A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children.

BACKGROUND: The differential diagnosis of paediatric respiratory conditions is difficult and suboptimal. Existing diagnostic algorithms are associated with significant error rates, resulting in misdiagnoses, inappropriate use of antibiotics and unacceptable morbidity and mortality. Recent advances in acoustic engineering and artificial intelligence have shown promise in the identification of respiratory conditions based on sound analysis, reducing dependence on diagnostic support services and clinical expertise. We present the results of a diagnostic accuracy study for paediatric respiratory disease using an automated cough-sound analyser. METHODS: We recorded cough sounds in typical clinical environments and the first five coughs were used in analyses. Analyses were performed using cough data and up to five-symptom input derived from patient/parent-reported history. Comparison was made between the automated cough analyser diagnoses and consensus clinical diagnoses reached by a panel of paediatricians after review of hospital charts and all available investigations. RESULTS: A total of 585 subjects aged 29 days to 12 years were included for analysis. The Positive Percent and Negative Percent Agreement values between the automated analyser and the clinical reference were as follows: asthma (97, 91%); pneumonia (87, 85%); lower respiratory tract disease (83, 82%); croup (85, 82%); bronchiolitis (84, 81%). CONCLUSION: The results indicate that this technology has a role as a high-level diagnostic aid in the assessment of common childhood respiratory disorders. TRIAL REGISTRATION: Australian and New Zealand Clinical Trial Registry (retrospective) - ACTRN12618001521213 : 11.09.2018.

Correction to: Exhaustive mathematical analysis of simple clinical measurements for childhood pneumonia diagnosis.

In the original publication of the article "Declaration of conflict of interest" were not included. The following text is given below.

Exhaustive mathematical analysis of simple clinical measurements for childhood pneumonia diagnosis.

BACKGROUND: Pneumonia is the leading cause of mortality for children below 5 years of age. The majority of these occur in poor countries with limited access to diagnosis. The World Health Organization (WHO) criterion for pneumonia is the de facto method for diagnosis. It is designed targeting a high sensitivity and uses easy to measure parameters. The WHO criterion has poor specificity. METHODS: We propose a method using common measurements (including the WHO parameters) to diagnose pneumonia at high sensitivity and specificity. Seventeen clinical features obtained from 134 subjects were used to create a series of logistic regression models. We started with one feature at a time, and continued building models with increasing number of features until we exhausted all possible combinations. We used a k-fold cross validation method to measure the performance of the models. RESULTS: The sensitivity of our method was comparable to that of the WHO criterion but the specificity was 84%-655% higher. In the 2-11 month age group, the WHO criteria had a sensitivity and specificity of 92.0%±11.6% and 38.1%±18.5%, respectively. Our best model (using the existence of a runny nose, the number of days with runny nose, breathing rate and temperature) performed at a sensitivity of 91.3%±13.0% and specificity of 70.2%±22.80%. In the 12-60 month age group, the WHO algorithm gave a sensitivity of 95.7%±7.6% at a specificity of 9.8%±13.1%, while our corresponding sensitivity and specificity were 94.0%±12.1% and 74.0%±23.3%, respectively (using fever, number of days with cough, heart rate and chest in-drawing). CONCLUSIONS: The WHO algorithm can be improved through mathematical analysis of clinical observations and measurements routinely made in the field. The method is simple and easy to implement on a mobile phone. Our method allows the freedom to pick the best model in any arbitrary field scenario (e.g., when an oximeter is not available).

Wavelet augmented cough analysis for rapid childhood pneumonia diagnosis.

Pneumonia is the cause of death for over a million children each year around the world, largely in resource poor regions such as sub-Saharan Africa and remote Asia. One of the biggest challenges faced by pneumonia endemic countries is the absence of a field deployable diagnostic tool that is rapid, low-cost and accurate. In this paper, we address this issue and propose a method to screen pneumonia based on the mathematical analysis of cough sounds. In particular, we propose a novel cough feature inspired by wavelet-based crackle detection work in lung sound analysis. These features are then combined with other mathematical features to develop an automated machine classifier, which can separate pneumonia from a range of other respiratory diseases. Both cough and crackles are symptoms of pneumonia, but their existence alone is not a specific enough marker of the disease. In this paper, we hypothesize that the mathematical analysis of cough sounds allows us to diagnose pneumonia with sufficient sensitivity and specificity. Using a bedside microphone, we collected 815 cough sounds from 91 patients with respiratory illnesses such as pneumonia, asthma, and bronchitis. We extracted wavelet features from cough sounds and combined them with other features such as Mel Cepstral coefficients and non-Gaussianity index. We then trained a logistic regression classifier to separate pneumonia from other diseases. As the reference standard, we used the diagnosis by physicians aided with laboratory and radiological results as deemed necessary for a clinical decision. The methods proposed in this paper achieved a sensitivity and specificity of 94% and 63%, respectively, in separating pneumonia patients from non-pneumonia patients based on wavelet features alone. Combining the wavelets with features from our previous work improves the performance further to 94% and 88% sensitivity and specificity. The performance far surpasses that of the WHO criteria currently in common use in resource-limited settings.