Researchers have developed a self-administered smartphone app to detect neurodegenerative conditions such as Alzheimer’s disease and mild cognitive impairment by analyzing speech patterns. Since subtle speech disorders are an early indicator of these conditions, this can be an easy way to get a faster diagnosis, according to newatlas.com.
Despite the worldwide prevalence of Alzheimer’s disease (AD), an estimated 75% of people with the condition have not been diagnosed. Language impairment is usually one of the first signs of Alzheimer’s disease. Early on, individuals may develop slurred speech and have difficulty remembering words or finding the right word to convey what they are trying to say.
Using technology to capture the often subtle changes in a person’s voice is one way to help doctors diagnose Alzheimer’s disease and mild cognitive impairment (MCI) early. The earlier the diagnosis, the greater the chances that the progression of the disease will be slowed. However, recognizing speech patterns in older people can be difficult.
Researchers at the University of Tsukuba (Japan) and IBM Research have developed a prototype self-administered smartphone app to accurately analyze someone’s speech for telltale signs of these neurological conditions.
The researchers collected speech data from 114 participants. Their responses were recorded on an iPad and transcribed using the IBM Watson Speech-to-Text automatic speech recognition service. Machine learning was used to classify the three groups – AD, MCI and control – through speech features, with the researchers inputting 92 speech features extracted from each task. The study was published in the journal Computer Speech and Language.
The researchers found statistically significant differences in the speech patterns of control participants and those with AD or MCI. Furthermore, the machine learning model detected AD and MCI with 91% and 88% accuracy, respectively.
To their knowledge, this is the first study to show the feasibility of using an automated, self-administered tool to detect AD and MCI using speech as a marker. They propose further studies to test whether the speech variations picked up by their app coincide with the pathological changes observed in these conditions.
The researchers acknowledge that their study has some limitations. The speech data were collected in a laboratory setting, which may have influenced how the participants answered the questions. Second, the sample size was small, which affects the generalizability of the study findings.
However, their research demonstrates the potential of using speech analysis via a self-administered smartphone app to detect these debilitating diseases.
Post Views: 23
2023-08-01 16:14:55
#smartphone #app #detect #early #signs #Alzheimers #disease #Money
