Using voice monitoring to help diagnose and treat dementia at home
Dementia is a heart-breaking condition that cannot be cured today, but if detected early enough its progress can be slowed. Yet traditional methods of diagnosis and treatment, based on limited professional medical observation, will become increasingly inadequate as the world’s elderly population explodes in the coming decades. In 1995, 30 countries had elderly populations of at least 2 million; by 2030 it’s expected that more than 60 countries will reach this level1.
To address this growing healthcare issue, IBM researchers are collaborating on a project with the potential to dramatically increase the accuracy and affordability of early detection through an unlikely source – the analysis of voice patterns using some of the same technology found in IBM’s Watson system.
Dementia is a loss of brain function that affects memory, cognitive skills, and behavior beyond what is expected as part of the normal aging process. Alzheimer’s disease is the most common form of dementia.
Treating dementia at home
Many patients with dementia are placed in nursing homes to receive the round-the-clock monitoring and care they require, which can be stressful and financially challenging for both patients and their families. Diagnosis and treatment also requires doctors and caregivers to observe the patient, but these observations are often limited to the behavior shown during short visits, making it difficult to accurately diagnose the patient and provide the right type of treatment.
To make dementia diagnosis and treatment more accurate and affordable, IBM Research is working with ten academic and industrial partners on [email protected], a four-year project to develop an integrated system of sensors to diagnose dementia, and provide follow up treatment by measuring a patient’s condition over time at home. Scientists at IBM Research – Haifa are contributing to the project by exploring how voice analysis can help diagnose and monitor people with dementia.
According to Aharon Satt, an IBM researcher specializing in detecting voice pathologies, the use of voice monitoring can be quite effective in diagnosing diseases. “Our past research work revealed that laryngeal cancer can be effectively diagnosed based on automatic voice analysis,” he said. “Other studies show that certain neurological and mental disorders also manifest themselves in voice.”
Changes in voice patterns could serve as warning signs for diagnosticians. For example, a high percentage of pauses while performing a simple task could indicate cognitive problems associated with dementia. There are other voice features that classify a specific condition, including:
- Low level voice quality, such as pitch, jitter and shimmer
- Speech continuity and fluency, such as the amount and length of the pauses, length of speech parts, time to respond to questions, etc.
- Semantics, such as the vocabulary richness, lack of words, ratio of verbs to nouns, etc.
The speech analysis is done by using simple and inexpensive equipment like a microphone or telephone, and is part of a system of sensors, including accelerometers, video cameras and physiological sensors. This system could help dementia patients live independently and be monitored in their own homes.
Machine learning tools, similar to those used in IBM’s Watson system, can detect patterns in voice recordings to assess a patient’s condition. The system will also give patients and their family member’s guidance on managing the condition. Doctors will receive data regarding the patient’s health status, which can be used to gauge the effectiveness of a treatment, identify warning signs, and support preventive care decision making. For example, if voice and behavioral patterns analysis revealed an apathetic state of mood, a physician might increase a patient’s level of activity or adjust levels of medication.
As the population ages and average life spans increase, news ways of managing the diseases associated with aging are needed. Providing patients and family members with the support and guidance they need, while reducing the number of people in nursing homes and helping doctors make more informed decisions about treatment, can significantly improve the quality of life for the elderly and ease the financial burden on their families and society.