Dementia sufferers can now be accurately identified through voice and face recognition. Indeed, the accuracy level is at an amazing 90%.
Dementia is a devastating disease. An estimated 5.3 million are age 65 and older in the United States, suffer from dementia and Alzheimer’s disease. As it progresses, it can devastate a person’s life. Every 3 seconds a new case of dementia is diagnosed, according to the World Health Organization (WHO).
Dementia is characterized by cognitive impairment, such as inability recalling memories, solving problems, and reasoning logically.
The biggest risk factors are aging, stroke, and high blood pressure.
Dementia Sufferers: Diagnosis Goes High Tech
Onset dementia progresses very slowly and develops without much notice in many patients. Monitoring these changes is not easy. Professional experts are required to interpret symptoms through standard questionnaires. Patients get used to the tests and improve their answers, thereby skewing the results. Thus, the actual number of early stage dementia patients that fall through the cracks is unknown. Unfortunately, any drug or behavioral intervention in full blown dementia patients is unlikely to reverse or even temper the disease.
Now, researchers at Osaka University and Nara Institute of Science and Technology in Japan have developed a totally computer-driven approach that asks questions and monitors responses. Both face and vocal responses to these questions are carefully monitored.
As the user answers questions, the software identifies different parameters of the speech, such as tone, speed, intonation, and usage of verbs and nouns. At the same time, a camera watches the person’s face and also measures a number of visual parameters as well.
All of this data was processed through a machine learning system that was developed with recordings of individuals already confirmed to suffer from dementia and non-dementia participants.
In this first study, the computer system evaluated 12 healthy people and 12 people diagnosed with dementia. Dementia criteria was based on the Diagnostic and Statistical Manual of Mental Disorders (DSM)-IV). This manual is recognized by all doctors and clinicians.
The results showed that the computer system had a diagnostic accuracy rate of 90%. Most impressive, this was achieved with only a total of 6 questions, each of 2-3 minutes duration.