Homepage Round-Up: A Machine-Learning Algorithm that Predicts Hospital Readmissions, Why White Meat is No Better for Your Heart Health Than Red Meat, and More.

By Rob Dillard - Last Updated: April 10, 2023

Here are the top stories covered by DocWire News this week in the Homepage section. In this week’s issue find out if a machine learning model can potentially predict hospital readmissions, if white meat is any better for your heart than red meat, how a Smartphone app can manage migraines, and how detrimental airborne metal pollution is for your health.

Advertisement

A machine learning algorithm called the Baltimore score (B score) can potentially help hospitals predict which discharged patients will be readmitted, according to a University of Maryland School of Medicine study that was published in JAMA. In this prognostic study, researchers identified 14,062 consecutive adult hospital patients with 16,649 discharges from the University of Maryland Medical Center, Saint Joseph Medical Center, and Maryland Midtown Hospital from September to December 2016. According to the study results, the B score machine learning score was notably higher than all others, scoring a 0.72 (95% CI, 0.70 to 0.73) 48 hours after admission, and subsequently increasing to 0.78 (95% CI, 0.77 to 0.79) at the time of discharge. The study authors concluded by writing that “although the B score had access to some social determinants of health such as home zip code, insurance type, and homelessness, the validity of such data in the EHR is uncertain. Further work on predicting and targeting readmission prevention efforts needs to account for social determinants of health.”

Contrary to popular belief, consuming white meat is just as detrimental to your heart as eating red meat, according to a new study published in The American Journal of Clinical Nutrition. To conduct this study, researchers enrolled over 100 individuals to participate in a randomized parallel arms study. The population of interest were generally healthy men and women aged 21-65. The participants were randomly allocated to one of two parallel arms; either high SFA (n=61), or low SFA (n=52). Following a two-week baseline that was intended to test their compliance to a controlled diet, the participants cycled through three food sources of protein (red meat, white poultry meat, or plant-based nonmeat) for four weeks each, separated by a two to seven week “washout” period during which they were permitted to consume their normal diets. Primary outcomes of the study suggest no discernible differences between the effects of red and white meat.

A new Smartphone app can reduce headache (HA) days in patients with migraines, according to study authors who published their findings in Nature Digital Medicine. The app was developed by researchers at NYU School of Medicine and is called RELAXaHEAD. Progressive muscle relaxation (PMR) is an effective yet under-utilized treatment for migraines. The researchers sought to examine if RELAXaHEAD might mitigate HA occurrences while evaluating potential predictors of app/and or PMR use. To conduct this study, they recruited 51 patients between July 7, 2017 and April 12, 2018 to participate in a single-arm pilot study. More than half of participants had severe migraine disability at study baseline. Results of the study suggest positive efficacy as participants who were high app/PMR users (PMR 2+ days/week in the first month) reported four fewer HA days in month two versus month one, whereas low app/PMR users (PMR for less than two weeks/week in the first month) had only two fewer HA days by the second month.

Exposure to airborne metal pollution heightens the risk of natural-cause mortality, according to a study conducted by the Barcelona Institute for Global Health (ISGlobal), who published their results in Environmental International. One of the study’s authors said that “We thought that moss, because of its capacity to retain these metals, would be a useful tool for estimating the atmospheric metal exposure of people living in rural areas.” To conduct this study, they analyzed data from 11,382 participants of the Gazel cohort, a biomonitoring program established in 1989 that obtained exposure estimates across France. The data on mosses was acquired from the BRAMM database. According to the results of the study, between 1996-2017 1,313 deaths occurred in the Gazel cohort, of which 181 were cardiovascular related and 33 respiratory related. Overall, the study found that exposure to the anthropogenic metals was linked to an augmented risk of natural-cause mortality (HR=1.16) while natural metals were not associated with increased mortality.

Advertisement