Could AI diagnose STIs with a selfie?

Imagine diagnosing a sexually transmitted infection (STI) with just the click of a button. Such a futuristic scenario might soon be a reality thanks to a groundbreaking app developed by researchers at the Melbourne Sexual Health Centre and Monash University.

Said app uses artificial intelligence (AI) to assist in the detection of STIs and other common genital skin conditions.

How does it work?

The app works by having users upload a photo of an abnormal lesion area. The AI then analyzes the image to detect potential STIs or other skin conditions. The app's development framework is based on a collection of over 5000 images gathered with the assistance of MSHC clinicians and patient volunteers. These volunteers consented to their lesion images being used for research purposes. Initial testing of the app has shown promising accuracy rates of between 60 to 90 percent.

Professor Lei Zhang, MSHC epidemiologist and development team leader, expects the app's accuracy to improve as more data is collected. "Over time, its performance will improve with more image accumulation and the inclusion of additional metadata," said Prof Zhang.

The ultimate goal is to make this tool a publicly accessible and effective self-screening resource for the community.

Why does it matter?

The novel app addresses a significant barrier in STI diagnosis: the reluctance of individuals to see a clinician due to embarrassment or shyness. Early diagnosis is a key benefit of this tool.

A negative self-screening result can save individuals a clinic visit, while an early positive finding can encourage timely clinical intervention. Additionally, the tool can aid clinicians by offering valuable diagnostic suggestions.

The context

The development of the "STI-selfie" app is part of a broader trend of using AI in medical diagnostics.

"This technology has already been successfully used in other settings, such as in melanoma detection," said Prof Zhang. He envisions similar applications for the early diagnosis of cervical and anal cancers, as high-resolution colposcopy and anoscopy images become more readily available.

The app represents a significant step forward in the use of AI for healthcare, offering a practical solution to improve early diagnosis and treatment of STIs and other genital skin conditions.

As Prof Zhang noted, "Ultimately, the goal is for this tool to become a publicly accessible and effective self-screening resource for the community."