A team of Lithuanian software developers from the Kaunus University of Technology (KTU) have worked alongside medics to develop new technology which could identify laryngeal cancer.
When a patient is treated for advanced laryngeal cancer, a complex surgery known as a laryngectomy is performed by surgeons. A laryngectomy requires the person’s vital speech organ to be removed. After surgery, the patient can only breathe through a tracheal hole made in the neck. This process will change the patient’s life significantly; Rytis Maskeliūnas, the lead researcher on the project, described the effect on patients by saying, “For some, the voice changes slightly, others talk like robots, others wheeze’’.
Keen to help sufferers of laryngeal cancer, Maskeliūnas’s team from KTU worked alongside a team of medics from the Lithuanian University of Health Sciences to develop new artificial intelligence which can help monitor pathologies. Maskeliūnas hypothesises that this new Artificial Intelligence will be able to help doctors identify changes in a patient’s voice, in turn helping doctors provide the best treatment for those who have suffered laryngeal cancer.
“The AI algorithm used in this research will potentially allow us to screen and evaluate various voice parameters, then assign them to a certain class. It can also become a tool to follow how a person heals, how his voice changes, in a good or bad sense,” explained Maskeliūnas.
How does this innovation help medics and patients with laryngeal cancer?
The existing method used by doctors to screen patients for voice pathologies requires a doctor to analyse a patient’s voice, as well as requiring the patient themselves to complete a questionnaire based on how they perceive the quality of their own voice. Those working on the project believe their research will help create a more efficient method of analysing voice pathologies in patients with laryngeal cancer.
How the technology works
This new technology will allow patients with laryngeal cancer to upload a recording of their voice through a smartphone or any device with an internet connection. Using the audio recording, the system will provide an estimation of the individual’s condition. Medical staff can then use this information to help determine the best course of action for the patient.
Maskeliūnas emphasises the importance of the research, commenting that “Previous studies have never fully utilised methods of Artificial Intelligence as “an expert assistant” to do the voice analysis, and only a low level of automation has been applied in regional medical IT practice for this area”. Similar technology has been used to study the voices of patients suffering from Parkinson’s disease. However, this is the first of its kind being used to treat cases of laryngeal cancer.