Can ChatGPT-led artificial intelligence detect Alzheimer’s early on?

A technology that is going viral ever since its inception is ‘ChatGPT’, the artificial intelligence-based text-to-image generator chatbot, which is conversational and is said to answer queries just like humans.

According to parent company OpenAI’s description, ChatGPT can answer “follow-up questions” and also “admit its mistakes, challenge incorrect premises, and reject inappropriate requests.” Based on the company’s GPT 3.5 series of language learning models (LLM), GPT stands for Generative Pre-trained Transformer 3, which is said to be a kind of computer language model that relies on deep learning techniques to produce human-like text based on inputs.

Now, a study published in journal PLOS Digital Health has noted that predicting dementia from spontaneous speech using large language models “might one day be able to help doctors detect Alzheimer’s disease in its early stages” and that, too, with “80 per cent accuracy”.

Alzheimer’s disease is a currently an incurable brain disorder. Speech, a quintessential human ability, has emerged as an important biomarker of neurodegenerative disorders like Alzheimer’s, the study notes.

The Drexel University study mentions that detection of subtle language impairment which is seen in early stages of Alzheimer’s disease such as — hesitation, making grammar and pronunciation mistakes and forgetting the meaning of words — run like a quick test that could indicate whether or not a patient should undergo a full examination. Notably, while Alzheimer’s remains incurable, early detection can provide rehabilitation with cognitive and behaviour therapies.

Alzheimer’s disease is a progressive brain disorder (Source: Getty Images/Thinkstock)

“GPT3’s systemic approach to language analysis and production makes it a promising candidate for identifying the subtle speech characteristics that may predict the onset of dementia,” said Felix Agbavor, a doctoral researcher in the School and the lead author of the paper, reported Britt Faulstick, Drexel University in thebrighterside.news.

Also Read | Alzheimer’s progression slowed by drug in major trial

According to the study author, “Training GPT-3 with a massive dataset of interviews – some of which are with Alzheimer’s patients — would provide it with the information it needs to extract speech patterns that could then be applied to identify markers in future patients”.

How was it done?

Story continues below this ad

The researchers tested their theory by feeding the program with a set of transcripts from a portion of a dataset of speech recordings compiled with the support of the National Institutes of Health specifically for the purpose of testing natural language processing programs’ ability to predict dementia. Capturing meaningful characteristics of the word-use, sentence structure and meaning from the text to produce what researchers call an “embedding” – a characteristic profile of Alzheimer’s speech, the study author then used the embedding to re-train the program, now into an Alzheimer’s screening machine. To test it, they asked the program to review dozens of transcripts from the dataset and decide whether or not each one was produced by someone who was developing Alzheimer’s.

According to Faulstick’s report, running two of the top natural language processing programs through the same paces, the group found that GPT-3 performed better than both, in terms of accurately identifying Alzheimer’s examples, identifying non-Alzheimer’s examples and with fewer missed cases than both programs.

Also Read | What lifestyle changes should you make for your brain health?

In addition, a second test used GPT-3’s textual analysis to predict the score of various patients from the dataset on a common test for predicting the severity of dementia, called the Mini-Mental State Exam (MMSE). GPT-3 proved to be almost 20 per cent more accurate in predicting patients’ MMSE scores.

Can AI-driven speech analysis like ChatGPT help identify Alzheimer’s?

Story continues below this ad

Dr Arun B Shah, consultant neurologist, director, Department of Neurosciences at Sir HN. Reliance Foundation Hospital called it a “promising tool” for Alzheimer’s disease screening. “Incorporation and development of this algorithm into a web application is underway and should be readily available to patients and clinicians for home and office use which could help make the patient and their caregivers,” Dr Shah said.

Dr Bhupesh Kumar, neurologist, Neuro and Pain Care Clinic, Gurugram called the tech “too ambiguous” and “too ambitious”. “It is a good suggestion but is vague, ambiguous and too ambitious to determine one as an Alzheimer’s patient without any blood test, brain mapping, or scan. There are chances that a simple spelling mistake may decide on your patient status. So, it is too early for this technology which is completely computer-enabled at the moment,” Dr Kumar told indianexpress.com.

📣 For more lifestyle news, follow us on Instagram | Twitter | Facebook and don’t miss out on the latest updates!

From the homepage