RESUMO
Acoustic signal analysis has been employed in various medical devices. However, studies involving cough sound analysis to screen the potential pulmonary tuberculosis (PTB) suspects are very few. The main objective of this cross-sectional validation study was to develop and validate the Swaasa AI platform to screen and prioritize at risk patients for PTB based on the signature cough sound as well as symptomatic information provided by the subjects. The voluntary cough sound data was collected at Andhra Medical College-India. An Algorithm based on multimodal convolutional neural network architecture and feedforward artificial neural network (tabular features) was built and validated on a total of 567 subjects, comprising 278 positive and 289 negative PTB cases. The output from these two models was combined to detect the likely presence (positive cases) of PTB. In the clinical validation phase, the AI-model was found to be 86.82% accurate in detecting the likely presence of PTB with 90.36% sensitivity and 84.67% specificity. The pilot testing of model was conducted at a peripheral health care centre, RHC Simhachalam-India on 65 presumptive PTB cases. Out of which, 15 subjects truly turned out to be PTB positive with a positive predictive value of 75%. The validation results obtained from the model are quite encouraging. This platform has the potential to fulfil the unmet need of a cost-effective PTB screening method. It works remotely, presents instantaneous results, and does not require a highly trained operator. Therefore, it could be implemented in various inaccessible, resource-poor parts of the world.
Assuntos
Mycobacterium tuberculosis , Tuberculose Pulmonar , Humanos , Estudos Transversais , Tosse/diagnóstico , Escarro , Tuberculose Pulmonar/diagnóstico , Inteligência ArtificialRESUMO
Background: Hypertension in women of reproductive age group is of special concern because of the vulnerability of women to pregnancy-induced hypertension apart from socio-cultural vulnerability. Aim: The objective of the study was to identify the predictors for hypertension among Indian women and to develop a risk score which would provide an opportunity for early detection and appropriate action. Material and Methods: This study was based on the data collected in National Family Health Survey in 2015-2016. Women in India of 15-49 years were the study population. Data were analysed using SPSS v17. Logistic regression analysis was carried and expressed as odds ratio with 95% confidence intervals to identify predictors of hypertension. The risk score for hypertension was developed after shrinkage of variables and by using regression coefficients obtained by standard Logistic Regression Model. Results: Among 6,87,230 women between 15 and 49 years, 77,788 (11.3%) were hypertensive. The study results revealed that there was an increasing trend in the prevalence of hypertension (26.5%) with increasing age, and with increasing weight (23.4%). Urban areas (12.3% vs 10.9%), alcoholics (19.2%) and various forms of tobacco users (14.8%) had more prevalence of hypertension. Conclusion: Age, residing in urban area, consuming tobacco products, consumption of alcohol, non-vegetarian diet and overweight, were found to be the significant predictor variables, and were used to develop the Risk Prediction score using logistic regression model.
RESUMO
BACKGROUND: In curriculum reforms under Competency-Based Medical Education (CBME) introduced by the National Medical Commission, medical students are recognized as one of the stake holders. The well-designed multiple-choice questions (MCQs) help students in assessment as well as promote deep learning. The objective of this study is to assess the perceptions of the Indian medical students towards the examination patterns in their undergraduate curriculum with particular reference to MCQs. MATERIALS AND METHODS: An observational cross-sectional study was conducted among the medical colleges in India. A total of 7875 students took part in the study. The study instrument was a validated pretested self-administered questionnaire. The study was conducted as an online survey using the Google Forms platform. Inclusion criteria were students from all professional years as well as interns and those who were willing to participate in the study. RESULTS: For the question of initiation of MCQs as a tool for the assessment, many of the students (46%) expressed that it should start from the 1st MBBS itself. The majority of the students (85%) felt that MCQ oriented preparation will be helpful for MBBS professional (theory and practical) examinations. Most of the students (90.9%) preferred that the MCQs should be concept and case scenario based. To the question of whether the current system of the university theory examinations of essays and short notes be replaced in total with MCQs so that they are more prepared for NEXT and USMLE examination, 65.5% responded with an answer of yes. CONCLUSION: The findings of this study provide input to the regulatory authorities and other stakeholders responsible for designing and implementing the medical curriculum.
RESUMO
Background: The benefits of breastfeeding for the health and wellbeing of the mother and babies are well documented. A recent trial has shown that early initiation of breastfeeding could reduce neonatal mortality, which would contribute to the achievement of the Millennium development goals. The positive effects of breastfeeding on the new-born’s health can be attributed to the components of breast milk, as well as the contact between mother and baby.Methods: This is a hospital based, cross sectional study conducted in the Department of Pediatrics and Department of Obstetrics and Gynaecology, at a tertiary care hospital in North Coastal Andhra Pradesh. Study period was one year between March 2018 to February 2019. 310 healthy term new-born babies of singleton pregnancy were included.Results: The prevalence of initiation of breast breastfeeding within one hour in this study is 48.7% (151 neonates). Hindu religion, literacy, urban residence, vaginal delivery, male child, breast feeding advice during antenatal period, birth spacing <2 years, not giving prelacteal feeds, absence of breast-feeding problems and maternal illness were found to have a significant association with initiation of breast feeding within 1 hour after delivery (p value <0.05).Conclusions: Innovative strategies like provision of breastfeeding counsellors in the hospital setup; constant counselling to mothers and their immediate relatives who take care of baby and mothers can increase early initiation of breast feeding.