Researchers at Washington University School of Medicine in St. Louis in the US have developed an algorithm that identifies early, pre-symptoms of Parkinson’s disease based on data from a patient’s electronic health record (EHR).
By having access to this information, doctors will be able to reduce unnecessary tests and speed the process of diagnosis, ensuring more effective treatment.
Parkinson’s disease is a chronic and progressive movement disorder whose symptoms worsen over time. The disease is characterised by tremors, slowness of movement, stiffness and difficulty with balance and coordination.
Despite on-going research the cause is still unknown, and while there are treatment options, such as medication and surgery to help people deal with the symptoms, there isn’t a cure.
While the prevalence of Parkinson’s disease in South Africa is unknown, internationally it affects between one and two individuals in every 100 people over the age of 60 years, and four in every 100 people over the age of 80 years. About 15% of Parkinson’s disease patients develop symptoms before the age of 50; actor Michael J. Fox is notable for being diagnosed with Parkinson’s disease at the age of 30.
Before symptoms become pronounced, there is no reliable way to identify who is on track to develop Parkinson’s disease. Therefore the new algorithm is an important step in the diagnosis of the disease.
A study published by the researchers in the journal Neurology explained how data in EHRs can provide a clue to which patients will eventually be diagnosed with Parkinson’s disease.
As part of the study, the researchers analysed de-identified medical claims data of more than 200,000 Americans, ages 66 to 90, to develop an algorithm to predict whether a patient will one day be diagnosed with Parkinson’s disease. The algorithm uses patient information such as tests and diagnoses of various medical conditions.
“Using this algorithm, EHRs could be scanned and physicians could be alerted to the potential that their patients may need to be evaluated for Parkinson’s disease,” said the Robert Allan Finke Professor of Neurology and the study’s senior author, Dr Brad A. Racette.
“One of the most interesting findings is that people who are going to develop Parkinson’s have medical histories that are notably different from those who don’t develop the disease. This suggests there are lifelong differences that may permit identification of those likely to develop the disease decades before onset,” continued Dr Racette.
The study found 89,790 people who had been diagnosed with Parkinson’s disease in 2009, and matched them with 118,095 people in the same age range who had not been diagnosed with the disease in 2009 or before. The researchers then went through each person’s claims history to draw up a list of all diagnoses received and medical procedures undergone from 2004 to 2009.
Next an algorithm using medical history was developed – combined with age, sex, ethnicity and history of tobacco smoking – that correctly identified 73% of the people who would be diagnosed with the disease in 2009, and 83% of the people who would not.
Many of the claims codes that helped predict the disease referred to problems already known to be associated with Parkinson’s disease, such as tremors, posture abnormalities, psychiatric or cognitive dysfunction, gastrointestinal problems, sleep disturbances, fatigue and trauma, including falls. Other factors associated with the disease included weight loss and multiple forms of chronic kidney disease.
“We want to be able to catch people as early as possible. If I know someone may be in the beginning stages of Parkinson’s disease, I would evaluate their gait and balance to determine if they have unrecognised impairments that could lead to falls, or whether they have difficulty performing activities of daily living. Either of these scenarios may benefit from treatment,” said Dr Racette.
The study was supported by the National Institute for Environmental Health Sciences of the National Institutes of Health (NIH), the Michael J. Fox Foundation and the American Parkinson Disease Association.