Metabolomics, with its wealth of data, offers a valuable avenue for enhancing predictions and decision-making in diabetes. This observational study aimed to leverage machine learning (ML) algorithms to predict the 4-year risk of developing type 2 diabetes mellitus (T2DM) using targeted quantitative metabolomics data. A cohort of 279 cardiovascular risk patients who underwent coronary angiography and who were initially free of T2DM according to American Diabetes Association (ADA) criteria was analyzed at baseline, including anthropometric data and targeted metabolomics, using liquid chromatography (LC)–mass spectroscopy (MS) and flow injection analysis (FIA)–MS, respectively. All patients were followed for four years. During this time, 11.5% of the patients developed T2DM. After data preprocessing, 362 variables were used for ML, employing the Caret package in R. The dataset was divided into training and test sets (75:25 ratio) and we used an oversampling approach to address the classifier imbalance of T2DM incidence. After an additional recursive feature elimination step, identifying a set of 77 variables that were the most valuable for model generation, a Support Vector Machine (SVM) model with a linear kernel demonstrated the most promising predictive capabilities, exhibiting an F1 score of 50%, a specificity of 93%, and balanced and unbalanced accuracies of 72% and 88%, respectively. The top-ranked features were bile acids, ceramides, amino acids, and hexoses, whereas anthropometric features such as age, sex, waist circumference, or body mass index had no contribution. In conclusion, ML analysis of metabolomics data is a promising tool for identifying individuals at risk of developing T2DM and opens avenues for personalized and early intervention strategies.

Since the onset of the COVID-19 pandemic in March 2020, over 769 million confirmed COVID-19 cases, including close to 7 million COVID-19-related deaths, have been reported. Although mortality rates have dropped notably compared to the first months of the pandemic, spikes in reported cases and mortality rates continue to be registered. Both recent spikes in case numbers and the continued emergence of new variants suggest that vulnerable patient groups, including older adults, immunocompromised patients, and patients with severe comorbidities, are going to continue to be affected by COVID-19. In order to curb the pandemic, relieve the pressure on primary care facilities, and reduce mortality rates, global vaccination programs have been established by the WHO, with over 13.5 billion vaccine doses having been administered globally. In most immunocompetent individuals, vaccination against COVID-19 results in the production of anti-SARS-CoV-2 spike antibodies. However, certain patient subsets have inadequate or reduced immune responses, and immune responses are known to decrease with age. General recommendations on the timing of booster vaccinations may therefore be insufficient to protect vulnerable patients. This review aims to evaluate the clinical role of anti-SARS-CoV-2 antibodies, focusing on measurement indications, prognostic value, and potential as a correlate of protection to guide future booster vaccination strategies.

BACKGROUND: Despite the currently prevailing, milder Omicron variant of COVID-19, older adults remain at elevated risk of hospital admission, critical illness, and death. Loss of efficacy of the immune system, including reduced strength, quality, and durability of antibody responses, may render generalized recommendations on booster vaccinations inadequate. There is a lack of data on the efficacy of antibody levels in older adults and on the utility of vaccination status versus antibody levels as a correlate of protection. It is further unclear whether antibody levels may be used to guide the timing of booster vaccinations in older adults. METHODS: We conducted a prospective multicenter cohort study comprising hospitalized patients with COVID-19. Anti–SARS-CoV-2 spike antibodies were measured on hospital admission. The primary endpoint was in-hospital mortality. Patients were stratified by age, antibody levels, and vaccination status. Multiple logistic regression and Cox regression analyses were conducted. RESULTS: In total, 785 older patients (≥60 years of age [a]) and 367 controls (<60a) were included. After adjusting for confounders, risk of mortality, ICU admission, endotracheal intubation, and oxygen administration was 4.9, 2.6, 6.5, and 2.3 times higher, respectively, if antibody levels were < 1,200 BAU/mL (aOR, 4.92 [95%CI, 2.59–9.34], P < 0.0001; aOR, 2.64 [95%CI, 1.52–4.62], P = 0.0006; aOR, 6.50 [95%CI, 1.48–28.47], P = 0.013; aOR, 2.34 [95%CI, 1.60–3.343], P < 0.0001). Older adults infected with the Omicron variant were approximately 6 times more likely to die if antibody levels were < 1,200 BAU/mL (aOR, 6.3 [95% CI, 2.43–16.40], P = 0.0002). CONCLUSION: Antibody levels were a stronger predictor of in-hospital mortality than vaccination status. Monitoring antibody levels may constitute a better and more direct approach for safeguarding older adults from adverse COVID-19 outcomes.

Objectives: Globally, over 772 million cases of COVID-19 have been reported. New variants of interest with corresponding spikes in case numbers continue to be identified. Vulnerable patients, including older adults or patients with severe comorbidities, continue to be at risk. A large body of evidence has been accumulated regarding anti-SARS-CoV-2-antibodies and COVID-19 but the usefulness of antibody measurements remains unclear. This systematic review aims to assess the prognostic value of anti-SARS-CoV-2-antibodies and their usefulness for guiding booster vaccinations. Methods: Studies in English and published between January 2020 and October 2023 were included. Studies that relied on multiparameter-models or comprised fewer than 100 participants were excluded. PubMed and via the WHO COVID-19 research database, Embase and Medline databases were searched. Study selection and quality assessment was conducted independently by two researchers. Results: After screening 1,160 studies, 33 studies comprising >30 million individuals were included. Anti-SARS-CoV-2-antibodies were strongly associated with reduced risk of SARS-CoV-2-infection and better outcomes, including mortality. Risk of infection and COVID-19 severity decreased with increasing antibody levels. Conclusions: Anti-SARS-CoV-2-antibodies are useful for early identification of high-risk patients and timely adjustment of therapy. Protective thresholds may be applied to advise booster vaccinations but verification in separate cohorts is required.