Cough is a common symptom of almost all childhood respiratory diseases. In a typical consultation session, physicians may seek for qualitative information (e.g. wetness) and quantitative information (e.g. cough frequency) either by listening to voluntary coughs or by interviewing the patients/carers. This information is useful in the differential diagnosis and in assessing the treatment outcome of the disease. The manual cough assessment is tedious, subjective, and not suitable for long-term recording. Researchers have attempted to develop automated systems for cough assessment but none of the existing systems have specifically targeted the pediatric population. In this paper we address these issues and develop a method to automatically identify cough segments from the pediatric sound recordings. Our method is based on extracting mathematical features such as non-Gaussianity, Shannon entropy, and cepstral coefficients to describe cough characteristics. These features were then used to train an Artificial Neural Network to detect coughs segment in the sound recordings. Working on a prospective data set of 14 subjects (sound recording length 840 minutes), proposed method achieved sensitivity, specificity, and Cohen's Kappa of 93%, as an automated pediatric cough counting device as well as the front-end of a cough analysis system.

Cough is the most common symptom of several respiratory diseases. It is a defense mechanism of the body to clear the respiratory tract from foreign materials inhaled accidentally or produced internally by infections. The identification of wet and dry cough is an important clinical finding, aiding in the differential diagnosis especially in children. Wet coughs are more likely to be associated with lower respiratory track bacterial infections. At present during a typical consultation session, the wet/dry decision is based on the subjective judgment of a physician. It is not available for the non-trained person, long term monitoring or in the assessment of treatment efficacy. In this paper we address these issues and develop an automated technology to classify cough into 'wet' and 'dry' categories. We propose novel features and a Logistic regression model (LRM) for the classification of coughs into wet/dry classes. The performance of the method was evaluated on a clinical database of pediatric coughs (C = 536) recorded using a bed-side non-contact microphone from N = 78 patients. Results of the automatic classification were compared against two expert human scorers. The sensitivity and specificity of the LRM in picking wet coughs were between 87 and 88% with 95% confidence interval on training/validation dataset (310 cough events from 60 patients) and 84 and 76% respectively on prospective dataset (117 cough events from 18 patients). The kappa agreement with two expert human scorers on prospective dataset was 0.51. These results indicate the potential of the method as a useful clinical tool for cough monitoring, especially at home settings.

Background Transmission within families and multiple spike protein mutations have been associated with the rapid transmission of SARS-CoV-2. We aimed to: (1) describe full genome characterization of SARS-CoV-2 and correlate the sequences with epidemiological data within family clusters, and (2) conduct phylogenetic analysis of all samples from Yogyakarta and Central Java, Indonesia and other countries. Methods The study involved 17 patients with COVID-19, including two family clusters. We determined the full-genome sequences of SARS-CoV-2 using the Illumina MiSeq next-generation sequencer. Phylogenetic analysis was performed using a dataset of 142 full-genomes of SARS-CoV-2 from different regions. Results Ninety-four SNPs were detected throughout the open reading frame (ORF) of SARS-CoV-2 samples with 58% (54/94) of the nucleic acid changes resulting in amino acid mutations. About 94% (16/17) of the virus samples showed D614G on spike protein and 56% of these (9/16) showed other various amino acid mutations on this protein, including L5F, V83L, V213A, W258R, Q677H, and N811I. The virus samples from family cluster-1 (n = 3) belong to the same clade GH, in which two were collected from deceased patients, and the other from the survived patient. All samples from this family cluster revealed a combination of spike protein mutations of D614G and V213A. Virus samples from family cluster-2 (n = 3) also belonged to the clade GH and showed other spike protein mutations of L5F alongside the D614G mutation. Conclusions Our study is the first comprehensive report associating the full-genome sequences of SARS-CoV-2 with the epidemiological data within family clusters. Phylogenetic analysis revealed that the three viruses from family cluster-1 formed a monophyletic group, whereas viruses from family cluster-2 formed a polyphyletic group indicating there is the possibility of different sources of infection. This study highlights how the same spike protein mutations among members of the same family might show different disease outcomes.

Background Pneumonia is one of the main causes of death in children in developing countries. It is important to identify clinical signs, demographic factors, and laboratory data which can be used to predict children who have higher risk of mortality from pneumonia.Objective To find the clinical signs, demographic factors and laboratory data that can be used as predictors of mortality from pneumonia.Methods T his historical case􀀽control study was carried out in Sardjito Hospital between January 2004 and December 2006. Data were obtained from medical records. Differential proportion between groups was analyzed with chi square. Regression analysis was used to identify clinical factors, demographic factors and laboratory factors that associated with mortality from pneumonia.Results Fifty􀀽eight patients were enrolled in this study, 29 patients were dead (case group) and 29 patients were cured (control group). Baseline data between the two groups were similar in terms of gender and mean of age. Bivariate analyses show that the predictors of mortality in children with pneumonia were: age < 1 year (OR3.11, 95% CI 1.06 to 9.08), malnutrition (OR 7.30,95% CI 1.62- to 21.03), age of the mother < 20 years (OR 2.21,95%CI 1.64 to 2.97),t achycardia (OR 6.075,95% CI 1.18 to 31.24), and anemia (OR 5 .83, 95% CI 1.88 to 18.10). Logistic regression analysis shows that tachycardia (OR 6.04, 95% CI 1.01 to 36.17) and anemia (OR 4.41,95% CI 1.25 to 15.51) were predictor of mortality in children 'With pneumonia.Conclusions Tachycardia and anemia play as independent mortality predictors of pneumonia in children.

Cough is the most common symptom of the several respiratory diseases containing diagnostic information. It is the best suitable candidate to develop a simplified screening technique for the management of respiratory diseases in timely manner, both in developing and developed countries, particularly in remote areas where medical facilities are limited. However, major issue hindering the development is the non-availability of reliable technique to automatically identify cough events. Medical practitioners still rely on manual counting, which is laborious and time consuming. In this paper we propose a novel method, based on the neural network to automatically identify cough segments, discarding other sounds such a speech, ambient noise etc. We achieved the accuracy of 98% in classifying 13395 segments into two classes, 'cough' and 'other sounds', with the sensitivity of 93.44% and specificity of 94.52%. Our preliminary results indicate that method can develop into a real-time cough identification technique in continuous cough monitoring systems.