Perceptions about Telemedicine among Populations with Chronic Diseases amid COVID-19: Data from a Cross-Sectional Survey.

Chronic diseases, including non-communicable diseases (NCDs), have arisen as a severe threat to health and socio-economic growth. Telemedicine can provide both the highest level of patient satisfaction and the lowest risk of infection during a pandemic. The factors associated with its usage and patient adherence are not visible in Bangladesh's resource-constrained settings. Therefore, this study aimed to identify perceptions about telemedicine among populations with chronic diseases amid the COVID-19 pandemic. A closed-ended self-reported questionnaire was created, and the questionnaire was written, reviewed, and finalized by a public health investigator, a psychiatrist, and an epidemiologist. The data for this study were collected from individuals using simple random sampling and snowball sampling techniques. Ethics approval was granted, and written/verbal consent was taken before interviews. Most of the participants showed a positive attitude towards telemedicine. People aged 35-54 years old and a higher level of education were less frequently associated with willingness to receive telemedicine services for current chronic disease (WRTCCD) than their counterparts. People living in urban areas and lower-income participants were more strongly associated with WRTCCD. Additionally, people who did not lose their earnings due to the pandemic were less strongly associated with WRTCCD. However, the main strength of this research is that it is a broad exploration of patient interest in several general forms of telehealth. In Bangladesh, there are many opportunities for telemedicine to be integrated into the existing healthcare system, if appropriate training and education are provided for healthcare professionals.

An online cursive handwritten medical words recognition system for busy doctors in developing countries for ensuring efficient healthcare service delivery.

Doctors in developing countries are too busy to write digital prescriptions. Ninety-seven percent of Bangladeshi doctors write handwritten prescriptions, the majority of which lack legibility. Prescriptions are harder to read as they contain multiple languages. This paper proposes a machine learning approach to recognize doctors' handwriting to create digital prescriptions. A 'Handwritten Medical Term Corpus' dataset is developed containing 17,431 samples of 480 medical terms. In order to improve the recognition efficiency, this paper introduces a data augmentation technique to widen the variety and increase the sample size. A sequence of line data is extracted from the augmented images of 1,591,100 samples and fed to a Bidirectional Long Short-Term Memory (LSTM) network. Data augmentation includes pattern Rotating, Shifting, and Stretching (RSS). Eight different combinations are applied to evaluate the strength of the proposed method. The result shows 93.0% average accuracy (max: 94.5%, min: 92.1%) using Bidirectional LSTM and RSS data augmentation. This accuracy is 19.6% higher than the recognition result with no data expansion. The proposed handwritten recognition technology can be installed in a smartpen for busy doctors which will recognize the writings and digitize them in real-time. It is expected that the smartpen will contribute to reduce medical errors, save medical costs and ensure healthy living in developing countries.

Risk Factors and Outcomes of Hospital Acquired Pneumonia in Young Bangladeshi Children.

Hospital acquired pneumonia (HAP) is common and often associated with high mortality in children aged five or less. We sought to evaluate the risk factors and outcome of HAP in such children. We compared demographic, clinical, and laboratory characteristics in children <5 years using a case control design during the period of August 2013 and December 2017, where children with HAP were constituted as cases (n = 281) and twice as many randomly selected children without HAP were constituted as controls (n = 562). HAP was defined as a child developing a new episode of pneumonia both clinically and radiologically after at least 48 h of hospitalization. A total of 4101 children were treated during the study period. The mortality was significantly higher among the cases than the controls (8% vs. 4%, p = 0.014). In multivariate logistic regression analysis, after adjusting for potential confounders, it was found that persistent diarrhea (95% CI = 1.32-5.79; p = 0.007), severe acute malnutrition (95% CI = 1.46-3.27; p < 0.001), bacteremia (95% CI = 1.16-3.49; p = 0.013), and prolonged hospitalization of >5 days (95% CI = 3.01-8.02; p < 0.001) were identified as independent risk factors for HAP. Early identification of these risk factors and their prompt management may help to reduce HAP-related fatal consequences, especially in resource limited settings.