Summary: Researchers have used machine learning to identify three subtypes of Parkinson’s disease based on their rate of progression. These subtypes, characterized by distinct genetic factors, could improve diagnostic and treatment strategies.
The study also found that the diabetes drug metformin may improve symptoms, particularly in the rapidly progressive subtype. These findings pave the way for personalized treatment approaches for patients with Parkinson’s disease.
Highlights:
- Three subtypes: Parkinson’s disease subtypes defined by rate of progression: progressive rate, moderate rate, and rapid rate.
- Separate drivers: Each subtype has unique genetic and molecular markers.
- Potential treatment: Metformin shows promise in improving symptoms, particularly in the Rapid Pace subtype.
Source: Weill Cornell University
Researchers at Weill Cornell Medicine used machine learning to define three subtypes of Parkinson’s disease based on the rate at which the disease progresses.
In addition to potentially becoming an important diagnostic and prognostic tool, these subtypes are characterized by distinct driver genes. If validated, these markers could also suggest ways to target the subtypes with new and existing drugs.
The research was published July 10 in npj Digital medicine.
“Parkinson’s disease is very heterogeneous, meaning that people with the same disease can have very different symptoms,” said lead author Dr. Fei Wang, professor of population health sciences and founding director of the AI Institute for Digital Health (AIDH) in the Department of Population Health Sciences at Weill Cornell Medicine.
“This indicates that there is probably no single solution to treat this disease. We may need to consider personalized treatment strategies based on the patient’s disease subtype.”
The researchers defined the subtypes based on their different patterns of disease progression. They named them the progressive-rate subtype (PD-I, about 36% of patients) for cases with mild initial severity and moderate rate of progression, the moderate-rate subtype (PD-M, about 51% of patients) for cases with mild initial severity but moderate progression, and the rapid-rate subtype (PD-R), for cases with the fastest rate of symptom progression.
They were able to identify the subtypes by using deep learning-based approaches to analyze anonymized clinical records from two large databases. They also explored the molecular mechanism associated with each subtype through the analysis of patients’ genetic and transcriptomic profiles with network-based methods.
For example, the PD-R subtype showed activation of specific pathways, such as those related to neuroinflammation, oxidative stress, and metabolism. The team also found distinct brain imaging and cerebrospinal fluid biomarkers for the three subtypes.
Dr. Wang’s lab has been studying Parkinson’s disease since 2016, when the group participated in the Parkinson’s Progression Markers Initiative (PPMI) data collection challenge sponsored by the Michael J. Fox Foundation. The team won the challenge on the topic of subtype derivation and has since received funding from the foundation to continue this work.
They used data collected from the PPMI cohort as the primary subtype development cohort in their research and validated it with the National Institute of Neurological Disorders and Stroke (NINDS) Parkinson’s Disease Biomarker Program (PDBP) cohort.
The researchers used their findings to identify potential drug candidates that could be repurposed to target the specific molecular changes seen in the different subtypes. They then used two large-scale databases of patient medical records to confirm that these drugs could help improve the progression of Parkinson’s disease. These databases, called INSIGHT
The New York-based Clinical Research Network and the OneFlorida+ Clinical Research Consortium are both part of the National Patient-Centered Clinical Research Network (PCORnet). INSIGHT is led by Dr. Rainu Kaushal, senior associate dean of clinical research at Weill Cornell Medicine and chair of the Department of Population Health Sciences at Weill Cornell Medicine and NewYork-Presbyterian/Weill Cornell Medical Center.
“When we looked at these databases, we found that people taking the diabetes drug metformin appeared to have improved disease symptoms, particularly symptoms related to cognition and falls, compared with those not taking metformin,” said first author Dr. Chang Su, assistant professor of population health sciences and also an AIDH fellow at Weill Cornell Medicine.
This was particularly true among people with the PD-R subtype, who are most likely to have cognitive deficits early in their Parkinson’s disease.
“We hope our research will inspire other researchers to think about using diverse data sources when conducting studies like ours,” Dr. Wang said.
“We also believe that translational bioinformatics researchers will be able to further validate our results, both computationally and experimentally.”
Several collaborators contributed to this work, including scientists from the Cleveland Clinic, Temple University, the University of Florida, the University of California, Irvine, the University of Texas at Arlington, as well as doctoral candidates from Cornell Tech’s computer science program and the computational biology program at Cornell University’s Ithaca campus.
About this news on AI and Parkinson’s disease research
Author: Barbara Prempeh
Source: Weill Cornell University
Contact: Barbara Prempeh – Weill Cornell University
Picture: Image credited to Neuroscience News
Original research: Free access.
“Identification of PACE subtypes of Parkinson’s disease and reorientation of treatments through integrative analyses of multimodal data” by Fei Wang et al. Digital medicine npj
Abstract
Identification of PACE subtypes of Parkinson’s disease and reorientation of treatments through integrative analyses of multimodal data
Parkinson’s disease (PD) is a severe neurodegenerative disease characterized by significant clinical and evolutionary heterogeneity. This study aimed to address the heterogeneity of PD through an integrative analysis of various data modalities.
We analyzed clinical progression data (≥5 years) of individuals with de novo PD using machine learning and deep learning, to characterize individuals’ phenotypic progression trajectories for PD subtyping.
We discovered three PD rhythm subtypes with distinct progression patterns: the progressive rhythm subtype (PD-I) with mild baseline severity and mild progression rate; the moderate rhythm subtype (PD-M) with mild baseline severity but progressing at a moderate progression rate; and the rapid rhythm subtype (PD-R) with the fastest rate of symptom progression.
We found the P-tau/α-synuclein ratio in cerebrospinal fluid and atrophy in some brain regions as potential markers of these subtypes. Genetic and transcriptomic profiling analyses with network-based approaches identified molecular modules associated with each subtype.
For example, the suggested PD-R specific module STAT3, FYN, BECN1, APOA1, NEDD4And GATA2 as potential driver genes of PD-R. It also suggested that neuroinflammation, oxidative stress, metabolism, PI3K/AKT, and angiogenesis pathways were potential drivers of rapid PD progression (i.e., PD-R).
Furthermore, we identified reusable drug candidates by targeting these subtype-specific molecular modules using a network-based approach and cell line drug-gene signature data. We further estimated their therapeutic effects using two large-scale real-world patient databases; the real-world evidence we obtained highlighted the potential of metformin to improve PD progression.
In conclusion, this work allows us to better understand the clinical and pathophysiological complexity of PD progression and to accelerate precision medicine.
News Source : neurosciencenews.com
Gn Health
