Artificial Intelligence Tool Predicts Which Dystonia Patients Respond to Botox Treatment – FindNow
Connect with us

Artificial Intelligence

Artificial Intelligence Tool Predicts Which Dystonia Patients Respond to Botox Treatment

Published

on

Dystonias are potentially disabling neurological conditions that can greatly affect the quality of life. Effective treatments are rare, with injections of botulinum toxin (Botox) into affected muscles being considered the first-line treatment. However, injections do not work for all patients with dystonia, and there is no established way for clinicians to determine who would benefit and who would not before treatment begins.

Advertisement

In a new study published Nov. 28 in Annales de Neurologie, an artificial intelligence platform called DystoniaBoTXNet used brain MRIs to automatically identify patients who would respond to botulinum toxin treatment with 96.3% accuracy. Such a platform can inform clinicians’ treatment decisions, according to lead study author Kristina Simonyan, MD, PhD, Dr. med, director of laryngology research at Mass Eye and Ear, member of Mass General Brigham and Professor of Otorhinolaryngology-Head and Neck Surgery at Harvard Medical School.

“Typically, a patient with dystonia would undergo a series of dosing and localization injections to determine if botulinum toxin relieves their symptoms. The injections are painful and expensive,” Dr Simonyan said. “Yet some may find no benefit from this treatment despite repeated injection attempts, while others may benefit from injections but give up after a single dose or forgo treatment altogether. Thanks to this artificial intelligence algorithm, we can empower clinicians and patients in their therapeutic approach. decision-making by providing them with an objective tool to replace the trial and error approach to botulinum toxin efficacy.”

Pervasive treatment challenges for patients with dystonia

People with dystonia experience involuntary muscle twitching or tensing that can lead to uncontrolled movements that significantly impact their physical and emotional quality of life. Isolated focal dystonias affect one part of the body, with common examples including laryngeal dystonia affecting the vocal cords when speaking, blepharospasm causing involuntary eyelid twitching, cervical dystonia causing neck muscles to contract and twist pain in the head and writer’s cramp dystonia affecting the fingers during writing. About 35 out of 100,000 people have isolated or primary dystonia, a prevalence likely underestimated due to difficulties in diagnosing the disease.

Botulinum toxin injections are considered the first-line treatment for focal dystonias. The injection paralyzes the affected muscle, aiming to prevent involuntary contractions. The effects are usually temporary and an injection often needs to be repeated every three to four months for life.

Only about 60% of patients with dystonia have these injections, and not all patients respond to treatment. This may be due to underlying biological reasons, the complexity of the symptoms, or the experience and expertise of the injecting physician. This can lead to the overtreatment of patients who would not respond to botulinum toxin in the first place, and the undertreatment of patients who may respond but never seek treatment or may stop treatment prematurely.

This great variability led Dr Simonyan and his team to turn to artificial intelligence to find a solution to objectively assess the benefits of botulinum toxin injections before initiating treatment.

Predicting Treatment Efficacy with MRIs

In the new study published in Annales de Neurologie, the research team trained a deep learning algorithm to analyze brain MRI scans of 284 patients with four types of dystonia who responded and did not respond to injections of botulinum toxin. The effectiveness of the injections was determined by medical records and feedback from physicians and patients.

DystoniaBoTXNet revealed that there were eight regions of the brain as a neural biomarkers of the effectiveness of injections. Using this newly discovered biomarker, DystoniaBoTXNet achieved an overall accuracy of 96.3% in predicting the efficacy of botulinum toxin in focal dystonia, with a sensitivity of 100% and a specificity of 86.1%. The platform achieved these results in 19.2 seconds per case.

“Our study shows that DystoniaBoTXNet can be a very robust and easy-to-use AI platform that physicians can use for refined clinical decisions. An individual AI-generated predictive result of botulinum toxin injections prior to treatment delivery can aid in more accurate patient selection, refine treatment regimen, or other benchmarks, thereby increasing toxin utilization botulinum for patients with dystonia,” Dr Simonyan offered as an example. “On the other hand, the platform can predict that the patient has a very low probability of benefiting from injections, which would be informative for the doctor to consider other treatment options instead of overtreatment with the toxin. botulinum.”

Artificial Intelligence Tackles Dystonia Diagnosis and Treatment Problems

The DystoniaBoTXNet tool is the second artificial intelligence platform invented by Dr Simonyan and his team to help with clinical decision-making. This study builds on previous research by this team that reported the success of a separate platform called DystoniaNet that was able to diagnose dystonia from patient MRI scans with an accuracy of 98.8% in 0, 36 seconds. Dystonias are notoriously misdiagnosed and underdiagnosed, with some studies showing that it can take patients up to 10 years to receive a correct diagnosis.

Interestingly, five of the eight regions identified as a neural biomarker of botulinum toxin efficacy by DystoniaBoTXNet in the new paper were previously found to be the diagnostic biomarker of DystoniaNet. For years, clinicians have had no objective biomarkers to identify these conditions, so the overlapping regions may provide additional evidence for their roles in dystonia that scientists can better explore.

With further study of both platforms, the hope is that one day a patient may walk into a clinician’s office after experiencing symptoms and undergo an MRI and receive a diagnosis via DystoniaNet; Then DystoniaBoTXNet can help determine if botulinum toxin treatment would work for them.

To achieve this goal, researchers are embarking on multiple clinical trials within Mass General Brigham to determine the usefulness of these tools in the clinic. Another future direction of work is to investigate whether additional treatments, such as deep brain stimulation, could be predicted by an AI-based tool.

Continue Reading
Advertisement