Development and validation of the Salzburg COPD-screening questionnaire (SCSQ): a questionnaire development and validation study

Patient-Oriented Questionnaires and Machine Learning for Rare Disease Diagnosis: A Systematic Review

Background: A major challenge faced by patients with rare diseases (RDs) often stems from delays in diagnosis, typically due to nonspecific clinical symptoms or doctors' limited experience in connecting symptoms to the underlying RD. Using patient-oriented questionnaires (POQs) as a data source for machine learning (ML) techniques can serve as a potential solution. These questionnaires enable patients to portray their day-to-day experiences living with their condition, irrespective of clinical symptoms. This systematic review-registered at PROSPERO with the Registration-ID: CRD42023490838-aims to present the current state of research in this domain by conducting a systematic literature search and identifying the potentials and limitations of this methodology. Methods: The review adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and was primarily funded by the German Federal Ministry of Education and Research under grant no. 16DHBKI056 (ki4all). The methodology involved a systematic search across the databases PubMed, Semantic Scholar and Google Scholar, covering articles published until June 2023. The inclusion criteria encompass examining the use of POQs in diagnosing rare and common diseases. Additionally, studies that focused on applying ML techniques to the resulting datasets were considered for inclusion. The primary objective was to include English as well as German research that involved the generation of predictions regarding the underlying disease based on the information gathered from POQs. Furthermore, studies exploring identifying predictive indicators associated with the underlying disease were also included in the literature review. The following data were extracted from the selected studies: year of publication, number of questions in the POQs, answer scale in the questionnaires, the ML algorithms used, the input data for the ML algorithms, the performance of these algorithms and how the performance was measured. In addition, information on the development of the questionnaires was recorded. Results: This search retrieved 421 results in total. After one superficial and two comprehensive screening runs performed by two authors independently, we ended up with 26 studies for further consideration. Sixteen of these studies deal with diseases and ML algorithms to analyse data; the other ten studies provide contributing research in this field. We discuss several potentials and limitations of the evaluated approach. Conclusions: Overall, the results show that the full potential has not yet been exploited and that further research in this direction is worthwhile, because the study results show that ML algorithms can achieve promising results on POQ data; however, their use in everyday medical practice has not yet been investigated.

Proposing the potential of utilizing the CAT score for early detection of COPD in asymptomatic patients, shifting towards a patient-centered approach: A review

Chronic obstructive pulmonary disease (COPD) constitutes a significant public health challenge, with delayed diagnosis and underdiagnosis being pervasive issues. The United States Preventive Service Task Force recommends restricting COPD screening to symptomatic smokers, a focus that has exhibited limitations, leading to delayed diagnoses, and imposing a substantial burden on patients, their families, and the healthcare system. This paper explores an alternative approach, highlighting the potential utility of the COPD assessment test (CAT) score as a prescreening tool. A CAT score of 10 or higher could serve as an appropriate threshold for further diagnostic procedures, given its robust correlation with pulmonary function test parameters and is valuable capacity to quantify patients' symptoms. The utilization of CAT as a prescreening tool in primary care signifies a transition towards a more patient-centered and comprehensive approach to COPD diagnosis and care.

Undiagnosed chronic respiratory disorders in symptomatic patients with initially suspected and excluded coronary artery disease: insights from a prospective pilot study

Background

Chronic respiratory diseases represent the third-leading cause of death on a global scale. Due to mutual symptoms with cardiovascular diseases and potential inappropriate attribution of symptoms, pulmonary diseases often remain undiagnosed. Therefore, we aimed to evaluate the prevalence of chronic respiratory disorders among symptomatic patients in whom suspected coronary artery disease (CAD) was ruled out.

Methods

After CAD was excluded by invasive coronary angiography (ICA), 50 patients with chest pain or dyspnea were prospectively enrolled in this study. All patients underwent lung function testing, including spirometry and diffusion measurements. At baseline and the 3-month follow-up, standardized assessments of symptoms (CCS chest pain, mMRC score, CAT score) were performed.

Results

Chronic respiratory disease was diagnosed in 14% of patients, with a prevalence of 6% for chronic obstructive ventilation disorders. At 3-month follow-up, patients with normal lung function tests revealed a substantial improvement in symptoms (mean mMRC 0.70 to 0.33, p = 0.06; median CAT 8 to 2, p = 0.01), while those with pulmonary findings showed non-significant alterations or unchanged symptoms (mean mMRC 1.14 to 0.71, p = 0.53; median CAT 6 to 6, p = 0.52).

Conclusion

A substantial proportion of patients with an initial suspicion of coronary artery disease was diagnosed with underlying chronic respiratory diseases and exhibited persistent symptoms.

Performance of alternative COPD case-finding tools: a systematic review and meta-analysis

RATIONALE

Guidelines recommend pre-/post-bronchodilator spirometry for diagnosing COPD, but resource constraints limit the availability of spirometry in primary care in low- and middle-income countries. Although spirometry is the diagnostic gold standard, we shall assess alternative tools for settings without spirometry.

METHODS

A systematic literature review and meta-analysis was conducted, utilising Cochrane, CINAHL, Google Scholar, PubMed and Web of Science (search cut-off was May 01, 2020). Published studies comparing the accuracy of diagnostic tools for COPD with post-bronchodilator spirometry were considered. Studies without sensitivity/specificity data, without a separate validation sample and outside of primary care were excluded. Sensitivity, specificity and area under the curve (AUC) were assessed.

RESULTS

Of 7578 studies, 24 were included (14 635 participants). Hand devices yielded a larger AUC than questionnaires. The meta-analysis included 17 studies and the overall AUC of micro-spirometers (0.84, 95% CI 0.80-0.89) was larger when compared to the COPD population screener (COPD-PS) questionnaire (0.77, 95% CI 0.63-0.85) and the COPD diagnostic questionnaire (CDQ) (0.72, 95% CI 0.64-0.78). However, only the difference between micro-spirometers and the CDQ was significant.

CONCLUSIONS

The CDQ and the COPD-PS questionnaire were approximately equally accurate tools. Questionnaires ensured testing of symptomatic patients, but micro-spirometers were more accurate. A combination could increase accuracy but was not evaluated in the meta-analysis.

Utility of Self-Administered Questionnaires for Identifying Individuals at Risk of COPD in Japan: The OCEAN (Okinawa COPD casE finding AssessmeNt) Study

Purpose

A considerable proportion of patients with chronic obstructive pulmonary disease (COPD) remain undiagnosed and untreated even though they may have a burden of respiratory symptoms that impact quality of life. The OCEAN study assessed the ability of screening questionnaires to identify individuals with, or at risk of, COPD by comparing questionnaire outcomes with spirometric measures of lung function.

Methods

This observational study included participants ≥40 years of age presenting for their annual health examination at a single medical center in Okinawa, Japan. Participants completed COPD screening questionnaires (CAPTURE and COPD-Q), the Chronic Airways Assessment Test (CAAT), and general demographic and health-related questionnaires. The performance characteristics of CAPTURE and COPD-Q were compared with spirometry-based airflow limitation by calculating the area under the receiver operating characteristic (ROC-AUC) curve.

Results

A total of 2518 participants were included in the study; 79% of whom were <60 years of age (mean 52.0 years). A total of 52 (2.1%) participants had airflow limitation defined as forced expiratory volume in 1 second (FEV₁)/forced vital capacity (FVC) <0.7, and 420 (16.7%) participants were classified as Preserved Ratio Impaired Spirometry (PRISm). Among participants with PRISm, 75 (17.9%) had a CAAT total score ≥10. Airflow limitation and PRISm were more prevalent in current smokers versus past smokers. For the CAPTURE questionnaire, ROC-AUC for screening airflow limitation, PRISm, and PRISm with a CAAT total score ≥10 were 0.59, 0.55, and 0.69, respectively; for COPD-Q, these three clinical features were 0.67, 0.58 and 0.68, respectively.

Conclusion

This study demonstrated that CAPTURE and COPD-Q appear to be effective screening tools for identifying symptomatic individuals with undiagnosed, or at risk of developing COPD in adults ≥40 years of age in Okinawa. Furthermore, early diagnosis and management of PRISm is important to improve future outcomes and the societal burden of disease.

Inspiratory crackles-early and late-revisited: identifying COPD by crackle characteristics

BACKGROUND

The significance of pulmonary crackles, by their timing during inspiration, was described by Nath and Capel in 1974, with early crackles associated with bronchial obstruction and late crackles with restrictive defects. Crackles are also described as 'fine' or 'coarse'. We aimed to evaluate the usefulness of crackle characteristics in the diagnosis of chronic obstructive pulmonary disease (COPD).

METHODS

In a population-based study, lung sounds were recorded at six auscultation sites and classified in participants aged 40 years or older. Inspiratory crackles were classified as 'early' or 'late and into the types' 'coarse' and 'fine' by two observers. A diagnosis of COPD was based on respiratory symptoms and forced expiratory volume in 1 s/forced inspiratory vital capacity below lower limit of normal, based on Global Lung Function Initiative 2012 reference. Associations between crackle characteristics and COPD were analysed by logistic regression. Kappa statistics was applied for evaluating interobserver agreement.

RESULTS

Of 3684 subjects included in the analysis, 52.9% were female, 50.1% were ≥65 years and 204 (5.5%) had COPD. Basal inspiratory crackles were heard in 306 participants by observer 1 and in 323 by observer 2. When heard bilaterally COPD could be predicted with ORs of 2.59 (95% CI 1.36 to 4.91) and 3.20 (95% CI 1.71 to 5.98), annotated by observer 1 and 2, respectively, adjusted for sex and age. If bilateral crackles were coarse the corresponding ORs were 2.65 (95% CI 1.28 to 5.49) and 3.67 (95% CI 1.58 to 8.52) and when heard early during inspiration the ORs were 6.88 (95% CI 2.59 to 18.29) and 7.63 (95%CI 3.73 to 15.62). The positive predictive value for COPD was 23% when early crackles were heard over one or both lungs. We observed higher kappa values when classifying timing than type.

CONCLUSIONS

'Early' inspiratory crackles predicted COPD more strongly than 'coarse' inspiratory crackles. Identification of early crackles at the lung bases should imply a strong attention to the possibility of COPD.

Use of the COPD Assessment Test (CAT) to screen for COPD in dairy farmers: AIRBAg study

OBJECTIVES

People at risk of chronic obstructive pulmonary disease (COPD) can benefit from appropriate medical management before severe symptoms appear. This study assesses the value of the COPD Assessment Test (CAT) questionnaire for screening dairy farmers, who tend to be slow or reluctant to seek health care.

METHODS

During the time period 2012-2017, 2089 randomly selected dairy farmers in Brittany (France) were invited to complete self-administered questionnaires (including the CAT) and to undergo an occupational health check-up using an electronic mini-spirometer and conventional spirometry. Those showing symptoms suggestive of COPD and/or a ratio FEV₁ /FEV₆ < 80% were sent to a pulmonologist for a further check-up, including spirometry with a reversibility test. Multivariate logistic models based on CAT scores and socio-demographic or work-related factors were developed to predict COPD.

RESULTS

The 1231 farmers who underwent the occupational health check-up included 1203 who met the inclusion/exclusion criteria. Pulmonologist identified 16 (1.3%) cases of COPD. A multivariate logistic regression model (covariates: CAT sum score, on-farm time, BMI, smoking status, free-stall mulching) provided an area under the receiver-operating characteristic curve (AUC) of 0.87 (95% CI: 0.75-0.98). Using a cut-off of 0.007 gave a sensitivity of 93.8% and a specificity of 62.4%. Another model that included CAT breathlessness and the same covariates performed marginally better (AUC = 0.88, 95% CI: 0.77-0.98).

CONCLUSION

Our predictive models can both benefit dairy farmers by providing early diagnosis and management of their COPD and avoid unnecessary, costly spirometry during the screening process.

Validation of Questionnaire-based Case Definitions for Chronic Obstructive Pulmonary Disease

BACKGROUND

Various questionnaire-based definitions of chronic obstructive pulmonary disease (COPD) have been applied using the US representative National Health and Nutrition Examination Survey (NHANES), but few have been validated against objective lung function data. We validated two prior definitions that incorporated self-reported physician diagnosis, respiratory symptoms, and/or smoking. We also validated a new definition that we developed empirically using gradient boosting, an ensemble machine learning method.

METHODS

Data came from 7,996 individuals 40-79 years who participated in NHANES 2007-2012 and underwent spirometry. We considered participants "true" COPD cases if their ratio of postbronchodilator forced expiratory volume in 1 second to forced vital capacity was below 0.7 or the lower limit of normal. We stratified all analyses by smoking history. We developed a gradient boosting model for smokers only; predictors assessed (25 total) included sociodemographics, inhalant exposures, clinical variables, and respiratory symptoms.

RESULTS

The spirometry-based COPD prevalence was 26% for smokers and 8% for never smokers. Among smokers, using questionnaire-based definitions resulted in a COPD prevalence ranging from 11% to 16%, sensitivity ranging from 18% to 35%, and specificity ranging from 88% to 92%. The new definition classified participants based on age, bronchodilator use, body mass index (BMI), smoking pack-years, and occupational organic dust exposure, and resulted in the highest sensitivity (35%) and specificity (92%) among smokers. Among never smokers, the COPD prevalence ranged from 4% to 5%, and we attained good specificity (96%) at the expense of sensitivity (9-10%).

CONCLUSION

Our results can be used to parametrize misclassification assumptions for quantitative bias analysis when pulmonary function data are unavailable.

Adult Asthma Scores-Development and Validation of Multivariable Scores to Identify Asthma in Surveys

BACKGROUND

One of the questions in epidemiology is the identification of adult asthma in studies.

OBJECTIVE

To develop and validate multivariable scores for adult asthma identification in epidemiological studies and to explore cutoffs to rule in/rule out asthma, compared with asthma diagnosed by a physician after clinical examination and diagnostic tests, blinded to the self-administered questions.

METHODS

We analyzed data (n = 711 adults) from a nationwide population-based study. The predictors were self-administered questions identified in a literature review (the Adult Asthma Epidemiological Score [A2 score]) and from the Global Allergy and Asthma Network of Excellence (GA2LEN) questionnaire (the GA2LEN Asthma Epidemiological Score [GA2LEN score]). Scores were developed using exploratory factor analysis. Internal consistency, discriminative power, and diagnostic accuracy were assessed.

RESULTS

The A2 score comprises 8 questions (including "Did a physician confirm you had asthma?") and the GA2LEN score comprises 6 questions (including "Have you ever had asthma?"). Both had high Cronbach α (0.89 and 0.85, respectively, for the A2 score and the GA2LEN score) and good area under the receiver-operating characteristic curve (90.4% and 89.0%). The scoring is the sum of positive answers. Asthma is present (rule in) for scores of 4 or more (specificity, 99.2%; PPV, 93.3% and 91.7%; accuracy, 89.4% and 87.4%, respectively, for the A2 score and the GA2LEN score). Asthma is excluded (rule out) for A2 scores of 0 to 1 and a GA2LEN score of 0 (sensitivity, 93.1%; NPV, 98.2% and 98.0%; accuracy 89.4% and 82.8%, respectively, for the A2 score and the GA2LEN score).

CONCLUSIONS

These practical scores can be used to rule in/rule out asthma in epidemiological studies and clinical screening/triage settings. They may help physicians in primary care or other specialties to screen patients with asthma using a simple score with a high level of discrimination and to identify the best candidates to be referred for a diagnostic workup. Moreover, their use may contribute to reducing the inconsistencies of operational definitions of asthma across studies and surveys.

Case-Finding for Persistent Airway Obstruction in Farmers: A Questionnaire With Optimal Diagnosis Criteria

INTRODUCTION

Appropriate identification of subjects who are candidates for spirometry through case-finding questionnaires may help solve the problem of chronic obstructive pulmonary disease misdiagnosis. The performance of case-finding questionnaires depends at least partially on the characteristics of the population used for their development. The use of an accurate threshold for the forced expiratory volume in 1 second / forced vital capacity ratio to define persistent airway obstruction is also vital in ascertaining chronic obstructive pulmonary disease.

METHODS

Using a population examined between October 2012 and May 2013 that included a large subset of agricultural workers both exposed and unexposed to tobacco smoking, the authors aimed to select a combination of items that would identify persons most likely to have persistent airway obstruction defined as forced expiratory volume in 1 second / forced vital capacity less than the lower limit of normal according to the Global Lung Initiative-2012 equations. Two thirds of the population (n=3,397) were randomly selected to develop a questionnaire, and one third (n=1,698) was reserved for questionnaire validation. Statistical analysis was performed in 2016.

RESULTS

The selected items were sex, dyspnea, BMI, tobacco smoking habits, age, history of respiratory diseases, and history of occupation at risk. The C-index of the model was 0.84 (95% CI=0.80, 0.88) for the development population and 0.76 (95% CI=0.66, 0.86) for the validation population. Using the selected items in combination, the sensitivity and specificity in identifying persistent airway obstruction were 76% and 77%, respectively, in the development population (and 68% and 73%, respectively, in the validation population) for a threshold value of 2.50%.

CONCLUSIONS

This seven-item questionnaire is the first developed from a population comprising a large subset of agricultural workers and using the Global Lung Initiative-2012 equations.