Implications of Big Data Analytics, AI, Machine Learning, and Deep Learning in the Health Care System of Bangladesh: Scoping Review.

BACKGROUND: The rapid advancement of digital technologies, particularly in big data analytics (BDA), artificial intelligence (AI), machine learning (ML), and deep learning (DL), is reshaping the global health care system, including in Bangladesh. The increased adoption of these technologies in health care delivery within Bangladesh has sparked their integration into health care and public health research, resulting in a noticeable surge in related studies. However, a critical gap exists, as there is a lack of comprehensive evidence regarding the research landscape; regulatory challenges; use cases; and the application and adoption of BDA, AI, ML, and DL in the health care system of Bangladesh. This gap impedes the attainment of optimal results. As Bangladesh is a leading implementer of digital technologies, bridging this gap is urgent for the effective use of these advancing technologies. OBJECTIVE: This scoping review aims to collate (1) the existing research in Bangladesh's health care system, using the aforementioned technologies and synthesizing their findings, and (2) the limitations faced by researchers in integrating the aforementioned technologies into health care research. METHODS: MEDLINE (via PubMed), IEEE Xplore, Scopus, and Embase databases were searched to identify published research articles between January 1, 2000, and September 10, 2023, meeting the following inclusion criteria: (1) any study using any of the BDA, AI, ML, and DL technologies and health care and public health datasets for predicting health issues and forecasting any kind of outbreak; (2) studies primarily focusing on health care and public health issues in Bangladesh; and (3) original research articles published in peer-reviewed journals and conference proceedings written in English. RESULTS: With the initial search, we identified 1653 studies. Following the inclusion and exclusion criteria and full-text review, 4.66% (77/1653) of the articles were finally included in this review. There was a substantial increase in studies over the last 5 years (2017-2023). Among the 77 studies, the majority (n=65, 84%) used ML models. A smaller proportion of studies incorporated AI (4/77, 5%), DL (7/77, 9%), and BDA (1/77, 1%) technologies. Among the reviewed articles, 52% (40/77) relied on primary data, while the remaining 48% (37/77) used secondary data. The primary research areas of focus were infectious diseases (15/77, 19%), noncommunicable diseases (23/77, 30%), child health (11/77, 14%), and mental health (9/77, 12%). CONCLUSIONS: This scoping review highlights remarkable progress in leveraging BDA, AI, ML, and DL within Bangladesh's health care system. The observed surge in studies over the last 5 years underscores the increasing significance of AI and related technologies in health care research. Notably, most (65/77, 84%) studies focused on ML models, unveiling opportunities for advancements in predictive modeling. This review encapsulates the current state of technological integration and propels us into a promising era for the future of digital Bangladesh.

Pivotal relationship between heavy metal, PM2.5 exposures and tuberculosis in Bangladeshi children: protocol paper of a case-control study.

INTRODUCTION: Air pollution is a global issue that poses a significant threat to public health. Children, due to their developing physiology, are particularly susceptible to the inhalation of environmental pollutants. Exposure can trigger immune modulation and organ damage, increasing susceptibility to respiratory diseases. Therefore, we aim to examine the association between heavy metal and particulate matter exposure with tuberculosis in children. METHODS AND ANALYSIS: As a case-control study, we will include children diagnosed with pulmonary tuberculosis (n=60) and matched healthy controls (n=80) recruited from the same communities in Dhaka, Bangladesh. Exposure data for both cases and controls will be collected by a trained field team conducting home visits. They will administer an exposure questionnaire, measure child anthropometry, collect blood and household dust samples and instal 48-hour air quality monitors. The blood samples will be analysed by inductively coupled plasma mass spectrometry for serum heavy metal concentrations (lead, cadmium, arsenic, mercury and chromium), as a representative marker of exposure, and the presence of inflammatory biomarkers. Descriptive and inferential statistics, including independent samples t-tests, analysis of variance and conditional regression analysis, will be used to quantify heavy metal and particulate matter exposure status in tuberculosis cases compared with healthy controls, while accounting for potential confounders. Dust samples and air quality results will be analysed to understand household sources of heavy metal and particulate matter exposure. To test the study hypothesis, there is a positive association between exposure and tuberculosis diseases, we will also measure the accumulated effect of simultaneous exposures using Bayesian statistical modelling. ETHICS AND DISSEMINATION: This study has been approved by International Centre for Diarrhoeal Disease Research, Bangladesh's Institutional Review Board (PR-22030). The study findings will be disseminated at conferences and published in peer-reviewed journals.

Factors influencing delivery-related complications and their consequences in hard-to-reach areas of Bangladesh.

BACKGROUND AND OBJECTIVES: Bangladesh's high maternal mortality ratio is exacerbated by delivery-related complications, particularly in hard-to-reach (HtR) areas with limited healthcare access. Despite this, few studies have explored delivery-related complications and factors contributing to these complications among the disadvantaged population. This study aimed to investigate the factors contributing to delivery-related complications and their consequences among the mothers residing in the HtR areas of Bangladesh. METHODS: Data were collected using a cross-sectional study design from 13 HtR sub-districts of Bangladesh between September 2019 and October 2019. Data from 1,290 recently delivered mothers were analysed. RESULTS: Around 32% (95% CI: 29.7-34.8) of the mothers reported at least one delivery-related complication. Prolonged labour pain (21%) was the highest reported complication during the delivery, followed by obstructive labour (20%), fever (14%), severe headache (14%). Mothers with higher education, a higher number of antenatal care (ANC) visits, complications during ANC, employed, and first-time mothers had higher odds of reporting delivery-related complications. More than one-half (51%) of these mothers had normal vaginal delivery. Nearly one-fifth (20%) of mothers who reported delivery-related complications were delivered by unskilled health workers at homes. On the other hand, about one-fifth (19%) of the mothers without any complications during delivery had a caesarean delivery. Nine out of ten of these caesarean deliveries were done at the private facilities. CONCLUSION: Delivery-related complications are significantly related to a woman's reproductive history and other background characteristics. Unnecessary caesarean delivery is prominent at private facilities.

Community-based integrated intervention for skilled maternal health care utilization in riverine remote areas, Bangladesh.

INTRODUCTION: Despite the decrease in maternal mortality ratio, many women in Bangladesh are still at high-risk of death due to pregnancy-related morbidities. Increasing the rate of skilled maternal healthcare service utilization is effective to reduce maternal mortality rate. This paper examines the intervention effect of an integrated community-based maternal healthcare project implemented by a non-government organization, Friendship, aiming to provide maternal health services to women living in the remote riverine regions of Bangladesh. METHODS: We examined the skilled maternal healthcare service utilization before and after project implementation of the mothers with birth experience of 0-6 months from the intervention (N = 1,304) and comparison areas (N = 1,304). A difference-in-differences logistic model measured the effect of the intervention. RESULTS: After the intervention, mothers were three times more likely to receive ≥ 4 ANC visits from skilled providers (AOR: 2.9; 95 % CI: 2.1-4.2), 1.5 times more likely to have skilled birth attendants during deliveries (AOR: 1.5; 95 % CI: 1.1-2.1) and 1.5 times more likely to seek at least one PNC within 42 days after delivery (AOR: 1.5; 95 % CI: 1.1-2.2) as compared to the comparison group. CONCLUSION: The intervention showed positive effect on improving the ANC coverage, skilled delivery, and PNC among the mothers residing the remote riverine areas. Therefore, it opens up the opportunity for adaptation of such integrated community and facility-based interventions by other LMICs.

Trends and inequity in improved sanitation facility utilisation in Bangladesh: Evidence from Bangladesh Demographic and Health Surveys.

Improved sanitation is indispensable to human health. However, lack of access to improved sanitation remains one of the most daunting public health challenges of the twenty-first century in Bangladesh. The aim of the study was to describe the trends in access to improved sanitation facilities following the inequity gap among households in different socioeconomic groups in Bangladesh. Data from the Bangladesh Demographic and Health Survey (BDHS) 2007, 2011, 2014, and 2017-18 were extracted for this study. Inequity in access to improved sanitation was calculated using rich-poor ratio and concentration index to determine the changes in inequity across the time period. In Bangladesh, the proportion of households with access to improved sanitation increased steadily from 25.4% to 45.4% between 2007 and 2014, but slightly decreased to 44.0% in 2017-18. Age, educational status, marital status of household head, household wealth index, household size, place of residence, division, and survey year were significantly associated with the utilisation of improved sanitation. There is a pro-rich situation, which means that utilisation of improved sanitation was more concentrated among the rich across all survey years (Concentration Index ranges: 0.40 to 0.27). The government and other relevant stakeholders should take initiatives considering inequity among different socioeconomic groups to ensure the use of improved sanitation facilities for all, hence achieving universal health coverage.

Managing Cancer Pain, Monitoring for Cancer Recurrence, and Mitigating Risk of Opioid Use Disorders: A Team-Based, Interdisciplinary Approach to Cancer Survivorship.

Background: Palliative care (PC) teams increasingly care for patients with cancer into survivorship. Cancer survivorship transcends distinctions between acute, chronic, malignant, and nonmalignant pain. Partnering with oncologists, PC teams manage pain that persists after disease-directed treatment, evaluate changing symptoms as possible signs of cancer recurrence, taper opioids and mitigate risk of opioid misuse, and manage comorbid opioid use disorder (OUD). While interdisciplinary guidelines exist for pain management in survivorship, there is a need to develop a conceptual model that fully translates the biopsychosocial framework of PC into survivorship pain management. Objective: This review frames a model for pain management in cancer survivorship that balances analgesia with the imperative to minimize risk of OUD, recognizes signs of disease recurrence, and provides whole-person care. Methods: Comprehensive narrative review of the literature. Results: Little guidance exists for co-management of pain, psychological distress, and opioid misuse in survivorship. We identified themes for whole-person pain management in survivorship: use of opioids and co-analgesic medications to prevent recurrent pain from residual tissue damage following cancer treatment, opioid tapering to the lowest effective dose, utilization of nonpharmacologic psychological interventions shown to reduce pain, screening for and management of OUD in partnership with addiction medicine specialists, maintaining vigilance for disease recurrence, and engaging in shared medical decision making. Conclusions: The management of pain in cancer survivorship is complex and requires interdisciplinary care that balances analgesia with the imperative to reduce long-term inappropriate opioid use and manage OUD, while maintaining therapeutic presence with patients in the spirit of PC.