Clinical Validation

Clinical validation & data

The MammoAlert model was built and stress-tested computationally, then confirmed against real biological samples across 9 independent retrospective studies. Below is a summary of that work — investors and strategic partners can request the full underlying data and a conversation with our team.

Model development

In silico model training & testing

Reflects the current five-biomarker AI model.

5,000+

In silico patient profiles used to train the model

1,000+

In silico patient profiles used to test the model

95%+

Sensitivity and specificity achieved in silico

The model was then checked against 350+ actual patient samples obtained from research repositories in the US and Europe, ahead of the independent retrospective studies below.

Panel evolution

The pathway from 4-biomarker clinical validation to 5-biomarker in silico optimization

Harae Dx’s original four-biomarker panel was clinically validated in 9 independent retrospective studies. A fifth biomarker was then added to build the current AI model, which has been trained and tested in silico — with retrospective clinical validation of the five-biomarker panel now underway.

Step 1 · 4-biomarker panel — clinically validated

9 independent retrospective studies across 1,055 plasma samples from independent research institutions and clinical partners. Results below.

Step 2 · 5-biomarker panel — in silico optimized

The current AI model was trained on 5,000+ and tested on 1,000+ in silico patient profiles (95%+ sensitivity & specificity), then checked against 350+ real patient samples. Retrospective clinical validation of the five-biomarker panel is ongoing.

Real-world proof

9 independent retrospective studies

Conducted using Harae Dx’s original four-biomarker panel, across 1,055 plasma samples from independent research institutions, clinical partners, and lab validation studies — with performance consistent across sample sets and independent of patient ethnicity or cancer stage.

~90%

Average sensitivity & specificity

93.50%

Average positive predictive value

82.82%

Average negative predictive value

90.89%

Average accuracy

See the full study-by-study breakdown
Regulatory progress

Building toward a global regulatory pathway

FDA — Breakthrough Device pathway

Harae Dx is pursuing FDA Breakthrough Device Designation, which would support an expedited path toward regulatory review.

India — fast-track clinical pathway

Fast-track clinical trial pathway discussions underway in India.

“Most current cancer diagnostics are designed for patients who have already entered the healthcare system. Harae Dx is designed to expand access to the much larger population that is not routinely screened.”