Fortis AI
Empowering hospital staff and management to ideate and solve problems with AI.
year
JULY -AUG 2024
Problem
Fortis Hospital faces challenges in efficiently analysing and utilising the abundance of patient data available, leading to suboptimal care delivery and treatment outcomes.
The brief was to design an AI-based solution that optimises data analysis, enhances clinical decision-making processes, and enables personalised healthcare delivery.
Solution
To design an AI-based solution as per brief, we adapted the design thinking process with IBM's framework for AI products. We ended up proposing an AI powered triage system, assisted diagnosis & decision support to address patient wait times, costs, staff stress and record management.
While this was based on our identified pain points in limited time, we thought, what if the hospital staff and management could brainstorm on their pain points using this process?
Thus we also built a chat based design thinking assistant for hospital's management and staff.
Here I am showing the design thinking assistant in brief. Detailed case study of the design process and other parts of solution available upon request.
The adapted design process for AI products
While standard design thinking processes take user's needs into account, for building AI products, we also need to take AI's needs (type of data, security & privacy issues etc) too. To cater this, IBM's AI framework is used as an additional evaluation criteria in the evaluation stage shown below.

The AI Design Assistant
This flowchart explains the working of the assistant:
- The chatbot takes inputs from the user like Hospital Name, Problems faced, Which idea to choose, etc.
- We have added prompts for the AI model (Llama 3.1 in this case) like healthcare sector problems, AI & design frameworks , etc.
- Finally it gives you outputs like breakdown of problem, ideas, idea evaluation etc
Working of the assistant

