Rahul Kodgule

Exposure to biomass smoke as a cause for airway disease in women and children.

Purpose of reviewAn estimated 3 billion people (about half the worlds population) burn biomass fuel (wood, crop residues, animal dung and coal) for cooking and heating purposes exposing a large population, especially women and children, to high levels of indoor air pollution. Biomass smoke comprises gaseous air pollutants as well as particulate matter air pollutants, which have significant harmful effects. Recent findingsExposure to biomass smoke is a major contributor to morbidity and mortality. Children, women and the elderly are most affected. Apart from poor lung growth seen in growing children, the risk of developing respiratory tract infections (both upper as well as lower) is greatly increased in children living in homes using biomass. Women who spend many hours cooking food in poorly ventilated homes develop chronic obstructive lung disease (COPD), asthma, respiratory tract infections, including tuberculosis and lung cancer. It has been argued that exposure to biomass fuel smoke is a bigger risk factor for COPD than tobacco smoking. SummaryPhysicians need to be aware about the harmful effects of biomass smoke exposure and ensure early diagnosis and appropriate management to reduce the disease burden. More research needs to be done to study health effects due to biomass smoke exposure better. Reducing the exposure to biomass smoke through proper home ventilation, home design and, if possible, change of biomass to cleaner fuels is strongly recommended in order to reduce biomass smoke-induced mortality and morbidity.

Application of semi-supervised deep learning to lung sound analysis

The analysis of lung sounds, collected through auscultation, is a fundamental component of pulmonary disease diagnostics for primary care and general patient monitoring for telemedicine. Despite advances in computation and algorithms, the goal of automated lung sound identification and classification has remained elusive. Over the past 40 years, published work in this field has demonstrated only limited success in identifying lung sounds, with most published studies using only a small numbers of patients (typically N<;20) and usually limited to a single type of lung sound. Larger research studies have also been impeded by the challenge of labeling large volumes of data, which is extremely labor-intensive. In this paper, we present the development of a semi-supervised deep learning algorithm for automatically classify lung sounds from a relatively large number of patients (N=284). Focusing on the two most common lung sounds, wheeze and crackle, we present results from 11,627 sound files recorded from 11 different auscultation locations on these 284 patients with pulmonary disease. 890 of these sound files were labeled to evaluate the model, which is significantly larger than previously published studies. Data was collected with a custom mobile phone application and a low-cost (US

Mobile stethoscope and signal processing algorithms for pulmonary screening and diagnostics

30) electronic stethoscope. On this data set, our algorithm achieves ROC curves with AUCs of 0.86 for wheeze and 0.74 for crackle. Most importantly, this study demonstrates how semi-supervised deep learning can be used with larger data sets without requiring extensive labeling of data.

Peak flow meter with a questionnaire and mini-spirometer to help detect asthma and COPD in real-life clinical practice: a cross-sectional study

Pulmonary diseases represent a large disease burden in terms of morbidity and mortality worldwide. For many reasons, including household air pollution and a shortage of trained doctors, this burden is concentrated in the developing world. The standard diagnostic pathway for pulmonary diseases is prohibitively expensive in developing countries, so these diseases are often misdiagnosed or underdiagnosed. To assist doctors and health workers, there is a need to create tools that can automatically recognize specific lung sounds and provide diagnostic guidance. As a first step towards this long-term goal, we have created a low-cost stethoscope and smartphone application to record lung sounds. We discuss problems we encountered with the initial design and demonstrate an improved design that is currently being used in the field. We also demonstrate an algorithm capable of automatic detection of wheeze sounds. The automatic wheeze detection algorithm uses time-frequency analysis and the Short Time Fourier Transform to identify sections of wheezing in recorded lung sound files. Unlike most published sound classification studies, we trained and tested our algorithms using sound data collected from 38 actual patients at a pulmonary clinic in Pune, India. Despite variability in the quality of the data, our algorithm demonstrated an accuracy of 86% for successfully detecting the presence of wheeze in a sound file. This mobile platform and detection algorithm demonstrates an important step in creating an automated platform for the diagnosis of pulmonary diseases in a real-world setting.

A mobile platform for automated screening of asthma and chronic obstructive pulmonary disease

Peak flow meter with questionnaire and mini-spirometer are considered as alternative tools to spirometry for screening of asthma and chronic obstructive pulmonary disease. However, the accuracy of these tools together, in clinical settings for disease diagnosis, has not been studied. Two hundred consecutive patients with respiratory complaints answered a short symptom questionnaire and performed peak expiratory flow measurements, standard spirometry with Koko spirometer and mini-spirometry (COPD-6). Spirometry was repeated after bronchodilation. Physician made a final diagnosis of asthma, chronic obstructive pulmonary disease and others. One eighty nine patients (78 females) with age 51 ± 17 years with asthma (115), chronic obstructive pulmonary disease (33) and others (41) completed the study. “Breathlessness > 6months” and “cough > 6months” were important symptoms to detect obstructive airways disease. “Asymptomatic period > 2 weeks” had the best sensitivity (Sn) and specificity (Sp) to differentiate asthma and chronic obstructive pulmonary disease. A peak expiratory flow of < 80% predicted was the best cut-off to detect airflow limitation (Sn 90%, Sp 50%). Respiratory symptoms with PEF < 80% predicted, had Sn 84 and Sp 93% to detect OAD. COPD-6 device under-estimated FEV1 by 13 mL (95% CI: −212, 185). At a cut-off of 0.75, the FEV1/FEV6 had the best accuracy (Sn 80%, Sp 86%) to detect airflow limitation. Peak flow meter with few symptom questions can be effectively used in clinical practice for objective detection of asthma and chronic obstructive pulmonary disease, in the absence of good quality spirometry. Mini-spirometers are useful in detection of obstructive airways diseases but FEV1 measured is inaccurate.Chronic lung diseases: Differentiating conditions in poorly-equipped settingsA simple questionnaire and peak flow meter measurements can help doctors differentiate between asthma and chronic lung disease. In clinical settings where access to specialist equipment and knowledge is limited, it can be challenging for doctors to tell the difference between asthma and chronic obstructive pulmonary disease (COPD). To determine a viable alternative method for differentiating between these diseases, Rahul Kodgule and colleagues at the Chest Research Foundation in Pune, India, trialed a simplified version of two existing symptom questionnaires, combined with peak flow meter measurements. They assessed 189 patients using this method, and found it aided diagnosis with high sensitivity and specificity. Breathlessness, cough and wheeze were the minimal symptoms required for COPD diagnosis, while the length of asymptomatic periods was most helpful in distinguishing asthma from COPD.

Use of spirometry among chest physicians and primary care physicians in India

Chronic Obstructive Pulmonary Disease (COPD) and asthma each represent a large proportion of the global disease burden; COPD is the third leading cause of death worldwide and asthma is one of the most prevalent chronic diseases, afflicting over 300 million people. Much of this burden is concentrated in the developing world, where patients lack access to physicians trained in the diagnosis of pulmonary disease. As a result, these patients experience high rates of underdiagnosis and misdiagnosis. To address this need, we present a mobile platform capable of screening for Asthma and COPD. Our solution is based on a mobile smart phone and consists of an electronic stethoscope, a peak flow meter application, and a patient questionnaire. This data is combined with a machine learning algorithm to identify patients with asthma and COPD. To test and validate the design, we collected data from 119 healthy and sick participants using our custom mobile application and ran the analysis on a PC computer. For comparison, all subjects were examined by an experienced pulmonologist using a full pulmonary testing laboratory. Employing a two-stage logistic regression model, our algorithms were first able to identify patients with either asthma or COPD from the general population, yielding an ROC curve with an AUC of 0.95. Then, after identifying these patients, our algorithm was able to distinguish between patients with asthma and patients with COPD, yielding an ROC curve with AUC of 0.97. This work represents an important milestone towards creating a self-contained mobile phone-based platform that can be used for screening and diagnosis of pulmonary disease in many parts of the world.

Applying Augmented Reality to Enable Automated and Low-Cost Data Capture from Medical Devices

Although spirometry is the gold-standard diagnostic test for obstructive airways diseases, it remains poorly utilised in clinical practice. We aimed to investigate the use of spirometry across India, the change in its usage over a period of time and to understand the reasons for its under-utilisation. Two nationwide surveys were conducted in the years 2005 and 2013, among four groups of doctors: chest physicians (CPs), general physicians (GenPs), general practitioners (GPs) and paediatricians (Ps). A total of 1,000 physicians from each of the four groups were randomly selected from our database in the years 2005 and 2013. These surveys were conducted in 52 cities and towns across 15 states in India. A questionnaire was administered to the physicians, which captured information about their demographic details, type of practice and use of spirometry. The overall response rates of the physicians in 2005 and 2013 were 42.8% and 54.9%, respectively. Spirometry was reported to be used by 55% CPs, 20% GenPs, 10% GPs and 5% Ps in 2005, and this increased by 30.9% among CPs (P value <0.01), 18% among GenPs (P value=0.01), 20% among GPs (P value: not significant) and 224% among Ps (P value <0.01). The reasons for not using spirometry varied between 2005 and 2013. In all, 32.2% of physicians were unaware of which predicted equation they were using. The use of spirometry in India is low, although it seems to have improved over the years. The reasons identified in this study for under-utilisation should be used to address initiatives to improve the use of spirometry in clinical practice.

Is exposure to biomass smoke really associated with COPD

As an alternative to building custom electronic devices that connect to mobile phones (via Bluetooth or USB), we present a new approach using Augmented Reality (AR) and machine vision to digitally recognize a biomedical device and capture readings automatically. In the context of developing countries, this approach enables easy integration with low-cost devices, without the need for designing any electronics or obtaining new FDA regulatory approval. As an example, we illustrate the use of AR with a peak flow meter, a device used in the diagnosis and treatment of respiratory disease. In our mobile application, the AR graphic overlay is used to provide feedback to patients and doctors by displaying personalized reference values. Comparing the automated readings from this device to manual readings, our mobile application had a mean error of 5.8 L/min and a correlation of 0.99. A small user study was also conducted in an India field clinic with three health staff (two nurses and a doctor). Following one minute of instruction, the automated readings from the participants had a mean error of 5.5 L/min and a correlation of 0.99 compared to manual readings, with a median task duration of 17.5 seconds. This small case study illustrates how AR can be used to capture medical device data on a mobile phone and help automate the data recording tasks performed by health workers in developing countries. This technology can also be used in developed countries, enabling patients to automatically record readings from similar devices at home using their smart phones.

A randomized, double-blind study comparing the efficacy and safety of a combination of formoterol and ciclesonide with ciclesonide alone in asthma subjects with moderate-to-severe airflow limitation

and incorporate the Creative Commons Attribution – Non Commercial (unported, v3.0) License (http://creativecommons.org/licenses/by-nc/3.0/). By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms (https://www.dovepress.com/terms.php). International Journal of COPD 2017:12 651–653 International Journal of COPD Dovepress

Association between sputum cytology and lung function in patients with asthma and COPD

Context: The combination of inhaled corticosteroids (ICS) and long-acting beta-agonists (LABA) is widely used in the treatment of moderate-to-severe asthma uncontrolled by ICS alone. Aims: To evaluate the efficacy and safety of a new ICS-LABA combination inhaler containing Formoterol (F) and Ciclesonide (C). Settings and Design: A double-blind, double-dummy, parallel group fashion, multi-centric study. Subjects and Methods: A total of 169 asthma patients received Ciclesonide 80 μg once daily during a 4-week run-in period, after which, they were randomized to receive either C (80 μg) or a combination of F (4.5 μg) and C (80 μg) (FC) both delivered through a hydro-fluro-alkane pressurized-metered-dose inhaler as 1 puff twice daily, for 6 weeks. Statistical Analysis Used: Inter-group differences were compared using t-test for independent samples at a significance level of 5%. Results: From baseline, the improvements in forced expiratory volume in 1 s at 1, 3, and 6 weeks was significantly higher in the FC group compared to Group C (110 ml vs. 40 ml, 140 ml vs. 20 ml, and 110 ml vs. 40 ml, respectively, all P < 0.05). From baseline, the improvements in mean morning peak expiratory flow at 1, 3, and 6 weeks was significantly higher in the FC group compared to Group C (17 L/min vs.−3 L/min, 22 L/min vs. 3 L/min, and 30 ml vs. 8 L/min respectively, all P < 0.05). The changes in symptom scores were similar in both the groups. The adverse events in the FC group were not significantly different from those in the C group. Conclusions: FC provides better improvement than C alone in terms of lung function and symptoms without increased risk of adverse events in asthma patients.