New AI Software could Make Diagnosing Dementia Easier and Faster for Doctors

Although Alzheimer's is the most common cause of dementia - a catchall term for cognitive deficits that impact daily living, like the loss of memory or language - it's not the only one. Because multiple causes of dementia can happen simultaneously, reaching a definitive diagnosis isn't easy or quick. And often by then, it’s too late to intervene.

Boston University's Vijaya B. Kolachalama, an expert on using computers to aid medical diagnoses, has created an artificial intelligence tool that can determine what’s causing a person's cognitive decline, and assist doctors in more efficiently zeroing in on an accurate diagnosis.

Developed with a team of BU researchers and outside collaborators, it accurately identifies specific causes of dementia using commonly collected patient information - like medical history, medication use, demographic data, and neurological and neuropsychological exam scores - and neuroimaging data, such as magnetic resonance imaging (MRI) scans. For each case, all the available information is entered into the AI-powered software, which then generates a prediction of the type of dementia a person has and a confidence score. The findings are published in Nature Medicine.

"We believe AI can help by identifying these disorders early and assisting doctors in managing their patients more effectively, preventing the diseases from getting worse," says Kolachalama, a BU associate professor of medicine and computer science, and corresponding author on the paper.

The platform can diagnose 10 different types of dementia, including vascular dementia and frontotemporal dementia, even if they occur together. As new drugs gain approval for treating Alzheimer's - such as Kisunla, an injection that the US Food & Drug Administration recently approved 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 help bring more drugs to market.

The algorithm was trained on data from more than 50,000 individuals from nine different datasets collected around the world. To test the software's performance, the researchers gave neurologists working alone and neurologists using the computer model 100 cases to evaluate. They then compared the results of doctors working solo versus those using the software - and found the software boosted the doctors’ accuracy by 26 percent.

Kolachalama collaborates with neurologists and radiologists from around the world who all have access to different types of patient information. For that reason, the software works even with limited information. For example, MRI machines are not as prevalent in under-resourced hospitals in low-income countries, so having a tool that can use any type of available patient data is key for expanding the technology to areas that need it most.

"The ability to generate a diagnosis with routine clinical data is becoming increasingly important given the significant challenges in accessing gold-standard testing, not only in remote and economically developing regions, but [also] in urban healthcare centers," says Kolachalama.

He points out that there is a shortage of neurology experts around the world, and with the number of neurology patients growing, this mismatch is putting a big 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, Kolachalama says. 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.

Xue C, Kowshik SS, Lteif D, Puducheri S, Jasodanand VH, Zhou OT, Walia AS, Guney OB, Zhang JD, Pham ST, Kaliaev A, Andreu-Arasa VC, Dwyer BC, Farris CW, Hao H, Kedar S, Mian AZ, Murman DL, O'Shea SA, Paul AB, Rohatgi S, Saint-Hilaire MH, Sartor EA, Setty BN, Small JE, Swaminathan A, Taraschenko O, Yuan J, Zhou Y, Zhu S, Karjadi C, Alvin Ang TF, Bargal SA, Plummer BA, Poston KL, Ahangaran M, Au R, Kolachalama VB.
AI-based differential diagnosis of dementia etiologies on multimodal data.
Nat Med. 2024 Jul 4. doi: 10.1038/s41591-024-03118-z

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...