![aged hands holding transparent orchid pot](https://media.post.rvohealth.io/wp-content/uploads/sites/3/2024/07/AI-Parkinsons-Stocksy_txp5e1df3a8roy300_Medium_3774298-Header-1024x575.jpg)
- A machine-learning study at Weill Cornell Medicine was able to classify Parkinson’s disease into three subgroups, a development with the potential to effectively target patients with treatments specific to their disease’s progression.
- By analyzing data from an existing study, researchers split the cohort into Rapid Pace, Inching Pace, and Moderate Pace — an approach that acknowledges the heterogeneous nature of the disease.
- Experts say the findings are logical and hold great promise, but caution that larger populations need to be explored to create more accurate models.
On the heels of new research from Boston University showing that an artificial intelligence model was able to predict a person’s chances of developing Alzheimer’s disease, Weill Cornell Medicine researchers have been able to classify Parkinson’s disease into three subtypes using machine learning.
The findings — which appear in
Researchers at Cornell analyzed data from 406 people who participated in the Parkinson’s Progression Markers Initiative (PPMI), which is an international observational study that “systematically collected clinical, biospecimen, multi-omics, and brain imaging data of participants.”
They developed a deep-learning model called deep phenotypic progression embedding (DPPE), which was able to “holistically” model “multidimensional, longitudinal progression data of the participants,” as the authors explain in the study paper.
The authors further note that in recent years there has been a move toward observing Parkinson’s as a condition with heterogeneous symptoms and progression.
Not all individuals with Parkinson’s will have the same experience, in other words, and therefore treatment could be much more tailored to suit different patients’ needs.
The three subgroups of Parkinson’s identified by the machine learning are based on the pace of the disease’s progression:
- Rapid Pace (PD-R), which is marked by rapid progression of symptoms. Of the cohort observed, 54 people (13.3%) had this subtype.
- Inching Pace (PD-I), which has mild baseline symptoms and relatively mild progression. Of the cohort observed, 145 people (35.7%) had this variety.
- Moderate Pace (PD-M), which is characterized by mild baseline symptoms and moderate progression. This was the largest portion of the cohort observed, with 207 people (50.9%) living with this form of Parkinson’s.
The study authors note that their classifications “highlighted the necessity of treating [Parkinson’s disease] subtypes as unique sub-disorders within clinical practice, where our pace subtypes could inform patient stratification and management.”
By identifying specific varieties of the disease, clinical approaches could be much more targeted and effective.
Clemens Scherzer, MD, a physician-scientist and the Stephen & Denise Adams Professor of Neurology at Yale School of Medicine, who was not involved in the study, told Medical News Today that the study’s computational findings were very interesting, but cautioned that they are extremely preliminary and need larger populations to develop and validate such classifiers.
“The goal of precision medicine is to predict the disease course in a patient and to therapeutically intervene ahead of time to prevent complications from developing. To achieve this we need to identify the disease driver in each patient and develop targeted therapeutics,” Scherzer pointed out.
“For example, we have found that 10% of Parkinson’s patients in the [United States] have
Nevertheless, Daniel Truong, MD, a neurologist and medical director of the Truong Neuroscience Institute at MemorialCare Orange Coast Medical Center in Fountain Valley, CA, and editor in chief of the Journal of Clinical Parkinsonism and Related Disorders, who also was not involved in the study, told MNT that the subgroupings are a logical, systematic approach to treating Parkinson’s.
“For instance, patients with the Rapid Pace subtype (PD-R) might benefit from more aggressive therapeutic strategies and closer monitoring compared to those with the Inching Pace subtype (PD-I), who may need less intensive management. Knowledge of a patient’s subtype can guide the selection of medications, including the potential repurposing of existing drugs like metformin, which the study suggests might be particularly beneficial for the PD-R subtype.”
– Daniel Truong, MD
“It allows predictive and preventive healthcare to be designed for each subtype,” Truong explained.
“Early intervention may be required for rapid progressive patients. This is crucial for managing symptoms before they become severe and debilitating. Subtyping helps in stratifying patients based on their risk, enabling more focused and effective clinical trials for new treatments, as well as better allocation of healthcare resources,” he added.
Steven Allder, BMedSci, BMBS, FRCP, DM, a consultant neurologist at Re:Cognition Health, not involved in the study, agreed that advance identification of different subgroups would allow medical professionals to work on specific treatment plans for each one.
He listed the possible treatments for each, noting:
- Inching Pace (PD-I): “Treatments could focus on maintaining quality of life and preventing symptom progression through lifestyle modifications, physical therapy, and possibly neuroprotective drugs.”
- Moderate Pace (PD-M): “These patients exhibit moderate disease advancement. They might benefit from a combination of pharmacological treatments to manage symptoms and slow progression, such as dopamine agonists, MAO-B inhibitors or other disease-modifying therapies.”
- Rapid Pace (PD-R): “This subtype progresses quickly and often involves cognitive deficits. Metformin has shown promise in improving symptoms in this group, especially related to cognition and falls. Early intervention with Metformin and other neuroprotective agents could be crucial for managing this subtype.”
Allder’s main concern about using machine-learning technology to predict diseases such as Parkinson’s revolved around the accessibility of such a tool for people who need it.
“I don’t foresee problems with the AI model, but I do foresee problems with patients accessing it,“ he told us.
“While AI models are powerful tools for identifying disease subtypes and predicting progression, there are potential issues related to patient access. Not all patients may have access to advanced diagnostic tools or treatments derived from AI research, especially in under-resourced settings,“ Allder pointed out.
However, according to him, another issue might be “[t]he use of extensive patient data for AI model training,“ which “raises concerns about data privacy and security.“
“AI models need to be validated across diverse populations to ensure they are not biased towards specific cohorts,” said Allder.
Scherzer, echoing his earlier statement, said that the significant power of artificial intelligence toward precise medical treatments will ultimately depend on more research and trials.
“The success of AI to predict outcomes depends on the size and quality of the input data,” he noted. “A key gap in the field is that we need much larger, high quality, longitudinal data sets of Parkinson’s patients — data on large populations spanning prodromal stages and the entire disease course. These will be essential for training and validating AI models useful for augmented medicine.”