AI and Smartwatches Can Detect Parkinson’s Disease Early
The convergence of smartwatches and AI has led to a breakthrough in early detection of Parkinson’s disease.
Researchers used smartwatch data to identify individuals who would be clinically diagnosed with Parkinson’s seven years later, revealing slower movements and diminished sleep quality.
The study’s lead author, Dr. Kathryn Peall, found the model accurate and separates Parkinson’s disease from other conditions that could impair movement.
The technology has the potential to significantly impact our lives in the future, enabling early detection and intervention, personalized healthcare, improved disease management, empowerment of individuals, advancement in research and healthcare, prevention and public health, and data-driven decision-making.
The combination of smartwatches and AI can contribute to better healthcare practices, preventive measures, and data-driven decision-making.
The convergence of smartwatches and AI has enabled researchers to uncover hidden insights about individuals that were previously unknown. Now, a compelling case has emerged, demonstrating the potential of this technology.
Through the analysis of smartwatch data, researchers have made a breakthrough in the early detection of Parkinson’s disease. They were able to identify individuals who would be clinically diagnosed with Parkinson’s seven years later. The data revealed that even years before diagnosis, these individuals exhibited slower movements and diminished sleep quality.
To achieve this feat, the researchers trained ML models to distinguish those with Parkinson’s disease from the general population. Comparing their findings with models based on genetics, blood chemistry, lifestyle, or known prodromal symptoms such as constipation or loss of smell, the models trained on accelerometry data from smartwatches demonstrated superior performance in diagnosing Parkinson’s disease.
The study’s lead author, Dr. Kathryn Peall, told BBC News that it seemed to be accurate and separate Parkinson’s disease from other conditions that could impair movement, such as old age or frailty.
As a benefit of working with a dataset like the UK Biobank, she said, “We compared our model across a number of different disorders, including other types of neurodegenerative disorders, people with osteoarthritis, and other movement disorders, among others.”
However, it “will always remain an individual and personal choice” whether people should be informed they had Parkinson’s years before symptoms appeared.
By leveraging the wealth of data collected through smartwatches, individuals may gain valuable insights into their health and potentially seek appropriate medical attention sooner.
Dr. Sirwan Darweesh, a neurologist from the Department of Neurology at Erasmus University School of Medicine in Rotterdam, has dedicated extensive research to studying the onset and progression of Parkinson’s disease. In 1990, a team of researchers from the university initiated a comprehensive study with the objective of monitoring the health of all residents over 55 years of age in Ommord, a neighborhood in the Netherlands. Within this study, Dr. Darweesh specifically focused on a group of one hundred individuals who were eventually diagnosed with Parkinson’s disease.
Based on Dr. Darweesh’s research, it has been determined that the pathology of Parkinson’s disease manifests more than two decades before a clinical diagnosis can be made. In most cases, the initial symptoms become noticeable approximately ten years before an official diagnosis is reached. Dr. Darweesh shares the concern expressed by Grandas that Parkinson’s disease is often diagnosed at a late stage when disease-modifying therapies are less effective. The likely reason behind this inefficacy is that the disease pathology is already considerably advanced at that point, with more than 60% of the vital dopaminergic brain cells being depleted by the time of diagnosis.
One limitation of recent research is that smartwatches only recorded activity for a week. However, if this approach were applied in a real-world setting, continuous data collection over an extended period could enhance the accuracy of warning signals. Prior to Dr. Sandor’s current work, a group of scientists in the United States employed artificial intelligence to identify patterns in smartwatch data. They also utilized a sample from the UK Biobank, focusing on patients who had already received a diagnosis of Parkinson’s disease. Among the researchers involved, neurologist Dr. Karl Friedl emphasizes that a full week of monitoring movement patterns is sufficient to detect individuals who are likely to develop Parkinson’s. Looking from a broader perspective, Dr. Friedl emphasizes that analyzing an individual’s movement can provide valuable insights into various aspects of their health and well-being. When combined with emerging prodromal features associated with Parkinson’s, such as anosmia, REM sleep disturbance, and depression, predictive algorithms in our advancing AI world hold tremendous potential.
The smartwatch study also collected data on sleep patterns from a sample of 65,000 individuals. Once again, artificial intelligence demonstrated the ability to detect changes in sleep duration and quality, both in those already diagnosed with Parkinson’s disease at the time of activity recording and in those who were diagnosed years later. According to Dr. Sandor, the data from smartwatches revealed that individuals experience more frequent awakenings at night and longer sleep duration several years prior to a Parkinson’s diagnosis. By combining daytime and nighttime data, accelerometers could offer doctors the opportunity to intervene and potentially slow the progression of the disease.
The technology described above, the convergence of smartwatches and artificial intelligence for early detection of Parkinson’s disease, has the potential to significantly impact our lives in the future. Here are some ways this technology can make a difference:
- Early Detection and Intervention: By leveraging the data collected from smartwatches and utilizing advanced machine learning algorithms, individuals can gain early insights into their health conditions. Early detection of Parkinson’s disease or other similar conditions allows for timely intervention, potentially improving treatment outcomes and quality of life.
- Personalized Healthcare: The integration of smartwatches and AI enables personalized healthcare solutions. With continuous monitoring and analysis of health data, individuals can receive tailored recommendations, interventions, and preventive measures based on their specific health patterns and risks. This personalized approach has the potential to enhance overall well-being and disease management.
- Improved Disease Management: Smartwatches equipped with AI-powered algorithms can provide real-time feedback and reminders to individuals with Parkinson’s disease or other chronic conditions. This support can assist in managing symptoms, medication schedules, exercise routines, and other essential aspects of disease management, ultimately improving the overall quality of life for patients.
- Empowering Individuals: The technology empowers individuals to take an active role in their health and well-being. By providing access to personalized health insights, individuals can make informed decisions about their lifestyle, seek timely medical attention, and actively participate in their own healthcare journey.
- Advancement in Research and Healthcare: The vast amount of data collected through smartwatches and analyzed with AI algorithms can contribute to advancements in medical research. Researchers can gain valuable insights into disease progression, identify new biomarkers, and develop more effective treatments. This technology has the potential to accelerate medical research and improve healthcare practices.
- Prevention and Public Health: Early detection of Parkinson’s disease and other health conditions through smartwatches and AI can contribute to preventive measures and public health initiatives. By identifying high-risk individuals, healthcare providers and policymakers can implement targeted interventions and strategies to reduce the overall burden of disease.
- Data-Driven Decision Making: The wealth of data collected from smartwatches can be leveraged to inform healthcare policies and strategies. Aggregated and anonymized data can provide valuable insights into population health trends, allowing healthcare systems to allocate resources more effectively, identify emerging health risks, and develop evidence-based interventions.
Read more related news:
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.