HawkAI Smart Solutions

About the Team

We are a collective of Toronto-based software engineers and AI specialists completing our postgraduate specialization at Humber Polytechnic. Our team represents a fusion of diverse industry backgrounds—ranging from Financial, Software-as-a-Service Platforms to Healthcare Tech Engineers, unified by a shared focus on Artificial Intelligence and Machine Learning. Formed through our Capstone Sponsorship, we leverage high-performance CI/CD pipelines, iterative model improvements, automated model verification, and robust data analytics to transform complex & technical datasets into actionable predictive insights.
We don’t just build predictive models; we engineer informative solutions.

Core Capabilities

Predictive Analytics: Developing high-accuracy binary classification models tailored for complex datasets.
MLOps & CI/CD Integration: Implementing automated pipelines that handle everything from data ingestion to model packaging.
Automated Model Verification: Ensuring reliability through generated performance snapshots, confusion matrices, and JSON-based validation files.
Data Visualization: Transforming complex model outputs into human-readable insights using high-fidelity charting.

Our Work

Vitagent - The FHIR-Native Deterioration Detection Engine

Vitagent transitions patient monitoring from reactive alerts to proactive forecasting leveraging XGBoost's gradient-boosting algorithm. By analyzing trends in vital signs, Vitagent assesses health risks independently of underlying conditions, providing clinicians with actionable, data-driven foresight outside of the traditional black-box operations of most predictive models.

How it Works:

Trend-Based Analysis: Emulates EHR workflows by assessing risks based on changes between medical records over a rolling time window.

Two-Layer Intelligence: A 2-layered system designed to "Predict and Suggest," identifying Low-Risk or High-Risk states as data density increases.

Explainable AI (XAI): Every suggestion is backed by a SHAP explanation, detailing the specific vital signs that influenced the model’s assessment.