Connect with us

News

Machine Learning Can Help Healthcare Workers Predict Whether Patients May Require Emergency Hospital Admission

Published

on

Machine learning – a field of artificial intelligence that uses statistical techniques to enable computer systems to ‘learn’ from data – can be used to analyse electronic health records and predict the risk of emergency hospital admissions, a new study from The George Institute for Global Health at the University of Oxford has found.

The research, published in the journal PLOS Medicine, suggests that using these techniques could help health practitioners accurately monitor the risks faced by patients and put in place measures to avoid unplanned admissions, which are a major source of healthcare spending.

‘There were over 5.9 million recorded emergency hospital admissions in the UK in 2017, and a large proportion of them were avoidable. We wanted to provide a tool that would enable healthcare workers to accurately monitor the risks faced by their patients, and as a result make better decisions around patient screening and proactive care that could help reduce the burden of emergency admissions,’ said Fatemeh Rahimian, former data scientist at The George Institute UK, who led the research.

The study, of 4.6 million patients from 1985 to 2015, was conducted using linked electronic health records from the UK’s Clinical Practice Research Datalink. A wide range of factors was taken into account, including age, sex, ethnicity, socioeconomic status, family history, lifestyle factors, comorbidities, medication and marital status, as well as the time since first diagnosis, last use of the health system and latest laboratory tests.

Using more variables combined with information about their timing, machine learning models were found to provide a more robust prediction of the risk of emergency hospital admission than any models used previously.

‘Our findings show that with large datasets which contain rich information about individuals, machine learning models outperform one of the best conventional statistical models,’ Rahimian said.

‘We think this is because machine learning models automatically capture and ‘learn’ from interactions between the data that we were not previously aware of.’

Whether machine learning models can lead to similarly strong improvements in risk prediction in other areas of medicine requires further research.

News

Report Reveals Link Between Air Pollution And Increased Risk For Miscarriage

Published

on

Air quality has been associated with numerous adverse health outcomes from asthma to pre-term birth. Researchers at University of Utah Health found women living along the Wasatch Front — the most populous region in the state of Utah — had a higher risk (16 percent) of miscarriage following short-term exposure to elevated air pollution. The results are available online on December 5 in the journal Fertility and Sterility.

“Not being from Salt Lake originally, I noticed a pattern in the relation to air quality and pregnancy loss,” said Matthew Fuller, M.D., assistant professor of Surgery at U of U Health and senior author on the paper.

“I knew this was an understudied question so we decided to dig deeper.”

Fuller joined University of Utah research analyst Claire Leiser on a retrospective study consisting of more than 1,300 women (54 percent Caucasian, 38 percent Hispanic, and other/missing 8 percent; average age 28 years). The women in the study sought help at the U of U emergency department following a miscarriage (up to 20-weeks gestation) between 2007 to 2015.

The team examined the risk of miscarriage during a three- or seven-day window following a spike in the concentration of three common air pollutants: small particulate matter (PM 2.5), nitrogen dioxide and ozone. The study excluded women who lived outside Utah.

“We are really only seeing the most severe cases during a small window of time,” said Leiser, first author on the paper.

“These results are not the whole picture.”

Leiser notes the results suggest there could be an increased risk for an individual. Their research only captured women who sought help at an emergency department at one hospital in the region. It does not account for women who may have sought outpatient care through their obstetric or primary care providers.

The team found a slight increased risk in miscarriage for women exposed to elevated levels of nitrogen dioxide (16 percent for 10 ppb increase during the seven-day window). Although small particulate matter does track with nitrogen dioxide, these results did not significantly associate with an increased risk of miscarriage.

“While we live in a pretty unique geographic area, the problems we face when it comes to air pollution are not unique,” said Fuller.

“As the planet warms and population booms, air pollution is going to become a bigger problem not only in the developing world but across the United States.”

The Wasatch Front experiences short-periods of poor air quality, primarily during the winter months, when inversions trap pollutants close to the ground (for the 7-day window: PM2.5 min = 0.3 μg/m3; PM2.5 max = 73.0 μg/m3; O3 min = 4 ppb; O3 max= 80 ppb; NO2min = 0.5 ppb; NO2 max = 65 ppb). The researchers tracked air quality by zip code, establishing six designated air basins within the Wasatch Front. They compared air quality in each basin to their patients’ outcomes.

The team conducted a case cross-over study that estimated a woman’s risk of miscarriage multiple times in a month where air pollution exposure varied. This approach removed other risk factors, like maternal age, from the study. The scientists were unable to ascertain the age of the fetus at the time of the miscarriage and were unable pinpoint a critical period when the fetus may be most vulnerable to pollutants.

“The results of this study are upsetting, and we need to work together as a society to find constructive solutions,” Fuller said.

Fuller recommends women speak with their doctor about any health concerns. Women can manage the risk by using a N95 particulate respirator face mask to filter out pollutants or avoid outdoor physical activity on poor air quality days. Women can also use filters to lower indoor pollution and, if possible, time conception to avoid seasonal episodes of poor air quality.

Continue Reading

News

Alcohol Intake May Be Key to Long-term Weight Loss for People with Diabetes

Published

on

Research shows that losing weight can help prevent or delay the onset of diabetes. While best practice for weight loss often includes decreasing or eliminating calories from alcohol, few studies examine whether people who undergo weight loss treatment report changes in alcohol intake and whether alcohol influences their weight loss.

A new study from the University of Pennsylvania School of Nursing (Penn Nursing) suggests that alcohol consumption may attenuate long-term weight loss in adults with Type 2 diabetes.

In the study, close to 5,000 people who were overweight and had diabetes were followed for four years. One group participated in Intensive Lifestyle Intervention (ILI) and the other in a control group consisting of diabetes support and education. Data showed that participants in the ILI group who abstained from alcohol consumption over the four-year period lost more weight than those who drank any amount during the intervention. Results from the study also showed that heavy drinkers in the ILI group were less likely to have clinically significant weight loss over the four years.

“This study indicates that while alcohol consumption is not associated with short‐term weight loss during a lifestyle intervention, it is associated with worse long‐term weight loss in participants with overweight or obesity and Type 2 diabetes,” says lead investigator Ariana M. Chao, PhD, CRNP, Assistant Professor of Nursing in the Department of Biobehavioral Health Sciences.

“Patients with Type 2 diabetes who are trying to lose weight should be encouraged to limit alcohol consumption.”

Continue Reading

News

Hang In There. As Couples Age, Humor Replaces Bickering

Published

on

Honeymoon long over? Hang in there. A new UC Berkeley study shows those prickly disagreements that can mark the early and middle years of marriage mellow with age as conflicts give way to humor and acceptance.

Researchers analyzed videotaped conversations between 87 middle-aged and older husbands and wives who had been married for 15 to 35 years, and tracked their emotional interactions over the course of 13 years. They found that as couples aged, they showed more humor and tenderness towards one another.

Overall, the findings, just published in the journal Emotion, showed an increase in such positive behaviors as humor and affection and a decrease in negative behaviors such as defensiveness and criticism. The results challenge long-held theories that emotions flatten or deteriorate in old age and point instead to an emotionally positive trajectory for long-term married couples.

“Our findings shed light on one of the great paradoxes of late life,” said study senior author Robert Levenson, a UC Berkeley psychology professor.

“Despite experiencing the loss of friends and family, older people in stable marriages are relatively happy and experience low rates of depression and anxiety. Marriage has been good for their mental health.”

Consistent with previous findings from Levenson’s Berkeley Psychophysiology Laboratory, the longitudinal study found that wives were more emotionally expressive than their husbands, and as they grew older they tended toward more domineering behavior and less affection. But generally, across all the study’s age and gender cohorts, negative behaviors decreased with age.

“Given the links between positive emotion and health, these findings underscore the importance of intimate relationships as people age, and the potential health benefits associated with marriage,” said co-lead author Alice Verstaen, who conducted the study as a Ph.D. student at UC Berkeley and is currently a postdoctoral fellow at the VA Puget Sound Health Care System.

The results are the latest to emerge from a 25-year UC Berkeley study headed by Levenson of more than 150 long-term marriages. The participants, now mostly in their 70s, 80s and 90s, are heterosexual couples from the San Francisco Bay Area whose relationships Levenson and fellow researchers began tracking in 1989.

In their investigation of marital relationships, researchers viewed 15-minute interactions between spouses in a laboratory setting as they discussed shared experiences and areas of conflict. They tracked the emotional changes every few years.

The spouses’ listening and speaking behaviors were coded and rated according to their facial expressions, body language, verbal content and tone of voice. Emotions were coded into the categories of anger, contempt, disgust, domineering behavior, defensiveness, fear, tension, sadness, whining, interest, affection, humor, enthusiasm and validation.

Researchers found that both middle-aged and older couples, regardless of their satisfaction with their relationship, experienced increases in overall positive emotional behaviors with age, while experiencing a decrease in overall negative emotional behaviors.

“These results provide behavioral evidence that is consistent with research suggesting that, as we age, we become more focused on the positives in our lives,” Verstaen said.

Continue Reading

Like Us on Facebook

Trending Posts

Trending