Past Psychiatric Conditions as Risk Factors for Postpartum Depression

Johansen, Sara L.; Stenhaug, Ben; Robakis, Thalia; Williams, Katherine E.; Cullen, Mark R.

doi:10.4088/jcp.19m12929

Cited by 44 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interrogating our model performance, we found a similar prediction accuracy across maternal age risk groups (Johansen et al, 2020) and for primiparous women, with decrease performance when the population of births was stratified according to history of psychiatric disorder, implying the significant contribution of this predictor to our model. Furthermore, while the main model, based on the entire EHR data, provided a better prediction accuracy, a simpler and easier to implement Q‐based model preformed with only a modest reduction in accuracy.…”

Section: Discussionsupporting

confidence: 67%

Development and validation of a machine learning‐based postpartum depression prediction model: A nationwide cohort study

Hochman

Feldman

Weizman

et al. 2020

Depression and Anxiety

View full text Add to dashboard Cite

Background Currently, postpartum depression (PPD) screening is mainly based on self‐report symptom‐based assessment, with lack of an objective, integrative tool which identifies women at increased risk, before the emergent of PPD. We developed and validated a machine learning‐based PPD prediction model utilizing electronic health record (EHR) data, and identified novel PPD predictors. Methods A nationwide longitudinal cohort that included 214,359 births between January 2008 and December 2015, divided into model training and validation sets, was constructed utilizing Israel largest health maintenance organization's EHR‐database. PPD was defined as new diagnosis of a depressive episode or antidepressant prescription within the first year postpartum. A gradient‐boosted decision tree algorithm was applied to EHR‐derived sociodemographic, clinical, and obstetric features. Results Among the birth cohort, 1.9% (n = 4104) met the case definition of new‐onset PPD. In the validation set, the prediction model achieved an area under the curve (AUC) of 0.712 (95% confidence interval, 0.690–0.733), with a sensitivity of 0.349 and a specificity of 0.905 at the 90th percentile risk threshold, identifying PPDs at a rate more than three times higher than the overall set (positive and negative predictive values were 0.074 and 0.985, respectively). The model's strongest predictors included both well‐recognized (e.g., past depression) and less‐recognized (differing patterns of blood tests) PPD risk factors. Conclusions Machine learning‐based models incorporating EHR‐derived predictors, could augment symptom‐based screening practice by identifying the high‐risk population at greatest need for preventive intervention, before development of PPD.

show abstract

Section: Discussionsupporting

confidence: 67%

Development and validation of a machine learning‐based postpartum depression prediction model: A nationwide cohort study

Hochman

Feldman

Weizman

et al. 2020

Depression and Anxiety

View full text Add to dashboard Cite

show abstract

“…However, one recent study has demonstrated that women with bipolar disorder fear relapse in the context of motherhood (Anke et al, 2019). The association between current or previous mental illness and postpartum depression and/or mental illness is well established (Johansen et al, 2020; Norhayati et al, 2015), and most parents in the present study were aware of being at increased risk. Their fears of going back to a dark place were partly shaped by this knowledge, but these fears were also shaped by their own embodied knowledge and their ability to recognize symptoms, as well as their urgent wish not having to go through this again while having children.…”

Section: Discussionmentioning

confidence: 54%

“…Pregnant women and families facing social and/or psychological challenges, including mental illness, limited social support, young age, poverty, and low socioeconomic status, are considered to be in vulnerable positions as they are at increased risk of adverse birth outcomes and perinatal mental health problems (Daoud et al, 2015; de Graaf et al, 2013; Johansen et al, 2020; Kramer et al, 2000; Norhayati et al, 2015; Schmied et al, 2013). Although a disputed concept (Brown, 2011; Spiers, 2000; Virokannas et al, 2018), vulnerability thus refers to life conditions or situations, which potentially can place an individual at risk of adverse health outcome due to the existence of diverse and interrelated risk factors (de Groot et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Living With Fear: Experiences of Danish Parents in Vulnerable Positions During Pregnancy and in the Postnatal Period

2021

View full text Add to dashboard Cite

Targeted services are recommended to pregnant women/parents in vulnerable positions to support their well-being and improve health outcomes; however, being offered extra services is associated with feelings of fear and anxiety. Adopting an ethnographic approach, we explore what parents fear, how and why they experience fear, and how this shapes their childbearing experience and engagement with Danish maternity care services. We made field observations and conducted interviews with 39 parents in vulnerable positions, who shared multiple, ambiguous, and interrelated fears. Four main themes were constructed: fear of going back to a dark place, of having a negative impact on the baby, of being labeled, and of the consequences of service engagement and being open. We conclude that what parents fear, the intensity of these fears, and what potentially triggers it are contingent on their life story, their care pathways, and the maternity care system.

show abstract

“…Emergency department visits and hospitalizations with a mental health diagnosis as the primary diagnosis within 1 year after birth were identified using International Classification of Diseases codes for visits (see Appendix), a commonly used measure of postpartum mental health. [35][36][37] Preexisting mental health diagnoses were identified based on the presence of these same ICD codes in an ED visit or hospitalization record prior to giving birth, or on the birth record.…”

Section: Mental Health Care Utilizationmentioning

confidence: 99%

The association between preterm birth and postpartum mental healthcare utilization among California birthing people

Calthorpe¹,

Baer²,

Chambers³

et al. 2021

American Journal of Obstetrics & Gynecology MFM

View full text Add to dashboard Cite

Past Psychiatric Conditions as Risk Factors for Postpartum Depression

Cited by 44 publications

References 0 publications

Development and validation of a machine learning‐based postpartum depression prediction model: A nationwide cohort study

Development and validation of a machine learning‐based postpartum depression prediction model: A nationwide cohort study

Living With Fear: Experiences of Danish Parents in Vulnerable Positions During Pregnancy and in the Postnatal Period

The association between preterm birth and postpartum mental healthcare utilization among California birthing people

Contact Info

Product

Resources

About