Connect with us

Research

Artificial intelligence helps diagnose Parkinson’s disease

The method makes the clinical diagnosis of Parkinson’s disease more precise.

Published

on

Researchers are using artificial intelligence to make the clinical diagnosis of Parkinson’s more precise and help determine the stage of disease progression.

Scientists affiliated with the Department of Physical Education’s Human Movement Laboratory (Movi-Lab) at São Paulo State University (UNESP) in Brazil, are using artificial intelligence to help diagnose Parkinson’s disease and estimate its progression.

An article published in the journal Gait & Posture reports the findings of a study in which machine learning algorithms identified cases of the disease by analysing spatial and temporal gait parameters.

The researchers found four gait features to be most significant for the purposes of diagnosing Parkinson’s: step length, velocity, width and consistency (or width variability). 

To gauge the severity of the disease, the most significant factors were step width variability and double support time (during which both feet are in contact with the ground).

Fabio Augusto Barbieri, a co-author of the article and a professor in the Department of Physical Education at UNESP’s School of Sciences (FC), explained: “Our study innovated in comparison with the scientific literature by using a larger database than usual for diagnostic purposes. We chose gait parameters as the key criteria because gait impairments appear early in Parkinson’s and get worse over time, and also because they don’t correlate with physiological parameters like age, height and weight.”

The study sample comprised 63 participants in Ativa Parkinson, a multidisciplinary program of systematised physical activity for Parkinson’s patients conducted at FC-UNESP, and 63 healthy controls. All volunteers were over 50-years-old. 

Data was collected and fed into the repository used in the machine learning processes for seven years.

A baseline assessment was produced by analysing gait parameters for the healthy controls and comparing them with expected levels for this age group. This involved using a special motion capture camera to measure each person’s strides for length, width, duration, velocity, cadence, and single and double support time, as well as step variability and asymmetry.

The researchers used the data to create two different machine learning models – one for diagnosis of the disease and the other to estimate its severity in the patient assessed. Scientists at the University of Porto’s School of Engineering in Portugal collaborated on this part of the study.

They ran the data through six algorithms: Naïve Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR) and Multilayer Perceptron (MLP). NB achieved 84.6% diagnostic accuracy, while NB and RF performed best in assessing severity.

“Typical accuracy for clinical assessments is around 80 per cent. We could significantly reduce the probability of diagnostic error by combining clinical assessment with artificial intelligence,” Barbieri said. 

Forthcoming challenges

Parkinson’s disease is at least partly due to degeneration of nerve cells in the brain areas that control movement, as a result of deficient dopamine production. 

Dopamine is the neurotransmitter that transmits signals to the limbs. Low dopamine levels impair movement, producing symptoms such as tremors, slow gait, rigidity and poor balance, as well as alterations in speech and writing.

Diagnosis is currently based on the patient’s clinical history and a neurological examination, with no specific tests. Precise information is unavailable, but up to four per cent of the population aged over 65 is estimated to have Parkinson’s.

According to another co-author, PhD candidate Tiago Penedo, whose research is supervised by Barbieri, the results of the study will be useful to improve diagnostic assessment in future, but cost could be an inhibiting factor. 

The equipment used in the study costs around USD$100,000. 

“We made progress with the tool and contributed to expansion of the database, but we used expensive equipment that’s hard to find in clinics and doctor’s offices,” he said. 

“It’s possible to analyse gait with cheaper techniques, using a chronometer, force plate and so on, but the results aren’t precise.”

The techniques used in the study can contribute to a better understanding of the mechanisms underlying the disease, especially gait patterns, the researchers believe.

Previous research

An earlier study, reported in an article published in 2021, with Barbieri as last author, evidenced 53 per cent lower step-length synergy while crossing obstacles in Parkinson’s patients than in healthy subjects of the same age and weight. 

Synergy refers in this case to the capacity of the locomotor (or musculoskeletal) system to adapt movement, combining factors such as speed and foot position, while stepping off a curb, for example.

Another study, also published in Gait & Posture, showed that Parkinson’s patients were less able to maintain postural control and rambling-trembling stability than their neurologically healthy peers. The authors said the findings provided new insights to explain the larger, faster and more variable sway seen in Parkinson’s patients.

 

Research

Sitting still for long periods increases mortality risk, says study

Published

on

Sitting for long hours without breaks can increase risk mortality risk in older women, a new study shows.

The research, published in the Journal of the American Heart Association (JAHA), has data showing that older women who sat for 11.7 hours or more per day increased their risk of death by 30 percent, regardless of whether they exercised vigorously.

The study examined measurements of sitting and daily activity collected from hip devices worn for up to seven days by 6,489 women, aged 63 to 99, who were followed for eight years for mortality outcomes.

This data was collected  as part of a long-term national project known as the Women’s Health Initiative (WHI), which began in 1991 and is ongoing, led by Andrea LaCroix, Ph.D., M.P.H., Distinguished Professor at the Herbert Wertheim School of Public Health.

The paper is the first to apply a novel and validated machine-learned algorithm called CHAP to examine total sitting time and length of sitting bouts in relation to the risk of death.

Study co-author Steve Nguyen, PhD., M.P.H., a postdoctoral fellow at the University of California San Diego Herbert Wertheim School of Public Health and Human Longevity Science, said: “Sedentary behaviour is defined as any waking behaviour involving sitting or reclining with low energy expenditure.

“Previous techniques for calculating sedentary behaviour used cut points that identified low or absent movement. The CHAP algorithm was developed using machine-learning, a type of artificial intelligence, that enhanced its ability to accurately distinguish between standing and sitting.”

Fine-tuning “sitting” enabled Nguyen to parse total sitting time and usual sitting bout durations.

Sedentary behaviour is a health risk because it reduces muscle contractions, blood flow and glucose metabolism.

Exercise cannot undo these negative effects, according to the study, whether women participated in low or high amounts of moderate-to-vigorous intensity physical activity, they showed the same heightened risk if they sat for long hours.

LaCroix explained: “When you’re sitting, the blood flow throughout your body slows down, decreasing glucose uptake. Your muscles aren’t contracting as much, so anything that requires oxygen consumption to move the muscles diminishes, and your pulse rate is low.

“If I take a brisk long walk for an hour but sit the rest of the day, I’m still accruing all the negative effects on my metabolism.”

Based on the research, LaCroix makes the following recommendation: “The risk starts climbing when you’re sitting about 11 hours per day, combined with the longer you sit in a single session. For example, sitting more than 30 minutes at a time is associated with higher risk than sitting only 10 minutes at a time. Most people aren’t going to get up six times an hour, but maybe people could get up once an hour, or every 20 minutes or so. They don’t have to go anywhere, they can just stand for a little while.”

However, Nguyen points out that not all sitting is the same.

“Looking beyond conditions like cardiovascular disease, we start thinking about cognitive outcomes, including dementia,” he said.

“There are cognitively stimulating activities that can result in sedentary behavior, like sitting while studying a new language. Is sedentary behavior in that context overall bad for a person? I think it’s hard to say.” Nguyen has recently received a National Institute of General Medical Sciences K99 award for 12 months of mentored research to look at protein signatures of physical activity and how they relate to dementia.

LaCroix added: “We’ve created this world in which it’s so fascinating to sit and do things. You can be engrossed by TV or scroll on your Instagram for hours. But sitting all the time isn’t the way we were meant to be as humans, and we could reverse all of that culturally just by not being so attracted to all the things that we do while sitting.”

Continue Reading

Research

High risk of hospital readmission after surgery among older Americans

Published

on

A study finds an increased risk of hospital readmission for older Americans within 180 days of undergoing major surgery — a risk that is particularly acute for individuals who are frail or have dementia.

The findings from researchers at the University of Yale, were published in the journal JAMA Network Open.

Previous research by the same team demonstrated that major surgery is a common event for older Americans and also demonstrated a heightened mortality risk within one year of major surgery for people who are age 65 and older.

The new study is the first to describe both the short-term risk (within 30 days) and longer-term risk (within 180 days) of hospital readmission for older Americans who have recently had major surgery.

The study looked at hospital readmission among a nationally representative sample of 1,477 older Americans, not living in nursing homes, who had at least one major surgery between 2011 and 2018. More than one in four (27.6 per cent) had a readmission to the hospital within 180 days after major surgery; nearly one in eight (11.6 per cent) were readmitted within just 30 days.

Dr. Robert D. Becher, associate professor of surgery at Yale School of Medicine and co-senior author of the study, commented: “Prior to now, data on longer-term readmissions after major surgery in older persons have been lacking. This is problematic, as older persons undergoing major surgery represent a large and growing population.

“These readmission rates are high. And this study adds to our understanding of what it means to recover from major surgery as an older person.”

The numbers are even higher for those with geriatric-specific conditions such as frailty and dementia. Frail patients were readmitted within 180 days at a rate of 36.9 per cent; patients with probable dementia were readmitted at a rate of 39 per cent; and patients 90 years old and older were readmitted at a rate of 36.8 per cent.

Dr. Thomas M. Gill, the Humana Foundation Professor of Geriatric Medicine at Yale and co-senior author of the study, said: “These findings reenforce the importance of enhanced preoperative recognition of frailty and dementia in older persons and may inform patient and family expectations — and surgical decision making — about postoperative trajectories in the setting of these geriatric conditions.”

The issue of hospital readmission looms large in the USS health care system for a variety of reasons.

In 2018 alone, readmission costs totalled more than $50 billion, the researchers said. This was driven, in part, by the nearly 3.8 million 30-day hospital readmissions that year. The vast majority of those patients are Medicare beneficiaries aged 65 and older.

“From a patient perspective, the most important outcome among older persons with multiple conditions is maintaining independence and function. And we know that being readmitted to the hospital after major surgery can negatively impact that independence and function,” Becher said.

“So these new data put into perspective just how common hospital readmissions, and their negative downstream consequences, are to older persons.”

The researchers said the next steps in their examination of the issue will be to further understand why vulnerable older persons have such high readmission rates and suggest meaningful ways to minimise the risk of readmission.

Continue Reading

Research

Risk factors for frailty in old age different in men and women, finds study

Published

on

A study conducted by researchers at the Federal University of São Carlos (UFSCar) in Brazil and University College London (UCL), found the factors that increase the risk of frailty in old age to be different in men and women.

The study, which was funded by FAPESP, is published in the journal Archives of Gerontology and Geriatrics.

According to the results, osteoporosis, low weight, heart disease, and poor hearing increased the risk of frailty in men, while a high level of fibrinogen (a marker of cardiovascular disease) in the blood, diabetes and stroke were associated with a higher risk of frailty in women.

The findings were based on an analysis of data from 1,747 participants in the English Longitudinal Study of Ageing (ELSA), an ongoing population survey that explores the dynamic relationships between health, functioning, social networks and economic status in people aged 50 and over who reside in England. ELSA began in 2002. These participants were interviewed and assessed every four years between 2004 and 2016.

The researchers selected participants aged 60 or more who initially did not have frailty syndrome and were not classified as pre-frailty (with only one or two of the above factors).

Frailty syndrome is characterised by the presence of three or more of the following factors: involuntary weight loss, fatigue, muscle weakness, slow gait, and a low level of physical activity. It is more common in women than men, partly because of women’s greater life expectancy.

Tiago da Silva Alexandre, last author of the article and a professor in UFSCar’s Department of Gerontology, explained: “Frailty syndrome serves as a warning sign of the possibility of a negative outcome in an older person. We used to think of frailty as having a single pathway in the elderly, but our study shows there are several routes. The differences between men and women in this regard are important for policymakers to take into account. They should influence primary health care and could result in more gender-specific action plans and intervention for older people.”

Frailty syndrome has a phenotype, he explained – a set of easily identifiable signs and symptoms designed to identify older people with a heightened risk of falls, hospitalisations, incapacitation, and early death.

“Our study went back a few steps before this process begins to find out which characteristics may lead to frailty during the lives of these older people. When we think about aging and the quality of life in old age, it’s very important to identify the main risk factors so as to be able to foresee problems and formulate public policy for men and women,” he added.

According to Dayane Capra de Oliveira, first author of the article, although frailty as a tool is based on biology, sex-related differences in risk factors for development of the syndrome are mainly associated with the different social roles of men and women, and with their different degrees of access to resources during their lives.

“Another key aspect is that frailty is a multifactorial condition. While socioeconomic factors, skeletal muscle disorders, heart disease and low weight appear to underlie frailty in men, in women the process appears to be driven mainly by cardiovascular and neuroendocrine disturbances,” Oliveira said.

Differences and similarities

According to the researchers, while some risk factors for frailty are the same for men and women – including old age, low educational attainment, sedentarism and depression, for example – differences in body composition and fat deposition throughout life and especially in old age may lead directly or indirectly to the appearance of components of frailty, such as metabolic alterations that culminate in the development of diseases, which in turn increase the risk of frailty.

Alexandre said: “Our study is based on data for people now aged 60 or more and living in England. We don’t know how these sex-based differences will play out in future generations. However, the fact is that the men in the cohort we studied were more exposed to several kinds of working conditions considered risk factors for diseases. Their diet was less healthy. They didn’t go to the doctor as much as the women [so that there was less early diagnosis]. They drank more and were more exposed to other substances that increased the risk of cardiovascular disease and heart attack.”

Women are more affected by chronic diseases, which are not as lethal but can be incapacitating.

He added: “The sex-based differences are a lifelong backdrop and culminate in different ageing processes, different causes of death or disability, and different kinds of frailty in men and women.”

Continue Reading

Trending