Progression subtypes in Parkinson’s disease identified by a data driven multi cohort analysis


Share this post

Choose a social network to share with, or copy the shortened URL to share elsewhere

This is a representation of how your post may appear on social media. The actual post will vary between social networks

Discovering Subtypes of Parkinson's Disease Progression

Parkinson's disease (PD), a neurodegenerative disorder, is characterized by a variety of motor symptoms, cognitive impairment, autonomic symptoms, and neuropsychiatric symptoms. Thereby, it is known for its complexity and variability in progression among patients. This heterogeneity complicates patients counseling and inflates the number of patients needed to test potential neuroprotective treatments in clinical trials. However, a study conducted by a team of researchers from several institutions across Europe has made significant strides in understanding this variability by identifying distinct subtypes of PD progression. This new research provides insights that could change how we approach treatment and clinical trials for PD.

Methodology and Findings

Using a data-driven approach, the researchers analyzed multimodal longitudinal data from three large PD cohorts, leveraging advanced machine learning techniques to identify progression subtypes. The study utilized a Latent Time Joint Mixed-Effects Model (LTJMM) to align patients on a common disease timeline, and then applied a method called Variational Deep Embedding with Recurrence (VaDER) to categorize the subtypes.

Two clear subtypes emerged from the analysis: a fast-progressing subtype and a slow-progressing subtype, each characterized by distinct patterns of symptom progression, including motor and non-motor symptoms, survival rates, and responses to treatments. These findings were validated in two external cohorts of PD patients, thereby demonstrating a great generalizability.

Trajectories of fast-progressing and slow-progressing patients for several motor- and non-motor outcomes. The trajectories show a good separation between subtypes with only minor differences at baseline.
Progression of several PD symptoms for the fast-progressing and slow-progressing subtype.

Implications for Clinical Trials and Treatment

The identification of these subtypes has profound implications for clinical trials and treatment strategies. By categorizing patients into more homogenous groups based on their progression subtype, clinical trials can be designed with a greater degree of precision. The study found that enriching trial cohorts with fast-progressing patients could reduce the required sample size by up to 43%, significantly enhancing the efficiency and effectiveness of these studies.

Moreover, this research highlights the potential for personalized medicine in treating PD. Understanding a patient’s subtype could help allow clinicians to tailor therapies that are more suited to their specific progression pattern, potentially slowing the disease's advancement and improving quality of life.

Digital Gait Assessments and Biomarkers

An interesting aspect of the study was the use of digital gait assessments to objectively quantify the gait patterns observed in PD patients. Using two acceleration sensors attached to the shoes of the patients, the researchers were able to identify distinct patterns of gait impairment in the progression subtypes. In detail, patients of the fast-progressing exhibited lower gait speed, shorter stride length, a larger toe off angle, lower toe clearance, shorter relative swing time, higher relative stance time and a lower heel clearance.

Thereby, digital gait analysis may offer a promising tool for both diagnosing the progression subtype and monitoring the disease's progression.

Scatter plot of several digital gait biomarkers depicting a more severe gait impairment in the fast-progressing subtype.
Progression of several gait parameters obtained by a sensor-based digital gait assessment for the fast-progressing and slow-progressing PD subtype.

The Road Ahead

While this study marks a significant advancement in our understanding of Parkinson's disease, the researchers acknowledge that more work is needed. The next steps involve finding new biomarkers to precisely predict and categorize disease progression in individual PD patients. Therefore, digital biomarkers obtained from sensor-based or video-based assessments like gait analysis, speech recordings or hypomimia detection may be promising tools as they provide easy accessible biomarkers.


The researchers provide compelling evidence for the existence of a fast- and slow-progressing subtype in PD as their conclusions are derived from prospective, longitudinal cohorts including more than 1,100 patients and were replicated in three distinct cohorts. Their findings enhance the understanding of PD progression heterogeneity and highlight the potential of digital gait assessments to objectively monitor motor symptom progression. Finally, they offer a promising strategy to optimize clinical trial designs or investigate new therapeutic strategies in PD subtypes.

Please sign in or register for FREE

If you are a registered user on Research Communities by Springer Nature, please sign in

Follow the Topic

Parkinson's disease
Life Sciences > Biological Sciences > Neuroscience > Neurological Disorders > Parkinson's disease
Artificial Intelligence
Mathematics and Computing > Computer Science > Artificial Intelligence
Machine Learning
Mathematics and Computing > Computer Science > Artificial Intelligence > Machine Learning
Life Sciences > Health Sciences > Clinical Medicine > Neurology
Life Sciences > Biological Sciences > Neuroscience
Neurodegenerative diseases
Life Sciences > Biological Sciences > Neuroscience > Neurological Disorders > Neurodegenerative diseases

Related Collections

With collections, you can get published faster and increase your visibility.

Clinical research in neurological disorders

The editors at Nature Communications, Communications Medicine, npj Parkinson’s disease and Scientific Reports invite original research articles on the clinical aspects of neurological disorders and neurodegenerative diseases.

Publishing Model: Open Access

Deadline: Jun 30, 2024

Invasive and non-invasive neuromodulation in movement disorders

This Collection highlights cutting-edge advances in research on neuromodulation therapies for Parkinson’s Disease and related movement disorders.

Publishing Model: Open Access

Deadline: Jun 10, 2024