A major new study suggests that Parkinson’s disease may actually consist of several different diseases rather than a single condition.
Researchers from VIB and KU Leuven in Belgium used machine learning and advanced genetic analysis to identify different biological forms of Parkinson’s disease, helping explain why treatments often work well for some patients but not for others.
The findings were published in the journal Nature Communications and could open the door to more personalized treatments in the future.
Parkinson’s disease is one of the most common neurological disorders in the world. It affects millions of people and is usually known for causing shaking, stiffness, slow movement, balance problems, and difficulty walking.
As the disease progresses, many patients also develop sleep problems, memory issues, depression, and other symptoms affecting daily life.
For many years, doctors have treated Parkinson’s disease as a single illness. Patients are generally diagnosed based on symptoms, and many receive similar medications. However, scientists have long suspected that the disease may actually have many hidden biological causes.
Researchers already knew that mutations in different genes can increase the risk of Parkinson’s disease. Some patients inherit rare genetic mutations that directly contribute to the disorder, while others may develop Parkinson’s because of a combination of genes, aging, and environmental factors.
The challenge has been understanding how all these different causes connect together.
The new study may help answer that question.
The research team was led by Professor Patrik Verstreken from the VIB-KU Leuven Center for Neuroscience. Instead of starting with assumptions about how different genetic mutations affect Parkinson’s disease, the scientists decided to let the data guide the analysis.
To do this, they studied fruit flies carrying mutations in 24 different genes linked to Parkinson’s disease. Fruit flies are commonly used in neurological research because many important biological processes are surprisingly similar between flies and humans.
The scientists carefully monitored the flies’ movement and behavior over time. They then used machine learning and advanced computational analysis to search for hidden patterns.
Machine learning is a form of artificial intelligence that allows computers to analyze enormous amounts of data and identify patterns that humans may not easily detect.
Rather than grouping patients based on symptoms alone, the researchers focused on the underlying molecular changes caused by the different mutations.
The results were surprising.
The analysis revealed that the genetic forms of Parkinson’s disease naturally clustered into two major groups, which could then be divided into five smaller subgroups.
This means that different forms of Parkinson’s disease may involve different biological mechanisms happening inside brain cells.
According to Professor Verstreken, patients may look similar on the outside because they share common symptoms, but at the molecular level the disease can be very different from one person to another.
This discovery may help explain why many Parkinson’s treatments have shown mixed results.
If different patients actually have different biological forms of the disease, then a single drug may not work equally well for everyone.
Researchers believe this is one reason why developing new Parkinson’s medications has been so difficult.
The study also produced another important discovery. The researchers tested experimental compounds on the different subgroups of fruit flies and found that some drugs only worked in specific subgroups.
For example, a treatment that improved symptoms in one subgroup had little or no effect in another subgroup.
This suggests that future Parkinson’s treatments may need to be personalized based on the patient’s specific disease subtype.
Professor Verstreken explained that doctors may eventually be able to identify biomarkers linked to each subtype. Biomarkers are measurable biological signs that help doctors understand disease risk or treatment response.
If scientists can identify these markers in patients, doctors may one day match people with therapies designed specifically for their type of Parkinson’s disease.
The researchers believe this personalized approach could improve treatment success while reducing unnecessary side effects.
The study also highlights the growing role of artificial intelligence in medicine. Traditional medical research often begins with a specific theory and tests whether it is correct. In this study, researchers instead allowed machine learning to search freely for hidden biological patterns.
This unbiased strategy uncovered disease structures that might otherwise have remained invisible.
The researchers say the same approach could potentially be used for many other diseases that involve multiple genetic causes, including Alzheimer’s disease and other neurological disorders.
At the same time, the scientists caution that much more work is still needed before the findings can directly change patient care.
The current study was performed mainly in animal models rather than human patients. Researchers now hope to confirm whether the same Parkinson’s subtypes exist clearly in people and whether targeted treatments can successfully improve outcomes in clinical trials.
Even so, experts say the findings are very exciting because they offer a new way of thinking about Parkinson’s disease.
Instead of viewing Parkinson’s as a single condition, doctors may eventually classify it as several related diseases with different biological causes and different treatment needs.
This could lead to earlier diagnosis, more accurate drug development, and therapies better tailored to each patient.
Overall, the study provides important evidence that Parkinson’s disease is far more complex than previously understood and that personalized medicine may play a major role in its future treatment.
If you care about Parkinson’s disease, please read studies that Vitamin B may slow down cognitive decline, and Mediterranean diet could help lower risk of Parkinson’s.
For more information about brain health, please see recent studies that blueberry supplements may prevent cognitive decline, and results showing Plant-based diets could protect cognitive health from air pollution.
The research findings were published in Nature Communications.
