Accepted for/Published in: JMIR Formative Research

Date Submitted:

Open Peer Review Period: -

Date Accepted:

Date Submitted to PubMed:

closed for review but you can still tweet
  • Farjana Y
  • AI Chatbots for Healthcare in Bangladesh: Addressing Dengue Fever and Common Health Issues
  • JMIR Formative Research
  • DOI: 10.2196/11848
  • PMID: 30303485
  • PMCID: 6352016
Preprints Accepted Manuscript

AI Chatbots for Healthcare in Bangladesh: Addressing Dengue Fever and Common Health Issues

Abstract

background

Dengue fever is a recurrent and significant health concern in Bangladesh, often overwhelming healthcare resources during peak seasons. Limited access to timely medical assistance and high patient load create an urgent need for alternative solutions. Artificial Intelligence (AI) chatbots offer a promising intervention by providing immediate, accessible health advice, enabling early symptom assessment and potentially reducing strain on healthcare facilities.

objective

This study aims to develop and evaluate an AI-powered chatbot designed to assess the severity of dengue symptoms based on user demographic data. The chatbot’s goal is to deliver guidance tailored to individual risk levels, with a particular focus on cultural and linguistic adaptation for users in Bangladesh.

methods

Publicly available health datasets were used to train the chatbot’s underlying model, which primarily includes demographic information and dengue symptom data. Data preprocessing involved encoding categorical variables and handling missing values through forward-filling techniques. A Decision Tree Classifier was chosen for its interpretability and effectiveness in binary classification. The model’s features included age group, gender, and symptom severity levels. Model performance was evaluated using accuracy, precision, recall, and F1 score. Additionally, a user-friendly chatbot interface was developed to facilitate interaction.

results

The model achieved high accuracy in classifying severe and non-severe dengue cases, with an accuracy score of 1.00 on the test dataset. A confusion matrix demonstrated the model’s strong performance in distinguishing between the severity levels, while feature importance analysis revealed that gender and age group significantly contributed to accurate predictions. The chatbot interface provides instant symptom assessment, offering users health advice based on their severity classification and encouraging them to seek medical attention if symptoms suggest a severe case.

conclusions

This research demonstrates the utility of AI chatbots in providing health advice and symptom assessments for dengue fever. The high accuracy achieved by the Decision Tree model suggests a reliable method for classifying symptom severity [5] which is crucial in managing healthcare resources. Future development could focus on expanding the chatbot's scope to include other common diseases, integrating climate data for better prediction accuracy, and implementing multi-language support to cater to Bangladesh's linguistic diversity.

clinicalTrial

N/A

As per the author’s request the PDF is not available.
Copyright

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it’s website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.

Citation

Please cite as:

Farjana Y

AI Chatbots for Healthcare in Bangladesh: Addressing Dengue Fever and Common Health Issues

JMIR Formative Research

DOI: 10.2196/14886

URL: https://preprints.jmir.org/preprint/11848

PMID: 31789598

PMCID: 6352016

AI Chatbots for Healthcare in Bangladesh: Addressing Dengue Fever and Common Health Issues

Current Preprint Settings

(as selected by the authors)

  1. Allow access to the preprint PDF upon submission to:

    (a) Open peer-review purposes

    (b) Logged-in users only

    (c) Anybody, anytime

    (d) Nobody

  2. When the manuscript is accepted, display the accepted manuscript PDF to:

    (a) Logged-in users only

    (b) Anybody, anytime

    (c) Anybody, anytime, and the author has chosen to deposit the ahead-of-print metadata to PubMed

    (d) Nobody

  3. When a final paper is published in a JMIR journal, display the preprint as follows:

    (a) Allow download

    (b) Show abstract only

    (c) Do not display anything

  4. If the paper is rejected from JMIR journals, display the preprint to:

    (a) Logged-in users only

    (b) Anybody, anytime

    (c) Nobody