United States: Through research, Boston University scientists have been able to determine the probability of a person having Alzheimer’s disease. On the other hand, Weill Cornell Medicine scientists have employed machine learning to diagnose Parkinson’s disease into three subtypes.
The findings were first revealed in npj Digital MedicineTrusted Source, which would help researchers form treatments for those newly discovered subtypes.
More about the three subtypes
Cornell researchers undertook data from 406 patients who have participated in the Parkinson’s Progression Markers Initiative (PPMI), an international observational study, which “systematically collected clinical, biospecimen, multi-omics, and brain imaging data of participants.”
They formed a deep-learning model, which they called deep phenotypic progression embedding (DPPE), which is described as a “holistically” model, “multidimensional, longitudinal progression data of the participants,” as the authors explained, reported medicalnewstoday.com.
According to the researchers, recent efforts have been made to understand Parkinson’s, a condition with heterogeneous symptoms and progression.
As every individual with Parkinson’s has a different experience, the required treatment needs to be tailored and personalized according to the varied patients’ needs.
The identification of the three Parkinson’s subgroups has been made by machine learning, which is based on the speed at which the disease is progressing. These three subgroups are as follows:
The first is Rapid Pace (PD-R), marked by rapid progression of symptoms. The team found that 54 people (13.3 percent) were observed with this subtype.
Next is Inching Pace (PD-I), with mild symptoms and relatively mild progression. The team found 145 people (35.7 percent) with this variety.
The third one is Moderate Pace (PD-M), characterized by mild symptoms and moderate progression. The team noticed 27 people (50.9 percent) with this form of Parkinson’s.
According to the study authors, their classification “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,” as medicalnewstoday.com reported.
As the team identified, this disease classification would help clinics have a more targeted approach to prove more effective treatment.
What more have the experts stated?
Clemens Scherzer, MD, a physician-scientist and the Stephen & Denise Adams Professor of Neurology at Yale School of Medicine, who was not part of the study, said that the calculative findings of the study were potentially yielding good results. However, he mentioned that the study is extremely early, and a much larger-scale study is required to validate better such classifiers.
He said, “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,” as medicalnewstoday.com reported.
“For example, we have found that 10% of Parkinson’s patients in the [United States] have a mutation in the GBA geneTrusted Source and that different types of GBA mutations accelerate the course of the disease, “he explained. “Patients with GBA mutations can now be enrolled in clinical trials for targeted therapies and ultimately will benefit from disease-modifying GBA-directed therapeutics,” he continued.