Researchers at Boston University have developed an artificial intelligence tool that can help doctors diagnose dementia more efficiently and accurately. The AI software, created by Vijaya B. Kolachalama, an expert in using computers to aid medical diagnoses, can pinpoint specific causes of cognitive decline using commonly collected patient information such as medical history, medication use, demographic data, and neurological exam scores.
The algorithm was trained on data from over 50,000 individuals from nine different datasets around the world and can diagnose 10 different types of dementia, including vascular dementia and frontotemporal dementia, even if they occur together. In a test, the software boosted doctors’ accuracy by 26 percent when compared to neurologists working alone. The tool has the potential to assist in diagnosing dementia early, preventing the disease from getting worse, and could be particularly useful in under-resourced hospitals where access to advanced testing is limited.
AI-Powered Diagnosis for Dementia: A New Era in Medical Research
The diagnosis of dementia, a catchall term for cognitive deficits that impact daily living, is often a complex and time-consuming process. With multiple causes of dementia occurring simultaneously, reaching an accurate diagnosis can be challenging, even for experienced doctors. However, researchers at Boston University have made a significant breakthrough by developing an artificial intelligence (AI) tool capable of pinpointing the causes of cognitive decline using commonly collected patient information.
Accurate Diagnosis with Limited Data
The AI-powered software, developed by Vijaya B. Kolachalama and his team, can accurately identify specific causes of dementia using medical history, medication use, demographic data, neurological and neuropsychological exam scores, and neuroimaging data such as magnetic resonance imaging (MRI) scans. The platform can diagnose 10 different types of dementia, including vascular dementia and frontotemporal dementia, even if they occur together. This is particularly significant in under-resourced hospitals in low-income countries where access to advanced diagnostic tools like MRI machines may be limited.
Training the Algorithm
The algorithm was trained on data from over 50,000 individuals from nine different datasets collected around the world. To test its performance, researchers gave neurologists working alone and neurologists using the computer model 100 cases to evaluate. The results showed that the software boosted the doctors’ accuracy by 26 percent. This suggests that the AI tool can significantly improve diagnostic accuracy, even when used in conjunction with limited patient data.
Expanding Access to Diagnosis
Kolachalama collaborates with neurologists and radiologists from around the world who have access to different types of patient information. The software’s ability to work with limited information makes it an ideal solution for expanding access to diagnosis in areas where advanced diagnostic tools are scarce. This is particularly important given the significant challenges in accessing gold-standard testing, not only in remote and economically developing regions but also in urban healthcare centers.
Addressing the Shortage of Neurology Experts
The AI tool has the potential to address the shortage of neurology experts around the world. With the number of neurology patients growing, this mismatch is putting a significant strain on healthcare systems. Having a software program that can assist in diagnosing could help lift the burden that’s falling on doctors with limited time and resources. The next step for the AI tool is bringing it to hospitals and doctors’ offices for field testing, a goal that Kolachalama and his team are actively working toward.
Future Implications
The development of this AI-powered diagnostic tool has significant implications for the future of dementia diagnosis and treatment. As new drugs gain approval for treating Alzheimer’s, such as Kisunla, an injection recently approved by the US Food & Drug Administration for people with mild cognitive impairment, Kolachalama is hopeful that his team’s AI tool can help determine who can benefit from different treatments or participate in clinical trials to bring more drugs to market. The potential of this technology to improve patient outcomes and reduce healthcare costs is substantial, making it an exciting development in the field of medical research.
External Link: Click Here For More
