Machine learning prediction models for postpartum depression: A multicenter study in Japan

Matsuo, Seiko; Ushida, Takafumi; Emoto, Ryo; Moriyama, Yoshinori; Iitani, Yukako; Nakamura, Noriyuki; Imai, Kenji; Nakano‐Kobayashi, Tomoko; Yoshida, Shigeru; Yamashita, Mamoru; Matsui, Shigeyuki; Kajiyama, Hiroaki; Kotani, Tomomi

doi:10.1111/jog.15266

Cited by 5 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, a multicenter retrospective study conducted in 12 maternity hospitals in Japan investigated postpartum depression with the EPDS in 10,013 women who gave birth at ≥35 weeks of gestation who had undergone perinatal mental health care [71]. The authors attempted to develop machine learning models to predict depression using a conventional logistic regression and four machine learning algorithms based on maternal clinical data.…”

Section: Discussionmentioning

confidence: 99%

The Influence of Maternal Psychological Manifestations on the Mother–Child Couple during the Early COVID-19 Pandemic in Two Hospitals in Timisoara, Romania

et al. 2022

View full text Add to dashboard Cite

Background and objectives: The postpartum maternal physical and psychological state played a fundamental role in the mother–child relationship at the beginning of the COVID-19 pandemic. The aim of the study is to analyze the influence of maternal psychological manifestations on the mother–child couple through three objectives (briefly expressed): (I) Determination of the main acute and chronic conditions of newborns/infants. (II) Verification of the hypothesis of the existence of a link between the following neonatal variables: gestational age, birth weight, number of days of hospitalization, and specific neonatal therapies (oxygen, surfactant, and blood products’ transfusion). (III) Verification of the influence of postpartum maternal psychological status on the mother–child couple through three hypotheses. Materials and methods: This cross-sectional study was conducted in two hospitals in Timișoara, Romania, between 1 March and 1 September 2020, and included 165 mothers and their 175 newborns. Mothers answered the Edinburgh Postnatal Depression Scale, Spielberger’s Inventory of State-Trait Anxiety, and the Collins and Read Revised Adult Attachment Scale. Results: (I) The acute and chronic pathology of the infants in the study group was polymorphic. (II) Large correlations were identified between the following infant variables: gestational age with birth weight, and number of hospitalization days with birth weight, gestational age, and use of blood product transfusion (all p < 0.001). (III) (1) State anxiety was the only significant predictor of number of hospitalization days (p = 0.037), number of acute disorders (p = 0.028), and number of infant chronic diseases (p = 0.037). (2) Maternal depressive symptoms were the only predictor of postpartum maternal attachment (p = 0.018). (3) Depressive symptoms, state, and trait anxiety were non-significant in all models studied (all p > 0.05). Conclusions: Postpartum maternal physical and psychological state plays a fundamental role on the mother–child relationship in the new social and complex family conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

The Influence of Maternal Psychological Manifestations on the Mother–Child Couple during the Early COVID-19 Pandemic in Two Hospitals in Timisoara, Romania

et al. 2022

View full text Add to dashboard Cite

show abstract

Evaluating Bias-Mitigated Predictive Models of Perinatal Mood and Anxiety Disorders

Wong,

Saini,

Accortt

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceMachine learning for augmented screening of perinatal mood and anxiety disorders (PMADs) requires thorough consideration of clinical biases embedded in electronic health records (EHRs) and rigorous evaluations of model performance.ObjectiveTo mitigate bias in predictive models of PMADs trained on commonly available EHRs.Design, Setting, and ParticipantsThis diagnostic study collected data as part of a quality improvement initiative from 2020 to 2023 at Cedars-Sinai Medical Center in Los Angeles, California. The study inclusion criteria were birthing patients aged 14 to 59 years with live birth records and admission to the postpartum unit or the maternal-fetal care unit after delivery.ExposurePatient-reported race and ethnicity (7 levels) obtained through EHRs.Main Outcomes and MeasuresLogistic regression, random forest, and extreme gradient boosting models were trained to predict 2 binary outcomes: moderate to high-risk (positive) screen assessed using the 9-item Patient Health Questionnaire (PHQ-9), and the Edinburgh Postnatal Depression Scale (EPDS). Each model was fitted with or without reweighing data during preprocessing and evaluated through repeated K-fold cross validation. In every iteration, each model was evaluated on its area under the receiver operating curve (AUROC) and on 2 fairness metrics: demographic parity (DP), and difference in false negatives between races and ethnicities (relative to non-Hispanic White patients).ResultsAmong 19 430 patients in this study, 1402 (7%) identified as African American or Black, 2371 (12%) as Asian American and Pacific Islander; 1842 (10%) as Hispanic White, 10 942 (56.3%) as non-Hispanic White, 606 (3%) as multiple races, 2146 (11%) as other (not further specified), and 121 (&lt;1%) did not provide this information. The mean (SD) age was 34.1 (4.9) years, and all patients identified as female. Racial and ethnic minority patients were significantly more likely than non-Hispanic White patients to screen positive on both the PHQ-9 (odds ratio, 1.47 [95% CI, 1.23-1.77]) and the EPDS (odds ratio, 1.38 [95% CI, 1.20-1.57]). Mean AUROCs ranged from 0.610 to 0.635 without reweighing (baseline), and from 0.602 to 0.622 with reweighing. Baseline models predicted significantly greater prevalence of postpartum depression for patients who were not non-Hispanic White relative to those who were (mean DP, 0.238 [95% CI, 0.231-0.244]; P &lt; .001) and displayed significantly lower false-negative rates (mean difference, −0.184 [95% CI, −0.195 to −0.174]; P &lt; .001). Reweighing significantly reduced differences in DP (mean DP with reweighing, 0.022 [95% CI, 0.017-0.026]; P &lt; .001) and false-negative rates (mean difference with reweighing, 0.018 [95% CI, 0.008-0.028]; P &lt; .001) between racial and ethnic groups.Conclusions and RelevanceIn this diagnostic study of predictive models of postpartum depression, clinical prediction models trained to predict psychometric screening results from commonly available EHRs achieved modest performance and were less likely to widen existing health disparities in PMAD diagnosis and potentially treatment. These findings suggest that is critical for researchers and physicians to consider their model design (eg, desired target and predictor variables) and evaluate model bias to minimize health disparities.

show abstract

Artificial intelligence in perinatal mental health research: A scoping review

Kwok,

Zhang,

Wang

2024

Computers in Biology and Medicine

View full text Add to dashboard Cite

Machine learning prediction models for postpartum depression: A multicenter study in Japan

Cited by 5 publications

References 37 publications

The Influence of Maternal Psychological Manifestations on the Mother–Child Couple during the Early COVID-19 Pandemic in Two Hospitals in Timisoara, Romania

The Influence of Maternal Psychological Manifestations on the Mother–Child Couple during the Early COVID-19 Pandemic in Two Hospitals in Timisoara, Romania

Evaluating Bias-Mitigated Predictive Models of Perinatal Mood and Anxiety Disorders

Artificial intelligence in perinatal mental health research: A scoping review

Contact Info

Product

Resources

About