Condition Watch: May 2024

Machine Learning Can Predict Early Alzheimer Disease

A Machine learning model demonstrated the potential to improve early detection and management of Alzheimer disease (AD) but did not satisfy fairness metrics across race and ethnicity, according to results of a study published in JAMA Network Open.

Image credit: BillionPhotos.com | stock.adobe.com

Investigators aimed to determine the potential of predictive models in the early detection and management of AD as well as the tools’ fairness among racial and ethnic groups for AD progression. Investigators included data from the Alzheimer’s Disease Neuroimaging Initiative, which included patients aged 54 to 91 years across 57 sites in the US and Canada.

A total of 1730 individuals were included, with 44.9% female, 4% Hispanic, 1.7% Asian, 4.5% Black, 92.4% White, and 1.4% self-identified as another race. The mean age was 73.81 years. Approximately 86.2% were cognitively normal, 13.8% were cognitively normal-mild cognitive impairment (MCI) trajectory, 62.4% were MCI-stable trajectory, and 38.6% were MCI-AD trajectory, according to the study.

The results showed that the true positive rates between cognitively normal-stable and MCI-stable were close to 1, with no major differences between men and women. For the clinically normal-MCI trajectory group, the study authors reported notable differences between men and women, with all models tending to perform better for females. For MCI-AD trajectory, there were small differences observed.

For Hispanic patients, the true positive rates were high due to the small sample size, according to the study authors. Further, they said this was true for members of Asian, Black, and other racial groups, especially for the cognitively normal-MCI and MCI-AD trajectories, highlighting how underrepresentation could affect study results.—Ashley Gallagher, Associate Editor

Reference

Kelley MD, Obaid M, Miller EM, Bowie M, Heeter ZS. Observational analysis of the influence of medical marijuana use on quality of life in patients. Med Cannabis Cannabinoids. 2024;7(1):44-50. doi:10.1159/000536591

Researchers Link Stomach Bacteria With Higher Risk of Alzheimer Disease

Helicobacter Pylori has been associated with a higher risk of Alzheimer disease (AD), according to new study results. The risk of AD was approximately 24% after a decade of onset of clinically acquired H pylori infection (CAHPI), according to the study authors.

In the study, investigators included individuals 50 years or younger from the United Kingdom’s Clinical Practice Research Datalink GOLD, a primary care database of anonymous medical records. Individuals were recruited between January 1988 and December 2018, with follow-up until December 2019, according to the study authors. At time of enrollment, all individuals were free of dementia.

There were 4,262,092 individuals included, with an average age of 60.4 years and 52.1% female, according to the study. Characteristics were similar among the 40,455 AD cases and 1,610,502 individuals with AD, which were used as controls. Compared with those who had no exposure to CAHPI, those who were exposed were associated with moderately increased risk of AD. Investigators also reported that there were no major effects when adjusting for demographics or socioeconomic status.

An analysis with salmonellosis, used as a control exposure, showed no association with the risk of AD, according to the study authors. Furthermore, the results also demonstrated consistent outcomes with any type of dementia.—Ashley Gallagher, Associate Editor

Reference

Blended antioxidant supplement improves cognition and memory in aged mice. News release. Shibaura Institute of Technology; April 2, 2024. Accessed April 8, 2024. https://www.shibaura-it.ac.jp/en/headline/detail/20240327_7070_001.html

A Healthier Lifestyle Is Connected With Better Cognitive Function, Despite Alzheimer Disease Pathology

Investigators of a study published in JAMA Neurology investigated the impact of lifestyle interventions on cognition in older adults as a preventive measure. Further, the authors specifically examined individuals who had died and underwent autopsy to evaluate whether lifestyle factors had an influence on cognition prior to death.
The investigators analyzed 754 deceased individuals and their individual-level data on lifestyle factors, cognitive testing close to death, and a complete neuropathologic evaluation at the time of the analyses. Of the included 754 individuals, 586 had valid dietary and lifestyle data in addition to cognitive testing and complete autopsy data at the time of analyses. The authors also compared the participants’ demographic data as well as genetic characteristics available from the Rush Memory and Aging Project.
Using a food frequency questionnaire and a self-report of time spent on completing physical activities, participants were categorized as low-risk or “healthy” if they were in the healthiest 40% of the total analyzed population (equivalent to a diet score higher than 7.5 and cognitive activities score higher than 3.20). Once the patients were deceased, the brain was removed and examined to determine cognition or the presence of Alzheimer disease.
The results indicated that a healthier lifestyle was associated with better cognitive function prior to death. In addition, the lifestyle-cognition association was independent of Alzheimer disease pathology burden, indicating that strength of significance of the lifestyle-cognition association changed significantly when β-amyloid load, phosphorylated tau tangle, or other memory-related brain pathologies were included in the regression tool.—Gillian McGovern, Assistant Editor

Reference

Manuello J, Min J, McCarthy P, et al. The effects of genetic and modifiable risk factors on brain regions vulnerable to ageing and disease. Nat Commun. 2024;15(1):2576. doi:10.1038/s41467-024-46344-2