Back to News
InnovationAI Understanding briefing

Indian startup uses AI to analyze dog sniffs for cancer detection

Bengaluru-based Dognosis is using AI to interpret canine scent detection data, reporting over 90% accuracy in a recent study published in the Journal of Clinical Oncology.

4 min readRead the original reporting
Source-provided image accompanying Indian startup uses AI to analyze dog sniffs for cancer detection
Attributed reportingSource recorded
Publisher
straitstimes.com
Source link
straitstimes.comhttps://www.straitstimes.com/life/can-dogs-sniff-cancer-ai-joins-the-hunt-in-india
Source type
Reporting by a news outlet — not a first-party document.

What we could not confirm independently: This claim is attributed to the named outlet. We did not verify it against a first-party document. (straitstimes.com)

ContextUnderstand this in 60 seconds

Start here

Key terms

Artificial Intelligence (AI)
The broad field of building systems that perform tasks requiring pattern recognition, reasoning, language, or decision-making.
Test yourselfAI Models Explained Quiz

What happened

Dognosis, an Indian startup, has published a study in the Journal of Clinical Oncology demonstrating that AI analysis of dog scent detection can identify cancer with over 90% accuracy across seven types. The company is preparing for a commercial launch in 2027.

Bengaluru-based startup Dognosis has developed a system that uses artificial intelligence to analyze the physiological responses of dogs sniffing human breath samples. The company fits dogs with 3D-printed helmets and harnesses containing sensors to track brain activity, respiration, and body language. This data is processed by AI to determine if a sample contains cancer markers.

The company recently published a study involving more than 1,500 participants across six hospitals in Karnataka state in the Journal of Clinical Oncology. Dognosis reported an accuracy rate of over 90 percent for detecting seven major types of cancer. The testing process involves patients breathing into a cotton mask for 10 minutes, which is then sealed and sent to the lab for the dogs to analyze.

Dognosis is backed by venture capital firms including Accel India and is collaborating with government medical institutions. The startup aims to launch commercially in 2027, which would make it the third company of its kind globally, following firms from Germany and Israel. The technology is designed to serve as a first-layer screening tool to identify potential cases for further medical testing.

Source details: straitstimes.com

Why it matters

This development offers a potentially affordable, non-invasive screening tool for cancer in India, where late-stage diagnoses are common. By leveraging AI to standardize and interpret biological data from dogs, the technology could enable large-scale early detection, significantly improving survival rates if validated in broader real-world settings.

Cancer is a major public health concern in India, with one in nine people likely to develop the disease. Many patients are currently diagnosed only after the disease has advanced, reducing survival chances. A non-invasive, affordable screening method could address this gap by enabling earlier detection.

The use of AI is central to this innovation because it converts the subjective behavior of dogs into quantifiable, consistent data. While dogs have a superior sense of smell, their reactions can vary; AI helps standardize the interpretation of these reactions, making the test scalable and reliable for clinical use.

Independent oncologists in Bengaluru, such as Santhosh Kumar Devadas and Neelesh Reddy, have expressed cautious optimism. They note that while the study is a promising early signal, larger studies are needed before definitive conclusions can be drawn about its utility for actual patients.

Interactive Mechanism

Interactive Mechanism: How It Actually Works

Explore the underlying technology behind this development interactively.

Thinking Budget (Test-Time Tokens):1,024 tokens
Complex Accuracy79%Math & Code Logic
Latency3.2sTime to first full output
Inference Cost$0.0092Per query estimated
Reasoning StyleStep VerificationInternal chain depth
Active Thinking Trace:
1Deconstruct user problem into formal constraints
2Propose candidate hypotheses & step-by-step calculation
3Self-correction: Backtrack and refute subtle edge cases
4Exhaustive consistency check & final output synthesis
Core takeaway: Test-time compute fundamentally changes AI economics. Instead of only scaling during pre-training, giving reasoning models more tokens at inference time allows them to systematically solve PhD-level STEM problems.
Interactive Concept Check+10 Points
AI Models Explained Quiz

What is the best response when AI Models Explained makes a mistake in production?

What to watch next

Monitor the upcoming real-world pilot programs and regulatory approvals in India. Watch for independent replication of the 90% accuracy claim by third-party oncologists and the specific commercial access model Dognosis plans to use in 2027.

The next phase involves testing in real-world programs to validate the lab results in clinical settings. The success of these pilots will determine if the technology can be integrated into standard healthcare workflows.

Regulatory approval is a key hurdle. As Dognosis moves toward its 2027 commercial launch, it must navigate medical device regulations in India and potentially other markets.

Independent verification of the 90% accuracy claim is crucial. Current data comes from the company's own study; broader scientific consensus will depend on replication by independent research groups.

Related guides & quizzes

AI Models ExplainedFuture of AIAI EthicsTest what you know — try a free AI quizLook up an AI term in our glossary
Found this useful?