Parkinson’s disease (PD) is the most common neurodegenerative movement disorder, with a multifactorial etiology, a heterogeneous manifestation of motor and non-motor symptoms, and no cure, affecting 10 million people worldwide; a figure expected to nearly double by 2040. PD is often missed, or misdiagnosed, as early symptoms are subtle and common with other diseases, allowing for considerable damage to occur before treatment. Effective, symptomatic treatments, relying mainly on dopaminergic medications, are available, yet selecting the optimal regimen is usually a lengthy, “trial and error” process, leading to critical, costly non-adherence. Overall costs to Europe have been estimated at €13.9 billion annually, with the cost per patient increasing with severity. AI predictive and precision medicine models, and new monitoring technologies, hold the potential to improve PD diagnosis and care. Personalized risk assessment can lead citizens to suitable healthcare pathways early, enabling timely diagnosis and treatment initiation, while individualized prediction of disease progression and drug response could foster treatment optimization and adherence, improving patients’ quality of life (QoL) and lowering costs associated with advanced disability.
Digital biomarkers are objective, quantifiable measurements collected through various digital devices, such as smartphones, wearables, or specialized sensors. These biomarkers can provide continuous and non-invasive monitoring of the disease’s progression. By analyzing real-time data from wearable devices or other sources, the models can provide personalized risk assessments and predictions for patients, indicating the likelihood of disease progression or the severity of symptoms over time. The predictions generated by AI models can assist healthcare professionals in making informed decisions regarding treatment plans, medication adjustments, or the need for early interventions. By leveraging these predictions, clinicians can potentially improve patient outcomes and tailor their management strategies more effectively.
The model designed by AINIGMA Technologies estimates the time to higher disability transition, defined as significant motor aggravation, expressed by significant change in the UPDRS Part III scale. Other disability targets can also be explored, including the transition to H&Y Stage 3, or the occurrence of other disease severity milestones (i.a., cognitive dysfunction, hallucinations, freezing, and others, mentioned in the respective study annex). The model is able to make personalized predictions based on both cross-sectional patient characteristics obtained at specific time points and on available longitudinal variation patterns of characteristics (i.e., measured by HCPs during follow-up visits, tracked via dBMs in daily living, or self-reported by patients).
Technologies we use:
