NMR Spectroscopic Windows on the Systemic Effects of SARS-CoV-2 Infection on Plasma Lipoproteins and Metabolites in Relation to Circulating Cytokines

To investigate the systemic metabolic effects of SARS-CoV-2 infection, we analyzed 1H NMR spectroscopic data on human blood plasma and co-modeled with multiple plasma cytokines and chemokines (measured in parallel). Thus, 600 MHz 1H solvent-suppressed single-pulse, spin-echo, and 2D J-resolved spectra were collected on plasma recorded from SARS-CoV-2 rRT-PCR-positive patients (n = 15, with multiple sampling timepoints) and age-matched healthy controls (n = 34, confirmed rRT-PCR negative), together with patients with COVID-19/influenza-like clinical symptoms who tested SARS-CoV-2 negative (n = 35). We compared the single-pulse NMR spectral data with in vitro diagnostic research (IVDr) information on quantitative lipoprotein profiles (112 parameters) extracted from the raw 1D NMR data. All NMR methods gave highly significant discrimination of SARS-CoV-2 positive patients from controls and SARS-CoV-2 negative patients with individual NMR methods, giving different diagnostic information windows on disease-induced phenoconversion. Longitudinal trajectory analysis in selected patients indicated that metabolic recovery was incomplete in individuals without detectable virus in the recovery phase. We observed four plasma cytokine clusters that expressed complex differential statistical relationships with multiple lipoproteins and metabolites. These included the following: cluster 1, comprising MIP-1β, SDF-1α, IL-22, and IL-1α, which correlated with multiple increased LDL and VLDL subfractions; cluster 2, including IL-10 and IL-17A, which was only weakly linked to the lipoprotein profile; cluster 3, which included IL-8 and MCP-1 and were inversely correlated with multiple lipoproteins. IL-18, IL-6, and IFN-γ together with IP-10 and RANTES exhibited strong positive correlations with LDL1-4 subfractions and negative correlations with multiple HDL subfractions. Collectively, these data show a distinct pattern indicative of a multilevel cellular immune response to SARS CoV-2 infection interacting with the plasma lipoproteome giving a strong and characteristic immunometabolic phenotype of the disease. We observed that some patients in the respiratory recovery phase and testing virus-free were still metabolically highly abnormal, which indicates a new role for these technologies in assessing full systemic recovery.

Integrative Modeling of Plasma Metabolic and Lipoprotein Biomarkers of SARS-CoV-2 Infection in Spanish and Australian COVID-19 Patient Cohorts

Quantitative plasma lipoprotein and metabolite profiles were measured on an autonomous community of the Basque Country (Spain) cohort consisting of hospitalized COVID-19 patients (n = 72) and a matched control group (n = 75) and a Western Australian (WA) cohort consisting of (n = 17) SARS-CoV-2 positives and (n = 20) healthy controls using 600 MHz ¹H nuclear magnetic resonance (NMR) spectroscopy. Spanish samples were measured in two laboratories using one-dimensional (1D) solvent-suppressed and T₂-filtered methods with in vitro diagnostic quantification of lipoproteins and metabolites. SARS-CoV-2 positive patients and healthy controls from both populations were modeled and cross-projected to estimate the biological similarities and validate biomarkers. Using the top 15 most discriminatory variables enabled construction of a cross-predictive model with 100% sensitivity and specificity (within populations) and 100% sensitivity and 82% specificity (between populations). Minor differences were observed between the control metabolic variables in the two cohorts, but the lipoproteins were virtually indistinguishable. We observed highly significant infection-related reductions in high-density lipoprotein (HDL) subfraction 4 phospholipids, apolipoproteins A1 and A2,that have previously been associated with negative regulation of blood coagulation and fibrinolysis. The Spanish and Australian diagnostic SARS-CoV-2 biomarkers were mathematically and biologically equivalent, demonstrating that NMR-based technologies are suitable for the study of the comparative pathology of COVID-19 via plasma phenotyping.

Modeling community integration in workers with delayed recovery from mild traumatic brain injury

BACKGROUND

Delayed recovery in persons after mild traumatic brain injury (mTBI) is poorly understood. Community integration (CI) is endorsed by persons with neurological disorders as an important outcome. We aimed to describe CI and its associated factors in insured Ontario workers with delayed recovery following mTBI.

METHODS

A cross-sectional study of insured workers in the chronic phase following mTBI was performed at a rehabilitation hospital in Ontario, Canada. Sociodemographic, occupational, injury-related, clinical, and claim-related data were collected from self-reports, medical assessments, and insurers' referral files. Community Integration Questionnaire (CIQ) scores were compared using analysis of variance or Spearman's correlation tests. Stepwise multivariable linear regression models were used to evaluate the associations with CI.

RESULTS

Ninety-four workers with mTBI (45.2 ± 9.9 years old, 61.2% male) at 197 days post-injury (interquartile range, 139-416 days) were included. The CIQ total and subscale scores were similar to those reported in more severe TBI samples. The CIQ scores were moderately to strongly correlated with various sociodemographic, claim-related, and clinical variables. In the multivariable regression analysis, several covariates accounted for 36.4% of the CIQ variance in the final fully adjusted model.

DISCUSSION

This study evaluated CI in workers with mTBI, and analyzed its associated variables. Analysis revealed insomnia, head or neck pain, being married or in a relationship, time since injury, and a diagnosis of possible/probable malingering were independently associated with limited CI.

CONCLUSIONS

Workers with delayed recovery from mTBI experience difficulty with CI. Insomnia is a particularly relevant covariate, explaining the greater part of its variance. To enhance participation, care should focus on clinical and non-clinical covariates.

Applied artificial intelligence in dentistry: emerging data modalities and modeling approaches

Artificial intelligence (AI) is increasingly applied across all disciplines of medicine, including dentistry. Oral health research is experiencing a rapidly increasing use of machine learning (ML), the branch of AI that identifies inherent patterns in data similarly to how humans learn. In contemporary clinical dentistry, ML supports computer-aided diagnostics, risk stratification, individual risk prediction, and decision support to ultimately improve clinical oral health care efficiency, outcomes, and reduce disparities. Further, ML is progressively used in dental and oral health research, from basic and translational science to clinical investigations. With an ML perspective, this review provides a comprehensive overview of how dental medicine leverages AI for diagnostic, prognostic, and generative tasks. The spectrum of available data modalities in dentistry and their compatibility with various methods of applied AI are presented. Finally, current challenges and limitations as well as future possibilities and considerations for AI application in dental medicine are summarized.

Machine learning-based predictive models and drug prediction for schizophrenia in multiple programmed cell death patterns

Background

Schizophrenia (SC) is one of the most common mental illnesses. However, the underlying genes that cause it and its effective treatments are unknown. Programmed cell death (PCD) is associated with many immune diseases and plays an important role in schizophrenia, which may be a diagnostic indicator of the disease.

Methods

Two groups as training and validation groups were chosen for schizophrenia datasets from the Gene Expression Omnibus Database (GEO). Furthermore, the PCD-related genes of the 12 patterns were extracted from databases such as KEGG. Limma analysis was performed for differentially expressed genes (DEG) identification and functional enrichment analysis. Machine learning was employed to identify minimum absolute contractions and select operator (LASSO) regression to determine candidate immune-related center genes, construct protein-protein interaction networks (PPI), establish artificial neural networks (ANN), and validate with consensus clustering (CC) analysis, then Receiver operating characteristic curve (ROC curve) was drawn for diagnosis of schizophrenia. Immune cell infiltration was developed to investigate immune cell dysregulation in schizophrenia, and finally, related drugs with candidate genes were collected via the Network analyst online platform.

Results

In schizophrenia, 263 genes were crossed between DEG and PCD-related genes, and machine learning was used to select 42 candidate genes. Ten genes with the most significant differences were selected to establish a diagnostic prediction model by differential expression profiling. It was validated using artificial neural networks (ANN) and consensus clustering (CC), while ROC curves were plotted to assess diagnostic value. According to the findings, the predictive model had a high diagnostic value. Immune infiltration analysis revealed significant differences in Cytotoxic and NK cells in schizophrenia patients. Six candidate gene-related drugs were collected from the Network analyst online platform.

Conclusion

Our study systematically discovered 10 candidate hub genes (DPF2, ATG7, GSK3A, TFDP2, ACVR1, CX3CR1, AP4M1, DEPDC5, NR4A2, and IKBKB). A good diagnostic prediction model was obtained through comprehensive analysis in the training (AUC 0.91, CI 0.95-0.86) and validation group (AUC 0.94, CI 1.00-0.85). Furthermore, drugs that may be useful in the treatment of schizophrenia have been obtained (Valproic Acid, Epigallocatechin gallate).

Diagnosis of Benign and Malignant Newly Developed Nodules on the Surgical Side After Breast Cancer Surgery Based on Machine Learning

Objective: To enhance the diagnostic accuracy of new nodules on the surgical side after breast cancer surgery using machine learning techniques and to explore the role of multifeature fusion. Methods: Data from 137 breast cancer postoperative patients with new nodules from January 2016 to April 2024 were analyzed. Clinical, ultrasound, immunohistochemistry, and surgical features were combined. Multiple machine learning models, including support vector machine (SVM), random forest, gradient boosting, AdaBoost, and XGBoost, were trained and tested. Model performance was evaluated using stratified ten-fold cross-validation. Ablation experiments assessed the impact of different feature combinations on diagnostic performance. Results: The SVM model performed best, with an AUC of 0.8664, an accuracy of 0.8099, a sensitivity of 0.565, and a specificity of 0.9267. Ablation experiments indicated that multifeature fusion significantly improved diagnostic performance, especially when combining clinical, ultrasound, immunohistochemistry, and surgical features. Gradient boosting and random forest models showed slightly inferior performance, while AdaBoost had balanced but lower effectiveness. Conclusion: Machine learning, particularly the multifeature fusion SVM model, shows significant potential in diagnosing new nodules after breast cancer surgery. It can assist doctors in developing more effective treatment plans, improving patient outcomes. Future studies should expand sample sizes, include multicenter data, and explore advanced algorithms to further enhance diagnostic performance.

Identification of schizophrenia by applying interpretable radiomics modeling with structural magnetic resonance imaging of the cerebellum

AIMS

The cerebellum is involved in higher-order mental processing as well as sensorimotor functions. Although structural abnormalities in the cerebellum have been demonstrated in schizophrenia, neuroimaging techniques are not yet applicable to identify them given the lack of biomarkers. We aimed to develop a robust diagnostic model for schizophrenia using radiomic features from T1-weighted magnetic resonance imaging (T1-MRI) of the cerebellum.

METHODS

A total of 336 participants (174 schizophrenia; 162 healthy controls [HCs]) were allocated to training (122 schizophrenia; 115 HCs) and test (52 schizophrenia; 47 HCs) cohorts. We obtained 2568 radiomic features from T1-MRI of the cerebellar subregions. After feature selection, a light gradient boosting machine classifier was trained. The discrimination and calibration of the model were evaluated. SHapley Additive exPlanations (SHAP) was applied to determine model interpretability.

RESULTS

We identified 17 radiomic features to differentiate participants with schizophrenia from HCs. In the test cohort, the radiomics model had an area under the curve, accuracy, sensitivity, and specificity of 0.89 (95% confidence interval: 0.82-0.95), 78.8%, 88.5%, and 75.4%, respectively. The model explanation by SHAP suggested that the second-order size zone non-uniformity feature from the right lobule IX and first-order energy feature from the right lobules V and VI were highly associated with the risk of schizophrenia.

CONCLUSION

The radiomics model focused on the cerebellum demonstrates robustness in diagnosing schizophrenia. Our results suggest that microcircuit disruption in the posterior cerebellum is a disease-defining feature of schizophrenia, and radiomics modeling has potential for supporting biomarker-based decision-making in clinical practice.

Stratification of Sepsis Patients on Admission into the Intensive Care Unit According to Differential Plasma Metabolic Phenotypes

Delayed diagnosis of patients with sepsis or septic shock is associated with increased mortality and morbidity. UPLC-MS and NMR spectroscopy were used to measure panels of lipoproteins, lipids, biogenic amines, amino acids, and tryptophan pathway metabolites in blood plasma samples collected from 152 patients within 48 h of admission into the Intensive Care Unit (ICU) where 62 patients had no sepsis, 71 patients had sepsis, and 19 patients had septic shock. Patients with sepsis or septic shock had higher concentrations of neopterin and lower levels of HDL cholesterol and phospholipid particles in comparison to nonsepsis patients. Septic shock could be differentiated from sepsis patients based on different concentrations of 10 lipids, including significantly lower concentrations of five phosphatidylcholine species, three cholesterol esters, one dihydroceramide, and one phosphatidylethanolamine. The Supramolecular Phospholipid Composite (SPC) was reduced in all ICU patients, while the composite markers of acute phase glycoproteins were increased in the sepsis and septic shock patients within 48 h admission into ICU. We show that the plasma metabolic phenotype obtained within 48 h of ICU admission is diagnostic for the presence of sepsis and that septic shock can be differentiated from sepsis based on the lipid profile.