What do people affected by MS think about using AI in research and healthcare?

What does artificial intelligence (AI) have to do with patient-reported outcomes? How could it improve healthcare for people with MS? And what are the challenges of using AI? These are some of the questions explored in a recent article authored by members of the Global Patient Reported Outcomes for MS (PROMS) initiative, including people with MS.

Read the article here: Artificial intelligence and science of patient input: a perspective from people with multiple sclerosis

Everyone living with MS has a different experience of the condition and the impact that it has in their daily lives. Standard clinical tests do not always capture the full extent of these challenges. Patient reported outcome measures (PROMs) – tools such as questionnaires where people report their own symptoms, or passive sensors measuring aspects of daily living – can provide better insights into invisible symptoms and the changing nature of MS. Using PROMs from research to clinic can provide a more personalised approach to treatment and care, but despite their potential, PROMs are not yet widely integrated into healthcare systems.

This multi-stakeholder global PROMS Initiative, jointly led by MSIF and the European Charcot Foundation with the Italian MS Society acting as lead agency for and behalf of the Global MSIF Movement aims to improve the quality of life of people affected by MS by maximizing the impact of PROMs in MS research and clinical care. You can read more about this initiative and its activities here: https://proms-initiative.org/

How can MS research benefit from applying AI to patient-reported data?

Globally, there is a huge amount of data relating to MS, coming from hundreds of thousands of individuals. Some of this is demographic and clinical data, and some will have been reported by people with MS, for example through assessments in the clinic or by answering surveys in patient registries. Analysing and finding patterns in large, complex datasets can be difficult and time-consuming – and this is where AI can help.

By applying AI models to large datasets of patient-reported and clinical information, new insights might be gained about how symptoms change over time and in different MS populations and what this means for progression of the disease. Greater understanding of what is happening in MS ‘under the surface’ can lead to more effective ways of managing the condition, for example through early detection of relapses or, perhaps more importantly, progression irrespective of relapse (PIRA), which can be more insidious and difficult to assess.

What we can learn by applying AI to datasets is only as good as the data we have collected. Without patient-reported data from broader, more diversified segments of the MS population, any patterns detected may not be applicable or relevant to the entirety of the global MS community. The dataset on which an AI model is trained, therefore, may not reflect the real differences that may arise based upon geography, ethnicity, and other demographic factors. In addition, common symptoms of MS, such as cognitive dysfunction, may affect a person’s ability to provide data that accurately reflects their condition, if, for example, a questionnaire is too complex to understand. Relying on AI could lead to widening inequalities, so it is important we consider how representative our data is.

How could AI be used to improve an individual’s care?

On a smaller scale, AI can analyze a person’s individual health data. If people use wearable devices or smartphone apps, these can continuously collect data on aspects such as mobility, and sleep patterns, as well as daily temperature or atmospheric pressure readings. Into this data collection could be added feelings, use of medications and lifestyle factors such as diet and exercise.

Angela White, co-author, USA

“People with MS know that fatigue is a huge challenge to daily living. Patterns that are discovered by AI analysis of patient-reported data over time could provide insights into which factors increase or decrease levels of fatigue – whether they are environmental or aspects that can be influenced by the person through lifestyle changes or self-management. Importantly, if the AI model identifies consistent changes in data patterns over time, this might signal an underlying change in the condition, such as progression of MS, prompting referral to a healthcare professional or condition specialist.”

What are the challenges and ethical considerations?

Health interventions that involve AI will only make it successfully into the clinic if they are fully acceptable by pwMS as well as their clinicians and care providers. PwMS want to see that their healthcare professional is drawing on their experience and intuition as part of the decision-making process. AI might complement the role of healthcare professionals, but should not replace them.

Thinking globally, remote monitoring and digital technology that uses AI could help fulfil a need caused by a lack of specialist healthcare professionals in some settings. Yet the benefits of AI-assisted technology may not be available to everyone. The accessibility and costs of the technology – including any supporting infrastructure, personnel or regulatory requirements needed to integrate AI systems into the current system – may provide a barrier for lower socioeconomic populations or countries where MS is relatively rare.

A critically important consideration relates to privacy and security of personal health data. People must have a clear understanding of the purpose for which their data might be used and give consent for their data to be used in this way, and their data must be stored securely. It is important to remember, too, that analysis of data by AI may produce consequences outside of health systems, including decisions regarding pensions, disability payments, and other services. For pwMS who rely on access to treatment, therapy, and other forms of support, there is a constant concern that this support could be restricted based on incorrect interpretation of personal data, whether by human or AI decision-making.

How can we guard against unintended consequences?

Helga Weiland, co-author, South Africa

“The PROMS Initiative will help ensure that people with MS have space to raise ethical questions in relation to the growing use of AI as it applies to large, patient-reported datasets. We will work closely with other members of this multi-stakeholder initiative to consider the impact of any recommendations on all aspects of the life of a person with MS.”

The preferences of pwMS and acceptability for innovative digital interventions (patient preference information or PPI) will be instrumental for regulating the use of AI approaches in clinical practice.

As a community of pwMS, we urge that the use of AI in patient care proceeds with caution as well as anticipation. For care to maximize quality of life, it must be holistic, encompassing emotional, psychological and social as well as physical aspects. Any benefits from AI must not come at the expense of damage to the relationship between clinicians and the people they care for, widening health inequity, or worsening health and social outcomes for pwMS. Only by working collaboratively will we ensure that future advances in AI safeguard individuals and be acceptable to the whole MS community.

Access the full publication here: Artificial intelligence and science of patient input: a perspective from people with multiple sclerosis

This lay article was authored by members of the PROMS Initiative Engagement Coordination Team. Learn more at: MS Engagement Coordination Team | proms-initiative.org