Ben-Gurion University introduces AI platform for monitoring and predicting ALS progression

“In conjunction with further validating the platform for ALS using patient clinic data, we are now extending its ability to other neurodegenerative diseases such Parkinson's and Alzheimer's,” said Prof. Boaz Lerner.
By Dean Koh
11:35 pm
Share

Prof. Boaz Lerner of Ben-Gurion University with the new platform for predicting ALS progression​. Credit: BGU

BGN Technologies, the technology transfer company of Ben-Gurion University (BGU), today unveiled an artificial intelligence (AI) platform for monitoring and predicting the progression of neurodegenerative diseases for the purpose of identifying markers for personalised patient care and improved drug development.

Developed by Prof. Boaz Lerner of the Department of Industrial Engineering and Management at BGU, the technology will initially focus on amyotrophic lateral sclerosis (ALS) also known as Lou Gehrig's disease, and later be adapted to various other neurodegenerative diseases such as Parkinson's and Alzheimer's.

Why it matters

ALS is a motor neuron disease that almost invariably progresses with time. Research and drug development of this condition are complicated by the heterogeneity of the ALS population leading to variability in symptoms at onset, disease progression rate and pattern, and survival. Reliable patient stratification to homogenous sub-groups and personalised prediction of disease progression rate and pattern of sub-populations, accomplished by the new platform, will improve patient care and quality of life.

The platform can also improve the design of clinical trials and the ability to assess the influence of treatment in clinical studies by identifying markers of various patient sub-populations for which treatment is beneficial, thus improving success rate of the studies.

The platform analyses demographic and clinical data using machine learning and data mining algorithms to produce models that can predict the rate and pattern of ALS progression, identify factors essential for the prediction (such as specific lab tests or vital signs), and stratify homogenous sub-groups from the heterogeneous ALS population. As clinical data are added for each patient, the algorithms, and thus the disease progression prediction, improve.

What’s the trend

In the past, solutions to address ALS was more about helping patients better cope with the disease on a routine basis – for instance, in 2014, Philips and Accenture developed a proof of concept app that would allow such an ALS patient, equipped with an Emotiv sensor, to control Philips devices like the Philips Lifeline Emergency Alert system using only their minds.

In 2017, online health network PatientsLikeMe teamed up with rare disease-focused Shire Pharmaceuticals to develop digital communities and create research opportunities for people with highly specialised, often underserved conditions. PatientsLikeMe was originally founded in 1998 as a resource for people with ALS.

On the record

“One of the big challenges of designing and managing clinical trials for ALS stems from the fact that not only is it a rare disease, but also clinical heterogeneity makes it hard to identify markers correlating with disease severity for enabling successful clinical trials. As a result, after decades of research, there is still no real cure for ALS and other neurodegenerative diseases, such as Alzheimer's disease.

The novel platform, which uses machine learning algorithms, will enable not only accurate prediction of disease progression, a crucial ingredient for better clinical trials, but also identification of interrelationships between demographics and measurable factors from physical examinations and patient functionality that will advance clinical research of this devastating condition.

In conjunction with further validating the platform for ALS using patient clinic data, we are now extending its ability to other neurodegenerative diseases such Parkinson's and Alzheimer's,” Prof. Lerner explained in a statement.

nike free run 5.0 team