About
Shayan is a serial entrepreneur with a passion for leveraging technology and design for…
Services
Articles by Shayan
Contributions
-
You're launching a new product. How do you blend innovative design with market research data for success?
Irate quickly and being agile has its limitations and can’t be applied to all new products and services. How someone can iterate building an aircraft, design a city or a one-piece small but very complex device? While Design Thinking is useful for many cases it has been overused and overrated in the context of innovation.
-
What do you do if you're feeling stuck in your entrepreneurial journey and need inspiration?
iCorp program by NSF also expects participants to interview same number of prospect clients before working on the MVP. It automatically adopts a Design Thinking approach to understand the user and develop empathy for them.
-
How can you effectively delegate tasks on an AI project?
The difference between AI projects and regular software delivery is the need to constantly take feedback and validate the results. None of the existing tools such as Trello, Jira or Asana are designed to reflect such process. They are based on the paradigm of do it once, release and go to the next iteration. Defining and delegating task for the data team requires a different process and tool than feature development.
Activity
-
As an entrepreneur, I want to see physicians start using our innovation immediately. However, as a patient, while I want to benefit from the latest…
As an entrepreneur, I want to see physicians start using our innovation immediately. However, as a patient, while I want to benefit from the latest…
Posted by Shayan Mashatian
-
Discover how #genAI revolutionizes radiology by improving image quality, identifying patterns, and summarizing reports. This innovation saves…
Discover how #genAI revolutionizes radiology by improving image quality, identifying patterns, and summarizing reports. This innovation saves…
Liked by Shayan Mashatian
-
A few months ago, I realized that while seeing a weed store on the corner of my street feels strange to me, it seems completely normal to younger…
A few months ago, I realized that while seeing a weed store on the corner of my street feels strange to me, it seems completely normal to younger…
Shared by Shayan Mashatian
Experience
Education
-
Ryerson University
-
Activities and Societies: Ted Rogers School of Management
As part of my PhD student training and preparation program, I took research methods courses and PhD seminars and wrote a thesis applying Design Research methodology and data science (AI) to design an artifact to assess the privacy risks of using mobile phones. The artifact visualizes these risks and presents recommendations to the user to mitigate them. The artifact, in the form of an app, was used to gather empirical data and was subsequently acquired by a security company.
-
-
-
-
-
-
Activities and Societies: Cultural Studies Office
Licenses & Certifications
Volunteer Experience
-
Global Advisory Board Member - SHE Center
Dana-Farber Cancer Institute
- Present 5 years 8 months
Health
The unique Science Health Education (SHE) Center at Dana-Farber Cancer Institute empowers the health care community in the MENA to establish best practices in public health and medicine – stabilizing and strengthening the fabric of conflict-torn societies through health.
-
Resident BwB Volunteer
Grameen Foundation
- Present 14 years 9 months
Poverty Alleviation
Grameen Foundation harnesses the power of digital data to self-help tools for self-sufficiency and deliver them through local Community Agent networks.
-
Global Expert Network Member
WeWork
- Present 5 years 4 months
Education
I am a member of WeWorks Lab Global Expert network, mentoring and advising startups that work out of WeWork Labs. You can meet me in person in Bay area or online from anywhere.
Publications
-
How Generative AI is Transforming Patient Education and Engagement
AI Heathcare Symposium
I spoke at the AI Symposium by the VA on the latest advancements and use cases of AI in healthcare.
-
Building Trustworthy Generative Artificial Intelligence for Diabetes Care and Limb Preservation: A Medical Knowledge Extraction Case
Sage Journals
Abstract
Background:
Large language models (LLMs) offer significant potential in medical information extraction but carry risks of generating incorrect information. This study aims to develop and validate a retriever-augmented generation (RAG) model that provides accurate medical knowledge about diabetes and diabetic foot care to laypersons with an eighth-grade literacy level. Improving health literacy through patient education is paramount to addressing the problem of limb loss in the…Abstract
Background:
Large language models (LLMs) offer significant potential in medical information extraction but carry risks of generating incorrect information. This study aims to develop and validate a retriever-augmented generation (RAG) model that provides accurate medical knowledge about diabetes and diabetic foot care to laypersons with an eighth-grade literacy level. Improving health literacy through patient education is paramount to addressing the problem of limb loss in the diabetic population. In addition to affecting patient well-being through improved outcomes, improved physician well-being is an important outcome of a self-management model for patient health education.
Methods:
We used an RAG architecture and built a question-and-answer artificial intelligence (AI) model to extract knowledge in response to questions pertaining to diabetes and diabetic foot care. We utilized GPT-4 by OpenAI, with Pinecone as a vector database. The NIH National Standards for Diabetes Self-Management Education served as the basis for our knowledge base. The model’s outputs were validated through expert review against established guidelines and literature. Fifty-eight keywords were used to select 295 articles and the model was tested against 175 questions across topics.
Results:
The study demonstrated that with appropriate content volume and few-shot learning prompts, the RAG model achieved 98% accuracy, confirming its capability to offer user-friendly and comprehensible medical information.
Conclusion:
The RAG model represents a promising tool for delivering reliable medical knowledge to the public which can be used for self-education and self-management for diabetes, highlighting the importance of content validation and innovative prompt engineering in AI applications.Other authorsSee publication -
Speaker: How Generative AI is Transforming Healthcare and Clinical Informatics
C2SHIP
Speaking engagement at the think tank weekly forum by C2SHIP, the Center to Stream Care in Place.
-
Speaker: Preparing for the IoT Age with Apps and Intelligent Devices to improve Healthcare
11th Annual Mobile Healthcare Summit, Toronto, Canada
-
Speaker: Are Tablets Future of Education?
mEducation Alliance Symposium, Washington D.C.
-
Speaker: Protecting User Privacy on Mobile
International Privacy Day Seminar, Ryerson University
-
Speaker: Mobile Technology for Sustainability and Scalability of Micro-Finance Projects
International Telecommunication Unit (ITU) Conference, Geneva, Switzerland
-
Speaker: Mobile Cloud Computing
Mobile Monday, Cape Town University, South Africa
-
Speaker: Systemic Innovation for Mobile
National Conference of Engineers Without Borders, Ottawa
Patents
-
Context-based, Dynamic, Multi-Parameters Computer and Mobile Risk and Vulnerability Assessment and Vulnerability Remediation and Mitigation Methods
US .
Other inventors
Courses
-
Driving business towards the Sustainable Development Goals
SEWX8GKHXPNG
Projects
-
Data Mining and Knowledge Discovery - Adjunct Professor
-
A course for the students and professionals across industries on Data Mining & Knowledge Discovery Algorithms and their applications in solving real world problems
-
VC Lab, Cohort 4
-
VC Lab is a FREE virtual program that helps new managers to launch accelerators, pre-seed, seed or Series A venture capital firms globally. The goal is to help you complete your first closing in one year or less by providing a supportive community, tactical advice and resources through approximately 25 hours per week of structured work. https://fi.co/vc
-
Hoboken, N.J, Smart City
-
A smart city solution for Hoboken to enables assisted technology urban design and management
-
Virtual Antractica
-
A complex system modeling for data optimization
-
Community Knowledge Worker
-
A mobile solution to fight poverty by applying mobile technology for social innovation
Recommendations received
2 people have recommended Shayan
Join now to viewMore activity by Shayan
-
Apple has positioned itself as a privacy advocate. One of the most important features it could add to iOS is the ability for users to turn off the…
Apple has positioned itself as a privacy advocate. One of the most important features it could add to iOS is the ability for users to turn off the…
Posted by Shayan Mashatian
-
Deeply honoured to receive the Alberta Immigrant Impact Award in the Career and Academics Contribution category! Thursday’s event was special. So…
Deeply honoured to receive the Alberta Immigrant Impact Award in the Career and Academics Contribution category! Thursday’s event was special. So…
Liked by Shayan Mashatian
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More