Almost All Leading AI Chatbots Show Signs of Cognitive Decline

Almost all leading large language models or "chatbots" show signs of mild cognitive impairment in tests widely used to spot early signs of dementia, finds a study in the Christmas issue of The BMJ.

The results also show that "older" versions of chatbots, like older patients, tend to perform worse on the tests. The authors say these findings "challenge the assumption that artificial intelligence will soon replace human doctors."

Huge advances in the field of artificial intelligence have led to a flurry of excited and fearful speculation as to whether chatbots can surpass human physicians.

Several studies have shown large language models (LLMs) to be remarkably adept at a range of medical diagnostic tasks, but their susceptibility to human impairments such as cognitive decline have not yet been examined.

To fill this knowledge gap, researchers assessed the cognitive abilities of the leading, publicly available LLMs - ChatGPT versions 4 and 4o (developed by OpenAI), Claude 3.5 "Sonnet" (developed by Anthropic), and Gemini versions 1 and 1.5 (developed by Alphabet) - using the Montreal Cognitive Assessment (MoCA) test.

The MoCA test is widely used to detect cognitive impairment and early signs of dementia, usually in older adults. Through a number of short tasks and questions, it assesses abilities including attention, memory, language, visuospatial skills, and executive functions. The maximum score is 30 points, with a score of 26 or above generally considered normal.

The instructions given to the LLMs for each task were the same as those given to human patients. Scoring followed official guidelines and was evaluated by a practising neurologist.

ChatGPT 4o achieved the highest score on the MoCA test (26 out of 30), followed by ChatGPT 4 and Claude (25 out of 30), with Gemini 1.0 scoring lowest (16 out of 30).

All chatbots showed poor performance in visuospatial skills and executive tasks, such as the trail making task (connecting encircled numbers and letters in ascending order) and the clock drawing test (drawing a clock face showing a specific time). Gemini models failed at the delayed recall task (remembering a five word sequence).

Most other tasks, including naming, attention, language, and abstraction were performed well by all chatbots.

But in further visuospatial tests, chatbots were unable to show empathy or accurately interpret complex visual scenes. Only ChatGPT 4o succeeded in the incongruent stage of the Stroop test, which uses combinations of colour names and font colours to measure how interference affects reaction time.

These are observational findings and the authors acknowledge the essential differences between the human brain and large language models.

However, they point out that the uniform failure of all large language models in tasks requiring visual abstraction and executive function highlights a significant area of weakness that could impede their use in clinical settings.

As such, they conclude: "Not only are neurologists unlikely to be replaced by large language models any time soon, but our findings suggest that they may soon find themselves treating new, virtual patients - artificial intelligence models presenting with cognitive impairment."

Dayan R, Uliel B, Koplewitz G.
Age against the machine-susceptibility of large language models to cognitive impairment: cross sectional analysis.
BMJ. 2024 Dec 19;387:e081948. doi: 10.1136/bmj-2024-081948

Most Popular Now

AI System Helps Doctors Identify Patient…

A new study from Vanderbilt University Medical Center shows that clinical alerts driven by artificial intelligence (AI) can help doctors identify patients at risk for suicide, potentially improving prevention efforts...

Smartphone App can Help Reduce Opioid Us…

Patients with opioid use disorder can reduce their days of opioid use and stay in treatment longer when using a smartphone app as supportive therapy in combination with medication, a...

AI's New Move: Transforming Skin Ca…

Pioneering research has unveiled a powerful new tool in the fight against skin cancer, combining cutting-edge artificial intelligence (AI) with deep learning to enhance the precision of skin lesion classification...

Leveraging AI to Assist Clinicians with …

Physical examinations are important diagnostic tools that can reveal critical insights into a patient's health, but complex conditions may be overlooked if a clinician lacks specialized training in that area...

AI can Improve Ovarian Cancer Diagnoses

A new international study led by researchers at Karolinska Institutet in Sweden shows that AI-based models can outperform human experts at identifying ovarian cancer in ultrasound images. The study is...

Predicting the Progression of Autoimmune…

Autoimmune diseases, where the immune system mistakenly attacks the body's own healthy cells and tissues, often have a preclinical stage before diagnosis that’s characterized by mild symptoms or certain antibodies...

Major EU Project to Investigate Societal…

A new €3 million EU research project led by University College Dublin (UCD) Centre for Digital Policy will explore the benefits and risks of Artificial Intelligence (AI) from a societal...

Using AI to Uncover Hospital Patients�…

Across the United States, no hospital is the same. Equipment, staffing, technical capabilities, and patient populations can all differ. So, while the profiles developed for people with common conditions may...

New AI Tool Uses Routine Blood Tests to …

Doctors around the world may soon have access to a new tool that could better predict whether individual cancer patients will benefit from immune checkpoint inhibitors - a type of...

New Method Tracks the 'Learning Cur…

Introducing Annotatability - a powerful new framework to address a major challenge in biological research by examining how artificial neural networks learn to label genomic data. Genomic datasets often contain...

From Text to Structured Information Secu…

Artificial intelligence (AI) and above all large language models (LLMs), which also form the basis for ChatGPT, are increasingly in demand in hospitals. However, patient data must always be protected...

Picking the Right Doctor? AI could Help

Years ago, as she sat in waiting rooms, Maytal Saar-Tsechansky began to wonder how people chose a good doctor when they had no way of knowing a doctor's track record...