Back

The E-Patient Quality Improvement and Standardization (EQIS) Platform for Improving Maternal and Pediatric Clinical Care in Bangladesh: Study Protocol for a Prospective Open Cohort Study

Ahmed, S.; Khan, A. M.; Ibrahim, S. B.; Ahmad, F.; Hossain, M. M.; Tabassum, A.; Khan, S. A.; Ahmed, S.; Chowdhury, N. H.; Islam, M. S.; Kawser, C. A.; Shahidullah, M.; Begum, F.; Begum, F.; Dewan, F.; Johnson, S.; Ouenes, O.; Elias, M.; Baqui, A. H.; Peabody, J.

2026-01-08 medical education
10.64898/2026.01.07.26343582 medRxiv
Show abstract

IntroductionInappropriate healthcare practices are major contributors to poor outcomes of maternal and pediatric patients. Where resources are scarce, provider-level targeted interventions, such as implementation of standardized, evidence-based protocols and quality improvement initiatives are particularly needed to address these gaps in care. Simulation-based tools have been shown to have a promising effect on improving clinical care management. This study aims to evaluate the effectiveness of a simulation-based platform called E-Patient Quality Improvement and Standardization (EQIS) in improving maternal and pediatric health care in Bangladesh. Methods and analysisThe study employs a prospective, open-cohort design and will be conducted across five tertiary-level hospitals in Dhaka, Bangladesh. All physicians engaged in providing maternal or pediatric care will be recruited. The EQIS platform will facilitate the development of online simulated cases, aiming to enhance physician practice and patient outcomes through involvement and immediate personalized feedback. The development of cases will consist of several stages of review by expert clinicians, ensuring that the cases align with national and local practice guidelines. Each participant physician will work on three cases per round, completing one of six rounds every four months for two years. Data will be collected and analyzed after each round. Descriptive and inferential analysis will be done to assess trends in clinical performance and pinpoint areas for improvement. In addition, patient-level pre-and post-impact data will be collected. These data will evaluate the impact of the EQIS platform on physician performance, as measured by changes in patient satisfaction, treatment costs, referrals, and facility utilization. Ethics and disseminationThe study protocol was approved by the National Research Ethics Committee of the Bangladesh Medical Research Council (registration number: 59524062024). Dissemination of the study findings will be through meetings with stakeholders, conference presentations and publications in peer-reviewed journals. Strengths and limitations of this studyO_LIThis study will use simulated cases for the first time in Bangladesh to improve physicians standardization in diagnosing and treating maternal and pediatric patients. C_LIO_LIWe postulate that the EQIS platform will help physicians to improve and standardize their critical thinking and decision-making skills by presenting a variety of clinical scenarios. With this platform, physicians will improve their skills in diagnosing and treating various medical conditions, in accordance with national and international guidelines, without endangering patient safety. C_LIO_LIThis platform will provide an opportunity for physicians to receive prompt, serial feedback and self-reflection. This will help them learn from mistakes and possibly improve their clinical capability. C_LIO_LIThe study will be carried out in five tertiary-level hospitals in Dhaka city, Bangladesh, including one public hospital, one autonomous hospital, and three private hospitals. This approach might not represent the broader population or reflect healthcare practices in rural areas and lower-tier facilities across the country. C_LI

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.