Novel Chandra Das
Novel Chandra Das has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Alamgir Hossain
Maternal and Child Health Division, International Centre for Diarrhoeal Disease Research, Dhaka, Bangladesh
2 shared publications - Daniel Diamond Reidpath
Institute for Global Health and Development (IGHD), Queen Margaret University, Edinburgh, EH21 6UU, UK
2 shared publications - Fatema Khatun
Health Systems and Population Studies Division, International Centre for Diarrhoeal Disease Research, Dhaka, Bangladesh
2 shared publications - Kazi Nazmus Saqeeb
Nutrition Research Division, International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b)
2 shared publications - Kyung Ryul Park
Korea Advanced Institute of Science and Technology (KAIST)
2 shared publications - Monjur Rahman
Maternal and Child Health Division, International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka, Bangladesh
2 shared publications
Latest Publications
- 20 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
TopotiCerv: Multimodal classification of cervical lesions using acetowhite colposcopic images and clinical findings
- 20 January 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 117
TopotiCerv: Multimodal classification of cervical lesions using acetowhite colposcopic images and clinical findings
- Open Access
- 30 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0335442
Predicting hypertension and identifying most important factors among married women in Bangladesh using machine learning approach
Introduction: Hypertension is a leading contributor to maternal and cardiometabolic morbidity in Bangladesh. We developed and interpreted machine-learning (ML) models to predict hypertension and rank associated factors among married women with the goal of informing targeted screening and policy in low-resource settings. Methods: We analyzed 4,253 married women from the nationally representative BDHS 2017–18 survey (hypertension prevalence: 23.1%). Twelve ML algorithms were trained under six class-balancing strategies with hyperparameters tuned via random search. Validation used a hold-out test set (80/20) and repeated stratified k-fold cross-validation; bootstrap confidence intervals were estimated for the selected model. Model performance was compared with parametric and non-parametric tests. To interpret results, SHAP was used to rank the top 20 predictors and visualize feature effects. Models quantify associations rather than causation. Results: The Extra Trees classifier with SMOTE+ENN achieved the best discrimination (F1 = 0.94; AUC-PR = 0.95; ROC-AUC = 0.95). Compared with the original imbalanced training, minority-class detection improved substantially (Extra Trees F1 increased from 0.08 to 0.94; recall from 0.04 to 0.95) while accuracy and ROC-AUC remained relatively stable across samplers. Statistical testing favored SMOTE+ENN for recall, F1, G-mean and AUC-PR. SHAP identified age, parity, recent births, contraceptive use, spousal education and BMI as key predictors. Younger age (<35 years) and normal/underweight status were protective, while parity ≥2–3, husbands’ age ≥ 40 years and overweight/obesity increased risk. Conclusions: An interpretable ensemble model built primarily on sociodemographic and behavioral variables supplemented by limited biometric markers (BMI, glucose) can accurately flag hypertensive risk among married women in Bangladesh. Findings support programmatic integration of risk scores into eRegistries, routine blood pressure checks in family planning and postpartum visits, husband-focused education/SMS interventions and prioritization of high-parity households in high-risk regions. External validation on BDHS-2022 is planned to assess generalizability.
- 30 October 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (10) , e0335442
Open AccessPredicting hypertension and identifying most important factors among married women in Bangladesh using machine learning approach
Introduction: Hypertension is a leading contributor to maternal and cardiometabolic morbidity in Bangladesh. We developed and interpreted machine-learning (ML) models to predict hypertension and rank associated factors among married women with the goal of informing targeted screening and policy in low-resource settings. Methods: We analyzed 4,253 married women from the nationally representative BDHS 2017–18 survey (hypertension prevalence: 23.1%). Twelve ML algorithms were trained under six class-balancing strategies with hyperparameters tuned via random search. Validation used a hold-out test set (80/20) and repeated stratified k-fold cross-validation; bootstrap confidence intervals were estimated for the selected model. Model performance was compared with parametric and non-parametric tests. To interpret results, SHAP was used to rank the top 20 predictors and visualize feature effects. Models quantify associations rather than causation. Results: The Extra Trees classifier with SMOTE+ENN achieved the best discrimination (F1 = 0.94; AUC-PR = 0.95; ROC-AUC = 0.95). Compared with the original imbalanced training, minority-class detection improved substantially (Extra Trees F1 increased from 0.08 to 0.94; recall from 0.04 to 0.95) while accuracy and ROC-AUC remained relatively stable across samplers. Statistical testing favored SMOTE+ENN for recall, F1, G-mean and AUC-PR. SHAP identified age, parity, recent births, contraceptive use, spousal education and BMI as key predictors. Younger age (<35 years) and normal/underweight status were protective, while parity ≥2–3, husbands’ age ≥ 40 years and overweight/obesity increased risk. Conclusions: An interpretable ensemble model built primarily on sociodemographic and behavioral variables supplemented by limited biometric markers (BMI, glucose) can accurately flag hypertensive risk among married women in Bangladesh. Findings support programmatic integration of risk scores into eRegistries, routine blood pressure checks in family planning and postpartum visits, husband-focused education/SMS interventions and prioritization of high-parity households in high-risk regions. External validation on BDHS-2022 is planned to assess generalizability.
- Open Access
- 23 December 2024
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 11 (1) , e46566
Users’ Perceived Service Quality of National Telemedicine Services During the COVID-19 Pandemic in Bangladesh: Cross-Sectional Study
Background: COVID-19 created an opportunity for using teleconsultation as an alternative way of accessing expert medical advice. Bangladesh has seen a 20-fold increase in the use of teleconsultation during the pandemic. Objective: The aim of our study was to assess the influence of service quality and user satisfaction on the intention to use teleconsultation in the future among users of national teleconsultation services during the pandemic. Methods: A cross-sectional survey was conducted in 2020 among users of the national teleconsultation service—Shastho Batayon for acute respiratory infection. A validated mobile health service quality model based on structural equation modeling and confirmatory factor analysis was used to analyze the data with SmartPLS (version 3.0). Results: Among the 2097 study participants, 1646 (78.5%) were male, 1416 (67.5%) were aged 18‐39 years, 1588 (75.7%) were urban residents, 1348 (64.2%) had more than 10 years of schooling, and 1657 (79%) were from middle-income households. From a consumer perspective, the quality of the service platform (β=.946), service interaction (β=.974), and outcome (β=.955) contributed to service quality. Service quality was positively associated with user satisfaction (β=.327; P<.001) and intention to use teleconsultation services (β=.102; P<.001). User satisfaction was positively associated with the intention to use teleconsultation services (β=.311; P<.001). Conclusions: The increase in the use of teleconsultation during the pandemic indicated that such services were potentially used for emergencies. However, the future use of teleconsultation will be dependent on the quality of service and user satisfaction. Our findings are relevant for low-income contexts where teleconsultation services are used to address gaps in service delivery.
- 23 December 2024
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 11 (1) , e46566
Open AccessUsers’ Perceived Service Quality of National Telemedicine Services During the COVID-19 Pandemic in Bangladesh: Cross-Sectional Study
Background: COVID-19 created an opportunity for using teleconsultation as an alternative way of accessing expert medical advice. Bangladesh has seen a 20-fold increase in the use of teleconsultation during the pandemic. Objective: The aim of our study was to assess the influence of service quality and user satisfaction on the intention to use teleconsultation in the future among users of national teleconsultation services during the pandemic. Methods: A cross-sectional survey was conducted in 2020 among users of the national teleconsultation service—Shastho Batayon for acute respiratory infection. A validated mobile health service quality model based on structural equation modeling and confirmatory factor analysis was used to analyze the data with SmartPLS (version 3.0). Results: Among the 2097 study participants, 1646 (78.5%) were male, 1416 (67.5%) were aged 18‐39 years, 1588 (75.7%) were urban residents, 1348 (64.2%) had more than 10 years of schooling, and 1657 (79%) were from middle-income households. From a consumer perspective, the quality of the service platform (β=.946), service interaction (β=.974), and outcome (β=.955) contributed to service quality. Service quality was positively associated with user satisfaction (β=.327; P<.001) and intention to use teleconsultation services (β=.102; P<.001). User satisfaction was positively associated with the intention to use teleconsultation services (β=.311; P<.001). Conclusions: The increase in the use of teleconsultation during the pandemic indicated that such services were potentially used for emergencies. However, the future use of teleconsultation will be dependent on the quality of service and user satisfaction. Our findings are relevant for low-income contexts where teleconsultation services are used to address gaps in service delivery.
- Open Access
- 13 August 2024
- Published by Springer Nature in BMC Public Health
- Vol. 24 (1) , 1-13
Understanding the socio-demographic and programmatic factors associated with adolescent motherhood and its association with child undernutrition in Bangladesh
Background: Worldwide, a significant number of girls become mothers during adolescence. In Bangladesh, adolescent childbirth is highly prevalent and has adverse effects on children’s health and undernutrition. We aimed to identify the relationship between the undernutrition of children and adolescent motherhood, the factors associated with adolescent mothers’ age at first birth, and to examine the programmatic factors and gaps influencing children’s undernutrition in Bangladesh. Methods: We analysed the ‘Bangladesh Demographic and Health Survey’ BDHS-17-18 data and desk review. To examine the factors associated with adolescent motherhood and its impact on child undernutrition, data from 7,643 mother-child pairs were selected. Child stunting, wasting, and underweight were measured according to the World Health Organisation (WHO) median growth guidelines based on z-scores − 2. Univariate, bivariate, simple, and multiple logistic regressions were used for analyse. We followed the systematic procedures for the literature review. Results: Approximately, 89% of adolescents aged ≤ 19 years were married and 71% of them gave their first childbirth. Children of adolescent mothers (≤ 19 years) were significantly 1.68 times more wasted (aOR: 1.68; 95% CI: 1.08 to 2.64), 1.37 times more underweight (aOR: 1.37; 95% CI: 1.01 to 1.86) and either form 1.32 times more stunting, wasting or underweight (aOR:1.32; 95% Cl: 1.05 to 1.66) compared to the children of adult mothers (> 19 years) after adjusting potential confounders. The factors associated with mothers’ first childbirth during adolescence were the age gap between husband and wife 5–10 years (aOR: 1.81; 95% Cl: 1.57–2.10) and age gap > 10 years (aOR: 2.41; 95% Cl: 1.96–2.97) compared with the age group < 5 years, and husbands’ education (aOR: 1.29; 95% Cl: 1.04–1.61) compared with the uneducated husbands. In the literature review, we found potential gaps in focusing on the Adolescent Sexual and Reproductive Health (ASRH) program in Bangladesh, from thirty-two programmes only half of them focused on adolescents aged 10–19 years, and eleven programmes focused only on girls. Conclusion: Children of adolescent mothers are at risk of wasting, underweight, and any form of undernutrition. For effective policies and interventions in Bangladesh, it is important to emphasise delaying adolescent pregnancy and prioritising child undernutrition.
- 13 August 2024
- Published by Springer Nature in BMC Public Health
- Vol. 24 (1) , 1-13
Open AccessUnderstanding the socio-demographic and programmatic factors associated with adolescent motherhood and its association with child undernutrition in Bangladesh
Background: Worldwide, a significant number of girls become mothers during adolescence. In Bangladesh, adolescent childbirth is highly prevalent and has adverse effects on children’s health and undernutrition. We aimed to identify the relationship between the undernutrition of children and adolescent motherhood, the factors associated with adolescent mothers’ age at first birth, and to examine the programmatic factors and gaps influencing children’s undernutrition in Bangladesh. Methods: We analysed the ‘Bangladesh Demographic and Health Survey’ BDHS-17-18 data and desk review. To examine the factors associated with adolescent motherhood and its impact on child undernutrition, data from 7,643 mother-child pairs were selected. Child stunting, wasting, and underweight were measured according to the World Health Organisation (WHO) median growth guidelines based on z-scores − 2. Univariate, bivariate, simple, and multiple logistic regressions were used for analyse. We followed the systematic procedures for the literature review. Results: Approximately, 89% of adolescents aged ≤ 19 years were married and 71% of them gave their first childbirth. Children of adolescent mothers (≤ 19 years) were significantly 1.68 times more wasted (aOR: 1.68; 95% CI: 1.08 to 2.64), 1.37 times more underweight (aOR: 1.37; 95% CI: 1.01 to 1.86) and either form 1.32 times more stunting, wasting or underweight (aOR:1.32; 95% Cl: 1.05 to 1.66) compared to the children of adult mothers (> 19 years) after adjusting potential confounders. The factors associated with mothers’ first childbirth during adolescence were the age gap between husband and wife 5–10 years (aOR: 1.81; 95% Cl: 1.57–2.10) and age gap > 10 years (aOR: 2.41; 95% Cl: 1.96–2.97) compared with the age group < 5 years, and husbands’ education (aOR: 1.29; 95% Cl: 1.04–1.61) compared with the uneducated husbands. In the literature review, we found potential gaps in focusing on the Adolescent Sexual and Reproductive Health (ASRH) program in Bangladesh, from thirty-two programmes only half of them focused on adolescents aged 10–19 years, and eleven programmes focused only on girls. Conclusion: Children of adolescent mothers are at risk of wasting, underweight, and any form of undernutrition. For effective policies and interventions in Bangladesh, it is important to emphasise delaying adolescent pregnancy and prioritising child undernutrition.
- Open Access
- 25 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
User’s perceived service quality of national telemedicine services during COVID-19 pandemic in Bangladesh: Cross-sectional study (Preprint)
BACKGROUND The COVID-19 pandemic was a burden for our health system, and created opportunities for using teleconsultation as an alternative way of accessing expert medical advice. In Bangladesh, the use of tele consultation increased about 20-fold during the pandemic. OBJECTIVE This study aimed to assess the influence of service quality and user satisfaction on the intention to continue to use teleconsultation services among users of national teleconsultation services during the pandemic in Bangladesh. METHODS A cross-sectional survey was conducted in 2020 among users of national teleconsultation service - Shastho Batayon who availed the service for acute respiratory infection. A validated mHealth Service Quality model based on structural equation modelling (SEM) and Confirmatory Factor Analysis was used to analyse the data with SmartPLS 3.0. RESULTS Among the 2097 study participants, the majority were male (78%), aged 18-39 years (68%), residents of urban areas (76%), had more than 10 years of schooling (64%), and were from middle income households (79%). From consumer perspective the quality of service platform (β=.946), service interaction (β=.974) and outcome (β=.955) contributed to service quality. Service quality was positively associated with user satisfaction (β=0.327, P<.001) and intention to use teleconsultation services (β= 0.102, P<.001). User satisfaction was positively associated with intention to use teleconsultation services (β= 0.311, P<.001). CONCLUSIONS Our study findings showed that maintenance of the service quality is crucial for the user satisfaction and continuance of use of teleconsultation services; and that user satisfaction increased the continuance of use of teleconsultation services. Our findings are relevant for low income context where teleconsultation services are trying to address the gap in service delivery. CLINICALTRIAL
- 25 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessUser’s perceived service quality of national telemedicine services during COVID-19 pandemic in Bangladesh: Cross-sectional study (Preprint)
BACKGROUND The COVID-19 pandemic was a burden for our health system, and created opportunities for using teleconsultation as an alternative way of accessing expert medical advice. In Bangladesh, the use of tele consultation increased about 20-fold during the pandemic. OBJECTIVE This study aimed to assess the influence of service quality and user satisfaction on the intention to continue to use teleconsultation services among users of national teleconsultation services during the pandemic in Bangladesh. METHODS A cross-sectional survey was conducted in 2020 among users of national teleconsultation service - Shastho Batayon who availed the service for acute respiratory infection. A validated mHealth Service Quality model based on structural equation modelling (SEM) and Confirmatory Factor Analysis was used to analyse the data with SmartPLS 3.0. RESULTS Among the 2097 study participants, the majority were male (78%), aged 18-39 years (68%), residents of urban areas (76%), had more than 10 years of schooling (64%), and were from middle income households (79%). From consumer perspective the quality of service platform (β=.946), service interaction (β=.974) and outcome (β=.955) contributed to service quality. Service quality was positively associated with user satisfaction (β=0.327, P<.001) and intention to use teleconsultation services (β= 0.102, P<.001). User satisfaction was positively associated with intention to use teleconsultation services (β= 0.311, P<.001). CONCLUSIONS Our study findings showed that maintenance of the service quality is crucial for the user satisfaction and continuance of use of teleconsultation services; and that user satisfaction increased the continuance of use of teleconsultation services. Our findings are relevant for low income context where teleconsultation services are trying to address the gap in service delivery. CLINICALTRIAL