top of page

Digital healthin multiple sclerosis care

  • Writer: Milan Walraevens
    Milan Walraevens
  • Jan 27, 2021
  • 7 min read

Updated: May 13

The need for personalized medicine in multiple sclerosis

Research in multiple sclerosis (MS) treatments has brought tremendous progress. Since the launch of the first drug in 1993, the health of MS patients, expressed in quality-adjusted life years (QALYs), has increased by 66% thanks to the availability of more than a dozen disease-modifying drugs (DMTs)1. In addition, several new drugs are being developed for the relapsing and progressive forms of MS. However, despite these tremendous efforts, one in four patients currently begin their therapeutic pathway on a suboptimal treatment2.


Today, the primary endpoints for DMTs in clinical trials focus on slowing down of relapses and clinical disease progression. However, what lies ‘below the surface’ (subclinical) is just as important as what we see ‘above the surface’ (clinical). Subclinical progression can be identified on magnetic resonance imaging (MRI) by the presence of (new) lesions and atrophy in the brain and spinal cord. These biomarkers are becoming increasingly important as a therapeutic target, as they have been shown to be predictive of irreversible clinical damage3. Recent recommendations for the use of DMTs in MS management suggest initiating therapy sooner in newly diagnosed patients and administering high-efficacy medication to patients with very active forms of the disease 4,5. In addition, a treatment switch is advised in case of persisting disease activity 3,5.


As in oncology, and to some extent in diabetes, personalized medicine will have an enormous impact on neurological disorders such as MS. Indeed, it has been demonstrated that identifying the optimal MS therapy for a patient from the start can improve their long-term health by up to 34% 1. To put things in perspective, this is the equivalent of half of the pharmacological progress made over the last 30 years by the development of new disease-modifying treatments 1. Personalized medicine offers the potential to optimize treatment decisions and increase the impact of treatments by more than 50%, by assessing both disease activity (clinical and subclinical) and evaluating the risk of side effects 1.


Thanks to the pharmacological innovations during the last 30 years, people with MS are able to manage their chronic condition much better. Improvements of the same magnitude can be achieved in the upcoming 5 years by transitioning to more personalized management of MS. However, applying treatment guidelines on an individual patient basis will need a more data-driven decision-making pathway, including remote monitoring and MRI quantification.


The need for remote patient monitoring (especially in times like today)

During neurology consultations, relapses, symptoms, and the general well-being of MS patients are evaluated and discussed. However, due to the relatively long period of time between neurology visits, patients often fail to recall more distant events, resulting in a biased and limited reporting of symptoms. Hence, despite the significant role of managing and reducing relapses in the care of MS patients, many remain unreported 6. Indeed, according to a UK survey, one in two people with MS fail to report a relapse, highlighting the importance of close monitoring 7.


In this context, remote patient monitoring tools allow people with MS to log symptoms in a standardized format on a regular basis. As a result, for every individual with MS, care teams have access to their symptoms, treatment overviews, custom pre-consultation questionnaires, and tests on cognition, disability, fatigue, etc.    


The need for software-assisted MRI monitoring

For many years, MRI has been a crucial tool for the diagnosis and monitoring of MS. Indeed, MRI is incorporated into the diagnostic criteria, is consistently used in clinical trials, and is an important part of the treatment guidelines. Hence, people with MS typically undergo a yearly MRI scan to evaluate the presence of disease activity or progression. 


Nowadays, clinical MRI scans can be obtained with a very high resolution in a matter of minutes. Based on these 3D scans of the brain (and spinal cord) new and enlarging lesions are identified between follow-up scans. In addition, brain shrinkage is visually assessed in comparison to last year’s scan. The result of this assessment is included in the radiological report.


The trained radiological eye is an extraordinary pattern recognition tool that can instantly compare a scan to the thousands of scans that were previously analyzed by the radiologist’s brain. However, as it is much harder to visually quantify brain changes, radiological reports are typically qualitative descriptions. This unique radiological expertise is very complementary to artificial intelligence (AI) tools. These AI-driven tools don’t have the expertise of radiologists, but they do have the capability to analyze millions of pixel intensities within seconds and to quantify abnormalities and brain structures.


In MS, especially in patients with many existing brain lesions, quantifying changes compared to the previous scan is tedious and observer-dependent. However, combined with assistive AI software in clinical practice, the sensitivity of radiologists to detect disease activity increases by up to 300% 8,9. Similarly, it is extremely difficult to detect and quantify brain volume loss when visually comparing two MRI scans. Again, by combining radiological expertise with the power of AI, brain atrophy can today be measured reliably in a clinical setting.


Applying treatment guidelines on individual patients

Over the past decades, several guidelines for diagnosis and monitoring of MS have been published, including the McDonald, the American Academy of Neurology (AAN) criteria, and Brain Health Recommendations 3,10,11. These typically include a combination of disability measures (through the EDSS), relapses as well as the assessment of disease activity and progression on MRI. In addition, to assess treatment response, different scoring systems have been developed, most of which take into account relapses and the presence of new and/or enlarging lesions 12.


With the emergence of more efficacious DMTs, a ‘no evidence of disease activity’ (NEDA) approach has been introduced as the ultimate goal. The NEDA concept initially identified suboptimal treatments by the presence of relapses, worsening of disability, or lesion change (known as NEDA-3) 13,14. However, in recent years it has become clear that brain atrophy is also an important biomarker, as high-efficacy DMTs are able to normalize the accelerated brain volume loss in MS patients 15. ‘Silent’ progression of MS caused by brain atrophy is a major contributing factor of long-term disability in patients without relapses, suggesting that the underlying process of secondary progressive MS likely begins far earlier than is generally recognized 16.


The relevance of brain atrophy in treatment monitoring is reflected in recent guidelines and recommendations from the Magnetic Resonance Imaging in Multiple Sclerosis (MAGNIMS) research group and the Consortium of Multiple Sclerosis Centers (CMSC), as well as scoring systems such as Rio-4 and NEDA-4; and range from qualitative assessment to quantitative cutoffs 17-20. Indeed, the inclusion of brain volume changes increases the sensitivity to predict treatment responses and can result in a threefold higher probability in detecting treatment failure, thus, reducing the average time a patient is on suboptimal treatment from 3.9 to 1.3 years 21,22.


Digital health in multiple sclerosis care

Thanks to recent pharmacological innovations, the availability of multiple DMT’s, and modern technology, we’re entering the era of data-driven decision-making, patient empowerment, and personalized medicine for people with MS.  Today, all the pieces of this complex personalized care puzzle are on the table and will be brought together by digital health. 


icometrix strives to transform patient care through data-driven insights and personalized medicine, supported by artificial intelligence. icometrix’ cloud-based AI solutions assist patients and healthcare practitioners in the management of neurological conditions and securely connect care teams. icometrix supports pharmaceutical companies in phase I-III and Real-World Evidence (RWE) studies through imaging and data services, and digital health strategy.icobrain, an AI software solution that quantifies clinically meaningful changes in MRI scans, is a CE-marked and FDA-cleared tool to help detect disease progression in individual patients and assist healthcare professionals in adopting treatment guidelines.icompanion, an mHealth app for patients and integrated web platform for healthcare professionals, is a CE-marked remote monitoring solution that captures meaningful changes in clinical symptoms, cognition, disability, and fatigue.


References


  1. Hult KJ et al. (2017). Measuring the Potential Health Impact of Personalized Medicine: Evidence from MS Treatments. National Bureau of Economic Research. doi:10.3386/w23900

  2. Sa JS et al. (2014). Relapsing–Remitting Multiple Sclerosis: Patterns of Response to Disease-Modifying Therapies and Associated Factors: A National Survey, Neurol Ther. 3(2): 89–99.

  3. Giovannoni, G., et al. (2015). Brain health: time matters in multiple sclerosis. https://doi.org/10.21305/msbh.001

  4. He A. Timing of high-efficacy therapy for multiple sclerosis- a retrospective observational cohort study. Lancet Neurol. 2020 Apr;19(4)-307-316. doi- 10.1016/S1474-4422(20)30067-3

  5. Costello K, et al. (2019). The use of disease-modifying therapies in multiple sclerosis: principles and current evidence. A consensus paper by the Multiple Sclerosis Coalition.

  6. Nazareth TA, et al. (2018). Relapse prevalence, symptoms, and health care engagement: patient insights from the Multiple Sclerosis in America 2017 survey. Mult Scler Relat Disord. doi: 10.1016/j.msard.2018.09.002.

  7. Duddy M, et al. The UK patient experience of relapse in Multiple Sclerosis treated with first disease modifying therapies. Mult Scler Relat Disord. 2014 Jul;3(4):450-6.

  8. Dahan, A, et al. (2018). Computer-Aided Detection Can Bridge the Skill Gap in Multiple Sclerosis Monitoring. Journal of the American College of Radiology: JACR, 15(1 Pt A), 93–96.

  9. Sima DM, et al. On the use of icobrain's prepopulated radiology reporting template for multiple sclerosis follow-up. ECR 2020 / C-11342

  10. Thompson AJ, et al. (2018). Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol. 2018 Feb;17(2):162-173. doi: 10.1016/S1474-4422(17)30470-2.

  11. Rae-Grant A, et al. (2018). Practice guideline recommendations summary: Disease-modifying therapies for adults with multiple sclerosis: Report of the Guideline Development, Dissemination, and Implementation Subcommittee of the American Academy of Neurology. Neurology. 24;90(17):777-788. doi: 10.1212/WNL.0000000000005347.

  12. Trojano M, et al. (2017). Treatment decisions in multiple sclerosis – insights from real-world observational studies. Nat Rev Neurol. 13(2):105-118.

  13. Havrdova E, et al. (2009). Effect of natalizumab on clinical and radiological disease activity in multiple sclerosis: A retrospective analysis of the Natalizumab Safety and Efficacy in Relapsing–Remitting Multiple Sclerosis (AFFIRM) study. Lancet Neurol3 8: 254–260.

  14. Banwell B, et al. Editors’ welcome and a working definition for a multiple sclerosis cure. Mult Scler Relat Disord 2013; 2: 65–67.

  15. Ontaneda et al. (2020). Determining the effectiveness of early intensive versus escalation approaches for the treatment of relapsing-remitting multiple sclerosis: The DELIVER-MS study protocol. Contemporary Clinical Trials, 95, 106009.

  16. Cree, et al. (2019), University of California, San Francisco MS-EPIC Team. Silent progression in disease activity-free relapsing multiple sclerosis. Annals of Neurology 85(5), 653–666.

  17. Sastre-Garriga J, et al. (2020). MAGNIMS consensus recommendations on the use of brain and spinal cord atrophy measures in clinical practice. Nat Rev Neurol. 16(3):171-182. doi: 10.1038/s41582-020-0314-x.

  18. Montalban X, et al. (2018). ECTRIMS/EAN Guideline on the pharmacological treatment of people with multiple sclerosis. Mult Scler. 24(2):96-120. doi: 10.1177/1352458517751049.

  19. Kappos L, et al. (2016). Inclusion of brain volume loss in a revised measure of 'no evidence of disease activity' (NEDA-4) in relapsing-remitting multiple sclerosis. Mult Scler. 22(10):1297-305. doi: 10.1177/1352458515616701.

  20. Pérez-Miralles FC, et al. (2020). Adding brain volume measures into response criteria in multiple sclerosis: the Río-4 score. Neuroradiology. doi: 10.1007/s00234-020-02604-8. Epub ahead of print.

  21. Sá, MJ, et al. (2014). Relapsing-remitting multiple sclerosis: patterns of response to disease-modifying therapies and associated factors: a national survey. Neurology and therapy, 3(2), 89–99.

  22. Río J, et al. (2012). Change in the clinical activity of multiple sclerosis after treatment switch for suboptimal response. Eur J Neurol. 19(6):899-904.                                                                                                       



bottom of page