care. These groups are: 9 "non-COPD," otherwise healthy, smokers; 9 "grey zone" smokers (forced expiratory volume in 1 second/ forced vital capacity ≥0.70 after bronchodilator treatment; COPD Assessment Test ≥10); and 9 smokers diagnosed with Stage 1-3 COPD. Rates of recruitment, retention, and adherence will be measured. Overall, two mHealth devices will be utilized in the study: the AnaMed Original Equipment Manufacturer device (measures distance, energy expenditure, heart rate, and heart rate variability) and the Air Next mobile spirometry device. The mHealth devices will be compared against industry standards. Additionally, a questionnaire will be administered to assess the participants' perceptions of the mHealth technologies used.

RESULTS

The inclusion of participants started in June 2019. Study results will be published in peer-reviewed scientific journals.

CONCLUSIONS

This study will demonstrate whether a large-scale study to assess the use of mHealth devices to improve the treatment, assessment, compliance, and outcomes of chronic diseases, particularly COPD and cardio-metabolic syndrome, is feasible. It will also allow the research team to select the appropriate design and characteristics for the large-scale study.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04081961; https://clinicaltrials.gov/ct2/show/NCT04081961.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/16461.

Personalized medicine for patients with COPD: where are we?

Chronic airflow limitation is the common denominator of patients with chronic obstructive pulmonary disease (COPD). However, it is not possible to predict morbidity and mortality of individual patients based on the degree of lung function impairment, nor does the degree of airflow limitation allow guidance regarding therapies. Over the last decades, understanding of the factors contributing to the heterogeneity of disease trajectories, clinical presentation, and response to existing therapies has greatly advanced. Indeed, diagnostic assessment and treatment algorithms for COPD have become more personalized. In addition to the pulmonary abnormalities and inhaler therapies, extra-pulmonary features and comorbidities have been studied and are considered essential components of comprehensive disease management, including lifestyle interventions. Despite these advances, predicting and/or modifying the course of the disease remains currently impossible, and selection of patients with a beneficial response to specific interventions is unsatisfactory. Consequently, non-response to pharmacologic and non-pharmacologic treatments is common, and many patients have refractory symptoms. Thus, there is an ongoing urgency for a more targeted and holistic management of the disease, incorporating the basic principles of P4 medicine (predictive, preventive, personalized, and participatory). This review describes the current status and unmet needs regarding personalized medicine for patients with COPD. Also, it proposes a systems medicine approach, integrating genetic, environmental, (micro)biological, and clinical factors in experimental and computational models in order to decipher the multilevel complexity of COPD. Ultimately, the acquired insights will enable the development of clinical decision support systems and advance personalized medicine for patients with COPD.

Role of Artificial Intelligence within the Telehealth Domain

Objectives : This paper provides a discussion about the potential scope of applicability of Artificial Intelligence methods within the telehealth domain. These methods are focussed on clinical needs and provide some insight to current directions, based on reports of recent advances.

Methods : Examples of telehealth innovations involving Artificial Intelligence to support or supplement remote health care delivery were identified from recent literature by the authors, on the basis of expert knowledge. Observations from the examples were synthesized to yield an overview of contemporary directions for the perceived role of Artificial Intelligence in telehealth.

Results : Two major focus areas for related contemporary directions were established. These were first, quality improvement for existing clinical practice and service delivery, and second, the development and support of new models of care. Case studies from each focus area have been chosen for illustration purposes.

Conclusion : Examples of the role of Artificial Intelligence in delivery of health care remotely include use of tele-assessment, tele-diagnosis, tele-interactions, and tele-monitoring. Further developments of underlying algorithms and validation of methods will be required for wider adoption. Certain key social and ethical considerations also need consideration more generally in the health system, as Artificial-Intelligence-enabled-telehealth becomes more commonplace.

Effort Oxygen Saturation and Effort Heart Rate to Detect Exacerbations of Chronic Obstructive Pulmonary Disease or Congestive Heart Failure

Background: current algorithms for the detection of heart failure (HF) and chronic obstructive pulmonary disease (COPD) exacerbations have poor performance. Methods: this study was designed as a prospective longitudinal trial. Physiological parameters were evaluated at rest and effort (walking) in patients who were in the exacerbation or stable phases of HF or COPD. Parameters with relevant discriminatory power (sensitivity (Sn) or specificity (Sp) ≥ 80%, and Youden index ≥ 0.2) were integrated into diagnostic algorithms. Results: the study included 127 patients (COPD: 56, HF: 54, both: 17). The best algorithm for COPD included: oxygen saturation (SaO₂) decrease ≥ 2% in minutes 1 to 3 of effort, end-of-effort heart rate (HR) increase ≥ 10 beats/min and walking distance decrease ≥ 35 m (presence of one criterion showed Sn: 0.90 (95%, CI(confidence interval): 0.75–0.97), Sp: 0.89 (95%, CI: 0.72–0.96), and area under the curve (AUC): 0.92 (95%, CI: 0.85–0.995)); and for HF: SaO₂ decrease ≥ 2% in the mean-of-effort, HR increase ≥ 10 beats/min in the mean-of-effort, and walking distance decrease ≥ 40 m (presence of one criterion showed Sn: 0.85 (95%, CI: 0.69–0.93), Sp: 0.75 (95%, CI: 0.57–0.87) and AUC 0.84 (95%, CI: 0.74–0.94)). Conclusions: effort situations improve the validity of physiological parameters for detection of HF and COPD exacerbation episodes.

Design of a Study Assessing Disease Behaviour During the Peri-Diagnostic Period in Patients with Interstitial Lung Disease: The STARLINER Study

Background/Objectives

This study will aim to characterise disease behaviour during the peri-diagnostic period in patients with suspected interstitial lung disease (ILD), including idiopathic pulmonary fibrosis (IPF), using daily home spirometry and accelerometry. Additionally, this study will aim to increase collaboration between secondary and tertiary centres using a digital collaboration platform.

Methods

The STARLINER study (NCT03261037) will enrol approximately 180 symptomatic patients aged 50 years or more with radiological evidence of ILD/IPF from community and tertiary centres in Canada and Europe. Approximately two-thirds of sites will be community centres. Patients will be followed during pre-diagnosis (inclusion to diagnosis; up to a maximum of 12 months) and post-diagnosis (diagnosis to treatment initiation; up to a maximum of 6 months). The study will be facilitated by a digital ecosystem consisting of the devices used for home-based assessments and a digital collaboration platform enabling communication between community and tertiary centres, and between clinicians and patients.

Planned Outcomes

The primary endpoint will be time-adjusted semi-annual change in forced vital capacity (FVC; in millilitres) during the peri-diagnostic period. Physical functional capacity and patient-reported outcomes (PROs) will also be assessed. FVC and physical functional capacity will be measured using daily home spirometry and accelerometry, and at site visits using spirometry and the 6-min walk test. PROs will be assessed prior to, or during, site visits and will always be completed in the same order.

Conclusions

Findings from this study may help to facilitate the early and accurate diagnosis of ILDs by increasing knowledge about disease progression, enabling collaboration between community and tertiary centres and improving communication between clinicians and patients.

Trial Registration Number

NCT03261037.

Funding

F. Hoffmann-La Roche, Ltd., Basel, Switzerland.

Plain Language Summary

Plain language summary available for this article.

Electronic supplementary material

The online version of this article (10.1007/s12325-018-0845-3) contains supplementary material, which is available to authorized users.

An Expert Diagnostic System to Automatically Identify Asthma and Chronic Obstructive Pulmonary Disease in Clinical Settings

Respiratory diseases such as asthma and chronic obstructive pulmonary disease (COPD), are affecting a huge percentage of the world’s population with mortality rates exceeding those of lung cancer and breast cancer combined. The major challenge is the number of patients who are incorrectly diagnosed. To address this, we developed an expert diagnostic system that can differentiate among patients with asthma, COPD or a normal lung function based on measurements of lung function and information about patient’s symptoms. To develop accurate classification algorithms, data from 3657 patients were used and then independently verified using data from 1650 patients collected over a period of two years. Our results demonstrate that the expert diagnostic system can correctly identify patients with asthma and COPD with sensitivity of 96.45% and specificity of 98.71%. Additionally, 98.71% of the patients with a normal lung function were correctly classified, which contributed to a 49.23% decrease in demand for conducting additional tests, therefore decreasing financial cost.

Continuous remote monitoring of COPD patients-justification and explanation of the requirements and a survey of the available technologies

Remote patient monitoring should reduce mortality rates, improve care, and reduce costs. We present an overview of the available technologies for the remote monitoring of chronic obstructive pulmonary disease (COPD) patients, together with the most important medical information regarding COPD in a language that is adapted for engineers. Our aim is to bridge the gap between the technical and medical worlds and to facilitate and motivate future research in the field. We also present a justification, motivation, and explanation of how to monitor the most important parameters for COPD patients, together with pointers for the challenges that remain. Additionally, we propose and justify the importance of electrocardiograms (ECGs) and the arterial carbon dioxide partial pressure (PaCO2) as two crucial physiological parameters that have not been used so far to any great extent in the monitoring of COPD patients. We cover four possibilities for the remote monitoring of COPD patients: continuous monitoring during normal daily activities for the prediction and early detection of exacerbations and life-threatening events, monitoring during the home treatment of mild exacerbations, monitoring oxygen therapy applications, and monitoring exercise. We also present and discuss the current approaches to decision support at remote locations and list the normal and pathological values/ranges for all the relevant physiological parameters. The paper concludes with our insights into the future developments and remaining challenges for improvements to continuous remote monitoring systems. Graphical abstract ᅟ.

Oxygen saturation measurements in telemonitoring of patients with COPD: a systematic review

INTRODUCTION

Telemonitoring applications are expected to become a key component in future healthcare. Despite the frequent use of SpO₂ measurements in telemonitoring of patients with chronic obstructive pulmonary disease (COPD), no profound overview is available about these measurements. Areas covered: A systematic search identified 71 articles that performed SpO₂ measurements in COPD telemonitoring. The results indicate that long-term follow-up of COPD patients using daily SpO₂ spot checks is practically feasible. Very few studies specified protocols for performing these measurements. In many studies, deviating SpO₂ values were used to raise alerts that led to immediate action from healthcare professionals. However, little information was available about the exact implementation and performance of these alerts. Therefore, no firm conclusions can be drawn about the real value of SpO₂ measurements. Future research could optimize performance of alerts using individualized, time-dependent thresholds or predictive algorithms to account for individual differences and SpO₂ baseline changes. Additionally, the value of performing continuous measurements should be examined. Expert commentary: Standardization of the measurements, data science techniques and advancing technology can still boost performance of telemonitoring applications. All these opportunities should be thoroughly explored to assess the real value of SpO₂ in COPD telemonitoring.

Advances in Remote Respiratory Assessments for People with Chronic Obstructive Pulmonary Disease: A Systematic Review

BACKGROUND

Chronic obstructive pulmonary disease (COPD) is a leading cause of mortality. Advances in remote technologies and telemedicine provide new ways to monitor respiratory function and improve chronic disease management. However, telemedicine does not always include remote respiratory assessments, and the current state of knowledge for people with COPD has not been evaluated.

OBJECTIVE

Systematically review the use of remote respiratory assessments in people with COPD, including the following questions: What devices have been used? Can acute exacerbations of chronic obstructive pulmonary disease (AECOPD) be predicted by using remote devices? Do remote respiratory assessments improve health-related outcomes?

MATERIALS AND METHODS

The review protocol was registered (PROSPERO 2016:CRD42016049333). MEDLINE, EMBASE, and COMPENDEX databases were searched for studies that included remote respiratory assessments in people with COPD. A narrative synthesis was then conducted by two reviewers according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

RESULTS

Fifteen studies met the inclusion criteria. Forced expiratory volume assessed daily by using a spirometer was the most common modality. Other measurements included resting respiratory rate, respiratory sounds, and end-tidal carbon dioxide level. Remote assessments had high user satisfaction. Benefits included early detection of AECOPD, improved health-related outcomes, and the ability to replace hospital care with a virtual ward.

CONCLUSION

Remote respiratory assessments are feasible and when combined with sufficient organizational backup can improve health-related outcomes in some but not all cohorts. Future research should focus on the early detection, intervention, and rehabilitation for AECOPD in high-risk people who have limited access to best care and investigate continuous as well as intermittent monitoring.

Artificial Intelligence-Based Triage for Patients with Acute Abdominal Pain in Emergency Department; a Diagnostic Accuracy Study

Introduction:

Artificial intelligence (AI) is the development of computer systems which are capable of doing human intelligence tasks such as decision making and problem solving. AI-based tools have been used for predicting various factors in medicine including risk stratification, diagnosis and choice of treatment. AI can also be of considerable help in emergency departments, especially patients’ triage.

Objective:

This study was undertaken to evaluate the application of AI in patients presenting with acute abdominal pain to estimate emergency severity index version 4 (ESI-4) score without the estimate of the required resources.

Methods:

A mixed-model approach was used for predicting the ESI-4 score. Seventy percent of the patient cases were used for training the models and the remaining 30% for testing the accuracy of the models. During the training phase, patients were randomly selected and were given to systems for analysis. The output, which was the level of triage, was compared with the gold standard (emergency medicine physician). During the test phase of the study, another group of randomly selected patients were evaluated by the systems and the results were then compared with the gold standard.

Results:

Totally, 215 patients who were triaged by the emergency medicine specialist were enrolled in the study. Triage Levels 1 and 5 were omitted due to low number of cases. In triage Level 2, all systems showed fair level of prediction with Neural Network being the highest. In Level 3, all systems again showed fair level of prediction. However, in triage Level 4, decision tree was the only system with fair prediction.

Conclusion:

The application of AI in triage of patients with acute abdominal pain resulted in a model with acceptable level of accuracy. The model works with optimized number of input variables for quick assessment.

Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

This study examines the clinical decision support systems in healthcare, in particular about the prevention, diagnosis and treatment of respiratory diseases, such as Asthma and chronic obstructive pulmonary disease. The empirical pulmonology study of a representative sample (n = 132) attempts to identify the major factors that contribute to the diagnosis of these diseases. Machine learning results show that in chronic obstructive pulmonary disease's case, Random Forest classifier outperforms other techniques with 97.7 per cent precision, while the most prominent attributes for diagnosis are smoking, forced expiratory volume 1, age and forced vital capacity. In asthma's case, the best precision, 80.3 per cent, is achieved again with the Random Forest classifier, while the most prominent attribute is MEF2575.

Implementation of Activity Sensor Equipment in the Homes of Chronic Obstructive Pulmonary Disease Patients

INTRODUCTION

Telemedicine care models for managing advanced chronic obstructive pulmonary disease (COPD) may benefit from the addition of motion sensing, spirometry, and tablet-based symptom diary tracking.

METHODS

We conducted a feasibility study of telemedicine in the home setting using multiple activity sensor monitoring equipment. Deployment and monitoring were supported by home health nurses with technical advice from the equipment makers as needed. Data analytics for motion sensing was provided by the research sponsor, but was not used for care decisions. On study intake, a health risk assessment, Quality of Life (SF-36) survey, and the St. George Respiratory Questionnaire were administered to assess patients' self-perception of quality of life, activities of daily life function, and difficulty living with COPD.

RESULTS

Twenty-eight patients were enrolled and data were gathered for a minimum of 6 months and maximum of 9 months. The researchers demonstrated that augmentation of traditional telemedicine methods with motion sensing, spirometry, and symptom diaries appears feasible. The technical, process, logistics barriers, and solutions required for system deployment are described. The researchers demonstrated that augmentation of traditional telemedicine methods with motion sensing, spirometry, and symptom diaries appears feasible.

CONCLUSIONS

Further exploration will be needed to determine the value of this information in preventing outcomes relevant to patients.

Exacerbations in Chronic Obstructive Pulmonary Disease: Identification and Prediction Using a Digital Health System

Background

Chronic obstructive pulmonary disease (COPD) is a progressive, chronic respiratory disease with a significant socioeconomic burden. Exacerbations, the sudden and sustained worsening of symptoms, can lead to hospitalization and reduce quality of life. Major limitations of previous telemonitoring interventions for COPD include low compliance, lack of consensus on what constitutes an exacerbation, limited numbers of patients, and short monitoring periods. We developed a telemonitoring system based on a digital health platform that was used to collect data from the 1-year EDGE (Self Management and Support Programme) COPD clinical trial aiming at daily monitoring in a heterogeneous group of patients with moderate to severe COPD.

Objective

The objectives of the study were as follows: first, to develop a systematic and reproducible approach to exacerbation identification and to track the progression of patient condition during remote monitoring; and second, to develop a robust algorithm able to predict COPD exacerbation, based on vital signs acquired from a pulse oximeter.

Methods

We used data from 110 patients, with a combined monitoring period of more than 35,000 days. We propose a finite-state machine–based approach for modeling COPD exacerbation to gain a deeper insight into COPD patient condition during home monitoring to take account of the time course of symptoms. A robust algorithm based on short-period trend analysis and logistic regression using vital signs derived from a pulse oximeter is also developed to predict exacerbations.

Results

On the basis of 27,260 sessions recorded during the clinical trial (average usage of 5.3 times per week for 12 months), there were 361 exacerbation events. There was considerable variation in the length of exacerbation events, with a mean length of 8.8 days. The mean value of oxygen saturation was lower, and both the pulse rate and respiratory rate were higher before an impending exacerbation episode, compared with stable periods. On the basis of the classifier developed in this work, prediction of COPD exacerbation episodes with 60%-80% sensitivity will result in 68%-36% specificity.

Conclusions

All 3 vital signs acquired from a pulse oximeter (pulse rate, oxygen saturation, and respiratory rate) are predictive of COPD exacerbation events, with oxygen saturation being the most predictive, followed by respiratory rate and pulse rate. Combination of these vital signs with a robust algorithm based on machine learning leads to further improvement in positive predictive accuracy.

Trial Registration

International Standard Randomized Controlled Trial Number (ISRCTN): 40367841; http://www.isrctn.com/ISRCTN40367841 (Archived by WebCite at http://www.webcitation.org/6olpMWNpc)

Monitoring of Physiological Parameters to Predict Exacerbations of Chronic Obstructive Pulmonary Disease (COPD): A Systematic Review

INTRODUCTION

The value of monitoring physiological parameters to predict chronic obstructive pulmonary disease (COPD) exacerbations is controversial. A few studies have suggested benefit from domiciliary monitoring of vital signs, and/or lung function but there is no existing systematic review.

OBJECTIVES

To conduct a systematic review of the effectiveness of monitoring physiological parameters to predict COPD exacerbation.

METHODS

An electronic systematic search compliant with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines was conducted. The search was updated to April 6, 2016. Five databases were examined: Medical Literature Analysis and Retrieval System Online, or MEDLARS Online (Medline), Excerpta Medica dataBASE (Embase), Allied and Complementary Medicine Database (AMED), Cumulative Index of Nursing and Allied Health Literature (CINAHL) and the Cochrane clinical trials database.

RESULTS

Sixteen articles met the pre-specified inclusion criteria. Fifteen of these articules reported positive results in predicting COPD exacerbation via monitoring of physiological parameters. Nine studies showed a reduction in peripheral oxygen saturation (SpO₂%) prior to exacerbation onset. Three studies for peak flow, and two studies for respiratory rate reported a significant variation prior to or at exacerbation onset. A particular challenge is accounting for baseline heterogeneity in parameters between patients.

CONCLUSION

There is currently insufficient information on how physiological parameters vary prior to exacerbation to support routine domiciliary monitoring for the prediction of exacerbations in COPD. However, the method remains promising.

Machine learning approaches to personalize early prediction of asthma exacerbations

Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

Use of predictive algorithms in-home monitoring of chronic obstructive pulmonary disease and asthma: A systematic review

Major reported factors associated with the limited effectiveness of home telemonitoring interventions in chronic respiratory conditions include the lack of useful early predictors, poor patient compliance and the poor performance of conventional algorithms for detecting deteriorations. This article provides a systematic review of existing algorithms and the factors associated with their performance in detecting exacerbations and supporting clinical decisions in patients with chronic obstructive pulmonary disease (COPD) or asthma. An electronic literature search in Medline, Scopus, Web of Science and Cochrane library was conducted to identify relevant articles published between 2005 and July 2015. A total of 20 studies (16 COPD, 4 asthma) that included research about the use of algorithms in telemonitoring interventions in asthma and COPD were selected. Differences on the applied definition of exacerbation, telemonitoring duration, acquired physiological signals and symptoms, type of technology deployed and algorithms used were found. Predictive models with good clinically reliability have yet to be defined, and are an important goal for the future development of telehealth in chronic respiratory conditions. New predictive models incorporating both symptoms and physiological signals are being tested in telemonitoring interventions with positive outcomes. However, the underpinning algorithms behind these models need be validated in larger samples of patients, for longer periods of time and with well-established protocols. In addition, further research is needed to identify novel predictors that enable the early detection of deteriorations, especially in COPD. Only then will telemonitoring achieve the aim of preventing hospital admissions, contributing to the reduction of health resource utilization and improving the quality of life of patients.

Home oxygen therapy reduces risk of hospitalisation in patients with chronic obstructive pulmonary disease: a population-based retrospective cohort study, 2005-2012

OBJECTIVE

This study evaluated the effect of home oxygen therapy (HOT) on hospital admissions in chronic obstructive pulmonary disease (COPD) patients.

DESIGN AND SETTING

Using nationwide health insurance claims from 2002-2012, we conducted a longitudinal population-based retrospective cohort study.

PARTICIPANTS

Individuals who were aged 40 years or above and newly diagnosed with COPD in 2005.

OUTCOME MEASURES

The primary outcome was total number of hospitalisations during the study period. Participants were matched using HOT propensity scores and were stratified by respiratory impairment (grade 1: FEV1 ≤25% or PaO2 ≤55 mm Hg; grade 2: FEV1 ≤30% or PaO2 56-60 mm Hg; grade 3: FEV1 ≤40% or PaO2 61-65 mm Hg; 'no grade': FEV1 or PaO2 unknown), then a negative binomial regression analysis was performed for each group.

RESULTS

Of the 36,761 COPD patients included in our study, 1330 (3.6%) received HOT. In a multivariate analysis of grade 1 patients performed before propensity score matching, the adjusted relative risk of hospitalisation for patients who did not receive HOT was 1.27 (95% CI 1.01 to 1.60). In a multivariate analysis of grade 1 patients performed after matching, the adjusted relative risk for patients who did not receive HOT was 1.65 (95% CI 1.25 to 2.18). In grade 2 or grade 3 patients, no statistical difference in hospital admission risk was detected. In the 'no grade' group of patients, HOT was associated with an increased risk of hospitalisation.

CONCLUSIONS

HOT reduces the risk of hospital admission in COPD patients with severe hypoxaemia. However, apart from these patients, HOT use is not associated with hospital admissions.

Computerised Analysis of Telemonitored Respiratory Sounds for Predicting Acute Exacerbations of COPD

Chronic obstructive pulmonary disease (COPD) is one of the commonest causes of death in the world and poses a substantial burden on healthcare systems and patients' quality of life. The largest component of the related healthcare costs is attributable to admissions due to acute exacerbation (AECOPD). The evidence that might support the effectiveness of the telemonitoring interventions in COPD is limited partially due to the lack of useful predictors for the early detection of AECOPD. Electronic stethoscopes and computerised analyses of respiratory sounds (CARS) techniques provide an opportunity for substantial improvement in the management of respiratory diseases. This exploratory study aimed to evaluate the feasibility of using: (a) a respiratory sensor embedded in a self-tailored housing for ageing users; (b) a telehealth framework; (c) CARS and (d) machine learning techniques for the remote early detection of the AECOPD. In a 6-month pilot study, 16 patients with COPD were equipped with a home base-station and a sensor to daily record their respiratory sounds. Principal component analysis (PCA) and a support vector machine (SVM) classifier was designed to predict AECOPD. 75.8% exacerbations were early detected with an average of 5 ± 1.9 days in advance at medical attention. The proposed method could provide support to patients, physicians and healthcare systems.