Home on phiz

Custom Vaccine Record Submission Portal: Enhancing Client Experience and Data Processes

Fri, 04 Sep 2026 00:00:00 +0000

Equity in AI for Public Health: Part 2 – From Clusters to Careful Personas

Wed, 19 Aug 2026 00:00:00 +0000

Plain-language takeaway: Clustering can help public health teams see how needs, strengths, risks, and supports overlap. Equity changes how the data is prepared, how patterns are tested, and whether a pattern should become a persona.

Part 1 explained why equity in AI must guide public health work. It also introduced the four actions in NIST AI RMF 1.0: govern, map, measure, and manage.

The second article illustrates what these commitments look like in practice. It follows the WHY Survey Personas project from survey preparation to human review. The examples given below are drawn from the project’s workflow, but no sensitive findings, subgroup differences, cluster sizes, or draft persona labels are disclosed.

Equity in AI for Public Health: Part 1 – Why Fairness Must Come First

Wed, 05 Aug 2026 00:00:00 +0000

Plain-language takeaway: AI can assist public health teams in discovering patterns within complex information. Equity makes sure these patterns are developed, understood, and used in ways that are fair, safe, and helpful.

Public health teams often need to understand how different aspects of people’s lives are interconnected. Mental health, family support, school experiences, access to services, discrimination, and other factors rarely occur in isolation. However, these connections can be difficult to identify when relevant information is dispersed across numerous survey questions.

Artificial intelligence, often referred to as AI, can be used to solve those problems. This involves computer-based techniques that can detect patterns, organize information, or make predictions. In the field of public health, such tools enable teams to examine large datasets more efficiently.

Yet the fact that a pattern has been found does not mean that it has been understood. A computer cannot judge whether the pattern shows an unmet need, an unfair social issue, a decision made during the design of the survey, or even a data error. Similarly, it cannot evaluate whether presenting the pattern will be beneficial or harmful to a community.

This is why Equity in AI needs to guide the work from the start.

At Wellington-Dufferin-Guelph Public Health (WDGPH), the WHY Survey Personas project is a real-world example. The project searches for patterns in the Wellbeing and Health of Youth (WHY) Survey to help staff see how youth needs, strengths, risks, and supports overlap.

The survey is a joint effort involving WDGPH, the Upper Grand District School Board, and the Wellington Catholic District School Board; for the 2025–26 survey cycle, WDGPH also collaborated with Conseil scolaire catholique MonAvenir, a French-language Catholic school board. It gathers information from students in Grades 4 to 12, parents or guardians, and school staff to help with school and community planning. The student portion of the survey lasts approximately 30 minutes and is available in separate versions for Junior (Grades 4 to 6) and Intermediate/Senior (Grades 7 to 12) students. The survey includes topics such as mental health, relationships, school climate, physical activity, substance use, and equity.

Year 1 of an AI Governance Program at a Medium-Sized Local Public Health Unit

Sun, 26 Jul 2026 00:00:00 +0000

AI governance has to work within the organization that actually exists. Wellington-Dufferin-Guelph Public Health (WDGPH) is a medium-sized local public health unit in Ontario, with approximately 200 staff serving about 350,000 people. Most of our staff work in public health nursing, inspection, health promotion, and other program areas.

We began formalizing governance while staff were already experimenting with AI and several projects were moving into production. Our first year focused on making governance workable in this environment: setting strategic direction before adding rules, extending processes the organization already trusted, and using an established framework while keeping our own values and obligations at the centre.

This article is adapted from a presentation delivered on July 21st in Montreal at the 2026 AI4PH Summer Institute.

ISPA Email Campaign: Automating Immunization Notice Sending

Tue, 21 Jul 2026 00:00:00 +0000

Making CCHS analysis faster and easier to repeat

Mon, 13 Jul 2026 00:00:00 +0000

Public health teams spend an appreciable amount of time responding to requests to analyze CCHS data. These requests often require complex code, and even small changes in scope can mean updating the analysis workflow. As a result, some opportunities to use CCHS data are missed. The work is time-intensive, and it often depends on a small number of experts who understand how to apply the required weighting and bootstrap techniques correctly.

At WDG Public Health, we are reimagining the CCHS analytics process by creating an automated way to analyze the data while maintaining the same technical accuracy. An automated approach would reduce the time required for routine requests and allow teams to reallocate that time to other priorities. The goal is to make the process easier to use, easier to share, and easier to improve through collaboration and an open approach to development.

ImmuKnow: Automating Immunization Notice Generation

Fri, 05 Jun 2026 00:00:00 +0000

CI/CD: Its Place in Public Health Software Teams

Mon, 04 May 2026 00:00:00 +0000

AI Scribes in Public Health: Reimagining Workflows Around Care

Tue, 28 Apr 2026 00:00:00 +0000

Introduction #

If you’ve worked in public health, you already know this feeling.

A single client interaction rarely stays in one place. Notes are written, then rewritten. Information is entered into one EMR (Electronic Medical Record) system, then entered again into another (e.g., iPHIS). Investigation forms, whether developed by Public Health Ontario (PHO) or by local public health units for specific diseases, must also be completed. What begins as a conversation can become a series of fragmented entries across platforms, pulling staff time and attention away from listening, care planning, and supporting people and communities.

AI scribes can help shift that attention back.

Data Lakehouses and Delta Lake: A Guide for BI Analysts

Tue, 21 Apr 2026 00:00:00 +0000

Designing Data Lakehouses for Public Health

Tue, 07 Apr 2026 00:00:00 +0000

VaxLink: streamlining vaccine workflows with barcodes

Wed, 18 Mar 2026 00:00:00 +0000

Delivering quality, attentive service in an immunization clinic requires seamless workflows, but documentation remains a persistent bottleneck. While every vaccine vial features a standardized barcode rich with product and expiry data, clinical systems often lack complete integration. Even with partial support like selecting a lot number from a predefined list, immunizers must still visually decode labels, manually transcribe complex alphanumeric strings, and verify expiration dates by hand, shifting their focus away from the client.

Manual transcription inevitably degrades data quality. A single transposed digit in a lot number necessitates downstream reconciliation, while an inaccurately recorded expiry date introduces genuine clinical risk. Across the thousands of weekly vaccination encounters happening Canada-wide, these small transcription tasks add up to lost time and more opportunities for error.

To mitigate these challenges, we built VaxLink, an lightweight browser extension that automates vaccine barcode capture directly into existing clinical workflows. VaxLink leverages the Public Health Agency of Canada’s National Vaccine Catalogue, for its comprehensive registry of vaccines and lot numbers, enabling VaxLink to verify and enrich scanned vaccine information with an authoritative open data source.

VaxLink: Vaccine Barcode Automation

Fri, 13 Mar 2026 00:00:00 +0000

Python GIS: Advantages and Integration

Fri, 06 Mar 2026 00:00:00 +0000

MLOps in Public Health: Workspaces, Pipelines, and Governance

Fri, 20 Feb 2026 00:00:00 +0000

Modern data science and ML work depends on consistent environments, controlled access patterns, and reproducible workflows. In public health, these needs underpin governance as much as they support productivity.

At Wellington-Dufferin-Guelph Public Health (WDGPH), we have found that the simplest way to address both delivery and risk is to standardize how tools are delivered into managed, isolated environments, and to route repeatable work through governed pipelines. This post focuses on those two foundations, developer environments and pipelines, within a larger MLOps program.

CCHS Tool

Fri, 06 Feb 2026 00:00:00 +0000

Explainable AI for Public Health: Client Linkage and Deduplication

Tue, 03 Feb 2026 00:00:00 +0000

Public health data is messy in very human ways. Families share phones and email addresses. Clinics rely on placeholder dates so work can keep moving. Organizations sometimes appear where people should. Any patient deduplication approach that ignores these realities will struggle to produce results teams can trust.

Probabilistic deduplication and linkage is a key public health AI use case that supports responsible stewardship of personal health information. Using machine learning, it estimates match likelihood across records that are often incomplete, transcription-heavy, and not consistently validated against authoritative sources. We treat it as governed, explainable decision support aligned with our responsibilities as a health information custodian (HIC), with equity considerations and routine human review.

Notification Automation: Enhancing Communication with Twilio

Mon, 26 Jan 2026 00:00:00 +0000

Power BI Public Publishing: Best Practices & Security Considerations

Mon, 19 Jan 2026 00:00:00 +0000

Power BI has become a foundational analytics platform for public health units, enabling teams to explore complex datasets, uncover trends, and communicate insights to a wide range of audiences. From disease surveillance dashboards to program performance monitoring, its ability to translate data into clear, interactive visuals has made it an indispensable tool for evidence-informed decision-making.

As public health organizations increasingly emphasize transparency and public reporting, the ability to share insights broadly can be both powerful and risky. Tools that make data easy to publish can also make it easy to share more than intended. Without careful governance and disciplined report design, well-intentioned public reporting can unintentionally expose sensitive or protected information.

This post outlines key best practices and security considerations for using Power BI’s public publishing capabilities responsibly, with a focus on ensuring that public-facing reports remain both informative and safe.

From Legacy Portals to Data Pipelines: Safe Water with Browser Automation

Mon, 12 Jan 2026 00:00:00 +0000

Public health work relies heavily on digital systems to support surveillance, reporting, and operations. In practice, this often means working within web-based portals accessed through a browser. Many of these systems were not designed with automation or modern data integration in mind. As a result, routine tasks can consume substantial staff time and, in some cases, make otherwise valuable workflows impractical.

Browser-based automation provides a pragmatic way to work within these constraints. Rather than replacing existing systems, it allows public health teams to interact with them programmatically, freeing capacity for analysis, decision-making, and community impact.

Complex Systems in Practice: Modernizing Public Health Data Flows

Tue, 06 Jan 2026 00:00:00 +0000

Complexity starts when causality breaks down.

— Nigel Goldenfeld¹

The first step in any innovation project is understanding where the friction lies. Where does the work slow down? Where do risks emerge? And who bears the burden of inefficient systems?

In public health, many of these pain points are embedded in our data flows. Manual processes, fragmented systems, and unclear ownership are common features of legacy infrastructure. While often invisible to those outside the system, these challenges directly affect our ability to deliver timely, effective, and equitable public health services.

Innovation in the open

Wed, 17 Dec 2025 00:00:00 +0000

Open-source is a way to build public health tooling that is portable, auditable, and easier to collaborate on. A commitment to open-source forces us to take best practices in our programming seriously, such as strong documentation and clear separation between code, sensitive data inputs, and system configurations. In the public sector, it allows us to maximize the value of public dollars and offer greater transparency into our processes.

Phiz: Designing the Future of Public Health - Together

Fri, 12 Dec 2025 00:00:00 +0000

Public health is powerful, but it deserves systems that match its purpose.

What if public health wasn’t defined by its constraints, but by its potential?

Across Ontario and beyond, public health teams do extraordinary work under extraordinary pressure. They manage complexity, navigate uncertainty, and protect communities using systems that weren’t built for the pace or demands of today’s world.

But what if that could change?

What if we chose to reimagine everything?

Phiz was created as a bold answer to that question.

Phiz is a public health innovation zone dedicated to weaving emerging data practices, human-centred design, modern technology, and collective creativity into the daily work of public health. We exist to help every community, large or small, experience the benefits of a stronger, smarter, more modernized public health system.

Not someday.

Not hypothetically.

But now.

STIX File Automated Validation & Remediation

Fri, 01 Mar 2024 00:00:00 +0000

ISPA Workflow — Suspension List Automation & List-Difference Reports

Sun, 25 Feb 2024 00:00:00 +0000

SMS Alerts for Vaccine Clinics

Tue, 20 Feb 2024 00:00:00 +0000

SMS Alerts for Safe Water

Thu, 15 Feb 2024 00:00:00 +0000

Data Lake Architecture Consultations

Sat, 10 Feb 2024 00:00:00 +0000

Named Entity Recognition for Redaction & Warning

Mon, 05 Feb 2024 00:00:00 +0000

Document AI Workflows

Thu, 01 Feb 2024 00:00:00 +0000

Probabilistic Client Linkage & Deduplication Consultations

Thu, 25 Jan 2024 00:00:00 +0000

Custom Immunization Notices

Sat, 20 Jan 2024 00:00:00 +0000

Safe Water Automation

Mon, 15 Jan 2024 00:00:00 +0000

Contact Us

Mon, 01 Jan 0001 00:00:00 +0000