Multimodal Data Integration Advances Longitudinal Prediction of the Naturalistic Course of Depression and Reveals a Multimodal Signature of Remission During 2-Year Follow-up.

BACKGROUND: The ability to predict the disease course of individuals with major depressive disorder (MDD) is essential for optimal treatment planning. Here, we used a data-driven machine learning approach to assess the predictive value of different sets of biological data (whole-blood proteomics, lipid metabolomics, transcriptomics, genetics), both separately and added to clinical baseline variables, for the longitudinal prediction of 2-year remission status in MDD at the individual-subject level. METHODS: Prediction models were trained and cross-validated in a sample of 643 patients with current MDD (2-year remission n = 325) and subsequently tested for performance in 161 individuals with MDD (2-year remission n = 82). RESULTS: Proteomics data showed the best unimodal data predictions (area under the receiver operating characteristic curve = 0.68). Adding proteomic to clinical data at baseline significantly improved 2-year MDD remission predictions (area under the receiver operating characteristic curve = 0.63 vs. 0.78, p = .013), while the addition of other omics data to clinical data did not yield significantly improved model performance. Feature importance and enrichment analysis revealed that proteomic analytes were involved in inflammatory response and lipid metabolism, with fibrinogen levels showing the highest variable importance, followed by symptom severity. Machine learning models outperformed psychiatrists' ability to predict 2-year remission status (balanced accuracy = 71% vs. 55%). CONCLUSIONS: This study showed the added predictive value of combining proteomic data, but not other omics data, with clinical data for the prediction of 2-year remission status in MDD. Our results reveal a novel multimodal signature of 2-year MDD remission status that shows clinical potential for individual MDD disease course predictions from baseline measurements.

Transcriptional and cell type profiles of cortical brain regions showing ultradian cortisol rhythm dependent responses to emotional face stimulation.

The characteristic endogenous circadian rhythm of plasma glucocorticoid concentrations is made up from an underlying ultradian pulsatile secretory pattern. Recent evidence has indicated that this ultradian cortisol pulsatility is crucial for normal emotional response in man. In this study, we investigate the anatomical transcriptional and cell type signature of brain regions sensitive to a loss of ultradian rhythmicity in the context of emotional processing. We combine human cell type and transcriptomic atlas data of high spatial resolution with functional magnetic resonance imaging (fMRI) data. We show that the loss of cortisol ultradian rhythm alters emotional processing response in cortical brain areas that are characterized by transcriptional and cellular profiles of GABAergic function. We find that two previously identified key components of rapid non-genomic GC signaling - the ANXA1 gene and retrograde endocannabinoid signaling - show most significant differential expression (q = 3.99e-10) and enrichment (fold enrichment = 5.56, q = 9.09e-4). Our results further indicate that specific cell types, including a specific NPY-expressing GABAergic neuronal cell type, and specific G protein signaling cascades underly the cerebral effects of a loss of ultradian cortisol rhythm. Our results provide a biological mechanistic underpinning of our fMRI findings, indicating specific cell types and cascades as a target for manipulation in future experimental studies.

Development and validation of a machine-learning algorithm to predict the relevance of scientific articles within the field of teratology.

The Dutch Teratology Information Service Lareb counsels healthcare professionals and patients about medication use during pregnancy and lactation. To keep the evidence up to date, employees perform a standardized weekly PubMed query where relevant literature is identified manually. We aimed to develop an accurate machine-learning algorithm to predict the relevance of PubMed entries, thereby reducing the labor-intensive task of manually screening the articles. We fine-tuned a pre-trained natural language processing transformer model to identify relevant entries. We split 15,540 labeled entries into case-control-balanced train, validation, and test datasets. Additionally, we externally validated the model prospectively with 1288 labeled entries obtained from weekly queries after developing the model. This dataset was also independently labeled by a team of six experienced human raters to evaluate our model's performance. The validation of our machine learning model on the retrospectively collected outheld dataset obtained an area under the sensitivity-versus-specificity curve of 89.3 % (CI: 88.2- 90.4). In the prospective external validation of the model, our model classified relevant literature with a sensitivity versus specificity curve area of 87.4 % (CI: 85.0-89.8). Our model achieved a higher sensitivity than the human raters' team without sacrificing too much specificity. The team of human raters showed weak to moderate levels of agreement in their article classifications (kappa range 0.40-0.64). The human selection of the latest relevant literature is indispensable to keep the teratology information up to date. We show that automatic preselection of relevant abstracts using machine learning is possible without sacrificing the selection performance.

Mineralocorticoid receptor status in the human brain after dexamethasone treatment: a single case study.

Background: Synthetic glucocorticoids like dexamethasone can cause severe neuropsychiatric effects. They preferentially bind to the glucocorticoid receptor (GR) over the mineralocorticoid receptor (MR). High dosages result in strong GR activation but likely also result in lower MR activation based on GR-mediated negative feedback on cortisol levels. Therefore, reduced MR activity may contribute to dexamethasone-induced neuropsychiatric symptoms. Objective: In this single case study, we evaluate whether dexamethasone leads to reduced MR activation in the human brain. Brain tissue of an 8-year-old brain tumor patient was used, who suffered chronically from dexamethasone-induced neuropsychiatric symptoms and deceased only hours after a high dose of dexamethasone. Main outcome measures: The efficacy of dexamethasone to induce MR activity was determined in HEK293T cells using a reporter construct. Subcellular localization of GR and MR was assessed in paraffin-embedded hippocampal tissue from the patient and two controls. In hippocampal tissue from the patient and eight controls, mRNA of MR/GR target genes was measured. Results: In vitro, dexamethasone stimulated MR with low efficacy and low potency. Immunofluorescence showed the presence of both GR and MR in the hippocampal cell nuclei after dexamethasone exposure. The putative MR target gene JDP2 was consistently expressed at relatively low levels in the dexamethasone-treated brain samples. Gene expression showed substantial variation in MR/GR target gene expression in two different hippocampus tissue blocks from the same patient. Conclusions: Dexamethasone may induce MR nuclear translocation in the human brain. Conclusions on in vivo effects on gene expression in the brain await the availability of more tissue of dexamethasone-treated patients.

Analysis of 567,758 randomized controlled trials published over 30 years reveals trends in phrases used to discuss results that do not reach statistical significance.

The power of language to modify the reader's perception of interpreting biomedical results cannot be underestimated. Misreporting and misinterpretation are pressing problems in randomized controlled trials (RCT) output. This may be partially related to the statistical significance paradigm used in clinical trials centered around a P value below 0.05 cutoff. Strict use of this P value may lead to strategies of clinical researchers to describe their clinical results with P values approaching but not reaching the threshold to be "almost significant." The question is how phrases expressing nonsignificant results have been reported in RCTs over the past 30 years. To this end, we conducted a quantitative analysis of English full texts containing 567,758 RCTs recorded in PubMed between 1990 and 2020 (81.5% of all published RCTs in PubMed). We determined the exact presence of 505 predefined phrases denoting results that approach but do not cross the line of formal statistical significance (P < 0.05). We modeled temporal trends in phrase data with Bayesian linear regression. Evidence for temporal change was obtained through Bayes factor (BF) analysis. In a randomly sampled subset, the associated P values were manually extracted. We identified 61,741 phrases in 49,134 RCTs indicating almost significant results (8.65%; 95% confidence interval (CI): 8.58% to 8.73%). The overall prevalence of these phrases remained stable over time, with the most prevalent phrases being "marginally significant" (in 7,735 RCTs), "all but significant" (7,015), "a nonsignificant trend" (3,442), "failed to reach statistical significance" (2,578), and "a strong trend" (1,700). The strongest evidence for an increased temporal prevalence was found for "a numerical trend," "a positive trend," "an increasing trend," and "nominally significant." In contrast, the phrases "all but significant," "approaches statistical significance," "did not quite reach statistical significance," "difference was apparent," "failed to reach statistical significance," and "not quite significant" decreased over time. In a random sampled subset of 29,000 phrases, the manually identified and corresponding 11,926 P values, 68,1% ranged between 0.05 and 0.15 (CI: 67. to 69.0; median 0.06). Our results show that RCT reports regularly contain specific phrases describing marginally nonsignificant results to report P values close to but above the dominant 0.05 cutoff. The fact that the prevalence of the phrases remained stable over time indicates that this practice of broadly interpreting P values close to a predefined threshold remains prevalent. To enhance responsible and transparent interpretation of RCT results, researchers, clinicians, reviewers, and editors may reduce the focus on formal statistical significance thresholds and stimulate reporting of P values with corresponding effect sizes and CIs and focus on the clinical relevance of the statistical difference found in RCTs.

Brain areas affected by intranasal oxytocin show higher oxytocin receptor expression.

Neuroimaging studies suggest that intranasal oxytocin (IN-OXT) may modulate emotional and social processes by altering neural activity patterns. The extent of brain penetration after IN-OXT is unclear, and it is currently unknown whether IN-OXT can directly bind central oxytocin receptors (OXTRs). We investigated oxytocin pathway gene expression in regions affected by IN-OXT on task-based fMRI. We found that OXTR is more highly expressed in affected than unaffected subcortical regions; this effect did not vary by task type or sex. Cortical results revealed higher OXTR expression in regions affected by IN-OXT in emotional processing tasks and in male-only data. No significant differences were found in expression of the closely related vasopressin receptors. Our findings suggest that the mechanism by which IN-OXT may alter brain functionality involves direct activation of central OXTRs.