AI for Public Health – AI Vision against Candy Threats
In recent years, the matter of public health safety concerning consumable goods has gained increasing prominence. The issue reached a critical point recently when more than 60 primary school students were hospitalized. The culprit? Candies infused with THC that were almost indistinguishable from regular candy. We couldn’t image the fear and uncertainty the children and their guardians experienced. This grave situation calls for a multidisciplinary approach, one where Artificial Intelligence (AI) plays a significant role, specifically multimodal AI models, working alongside public health officials and everyday Jamaicans.
What Are Multimodal AI Models?
A multimodal model is designed to understand, interpret, and generate insights based on multiple types of data, including but not limited to text and images. This capacity for varied data analysis makes it uniquely suited for complex tasks, such as differentiating harmless candies from harmful counterparts using just a photo.
Our Research
To address the issue of foods harmful to children disguised as ordinary candy, Section 9, a specialized research group in StarApple AI focusing on Social Good and Ethical AI, conducted an experiment using GPT-4V, a multimodal model. The study involved testing 24 popular candies brands, to date, across various scenarios, angles and backgrounds, aiming to discern which ones contained THC or could be harmful to children. This project was mobilized on October 4, 2023 and continues to test and generate useful real-world insights.
The model achieved an accuracy rate of 88%, remarkable! given the complexity of the problem and diversity of candy packaging. While human testers achieved a slightly higher accuracy of 92% on average. The model’s performance demonstrates the significant potential of AI-driven solutions in public health safety.
Expanding the Scope
The utilization of this multimodal model isn’t confined to identifying unsafe candies. It is inherently adaptable and can be further trained to analyze packaging designs for compliance with local regulations, generate safety recommendations, and more. As AI technologies continue to mature, their applicability in safeguarding public health can only be expected to grow.
This a Global Issue
It’s worth noting that incidents of THC poisoning due to misleading candies have been reported since at least 2019 in multiple countries, including the US, Canada, and the UK. The integration of AI models like the one used by Section 9 can serve as an invaluable tool in the toolbox of public health workers, citizens, and regulatory bodies, mitigating the risks associated with purchasing and consuming unsafe products.
AI and Public Welfare
We are at a critical juncture where technology and public health intersect. This study signifies a step in utilizing AI for real-world applications that can have immediate and long-lasting impact. With continuous advancements in scientific techniques, AI’s role in enhancing public safety is not just promising—it is inevitable.
A.I Researcher:
Adrian Dunkley
Forbes Technology Council
15+ years in AI Developer and Research
CEO, StarApple AI, Jamaica’s 1st AI company
- Share
-
-
-
Other articles
-
Is Artificial Intelligence the same as Machine Learning?
In the rapidly evolving world of technology, terms like Artificial Intelligence (AI) and Machine Learning (ML) are often used interchangeably. However, while they are closely related, they are not the same thing. In this blog post, we’ll dive into the intricacies of AI and ML, unravel their differences, and explore how they are shaping our […]
Enroll -
Caribbeans Can Win the World Cup with AI – The Island Blueprint for Global Football Glory
When people speak about the World Cup they often picture Europe or South America. Yet the Caribbean has entered a rare moment in football history. Curaçao has already qualified for 2026. Haiti is in. Jamaica and Suriname are still pushing through the playoffs. This is the first time in living memory that the region has […]
Enroll -
Hurricane Melissa vs AI
What AI Could Have Changed The satellite images told the story before most people wanted to believe it. On October 28, 2025, Hurricane Melissa made landfall near New Hope, Westmoreland, Jamaica, with sustained winds of 185 miles per hour and a central pressure of 892 millibars. It was one of the most powerful Atlantic hurricanes […]
Enroll -
AI and the Caribbean Climate
When Machines Learn Our Weather The fishermen leaving Castries harbor at 4 a.m. read weather in ways no app captures. They watch how the mountains hold mist, how the seabirds fly, how the water’s color shifts near the reef. Their fathers taught them, and their grandfathers before that, building prediction systems refined across generations. These […]
Enroll
