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

Hochman, Eldar; Feldman, Becca; Weizman, Abraham; Krivoy, Amir; Gur, Shay; Gabay, Hagit; Levy, Joseph; Levinkron, Ohad; Lawrence, Gabriella

doi:10.1002/da.23123

Cited by 64 publications

(49 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that these associations do not imply casual effects between the predictor variables and the outcome. Our results are consistent with a recent study [17] that reported an AUC of 0.71 for an EHR-based PPD prediction model applied to an Israeli cohort of 214K women with PPD prevalence of 1.9%. Our cohort had significantly higher prevalence of PPD (13.4%) and included only first live births.…”

Section: Discussionsupporting

confidence: 93%

See 1 more Smart Citation

Estimation of postpartum depression risk from electronic health records using machine learning

Amit

Girshovitz

Marcus

et al. 2021

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

Background Postpartum depression is a widespread disorder, adversely affecting the well-being of mothers and their newborns. We aim to utilize machine learning for predicting risk of postpartum depression (PPD) using primary care electronic health records (EHR) data, and to evaluate the potential value of EHR-based prediction in improving the accuracy of PPD screening and in early identification of women at risk. Methods We analyzed EHR data of 266,544 women from the UK who gave first live birth between 2000 and 2017. We extracted a multitude of socio-demographic and medical variables and constructed a machine learning model that predicts the risk of PPD during the year following childbirth. We evaluated the model’s performance using multiple validation methodologies and measured its accuracy as a stand-alone tool and as an adjunct to the standard questionnaire-based screening by Edinburgh postnatal depression scale (EPDS). Results The prevalence of PPD in the analyzed cohort was 13.4%. Combing EHR-based prediction with EPDS score increased the area under the receiver operator characteristics curve (AUC) from 0.805 to 0.844 and the sensitivity from 0.72 to 0.76, at specificity of 0.80. The AUC of the EHR-based prediction model alone varied from 0.72 to 0.74 and decreased by only 0.01–0.02 when applied as early as before the beginning of pregnancy. Conclusions 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.

show abstract

Section: Discussionsupporting

confidence: 93%

“…This limits the availability of reliable outcome measures and may introduce biases. Recently, a PPD prediction model using primary care EHR was reported to achieve AUC of 0.71 on a nationwide cohort [17]. The rate of PPD in this cohort was 1.9%, which is lower than the estimated population level prevalence.…”

Section: Introductionmentioning

confidence: 69%

Estimation of postpartum depression risk from electronic health records using machine learning

Amit

Girshovitz

Marcus

et al. 2021

BMC Pregnancy Childbirth

View full text Add to dashboard Cite

show abstract

“…Indeed, prenatal screening for anxiety can be implemented into prediction models used to earlier identify mothers and offspring at risk. [50]…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Depression, Anxiety and Stress in Women with Breech Pregnancy - "Be not Afraid": A Prospective Study

Schauer¹,

Latartara²,

Alonso-Espías³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Breech presentation at term is associated with higher perinatal complications through the increased incidence of cesarean section and complications by vaginal breech birth. The decision-making process between breech delivery, trial of external cephalic version or cesarean section may lead to maternal depression, stress and anxiety. Mental disorder in itself is associated with poorer maternal and fetal outcomes, such as preterm birth, small for gestational age infants, lower birth weight and increased risk for postnatal depression. This study aims to evaluate the level of psychological distress for women with breech presentation compared to cephalic presentation. We hypothesized, that women with breech presentation have higher levels of depression, stress and anxiety than other pregnant women. Secondary objectives were to analyze potential demographic risk factors and comorbidity of psychological distress in breech pregnancy. Methods: The breech study group was formed by 379 women with breech presentation. A sample of 128 women with cephalic presentation was recruited during routine clinical care. Depression, anxiety and stress symptoms were ascertained by means of the Depression-Anxiety-Stress-Score (DASS)-21 questionnaire. Categorial data was analyzed with Chi-square or exact test, continuous data with unpaired t-test or Mann-Whitney-U-test. Demographic risk factors were identified using a binary logistic regression model.Results: Prevalence of psychological distress among women with breech was not higher compared to those of other pregnant women. Symptomatic depression, anxiety and stress affected 5.8%, 14.5% and 11.9% of women with breech, respectively. Decreasing age was identified as a risk factor for anxiety (p = 0.006). Multiparity increased risk for depression (p = 0.001), for anxiety (p = 0.026) and for perinatal stress (p = 0.010). More than 80% of women with depressive symptoms had comorbidities of psychological distress.Conclusions: Breech presentation compared to cephalic presentation was not associated with higher levels of psychological distress. However, breech pregnancies are affected by symptoms of potential mental disorder. Multiparous women and younger women may need additional support and would benefit from a standardized screening tool for the assessment of perinatal psychological distress.Clinical Trial Registration: Ethical approval (EA2/241/18) was granted by the Ethics Commission of the Charité University Hospital on the 23.01.2019 (ClinicalTrials.gov Identifier: NCT03827226)

show abstract

“…Secondly, there is subjective deviation in the diagnosis of depression in clinic [ 5 ]. At present, the common method of the diagnosis of depression is mainly based on the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), which is subjective by doctors’ interviews with patients and evaluation scales [ 6 , 7 ]. Thus, it is difficult to identify depression, and there are some missed diagnoses and misdiagnoses.…”

Section: Introductionmentioning

confidence: 99%

A Convenient and Low-Cost Model of Depression Screening and Early Warning Based on Voice Data Using for Public Mental Health

Chen

Pan

2021

IJERPH

View full text Add to dashboard Cite

Depression is a common mental health disease, which has great harm to public health. At present, the diagnosis of depression mainly depends on the interviews between doctors and patients, which is subjective, slow and expensive. Voice data are a kind of data that are easy to obtain and have the advantage of low cost. It has been proved that it can be used in the diagnosis of depression. The voice data used for modeling in this study adopted the authoritative public data set, which had passed the ethical review. The features of voice data were extracted by Python programming, and the voice features were stored in the format of CSV files. Through data processing, a big database, containing 1479 voice feature samples, was generated for modeling. Then, the decision tree screening model of depression was established by 10-fold cross validation and algorithm selection. The experiment achieved 83.4% prediction accuracy on voice data set. According to the prediction results of the model, the patients can be given early warning and intervention in time, so as to realize the health management of personal depression.

show abstract

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

Cited by 64 publications

References 37 publications

Estimation of postpartum depression risk from electronic health records using machine learning

Estimation of postpartum depression risk from electronic health records using machine learning

Depression, Anxiety and Stress in Women with Breech Pregnancy - "Be not Afraid": A Prospective Study

A Convenient and Low-Cost Model of Depression Screening and Early Warning Based on Voice Data Using for Public Mental Health

Contact Info

Product

Resources

About