Search

Introduction: Postpartum depression (PPD) is a common condition, affecting 10-15% of mothers. PPD screening using the Edinburgh Postnatal Depression Scale (EPDS) has variable reported accuracy. Information from Electronic health records (EHR) may complement EPDS to provide higher detection rate. Objectives: To develop and evaluate a machine learning model for identifying PPD using EHR data. Methods: We analyzed primary care EHR records of 259,096 live births in the UK from 2000 to 2017. PPD was defined as having either a depression diagnosis, antidepressant prescriptions or psychotherapy referrals within 12 months after childbirth. The validation set included 5,823 women with recorded EPDS scores. The remaining population was split to training(70%) and testing(30%) sets. We built a prediction model using EHR information prior and during pregnancy, partially based on variables described in our complementary study (EPA2020 abstract by Zhang et.al.). We evaluated the performance of the EHR-model, compared to EPDS-alone and a combination of EHR+EPDS scores. Results: Table 1 details the main characteristics of the cohort. The strongest contributing variables were antidepressants, diagnosis or symptoms of depression/anxiety, and age. The combined model outperformed EPDS alone (area under the curve(AUC) 0.87 vs. 0.80) and EHR alone (AUC=0.77) (Table 2, Fig.1). Conclusions: EHR-based predictive algorithms can potentially complement and enhance the accuracy of existing PPD screening tools. [ABSTRACT FROM AUTHOR]

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., (© 2021. The Author(s).)