Leveraging the Potential of Digital Technology for Better Individualized Treatment of Parkinson's Disease

Abstract

Recent years have witnessed a strongly increasing interest in digital technology within medicine (sensor devices, specific smartphone apps) and specifically also neurology. Quantitative measures derived from digital technology could provide Digital Biomarkers (DMs) enabling a quantitative and continuous monitoring of disease symptoms, also outside clinics. This includes the possibility to continuously and sensitively monitor the response to treatment, hence opening the opportunity to adapt medication pathways quickly. In addition, DMs may in the future allow early diagnosis, stratification of patient subgroups and prediction of clinical outcomes. Thus, DMs could complement or in certain cases even replace classical examiner-based outcome measures and molecular biomarkers measured in cerebral spinal fluid, blood, urine, saliva, or other body liquids. Altogether, DMs could play a prominent role in the emerging field of precision medicine. However, realizing this vision requires dedicated research. First, advanced data analytical methods need to be developed and applied, which extract candidate DMs from raw signals. Second, these candidate DMs need to be validated by (a) showing their correlation to established clinical outcome measures, and (b) demonstrating their diagnostic and/or prognostic value compared to established biomarkers. These points again require the use of advanced data analytical methods, including machine learning. In addition, the arising ethical, legal and social questions associated with the collection and processing of sensitive patient data and the use of machine learning methods to analyze these data for better individualized treatment of the disease, must be considered thoroughly. Using Parkinson's Disease (PD) as a prime example of a complex multifactorial disorder, the purpose of this article is to critically review the current state of research regarding the use of DMs, discuss open challenges and highlight emerging new directions.

Keywords: Artificial Intelligence; Parkinson's Disease; digital biomarker; digital health; precision medicine.

Figure 1

Stagewise process from development of Digital Biomarkers until their integration into routine healthcare.

Figure 2

Machine learning (ML) refers to an approach, in which a statistical model is fit to data. After this “learning” process the model encompasses a “pattern” or a “rule.” ML can be supervised or unsupervised. In supervised learning, we train a model based on a dataset with hopefully many observations, each containing a (possibly large) number of features, coupled with the known clinical outcome (e.g., drug response, see example on the right). Based on the established model predictions for patients that were not part of the training data can be made (such as Mr. Smith). Machine learning models can make accurate predictions, even if there is no single biomarker that discriminates patient groups. For example, in the Figure neither blood pressure nor the digital biomarker alone allows for discriminating drug responders from non-responders. However, both features together admit a perfect separation (diagonal line). Notably, supervised learning is not restricted to classification, but also continuous outcomes can be predicted. As opposed to supervised learning, unsupervised learning aims at inferring patterns from data without having access to a label, such as phenotype. Many machine learning models can discard features that are irrelevant for the prediction (sparse models). The set of features selected by the algorithm then establishes a biomarker signature.