Introduction
Recent advancements in machine learning have opened new horizons in the understanding and treatment of Parkinson’s disease. Researchers at Weill Cornell Medicine have classified Parkinson’s disease into three subtypes, potentially revolutionizing personalized treatment strategies. This blog post delves into the details of this groundbreaking study, its methodology, and its implications for the future of Parkinson’s disease management.
Keywords
- Parkinson’s disease
- Machine learning
- AI in healthcare
- Parkinson’s subtypes
- Personalized medicine
- Neuroinflammation
- Genetic markers
- Disease progression
- Metformin
- Clinical research
- Deep learning
- Medical innovation
- AI models
- Digital health
- Translational bioinformatics
- Clinical trials
- Health data
- Precision medicine
- AI healthcare applications
- Parkinson’s treatment
The Study and Its Methodology
Published in npj Digital Medicine on July 10, the study from Weill Cornell Medicine utilized data from the Parkinson’s Progression Markers Initiative (PPMI), an international observational study that systematically collected clinical, biospecimen, multi-omics, and brain imaging data. Researchers developed a deep-learning model called deep phenotypic progression embedding (DPPE), which holistically modeled multidimensional, longitudinal progression data from 406 participants.
Identifying Three Subtypes
1. Rapid Pace (PD-R): This subtype is characterized by a rapid progression of symptoms and was observed in 13.3% of the cohort. Patients with this subtype often experience severe symptoms quickly, necessitating aggressive therapeutic strategies and closer monitoring.
2. Inching Pace (PD-I): Representing 35.7% of participants, this subtype has mild baseline symptoms and slow progression. Treatment for PD-I patients focuses on maintaining quality of life through lifestyle modifications, physical therapy, and potentially neuroprotective drugs.
3. Moderate Pace (PD-M): The most common subtype, affecting 50.9% of the cohort, exhibits mild baseline symptoms that advance at a moderate rate. These patients might benefit from a combination of pharmacological treatments to manage symptoms and slow progression.
Clinical Implications
The identification of these subtypes highlights the need for personalized treatment strategies. Dr. Daniel Truong, a neurologist and medical director at the Truong Neuroscience Institute, noted that patients with the Rapid Pace subtype might benefit from more aggressive therapies, whereas those with the Inching Pace subtype could be managed with less intensive interventions. This stratification could also guide the repurposing of existing drugs, such as metformin, which has shown promise in improving symptoms in PD-R patients.
Weill Cornell Medicine’s Contributions
Weill Cornell Medicine investigators have been at the forefront of using AI to discern subtypes of Parkinson’s disease from diverse data sources. According to Dr. Fei Wang, senior author and professor of population health sciences, “Parkinson’s disease is highly heterogeneous, which means that people with the same disease can have very different symptoms.” This indicates the necessity of customized treatment strategies based on a patient’s disease subtype.
The study identified distinct molecular mechanisms associated with each subtype through the analysis of patient genetic and transcriptomic profiles. For instance, the PD-R subtype showed activation of specific pathways related to neuroinflammation, oxidative stress, and metabolism. The team also found unique brain imaging and cerebrospinal fluid biomarkers for each subtype.
Ongoing Research and Future Directions
Dr. Wang’s lab has been studying Parkinson’s since 2016, participating in the Parkinson’s Progression Markers Initiative (PPMI) data challenge sponsored by the Michael J. Fox Foundation. Winning the challenge for deriving subtypes, the team has continued to receive funding to further this research.
The study’s results are promising, but experts like Dr. Clemens Scherzer from Yale School of Medicine caution that larger, more diverse populations need to be studied to validate these classifications. Steven Allder, a consultant neurologist at Re
Health, emphasized potential issues related to patient access to advanced diagnostic tools and treatments derived from AI research, particularly in under-resourced settings. Validating AI models across diverse populations is crucial to avoid biases and ensure equitable healthcare delivery.
Conclusion
The classification of Parkinson’s disease into three subtypes using machine learning marks a significant step forward in personalized medicine. By understanding the distinct progression patterns of these subtypes, researchers and clinicians can develop more targeted and effective treatments, ultimately improving the quality of life for patients with Parkinson’s disease. However, further research and validation across larger and more diverse populations are essential to fully realize the potential of these findings.
Weill Cornell Medicine investigators used AI to discern subtypes of Parkinson’s disease from diverse data sources. Credit: Shutterstock.
Researchers at Weill Cornell Medicine have used machine learning to define three subtypes of Parkinson’s disease based on the pace at which the disease progresses. In addition to having the potential to become an important diagnostic and prognostic tool, these subtypes are marked by distinct driver genes. If validated, these markers could also suggest ways the subtypes can be targeted with new and existing drugs.
“Parkinson’s disease is highly heterogeneous, which means that people with the same disease can have very different symptoms,” said senior author Dr. Fei Wang, a professor of population health sciences and the founding director of the Institute of AI for Digital Health (AIDH) in the Department of Population Health Sciences at Weill Cornell Medicine. “This indicates there is not likely to be a one-size-fits-all approach to treating it. We may need to consider customized treatment strategies based on a patient’s disease subtype.”
The investigators defined the subtypes based on their distinct patterns of disease progression. They named them the Inching Pace subtype (PD-I, about 36% of patients) for disease with a mild baseline severity and mild progression speed, the Moderate Pace subtype (PD-M, about 51% of patients) for cases that have mild baseline severity but advance at a moderate rate, and Rapid Pace subtype (PD-R), for cases with the most rapid symptom progression rate.
They were able to identify the subtypes by using deep learning-based approaches to analyze deidentified clinical records from two large databases. They also explored the molecular mechanism associated with each subtype through the analysis of patient genetic and transcriptomic profiles with network-based methods. For example, the PD-R subtype had 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 since 2016, when the group participated in the Parkinson’s Progression Markers Initiative (PPMI) data challenge sponsored by the Michael J. Fox Foundation. The team won the challenge on the topic of deriving subtypes, and since then has received funding from the foundation to continue this work. They employed the data collected from the PPMI cohort as the primary subtype development cohort in their research and validated them with National Institute of Neurological Disorders and Stroke (NINDS) Parkinson’s Disease Biomarkers Program (PDBP) cohort.
The researchers used their findings to identify possible drug candidates that could be repurposed to target the specific molecular changes seen in the different subtypes. They then used two large-scale, real-world databases of patient health records to confirm these drugs could help ameliorate Parkinson’s progression. These databases, the INSIGHT Clinical Research Network, based in New York, 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 for 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.
“By examining these databases, we found that people taking the diabetes drug metformin appeared to have improved disease symptoms—especially symptoms related to cognition and falls—compared with those who did not take metformin,” said first author Dr. Chang Su, an assistant professor of population health sciences and also a member of the AIDH at Weill Cornell Medicine. This was especially true in those with the PD-R subtype, who are most likely to have cognitive deficits early in the course of their Parkinson’s disease.
“We hope our research will lead other investigators to think about using diverse data sources when conducting studies like ours,” Dr. Wang said. “We also think that translational bioinformatics investigators will be able to further validate our findings, both computationally and experimentally.”
A number of collaborators contributed to this work, including scientists at the Cleveland Clinic, Temple University, University of Florida, University of California at Irvine, University of Texas at Arlington as well as doctoral candidates from the computer science program at Cornell Tech and the computational biology program at Cornell University’s Ithaca campus.
Many Weill Cornell Medicine physicians and scientists maintain relationships and collaborate with external organizations to foster scientific innovation and provide expert guidance. The institution makes these disclosures public to ensure transparency. For this information, see profile for Dr. Fei Wang.
Conclusion
The classification of Parkinson’s disease into three subtypes using machine learning marks a significant step forward in personalized medicine. By understanding the distinct progression patterns of these subtypes, researchers and clinicians can develop more targeted and effective treatments, ultimately improving the quality of life for patients with Parkinson’s disease. However, further research and validation across larger and more diverse populations are essential to fully realize the potential of these findings.
AI-generated medical content is not a substitute for professional medical advice or diagnosis; I hope you found this blog post informative and interesting. www.parkiesunite.com by Parkie
SEO keywords: Parkinson’s disease, AI in healthcare, Personalized medicine, Clinical research, Health data
DALL-E Prompt: “A watercolor painting of a scientist analyzing brain scans and genetic data on a computer screen, depicting the process