Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 8 min ago
Peer-reviewedCC BYFrontiers in digital health

A mini-review of medical question answering for Bangla: the methodological landscape and cross-lingual perspectives.

  • Jannatul Somiya Mahmud1
  • Khadija Akter Ratri2
  • Md Hamid Hosen3
  • Md Kishor Morol4
  • Liew Tze Hui5
  • Dip Nandi4,6
  • Abdullah Al Jubair4,6
  • Mashiour Rahman4,6
6 affiliations
  1. 1Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh.
  2. 2Department of Computer Science and Engineering, University of Asia Pacific, Dhaka, Bangladesh.
  3. 3Department of Computer Science and Engineering, East Delta University, Chittagong, Bangladesh.
  4. 4ELITE Research Lab, LLC, Queens, New York, NY, United States.
  5. 5Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia.
  6. 6Department of CSE, American International University-Bangladesh, Dhaka, Bangladesh.
Read full textPDFDOICite

Abstract

Large language models (LLMs) have advanced medical question answering (QA) significantly, yet low-resource languages such as Bangla remain critically underserved. This review examines the current landscape of LLM-based medical QA with a primary focus on Bangla, analyzing 15 representative studies (2022-2026), including English and multilingual works reviewed to contextualize findings for Bangla. We examine methodological approaches, datasets, and evaluation frameworks across diverse paradigms, including transformer architectures, retrieval-augmented generation (RAG), prompt engineering, and parameter-efficient fine-tuning, to identify pathways toward reliable and linguistically inclusive medical AI. The findings reveal a persistent performance gap driven by large-scale domain-specific pretraining and standardized benchmarks in English. Persistent challenges include dataset scarcity, heavy reliance on translated corpora, inconsistent evaluation practices, and a lack of clinician-validated benchmarks. This review identifies these gaps and outlines a structured research roadmap emphasizing native-language corpus development, multimodal data integration, standardized benchmarking, and bias auditing as essential steps toward building reliable and linguistically inclusive medical QA systems for Bangla healthcare.

Related

  1. A Curated Dataset for Question Answering on Laboratory Test Reference Ranges and Interpretation
    Balu Bhasuran, Qiao Jin, Angelique Deville +4
    Scientific DataPeer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthPMC
  2. Evidence-based clinical question answering using retrieval-augmented generation (RAG) and open-source large language models
    Ayesha Qasim, Jesus Jaime Moreno Escobar, Christian E. Maldonado-Sifuentes +3
    Scientific ReportsPeer-reviewedCC BY 4.0Full textEpidemiology & public healthCrossref
  3. Do question type and topic affect the performance of large language models in answering periodontology questions? A comparative study
    Hanife Merva Parlak
    BMC Medical EducationPeer-reviewedCC BYFull textEpidemiology & public healthDOAJ
  4. OncoAgentic-RAG: An evidence-grounded multi-agent hybrid retrieval-augmented system for patient-centric clinical oncology question answering
    S Jayasrilakshmi, Ansuman Mahapatra, Ankit Kujur +3
    Digital HealthPeer-reviewedCC BYFull textEpidemiology & public healthDOAJ
  5. BanglaDiaHallu: Hallucinations of large language models and the effect of guideline-grounded retrieval-augmented generation in Bangla diabetes question answering
    K. Nahid, M. Anam, M. T. H. Saon +3
    medRxivPreprintCC BYFull textEpidemiology & public healthmedRxiv

Cite

BibTeXRIS
BibTeX
@article{mahmud2026minireview,
  title = {{A mini-review of medical question answering for Bangla: the methodological landscape and cross-lingual perspectives.}},
  author = {Jannatul Somiya Mahmud and Khadija Akter Ratri and Md Hamid Hosen and Md Kishor Morol and Liew Tze Hui and Dip Nandi and Abdullah Al Jubair and Mashiour Rahman},
  journal = {Frontiers in digital health},
  year = {2026},
  month = oct,
  doi = {10.3389/fdgth.2026.1856734},
  url = {https://europepmc.org/article/MED/42953604},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - A mini-review of medical question answering for Bangla: the methodological landscape and cross-lingual perspectives.
AU  - Jannatul Somiya Mahmud
AU  - Khadija Akter Ratri
AU  - Md Hamid Hosen
AU  - Md Kishor Morol
AU  - Liew Tze Hui
AU  - Dip Nandi
AU  - Abdullah Al Jubair
AU  - Mashiour Rahman
PY  - 2026
DA  - 2026/10/14
JO  - Frontiers in digital health
DO  - 10.3389/fdgth.2026.1856734
UR  - https://europepmc.org/article/MED/42953604
AB  - Large language models (LLMs) have advanced medical question answering (QA) significantly, yet low-resource languages such as Bangla remain critically underserved. This review examines the current landscape of LLM-based medical QA with a primary focus on Bangla, analyzing 15 representative studies (2022-2026), including English and multilingual works reviewed to contextualize findings for Bangla. We examine methodological approaches, datasets, and evaluation frameworks across diverse paradigms, including transformer architectures, retrieval-augmented generation (RAG), prompt engineering, and parameter-efficient fine-tuning, to identify pathways toward reliable and linguistically inclusive medical AI. The findings reveal a persistent performance gap driven by large-scale domain-specific pretraining and standardized benchmarks in English. Persistent challenges include dataset scarcity, heavy reliance on translated corpora, inconsistent evaluation practices, and a lack of clinician-validated benchmarks. This review identifies these gaps and outlines a structured research roadmap emphasizing native-language corpus development, multimodal data integration, standardized benchmarking, and bias auditing as essential steps toward building reliable and linguistically inclusive medical QA systems for Bangla healthcare.
SN  - 2673-253X
ER  -