PROJECT OVERVIEW
Introduction: The Need for Smarter Research Tools
Can AI Chatbots Improve Pharmacy Research?
The rise of Generative AI (Gen AI) has revolutionized industries, including education and research.
Pharmacy students rely on credible, well-referenced information—but AI chatbots often lack certain things
This research, conducted at Thomas Jefferson University, investigates how AI chatbots can support pharmacy research, identifying their strengths, limitations, and areas for improvement.
My Role: UX Researcher
Designed and executed primary and secondary research.
Conducted user interviews (12 participants + 1 stakeholder).
Analyzed pain points & developed data-driven recommendations.
Team :
Krishna Patel
Tanuja bodas
Vishal Thakkar
Timeline :
January 2024 - May 2024
Research Objectives
How do pharmacy students currently use AI chatbots for research?
What are the key challenges they face?
How can we improve AI chatbots to enhance research efficiency?
RESEARCH PLAN
Mapping out the Research
journey
SECONDARY RESEARCH
Digging out what’s already out there
Amazon Echo
1
Building a multi-channel Q&A chatbot at Saint
Louis University using the open source Q n A
Bot
Sanofi bets on AI-powered decision making
By Brian Buntz | June 15, 2023
Relevance
The potential of AI in drug development, particularly
in strategies like Sanofi’s AI-powered pharma, is
becoming increasingly apparent. When these
complex models work, they expedite the drug
discovery process, accelerate time-to-market, and
unlock new therapeutic opportunities hidden within
vast seas of data.
Pfizer
2
Pfizer Is Using AI to Discover Breakthrough
Medicines
April 25, 2022
Relevance
Instead of doing experiments in a physical lab
setting, researchers can now use cloud-based
supercomputing with AI machine learning models
to test a manageable fraction of the millions of
compounds that might work as a new drug, said
Lidia Fonseca, Pfizer’s Chief Digital and Technology
Officer.Researchers can then focus on the
compounds with the highest chance of becoming
medicines and potentially reduce the time it takes
to bring breakthrough therapies to patients.
Atomwise
3
Atomwise Signs Strategic Multi-Target
Research Collaboration with Sanofi for AI-
Powered Drug Discovery
August 17, 2022
Relevance
The Atomwise approach shifts the mode of drug
discovery away from serendipitous discovery and
toward search based on structure, making the drug
discovery process more rational, effective, and
efficient. The AtomNet platform incorporates deep
learning for structure-based drug design, enabling
the rapid, AI-powered search of Atomwise’s
proprietary library of more than 3 trillion
synthesizable compounds.
See full secondary research report
PRIMARY RESEARCH
Understanding Challenges : Listening to Pharmacy students
Conducted in-depth interviews with 12 pharmacy students and 1 Stakeholder
Explored how AI chatbots are used for research and where they fall short.
Documented pain points, expectations, and user behaviors in Debriefs
Debriefs
RESULTS
Breaking down the findings of Interviews
PARTICIPANT 1 FINDINGS
STAKEHOLDER FINDINGS
See Affinity map for all particiants (13)
ANALYSIS
Identifying core issues
Persona
Meet Sia: The Pharmacy Student Who Needs Better AI
‘I just wish AI would tell me where the information is from so I could verify it!’
- P4
Journey map
Breaking Down the Problem: Why AI Chatbots Fall Short
Through our research, we uncovered four major pain points affecting pharmacy students using AI chatbots:
💬 Student Quote:
"I searched for hydrogel formulations, but AI gave vague and incomplete answers."
💬 Student Quote:
"The images AI generates are usually irrelevant and inaccurate."
Student Frustration:
"If AI chatbots could provide citations, I’d feel more confident using them."
Medical Student Concern:
"Incorrect medical information can be dangerous. Misinformation in pharmacy can have real consequences."
Through research and studies, a glaring issue has come to light:
Unreliability stands as the paramount challenge for pharmacy students when utilizing general AI chatbots for research purposes.
Root Cause Analysis
Key Insights from Interviews
KEY INSIGHT 1
KEY INSIGHT 2
KEY INSIGHT 3
KEY INSIGHT 4
Problem Statement
Pharmacy students encounter challenges using AI in research due to unreliable information lacking proper sources and citations, which undermines the credibility and trustworthiness of the data retrieved for their studies.
Needs and Expectations
How Might We Improve AI Chatbots for Pharmacy Research?
How might we enhance the accuracy of the chatbot data to ensure greater reliability in its responses?
RECOMMENDATIONS
The Solution: Enhancing AI for Academic Research
Solution 1: AI Training for Pharmacy Students & Faculty
Why is this Important
According to a Microsoft Work trend Survey, as of March 2023, They surveyed 31,000 people in 31 countries.
82%
of leaders say employees they
hire will need new skills to be
prepared for the growth of AI.
60%
of people say they don’t currently
have the right capabilities to get
their work done.
‘New skills for a New way of working’
Implementation Plan
Solution 2: Bridging Traditional methods with Advanced Technology
Develop an AI chatbot trained on trusted pharmacy databases.
Integrate it within university libraries for verified AI-assisted research.
Combine AI automation with human oversight to ensure accuracy.
Benefits and ROI’s
Machine learning process + Books
Possible Limitations
Conclusion
In conclusion, while AI chatbots offer significant benefits such as time- saving and ease of use in pharmacy education research, there is a critical need to improve their reliability in providing accurate responses. Addressing this challenge will maximize the potential of AI chatbots as valuable tools in advancing research and learning in the field.
Let’s Connect
Feel free to reach out for collaboration or just say Hello, I am always excited to meet people who love design and innovation as much as I do!
sayali.ux@gmail.com
