SAT-122 The Role of Targeted Plasma Proteomics for Identifying Inflammatory Signatures Associated with Risk for Perinatal Depression
Bibliographic record
Abstract
Abstract Disclosure: E. Braybrook: None. K. Natasha: None. D. Grammatopoulos: None. Depressive symptoms experienced either during pregnancy or postpartum, collectively termed perinatal depression (PND) affects around 17% of women globally, with significant impact to both the mother and child’s health. The underpinning mechanisms are not yet fully understood, however dysregulation of the HPA axis is believed to be central, with impairment of neurotransmitter function also linked to inflammation. Additionally, the occurrence of depression antenatally is shown to be a significant risk factor in the development of postpartum depression. Clinicians currently use questionnaires as the primary tool to identify risk of depression, however their performance is inadequate and only one fifth of women who experience PND actively seek help. Biomarker-based screening strategies might offer an additional tool for earlier identification, stratification and development of targeted therapies. Plasma proteomics is emerging as a powerful tool, enabling both improved understanding of key biological processes through the generation of molecular profiles, and the identification of novel biomarkers for disease prediction. This study analysed serum samples from 260 women between 24-28 weeks gestation, with risk of depression assessed through the Edinburgh Postnatal Depression Questionnaire. To capture depressive symptoms either during pregnancy or postpartum, scores were obtained between 24-29 weeks gestation and again 6-10 weeks postpartum, with a cut-off score of 10 used to indicate increased risk. 92 inflammatory markers were analysed in the serum samples using Olink Proseek Multiplex Inflammation I panel, utilising a proximity extension assay. Differential expression analysis revealed distinct profiles between the antenatal and postnatal depression groups. Machine learning models (e.g. Random Forrest, Classification and Regression Tree and Pearsons Chi-square Statistic) were applied to the data using SPSS Modeler, with similarities across the outputs in key proteins identified (STAMPB, SIRT2, AXIN1, LAP TGF-beta-1, IL-10, MMP-10 and IL17C). In addition, differing psychosocial variables were highlighted as contributing factors across the two groups (history of anxiety or depression in antenatal and family history of PND in postnatal). Functional enrichment analyses further explored the biological functions of key proteins. This work highlights the value of targeted proteomics approaches coupled with machine learning in uncovering biomarker signatures that add to our understanding of the underlying biological mechanisms of PND. Alterations in inflammatory protein networks suggest distinct mechanisms between antenatal and postnatal depression. Application of biomarker tools, incorporating key proteins alongside patient history, could pave the way for personalised PND diagnosis and development of novel therapies. Presentation: Saturday, July 12, 2025
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".