
Dognosis, a Bangalore-based startup in India, uses AI to analyze the physiological responses of sniffer dogs and has an accuracy rate of over 90% in screening seven common cancers. It hopes to provide affordable primary screening solutions.
AI-generated summary
Research shows that disease can alter human body odor, and dogs have the potential to detect disease due to their extremely high number of olfactory receptors.
(Central News Agency Bangalore Comprehensive Foreign News Report on the 7th) Can dogs really smell cancer? An Indian team combines dogs' sensitive sense of smell with AI technology to develop non-invasive cancer screening technology. Small-scale studies have shown that this technology has an accuracy rate of more than 90% in screening seven common cancers, hoping to help patients diagnose early.
Agence France-Presse reports that more and more studies around the world show that dogs can detect various human diseases such as cancer, Parkinson's disease, and COVID-19 after training. Research shows that disease may change the chemicals released by the human body, thereby producing a unique smell. Compared with humans, who only have about 5 million olfactory receptors, dogs have as many as 300 million, giving them a more sensitive sense of smell.
Dognosis, a startup based in Bengaluru, India, is using artificial intelligence (AI) to analyze dogs’ brain activity, breathing and body language, and convert their physiological responses to smells into analyzable data.
"In an hour, they can sniff thousands of times and evaluate a sample each time," 26-year-old co-founder Akash Kulgod, who comes from a family of doctors and graduated from the Department of Cognitive Science at the University of California, Berkeley, told AFP.
If cancer can be detected early, it will greatly affect the patient's survival rate. However, in India, many cancer patients are often diagnosed at an advanced stage. Dog sniff screening will provide a simple, affordable, and large-scale primary screening method to identify potential cases before further examination.
Dognosis looks forward to officially launching commercial operations next year and is expected to become the third company in the world to engage in this type of technology, following those in Germany and Israel. While striving for commercial approval, Dognosis has also received capital injections from Indian venture capital firm Accel and other companies, and is cooperating with government medical institutions.
Dognosis currently trains a total of 15 sniffer dogs, most of which are Migrus, and some of which are Malinois-Shepherd mixed-breed dogs, all of which are adopted or imported through legal breeders.
They will wear a special 3D-printed helmet and a harness full of sensors. They will sniff human samples on a work platform equipped with an automatic feeding machine. After completing the task, they will be rewarded with snacks. The daily working time is controlled to about 30 to 45 minutes.
The testing method is very simple. The patient only needs to breathe into the cotton mask for about 10 minutes, then put the mask in a sealed bag and send it to the laboratory. The tested patients will not have direct contact with the dogs.
A recent study conducted by Dognosis on more than 1,500 subjects in 6 hospitals in Karnataka found that this technology has an accuracy of more than 90% in detecting 7 major cancers. It is currently planning to test it in actual fields. The research results have been published in the "Journal of Clinical Oncology".
Cancer specialists in Bengaluru who are not involved in the project expressed optimism about the technology.
Santhosh Kumar Devadas, director of the oncology department at Ramaiah Memorial Hospital, said that the study initially appears to have potential, "but it needs to be studied in a larger group before a clear conclusion can be drawn."
AI outlook — possibilities, not facts
Dognosis is expected to be officially put into commercial operation next year.
Likely · Within months

The Ministry of Industry and Information Technology recently issued the "15th Five-Year Plan for the Development of the Information and Communications Industry", which proposes to build a new generation of communications network with leading performance by 2030 and build a safe and controllable industrial system. The plan has deployed six key tasks: infrastructure construction, industrial system cultivation, industry governance optimization, security enhancement, integrated application expansion and global development.

The First Hospital of Jilin University independently developed the Medsuper Harness multi-agent collaborative working platform to realize the transformation of AI from an auxiliary tool to a "digital employee". The platform has greatly improved efficiency in data governance and software development, and has begun to be explored in clinical scenarios while emphasizing the security of intra-hospital network deployment.

Huawei launched the Mate XT 2, a trifold smartphone featuring the new Kirin 9050 Pro processor and HarmonyOS 7. Priced at 19,999 yuan, the device marks Huawei's latest effort to enhance chip performance amid ongoing competition in the foldable phone market.

Cathay Pacific and Google are expanding AI-driven trials to steer aircraft away from contrail-forming zones. The project, involving ultra-long-haul flights across Asia and transpacific routes, seeks to reduce aviation's climate impact by avoiding heat-trapping condensation.

Lawyer Cai Chuiliang analyzed the new model of hacker attacks: stealing personal information by lurking for a long time, making it public once enough data has been accumulated, using the mandatory notification and accountability mechanism of personal information regulations to weaponize the law, thereby paralyzing the medical administration and judicial system, causing a systemic collapse at the national level.

Beijing recently issued "Beijing's Several Measures to Accelerate the Development of Intelligent Agents". As a new form of artificial intelligence, smart bodies have been implemented in Tiantan Hospital's imaging diagnosis, mobile phone manufacturing processes and the "one-person company" entrepreneurial model. Through policy support and standard formulation, Beijing is accelerating the construction of a smart body industry ecosystem.