AI deciphers how fast ALS progresses and which functions decline first

Nagoya University scientists develop a machine learning tool to uncover how ALS progresses in patients and offer clues to understand why some patients decline faster than others 

ALS (Amyotrophic Lateral Sclerosis) is a fatal neurodegenerative disease that gradually affects a person’s ability to move, speak, and breathe. It advances differently in every patient. Now, researchers at Nagoya University have developed an AI tool that uses data from patient follow-up studies to estimate the speed of disease progression and identify patterns of muscle decline. The study was published in npj Digital Medicine.  

Two questions, one tool 

ALS patients differ in two main ways: how fast their disease advances, and the order in which functions become impaired. Until now, existing AI-based research tools generally did not clearly separate these two differences in individuals. The research team developed DiSPAH, a machine learning system that addresses both at once by analyzing patient data collected during routine medical visits.  
 
Two datasets of patients with limb-onset ALS were used, a form of the disease where symptoms begin in the arms or legs rather than in the muscles controlling speech and swallowing (bulbar-onset ALS). The first provided data from 264 ALS patients and was used to train the model. The second, larger dataset of 2,565 patients was used to validate the results.

What the AI found 

The system identified six distinct patterns of disease progression among the patients. Some patients showed slow decline in motor function, with little effect on speech or breathing, while others experienced rapid deterioration.  
 
“Subtle differences between patients also emerged. For example, in some patients gross motor functions such as walking declined before fine motor skills such as writing or buttoning a shirt, while in others the opposite was true,” said Yuichiro Yada, coauthor and associate professor at Nagoya University’s Graduate School of Medicine. “These six patterns were identified in one patient dataset and largely reproduced in a second, larger dataset, suggesting that they  capture common progression patterns in limb-onset ALS.”  
 
Importantly, speed and decline pattern were found to be independent of each other. A patient could follow a severe pattern at a slow speed, or a milder one at a fast speed. Previous tools could not measure both dimensions at once.

Prediction from day one 

One of the most important findings was that DiSPAH could, to some extent, predict a patient’s progression speed and broad progression pattern from information available at the first medical visit. This consisted of basic functional assessments and the presence of certain gene mutations. 
 
These early predictions have important potential for patient care. Doctors could use them to plan treatment, prepare patients and families, and design better clinical trials by grouping participants according to how their disease advances. 

A genetic clue

The researchers also found that patients with a mutation in a gene called C9orf72 had faster disease progression. When they analyzed data from motor neurons grown in the laboratory from patients’ own stem cells, the results showed that faster ALS progression may be linked to problems in how cells produce and manage proteins, as well as signs of cellular stress. 
 
This points to a possible biological explanation for why some patients decline faster than others and gives scientists a new target for future research into ALS treatments.

Better tools for patients 

ALS currently has no cure. While a few drugs exist, they offer modest benefit. Better tools for prediction and monitoring are essential for the development of new therapies. 
 
Yada noted that DiSPAH is a prototype that needs further validation and refinement: “It’s a promising first step and better than anything that existed before for this specific purpose, but it’s not reliable enough yet to use to make decisions about individual patients.” 
 
The researchers aim to extend the tool to all ALS patient types, improve its reliability, and ultimately apply it to other chronic diseases such as Alzheimer’s and Parkinson’s disease. 


Paper information: 

Yuichiro Yada and Naoki Honda, 2026. Decomposing heterogeneity in disease progression speeds and pathways, npj Digital Medicine. DOI: https://doi.org/10.1038/s41746-026-02665-8 

Funding information:  

This work was partly supported by JSPS Grant-in-Aid for Early-Career Scientists (JP23K16994), Japan Agency for Medical Research and Development (AMED) Multidisciplinary Frontier Brain and Neuroscience Discoveries (Brain/MINDS 2.0)(JP24wm0625416 and JP25wm0625322), JST Moonshot R&D–MILLENNIA Program (JPMJMS2024) and JST CREST (JPMJCR25Q2). 

Expert contact: 

Yuichiro Yada 
Research Institute of Environmental Medicine 
Nagoya University 
yada.yuichiro.k4@f.mail.nagoya-u.ac.jp 

Media contact: 

Merle Naidoo   
International Communications Office   
Nagoya University   
Email: icomm_research@t.mail.nagoya-u.ac.jp

Top image:

DiSPAH is an AI tool that uses data from patient follow-up studies to estimate the speed of disease progression and identify patterns of muscle decline. Credit: Kano Okada, Nagoya University