Materiały źródłowe

• #1 Antenatal prediction of postpartum depression with blood DNA methylation biomarkers – PubMed

  https://pubmed.ncbi.nlm.nih.gov/23689534/

  Postpartum depression (PPD) affects 10-18% of women in the general population and results in serious consequences to both the mother and offspring. […] DNA methylation associated with PPD risk correlated significantly with E2-induced DNA methylation change, suggesting an enhanced sensitivity to estrogen-based DNA methylation reprogramming exists in those at risk for PPD. […] Using the combined mouse and human data, we identified two biomarker loci at the HP1BP3 and TTC9B genes that predicted PPD with an area under the receiver operator characteristic (ROC) curve (area under the curve (AUC)) of 0.87 in antenatally euthymic women and 0.12 in a replication sample of antenatally depressed women. […] Incorporation of blood count data into the model accounted for the discrepancy and produced an AUC of 0.96 across both prepartum depressed and euthymic women. […] Pathway analyses demonstrated that DNA methylation patterns related to hippocampal synaptic plasticity may be of etiological importance to PPD. […] Cell proportion and biomarker DNA methylation predict postpartum depression (PPD).

• #2 Estimation of postpartum depression risk from electronic health records using machine learning | BMC Pregnancy and Childbirth | Full Text

  https://bmcpregnancychildbirth.biomedcentral.com/articles/10.1186/s12884-021-04087-8

  Postpartum depression is a widespread disorder, adversely affecting the well-being of mothers and their newborns. […] PPD risk prediction using EHR data may provide a complementary quantitative and objective tool for PPD screening, allowing earlier (pre-pregnancy) and more accurate identification of women at risk, timely interventions and potentially improved outcomes for the mother and child. […] The prevalence of PPD in the analyzed cohort was 13.4%. […] The PPD outcome criteria was met by 35,708 patients (13.4%). […] Our machine learning-based models achieved fair prediction performance and provided additive value to existing screening tools (EPDS). Furthermore, it allowed early alert of PPD risk prior to pregnancy. Incorporation of such models in the workflow of PPD screening may improve the subjectivity and accuracy of the screening process, enable timely interventions and consequently contribute to improved outcomes for the mother and child.

• #3 Predicting women with depressive symptoms postpartum with machine learning methods | Scientific Reports

  https://www.nature.com/articles/s41598-021-86368-y

  Postpartum depression (PPD) is a detrimental health condition that affects 12% of new mothers. […] Despite PPD being a detrimental health condition for many women, numerous affected women fail to receive adequate care. […] The variables setting women at most risk for PPD were depression and anxiety during pregnancy, as well as variables related to resilience and personality. […] Future clinical models that could be implemented directly after delivery might consider including these variables in order to identify women at high risk for postpartum depression to facilitate individualized follow-up and cost-effectiveness. […] The strongest psychosocial factors are previous depression, severe life events, some forms of chronic stress and relationship struggles. […] The predictive algorithms reach an accuracy for the whole group of 73% and AUC of 81%, which is at the limit for possible use in clinical settings. […] These results suggest a possible benefit of using ML to screen new mothers at discharge from the delivery ward in order to identify those at high risk for postpartum depressive symptoms. […] The predictive algorithms have relatively good accuracy and AUC, with XRT performing best.

• #4 Prognosis of Postnatal Depression | Hospital Clínic Barcelona

  https://www.clinicbarcelona.org/en/assistance/diseases/postnatal-depression/progression-of-the-disease

  The recovery from a postnatal depression is slightly slower than that of the depression in other times of the life cycle. More than 50% of the women with postnatal depression need one year to completely recover, and one in every 10 have some symptoms that will persist, particularly if they did not receive adequate treatment. […] Recovery is more difficult and longer for women that have had previous depressive episodes or during the pregnancy and in difficult socio-economic situations. […] Furthermore, postnatal depression, particularly if it is severe and/or has become chronic, has a negative impact on the cognitive, emotional, and behavioural development of the children. The exposure to maternal depression in the first years of life is a risk factor for neurodevelopment. This impact, however, is not irreversible. The cognitive effects can improve with adequate treatment of the PND.

• #5 Postpartum depression

  https://womenshealth.gov/mental-health/mental-health-conditions/postpartum-depression

  Depression is a common problem after pregnancy. One in 8 new mothers report experiencing symptoms of postpartum depression in the year after childbirth. […] The U.S. Preventive Services Task Force recommends that doctors look for and ask about symptoms of depression during and after pregnancy, regardless of a woman’s risk of depression. […] Researchers believe postpartum depression in a mother can affect the healthy development of her child which can cause delays in language development and problems learning, problems with mother-child bonding, behavior problems, more crying or agitation, shorter height and higher risk of obesity in pre-schoolers, and problems dealing with stress and adjusting to school and other social situations. […] Untreated postpartum depression can affect your ability to parent. You may not have enough energy, have trouble focusing on the baby’s needs and your own needs, feel moody, not be able to care for your baby, and have a higher risk of attempting suicide.

• #6 Suicide in Postpartum Women: Can We Predict Who is at Risk? – MGH Center for Women’s Mental Health

  https://womensmentalhealth.org/posts/10746/

  Women are at significant risk for severe psychiatric illness after childbirth, particularly during the first three months. […] In order to reliably identify factors which predict risk for suicide, we need to be able to study large numbers of postpartum women. […] The maternal suicide rate was about threefold higher in women born in low-income countries. […] Unnatural cause of death represented about 40% of fatalities among women with postpartum psychiatric illness. […] Suicide risk increased dramatically and was nearly 300 times higher in the women with postpartum psychiatric illness than the suicide risk observed in women with no psychiatric history. […] While many women who attempt suicide during the postpartum period have contact with a mental health provider at some point prior to making an attempt, the Swedish study noted that about a quarter of the women who committed suicide had no history of psychiatric care.

• #7 Long-term outcome of postpartum psychosis: a prospective clinical cohort study in 106 women | International Journal of Bipolar Disorders | Full Text

  https://journalbipolardisorders.springeropen.com/articles/10.1186/s40345-021-00236-2

  Over two thirds of the women included in this study did not have major psychiatric episodes outside of the postpartum period during follow-up. […] The overall recurrence rate of mood/psychotic episodes outside the postpartum period was~32%. […] None of the women fulfilled diagnostic criteria for schizophrenia or schizophreniform disorder. […] No clinical markers significantly predicted recurrence outside of the postpartum period. […] For the majority of women with first-onset postpartum psychosis, the risk of illness was limited to the period after childbirth. […] For the remaining women, postpartum psychosis was part of a mood/psychotic disorder with severe non-postpartum recurrence, mainly in the bipolar spectrum. […] No clinical predictors for risk of severe episodes outside the postpartum period emerged.

• #8 Long-term outcome of postpartum psychosis: a prospective clinical cohort study in 106 women | International Journal of Bipolar Disorders | Full Text

  https://journalbipolardisorders.springeropen.com/articles/10.1186/s40345-021-00236-2

  Currently, little is known about which women are specifically at risk for recurrence outside the postpartum period. […] However, these studies were small and conducted retrospectively. […] Consequently, this prospective longitudinal study was designed to investigate recurrence in 106 women with postpartum psychosis over a four-year period. […] Understanding who is at risk of a mood or psychotic disorder during follow-up, and whose vulnerability is limited to the postpartum period, is particularly important in guiding treatment decisions including long-term pharmacotherapy. […] Unfortunately, no biomarkers are currently available to help guide these decisions. […] In clinical practice, this means that long-term monitoring is warranted for everyone with postpartum psychosis. […] Another reason for long-term monitoring are the high suicide rates during follow-up, reported by other studies. […] For the remaining women, postpartum psychosis was part of a mood or psychotic disorder with severe non-postpartum recurrence, mainly in the bipolar spectrum. […] No clinical predictors of a woman’s risk of severe episodes outside the postpartum period were found.

• #9 Long-term outcome of postpartum psychosis: a prospective clinical cohort study in 106 women | International Journal of Bipolar Disorders | Full Text

  https://journalbipolardisorders.springeropen.com/articles/10.1186/s40345-021-00236-2

  Our findings add to previous evidence suggesting a fundamental link between postpartum psychosis and bipolar disorder, which may represent two distinct diagnoses within the same spectrum. […] Despite the widespread use of the term postpartum psychosis, this diagnosis is not recognized in current classification systems, including the International Classification of Diseases, Tenth Revision (ICD-10) and the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5). […] It is important to note that most studies included in the meta-analysis were performed in the 1970s and 1980s, limiting the generalizability of the results. […] In addition, to improve long-term prognosis, it is pertinent to identify those women who may develop severe mood episodes outside the postpartum period.

• #10 Accuracy of the Edinburgh Postnatal Depression Scale (EPDS) for screening to detect major depression among pregnant and postpartum women: systematic review and meta-analysis of individual participant data | The BMJ

  https://www.bmj.com/content/371/bmj.m4022

  An EPDS cut-off value of 11 or higher maximised combined sensitivity and specificity; a cut-off value of 13 or higher was less sensitive but more specific. […] Our main finding was that combined sensitivity and specificity was maximised at a cut-off value of 11 or higher across reference standards. […] Accuracy was similar across reference standards, similar among pregnant and postpartum women, and similar based on other study and participant characteristics. […] The present study found that an EPDS cut-off value of 11 or higher maximised combined sensitivity and specificity. […] Clinicians considering screening for depression with the EPDS can refer to our online knowledge translation tool (depressionscreening100.com/epds) to identify alternative cut-off values that maximise other parameters.

• #11 Predicting allergy and postpartum depression from an incomplete compositional microbiome | bioRxiv

  https://www.biorxiv.org/content/10.1101/2025.02.28.640766v2.full

  Time series of compositional data are a common format for many high-throughput studies of biological molecules, e.g., analyzing the response to a treatment or with the aim of predicting an outcome. […] We forecast postpartum depression based on gut microbiome data collected during pregnancy, with a balanced accuracy of 0.62. Features extracted from the microbiome time series, specifically ratios of bacterial abundance, are statistically significant indicators of depression. […] Between 12% and 20% of mothers experience postpartum depression within the first three months after childbirth. […] Identifying such predictors can help detect depression earlier and facilitate timely treatment. […] For forecasting postpartum depression at six weeks after childbirth based on data collected during pregnancy, the balanced accuracy is 0.62, with a corresponding sensitivity of 0.39. […] We achieved a balanced accuracy of 0.62 and a sensitivity of 0.39, statistically outperforming random guessing and surpassing the accuracy of predictions on the basis of depression states observed during pregnancy.

• #12 Prediction of postpartum depression in women: development and validation of multiple machine learning models | Journal of Translational Medicine | Full Text

  https://translational-medicine.biomedcentral.com/articles/10.1186/s12967-025-06289-6

  The PPD outcome was assessed using the Edinburgh Postnatal Depression Scale at 6 weeks postpartum. […] The discrimination, calibration, and clinical net benefit were best in the LR and ANN models (for both PN-PPD and PP-PPD models). Collectively, the newly developed LR and ANN models, which incorporated readily available prenatal and postnatal variables, performed well, as supported by the AUC values of 0.7870.858 in the validation set. […] In this study, by combining biopsychosocial risk factors for PPD, we developed and validated ML predictive models to identify the risk of PPD. The LR and ANN models showed excellent and reliable prediction performance. Combining prenatal and postnatal predictors to establish predictive models can significantly improve prediction performance. Various risk assessment tools are easily implemented in practice and could help physicians make clinical decisions easily.

• #13 Machine Learning-Based Predictive Modeling of Postpartum Depression

  https://www.mdpi.com/2077-0383/9/9/2899

  This approach was previously evaluated and achieved a sensitivity of 63% and specificity of 83% for identifying postpartum depression cases. […] The classification performance of the nine ML models on Set 1 is illustrated in a ROC curve. […] Overall, the RF method achieved the highest area under the ROC curve (AUC) value, 0.884, followed by SVM with an AUC of 0.864. […] These results imply little variation across our models and that our models do not overfit the data—a characteristic of good ML models. […] In this study, prenatal depression was associated with postpartum depressive symptoms; the high prevalence of depression and suicidal ideation during adolescence and young adulthood may reflect family societal pressure on women to achieve high academic standards and perform traditional gender roles.

• #14 Investigating heart rate variability measures during pregnancy as predictors of postpartum depression and anxiety: an exploratory study | Translational Psychiatry

  https://www.nature.com/articles/s41398-024-02909-9

  Perinatal affective disorders are common, but standard screening measures reliant on subjective self-reports might not be sufficient to identify pregnant women at-risk for developing postpartum depression and anxiety. […] Lower heart rate variability (HRV) has been shown to be associated with affective disorders. […] Group comparisons indicated that lower pregnancy HRV was associated with depressive or anxious symptomatology at 6 weeks postpartum. […] Elastic net logistic regression analyses indicated that HRV indices alone were not predictive of postpartum depression or anxiety outcomes, but HRV indices were selected as predictors in a combined model with background and pregnancy variables. […] HRV indices predictive of postpartum depression generally differed from those predictive of postpartum anxiety.

• #15 Investigating heart rate variability measures during pregnancy as predictors of postpartum depression and anxiety: an exploratory study | Translational Psychiatry

  https://www.nature.com/articles/s41398-024-02909-9

  The majority of HRV indices predictive of symptoms of postpartum depression in the combined model were from the baseline measurement preceding the stressor, strongly suggesting that HRV alterations during resting-state have predictive value for depressive symptoms. […] With the exception of SDNN after stressor measurement, HRV indices predictive for the anxiety outcome in the combined model differed from those predictive in the depression outcome. […] The current study does not provide evidence for the use of HRV indices for prediction of postpartum depression and anxiety in women with known pregnancy depression and anxiety.

• #16 Machine Learning-Based Predictive Modeling of Postpartum Depression

  https://www.mdpi.com/2077-0383/9/9/2899

  Postpartum depression is a serious health issue beyond the mental health problems that affect mothers after childbirth. There are no predictive tools available to screen postpartum depression that also allow early interventions. […] Predictive modeling developed using ML-approaches may thus be used as a prediction (screening) tool for postpartum depression in future studies. […] Although these independent risk factors for postpartum depression are known, little is known about the predictive modeling of postpartum depression that includes maternal and paternal risk factors. […] The overall study objective was to develop and validate ML-based predictive models for postpartum depression using both maternal and paternal characteristics from the PRAMS 2012–2013 data. […] The diagnosis of postpartum depression was based on a modified version of the Patient Health Questionnaire-2 (PHQ-2).

Zobacz więcej