BreastSignal: Rethinking Early Breast Cancer Detection in Low-Resource Settings

[embed]If you would like to watch a demo of the app, be sure to check out my video!

The Moment That Comes Too Late

A woman in a rural village notices a small change in her breast. It doesn’t hurt. It doesn’t stop her from working, caring for her family, or going about her day. So she ignores it.

Days pass. Weeks pass. Months pass.

The change becomes more noticeable. Sometimes there is swelling. Sometimes the skin looks different. But the nearest clinic is hours away. The cost of travel alone is high, not to mention the hefty cost of care. There are other priorities, and so, life continues.

By the time she finally decides to seek medical attention, the diagnosis is no longer early-stage. It is advanced. The window for simple, effective treatment has closed.

This is not an isolated story. It is the reality for a majority of breast cancer patients in rural sub-Saharan Africa.

What’s Broken in the Current System

The problem is not that the early warning signs don’t exist. It’s because the system is not designed to catch them beforehand.

First, there is limited access to healthcare infrastructure. Many communities are located far from hospitals or diagnostic centers. Even when patients are willing to seek care, the journey itself becomes a barrier.

Second, there is financial pressure. Early detection is often seen as an optional cost, while late-stage symptoms force action to occur. This delay is not irrational; it is a response to economic reality.

Third, there is a severe gap in awareness and trust. Symptoms that could signal early cancer are often misunderstood, dismissed, or feared. Without clear guidance, people wait.

All of this leads to a system where diagnosis is reactive, not proactive. We end up waiting for the disease to become severe instead of catching it early, where there is a higher chance of stopping it.

The Missed Opportunity: Frontline Healthcare Workers

Despite these challenges, there is one part of the system that is consistently present: frontline healthcare workers.

Community health workers and local nurses are often the first point of contact. They visit homes, run local clinics, and interact with patients long before hospitals become involved.

But here’s the issue.

They are not always equipped with structured tools to assess early cancer risks. Without a clear framework, even trained workers may miss subtle patterns or underestimate symptoms.

This is where a simple shift can make a massive difference.

Not more hospitals. Not more expensive machines.

But better decision support at the first point of contact.

Introducing BreastSignal

BreastSignal is a mobile-based triage decision-support tool designed to help frontline healthcare workers identify potential early breast cancer cases in low-resource settings.

It does not diagnose cancer.

Instead, it answers a more immediate and practical question:

Who needs to be referred right now, and who can wait?

By structuring how symptoms are collected and interpreted, BreastSignal transforms scattered observations into clear, actionable decisions.

How the App Works: Step by Step

Step 1: Opening the App

A healthcare worker opens BreastSignal on a basic smartphone. The interface is simple, clean, and mobile-friendly.

At the top of the screen, they select a language: English, French, Swahili, or Hausa. This ensures the tool is usable across different regions and communities.

A short message appears:

“This tool provides triage guidance and does not diagnose breast cancer.”

They tap “Start Screening”.

Welcome Screen

Step 2: Patient Information

The app begins with a few quick questions to establish context about the patient, making the results as personal as possible.

Age group. Family history. Previous breast condition. Duration of symptoms.

These are not invasive questions. They are signals. Each is essential to help build a clearer picture of baseline risk.

The goal is speed and clarity. As a result, this entire section should take less than a minute.

Patient information inquiry questions

Step 3: Symptom Screening

Next, the app moves into symptom-based questions.

• Does the patient have a new breast lump or lump in the armpit area?
• Has there been nipple inversion?
• Is there skin dimpling or puckering?
• Are symptoms persistent for more than four weeks?
• Any spontaneous nipple discharge?
• Is there persistent redness or rashes?
• Has there been any change in breast shape and size?
• Any pain that is not linked to the patient’s menstrual cycle?

Each question is answered with a simple toggle for yes or no.

No medical jargon. No ambiguity. Just clear, structured input.

Symptom questions asked. Below this is the “Evaluate Risk” button

Step 4: Risk Evaluation

Once the questions are complete, the app processes the information using a rule-based system.

Certain symptoms, like a palpable lump or nipple inversion, immediately trigger a high-risk classification.

Others, like persistent pain or unilateral changes, contribute to a moderate risk.

If there are no concerning patterns present, the case is classified as low risk.

Step 5: Triage Output

The result is displayed clearly on the screen. A colour-coded card appears.

Green for low risk. Yellow for moderate. Red for high.

Each category includes a specific recommendation.

• Low risk means monitor and reassess if symptoms persist.
• Moderate risk means schedule a clinical examination within a short timeframe.
• High risk means urgent referral to a diagnostic center.

This is the most important moment. Instead of uncertainty, the healthcare worker now has direction.

Example Triage Result

Step 6: Referral Map

For moderate and high-risk cases, the app offers the next step. A button appears: “Find Nearby Referral Clinics.”

The app opens a map interface showing nearby healthcare facilities. Clinics, hospitals, diagnostic centers. Each location includes basic information: name, distance, and type of facility.

This solves a critical problem. It’s not enough to say “refer the patient.” The worker needs to know where exactly to send them.

Why This Approach Works

BreastSignal doesn’t try to solve everything. It focuses on a single leverage point: early identification at the frontline.

Standardizing how symptoms are evaluated, it reduces missed signals. Simplifying decision-making, it increases confidence among healthcare workers. By integrating referral guidance, it bridges the gap between detection and action.

This is not about replacing doctors. It’s about strengthening the system before a doctor is ever involved.

Where AI Fits In

Right now, the system is rule-based. Transparent. Explainable. Reliable. But there is room to grow. In future versions, AI could enhance the tool by analyzing visual data. For example, smartphone images could be used to detect skin changes or asymmetry that may not be obvious to the human eye.

Over time, aggregated screening data could also improve risk prediction, identifying patterns that go beyond simple rules.

But the key is this: AI should enhance the system, not define it.

The foundation must remain simple, accessible, and usable in low-resource environments.

A Shift in Perspective

The current system waits. It waits for symptoms to become severe. It waits for patients to travel long distances. It waits for conditions to become unavoidable.

BreastSignal challenges that model. It asks:

“What if we could act earlier, using the resources we already have?”

Now, with BreastSignal, the first point of contact will become the most powerful one.

Closing Thoughts

Early detection should not depend on where someone lives or how much they can afford. The signals are already there.

The question is: “Are we equipped to recognize them in time?”

BreastSignal is one step toward making that possible.

Hi, I’m Aria! I’m passionate about using simple, practical technology to make a real difference in healthcare, especially in communities with limited access to resources. I created **BreastSignal** because early detection is the hardest hurdle in breast cancer care, and I wanted to help frontline healthcare workers spot high-risk cases quickly and confidently. When I’m not building tools like this, I love sharing my work and ideas online — connect with me on LinkedIn or check out my stories on Medium. I’d love to hear from you! Thanks for reading!!