Researchers at Ankara University in Turkey have developed a novel means of diagnosing lung cancer without even having to touch a patient. Studies have shown that their AI-powered voice analysis app is over 90 per cent accurate at identifying the disease in its early stages.
This week, the group’s lead scientist Haydar Ankishan spoke with local reporters about the technology and the preliminary research demonstrating its efficacy.
“In our study, we considered the structure of the voice, the anatomical structure of the lungs, and the circulatory system and proposed that the voice can provide information about lung cancer,” Ankishan told local media. “We pursued this idea, and after nearly one-and-a-half years of work, we have achieved promising results.”
To determine the app’s level of accuracy, him and his team analyzed voice recordings of 100 subjects, half of whom had lung cancer. They were very pleased with the results.
“The model achieves a remarkable accuracy of 92.85 per cent in specifically identifying individuals with early stage [Stage 1] lung cancer,” they specified in their study.
Ankishan was featured on the popular Turkish television channel NTV on Monday. He also appeared in the local Gazete Oku newspaper for his achievement.
Turkish men smoke more than most
Lung cancer accounts for over 17 per cent of all cancer cases in Turkey and the country is in the top 10 among all nations for prevalence of the disease.
It primarily impacts Turkish men. Adult males account for approximately 90 per cent of domestic cases. This is largely attributable to the high number of fellows that smoke in the Middle Eastern nation.
The app developed by scientists at Ankara has brought hope with it for improving the national survival rate through early detection and swift intervention.
Read more: Breath Diagnostics onboards new president and closes critical financing
Read more: Breath Diagnostics pioneers novel lung cancer breath test
Follow Rowan Dunne on LinkedIn
rowan@mugglehead.com
