Can COVID-19 be detected by patients' voices? Vocalis claims that thanks to AI , this is possible.
See also: AI/algorithms used to hire and fire employees: Is this a good thing?
Detecting COVID-19 without a test is not an easy task, mainly because symptoms vary greatly from person to person. If someone has symptoms such as a sore throat, fever, cough, or loss of smell or taste, they should get tested.
See also: USA: Buying/selling fake COVID-19 vaccination cards is a crime
Many companies are trying to make this process easier, using simple technologies like mobile apps that claim to detect COVID-19. One of these companies is Israel-based Vocalis
What do these technologies help with?
Diagnosing COVID-19 or any other disease is difficult unless you go to a testing center to get tested. To make it easier for people, Vocalis has created an app based on artificial intelligence (AI) that examines people's vocal characteristics to determine if they are suffering from a disease, without having to visit a hospital.
See also: US DoJ: Charges 500 people for participating in COVID-19 scams!
This is an interesting approach, considering that other methods, such as temperature measurement, cannot detect asymptomatic patients. Vocalis' solution could help in these cases.
How does AI help?
Vocalis collects a lot of data related to a person's voice. It has developed an AI technology that determines whether a person has a disease, based on the analysis of their voice.
The company's algorithm extracts 512 features from a voice sample and creates an image – a spectrogram – with which it can diagnose potential diseases.
When the company wants to detect a specific disease, it first conducts clinical trials to identify what kind of recordings it will need to identify it and what elements in the sound it will need to detect.
For example, to detect COVID-19, AI needs to identify voice characteristics that could be associated with symptoms such as fever, headache, and shortness of breath.
Statistics
In February, Vocalis participated in a joint study with the Municipal Corporation of Greater Mumbai in India, which surveyed 2,000 participants.
They spoke a variety of languages, including English, Hindi, Marathi, and Gujarati. The company installed VocalisCheck tools on the participants’ smartphones to measure the effectiveness of the algorithms. In the end, the researchers found that the algorithm was 81.2% accurate in detecting COVID-19. Many of the patients were asymptomatic.
Vocalis tools are currently being deployed in the US, Chile, Indonesia, South Africa, Romania and Luxembourg.
The company wants to acquire more datasets to make COVID-19 detection even more accurate. It also wants to offer its tools in more regions.
Source: TheNextWeb
