CoChat
Sign Up
Cited by 21Maternal Mental Health During Pregnancy and PostpartumArtificial Intelligence in HealthcareMaternal and Neonatal Healthcare

Predicting Patients Requiring Treatment for Depression in the Postpartum Period Using Common Electronic Medical Record Data Available Antepartum

Open access
Wakefield, Colin, Frasch, Martin G.·2023·AJPM Focus
DOI 10.1016/j.focus.2023.100100PMC PMC10546501
Open this paper in CoChat — free accountOpen PDF

Abstract

Introduction: Depression requiring treatment in the postpartum period significantly impacts maternal and neonatal health. Although preventive management of depression in pregnancy has been shown to decrease the negative impacts, current methods for identifying at-risk patients are insufficient. Given the complexity of the diagnosis and interplay of clinical/demographic factors, we tested whether machine learning techniques can accurately identify at-risk patients in the postpartum period. Methods: This is a retrospective cohort study of the NIH Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be, which enrolled 10,038 nulliparous people. The primary outcome was depression in the postpartum period. We constructed and optimized 4 machine learning models using distributed random forest modeling and 1 logistic regression model on the basis of the NIH Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be dataset. Model 1 utilized only readily obtainable sociodemographic data. Model 2 added maternal prepregnancy mental health data. Model 3 utilized recursive feature elimination to construct a parsimonious model. Model 4 further titrated the input data to simplify prepregnancy mental health variables. The logistic regression model used the same input data as Model 3 as a proof of concept. Results: Of 8,454 births, 338 (4%) were complicated by depression in the postpartum period. Model 3 was the highest performing, showing the area under the receiver operating characteristics curve of 0.91 (±0.02). Models 1-3 identified the 9 variables most predictive of depression hierarchically, ranging from depression history (highest), history of mental health condition, recent psychiatric medication use, BMI, income, age, anxiety history, education, and preparedness for pregnancy (lowest). In Model 4, the area under the receiver operating characteristics curve remained at 0.79 (±0.05). Conclusions: Postpartum depression can be predicted with high accuracy for individual patients using antepartum information commonly found in electronic medical records. In addition, baseline mental health status and sociodemographic factors have a larger role in the postpartum period than previously understood.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.focus.2023.100100

Cites

17 of 17 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Prior studies predicting PPD risk have achieved AUCs of 0.80-0.90.

    “Prior studies predicting PPD risk have achieved further improved discriminatory ability (AUCs of 0.80–0.90) but have limitations related to generalizability [54, 55] and the finding that history of depression drives much of the discriminatory performance [54, 56].”

    From Factors associated with postpartum depression symptoms following antepartum hospitalization (2026) · cites this paper as [54]

    The Discussion (page unavailable) reports that one earlier PPD prediction model achieved an AUC of 0.804, within the claimed range. It does not establish AUCs of 0.80–0.90 across multiple prior studies; its Results report AUCs of 0.91–0.93 for its own best-performing models. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • In prior studies predicting PPD risk, history of depression drives much of the discriminatory performance.

    “Prior studies predicting PPD risk have achieved further improved discriminatory ability (AUCs of 0.80–0.90) but have limitations related to generalizability [54, 55] and the finding that history of depression drives much of the discriminatory performance [54, 56].”

    From Factors associated with postpartum depression symptoms following antepartum hospitalization (2026) · cites this paper as [54]

    The Discussion identifies prepregnancy depression as the largest contributor to the models’ PPD predictions. The Results show AUC falling from 0.91 to 0.79 when both depression and anxiety history were removed, but the paper does not isolate how much of that change was due to depression history alone; the Discussion also says predictive accuracy was largely maintained. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • All prior studies predicting PPD have found that varying aspects of mental health history are the strongest predictors of PPD.

    “Consistent with our findings, all prior studies predicting PPD have found that varying aspects of mental health history (i.e., anxiety disorders and prenatal EPDS score [53]; depression and anxiety history, recent psychiatric medication use [54]; psychiatric history [55]; anxiety, depression, and antidepressants during pregnancy [56]) are the strongest predictors of PPD.”

    From Factors associated with postpartum depression symptoms following antepartum hospitalization (2026) · cites this paper as [54]

  • Prior studies predicting PPD risk have limitations related to generalizability.

    “Prior studies predicting PPD risk have achieved further improved discriminatory ability (AUCs of 0.80–0.90) but have limitations related to generalizability [54, 55] and the finding that history of depression drives much of the discriminatory performance [54, 56].”

    From Factors associated with postpartum depression symptoms following antepartum hospitalization (2026) · cites this paper as [54]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [2]Mughal S Azhar Y Siddiqui W. Postpartum depression StatPearls 2022 StatPearls Publishing https://www.ncbi.nlm.nih.gov/pubmed/30085612

Cited by

Sorted by citations

Related

Authors
Wakefield, C., & Frasch, M. G.
Affiliations
  • Drexel University (US)
  • University of Washington (US)
Corresponding author
Frasch, Martin G.
ORCID
Venue
AJPM Focus
Publisher
Elsevier BV
Published
2023-09
Volume
2
Issue
3
Pages
100100
ISSN
2773-0654 (ISSN-L)
DOI
10.1016/j.focus.2023.100100
PMC
PMC10546501
OpenAlex
W4367043290
Cited by
21
References
17
Citations by year
2026: 7 · 2025: 10 · 2024: 3 · 2023: 1
FWCI
5.38
Type
journal article
Language
en
Open access
Licence
Locations
  • AJPM Focus (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Maternal Mental Health During Pregnancy and Postpartum
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Health Professions › General Health Professions › Maternal and Neonatal Healthcare
Keywords
postpartum depression, prenatal risk factors, electronic medical record data, nulliparous women, sociodemographic factors, distributed random forest, recursive feature elimination, maternal mental health, pregnancy outcomes

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review