Amyotrophic Lateral Sclerosis (ALS), also known as Motor Neuron Disease (MND) is a rare neurodegenerative disease. Over 400 people are living with MND in Ireland. Due to the lack of one specific test to identify the disease, diagnosis can be a rather long process of medical examinations. This process alone can be exhausting for people with ALS and their family. It is important for patients to have support from informal caregivers, such as family members or close friends. However, these new duties associated with caregiving, as well as the condition of their loved ones may have a great impact on the caregivers’ quality of life.
A recent study carried out by FutureNeuro Phd Candidate Anna Markella Antoniadi, Professor Orla Hardiman, Professor Catherine Mooney and others has found new factors relevant to caregiver quality of life in ALS and evidence of the potential of Artificial Intelligence (AI) to support the decision-making process in healthcare.
FutureNeuro Phd Candidate Anna Markella Antoniadi and spoke to us about the findings..
What was the research/study about? This study was based on information collected (a) via interviews with people with ALS and their primary caregiver on a variety of topics (such as demographic, financial, psychological, use of services), and (b) through the Irish ALS Registry, which contains clinical details on the patients. The aim was to analyse all this information, and the complex relationships that associate them with each other and to identify which aspects are connected with the caregivers’ quality of life. Our next goal was to use part of this information in order to develop a computer system that will alert clinicians when a caregiver may experience low quality of life, as part of the clinical workflow; this is known as a clinical decision support system.
What was the need in ALS/MND care you wanted to address? It is important for patients to have support from informal caregivers, such as family members or close friends. However, these new duties associated with caregiving, as well as the condition of their loved ones may have a great impact on the caregivers’ quality of life. Quality of life is defined as the general well-being of a person, and it includes the individual’s perception of their physical, social, and psychological state. The aim of this study is to examine a variety of features and discern their link to caregiver quality of life, which will inform the provision of the necessary supports to maintain or improve quality of life.
How was it carried out? All the information we had available from the ALS Registry and from the interviews that people with ALS and their caregivers had kindly participated to, we combined them together and then we tried to create a model of the caregivers’ quality of life. For this we used Machine Learning: a popular field of Computer Science that includes a variety of techniques that can be trained on large amounts of information and “learn” how to predict a specific outcome. In our case, the models were trained on the information we had from the people with ALS and their caregivers, and “learned” to predict whether they experience high or low quality of life. It is important to clarify that the Machine Learning models “learn” from existing patients, and they can predict the outcome for future patients.
What did you learn from it? That the caregiver’s existential well-being and their burden are highly related to their overall quality of life. Additionally, caregiver quality of life is associated to the patient’s depression and employment before the onset of symptoms. We also managed to create a model as a proof-of-concept for the future development of a clinical decision support system to alert clinicians when a caregiver is experiencing low quality of life. For that model we used a small subset of the total information so that it could be easy to collect in a clinical setting.
What will this mean for a caregiver and people living with ALS? Knowledge of the factors that are associated with the caregivers’ quality of life can lead to more tailored support for them. The types of support could be financial, psychological, education relating to the condition, or related to the patient’s care and supports (e.g. equipment, therapists, access to services, respite care). The clinical decision support system we are developing, can alert clinicians if a caregiver’s quality of life is lower. This alert would facilitate the initiation of a discussion with them and the healthcare team to identify ways to assist them.
What’s next? The clinical decision support system is under development, but it still requires evaluation. This would include user studies to improve its usability for the clinicians that will be using it and for the improvement of the model, as well as evaluation on new patient information. Additionally, we are also working on a similar model to predict the quality of life of the person with ALS, and we aim to incorporate them in one system that will assess the well-being of both.