Dr Jyoti Singh Honoured with Phoenix Award at Health AI Con 2026 for AI Innovations in Medical Research

Scientist Dr Jyoti Singh was honoured with the prestigious Phoenix Award at HealthAIcon 2026 for her contribution to AI-driven healthcare research and evidence-based medical innovation. The award was presented by Dr Abhijat Sheth, Chairperson, National Medical Commission (NMC) and President, NBEMS, along with Dr Anil Kohli, Former President of the Dental Council of India, and Dr Sanghamitra Pati, Additional Director General, ICMR, during the event held at Hotel Eros, New Delhi, on May 17, 2026.

Currently serving as a Medical Scientist at ICMR- NICHR, Dr Jyoti Singh works in the field of artificial intelligence, evidence synthesis, and healthcare research automation. With nearly 14 years of experience in medical research, her work focuses on reducing the time researchers spend on literature reviews, research gap identification, and evidence synthesis.

Dr Singh has developed two AI-powered platforms - EviFlow and EviXtract - designed to support systematic reviews and evidence-based healthcare research. EviFlow scans scientific literature from PubMed, identifies evidence gaps and inconsistencies, and generates structured research questions for future studies.

Her second innovation, EviXtract, is an AI-assisted data extraction platform that can process research papers, including scanned PDFs, and automatically extract quantitative and qualitative data into structured formats with confidence scoring and evidence tracking.

Systematic reviews are considered among the highest forms of scientific evidence in medicine, but they remain highly time-consuming and resource-intensive. Dr Singh’s work aims to make evidence synthesis faster, more transparent, and more accessible, particularly for researchers and institutions working in resource-limited settings.

A key aspect of her innovation is the “human-in-the-loop AI” approach, where artificial intelligence assists researchers without replacing scientific oversight or clinical judgment.

The Phoenix Award recognises transformative healthcare innovation, and Dr Singh’s work reflects the growing role of AI-assisted evidence-based medicine in India. In an exclusive conversation with Health Dialogues Managing Editor Deshbandhu Singh, Dr Singh spoke about AI-driven healthcare research, innovation challenges, and the future of evidence-based medicine in India. Excerpts:

Q: What was the biggest research challenge that inspired you to create EviFlow and EviXtract?

Ans: Whenever I searched for a new research topic, I spent months reviewing literature and trying to identify the research gap. I always wondered whether this process could be simplified and made more systematic.

During a workshop on systematic reviews, I realised that while there are systematic ways to to conduct ‘systematic reviews’review literature, there is no systematic approach to conduct literature review and generating truly relevant research questions. That thought inspired the development of EviFlow.

Similarly, while conducting systematic reviews, we often had to analyse nearly 300 papers manually for data extraction. It became an extremely time-consuming process, which motivated us to develop EviXtract to automate large parts of data extraction using AI.

Q: How much time can these AI tools realistically save during systematic reviews and evidence synthesis?

Ans: EviFlow can reduce months of literature review and research-gap identification work to a matter of minutes for a specific query.

Data extraction is one of the most time-consuming stages of systematic reviews. EviXtract can potentially reduce this process from 9–12 months to just a few weeks.

Q: Can you explain in simple words how EviFlow identifies research gaps and generates research questions?

Ans: EviFlow works like a scientific search engine. A query entered into the platform is converted into MeSH (Medical Subject Headings) terms and used to search PubMed systematically.

The platform then analyses published studies for gaps related to methodology, population groups, geography, quality of evidence, and conflicting findings. Based on this analysis, the system generates structured research questions using the PICO format.

Q: How is EviXtract different from existing AI tools available globally?

Ans: Many existing AI tools generate outputs that still require significant manual work and often lack transparency.

EviXtract generates validated multi-sheet Excel outputs with verbatim source citations, reasoning statements, and confidence scores. The system also flags doubtful outputs for manual verification, making the workflow more transparent and reliable.

Q: What safeguards have you built to ensure scientific reliability?

Ans: In EviFlow, search strategies are based directly on PubMed and MeSH terms, ensuring authentic references without hallucinations or false citations.

EviXtract also verifies its own outputs, corrects repairable errors, and flags low-confidence extractions for manual review. This allows researchers to maintain scientific accuracy and transparency.

Q: Why was it important to keep a “human-in-the-loop” approach instead of fully automated AI research?

Ans: The “human-in-the-loop” model ensures that AI-generated outputs remain transparent, verifiable, and auditable.

EviFlow includes multiple stages where researchers can intervene before automated tasks proceed, while EviXtract flags doubtful extractions for human review. The idea is to use AI as an assistant, not as a replacement for scientific judgment.

Q: How useful could these platforms be during future pandemics or public health emergencies?

Ans: These platforms can significantly reduce the time required for literature review, research planning, and evidence generation during outbreaks.

Q: Many researchers worry that AI may reduce scientific rigour. How do you respond?

Ans: AI is a powerful tool that can transform the way research is conducted and analysed. However, scientific rigour depends on how responsibly the technology is used.

Q: What has been the most difficult part of building these innovations?

Ans: One of the biggest challenges has been finding people willing to work beyond traditional research boundaries and collaborate across multiple disciplines.

Another major challenge has been securing funding, since most research support systems still focus primarily on conventional core research areas.

Q: What future upgrades do you want to add to EviFlow and EviXtract?

Ans: The goal is to integrate multiple research databases and build an end-to-end AI-assisted research ecosystem that supports researchers from literature review to data analysis and publishing.

The idea is not to reduce scientific rigour, but to free researchers from repetitive manual tasks so they can focus more on scientific thinking and decision-making.