Consecutive prediction of adverse maternal outcomes of preeclampsia, using the PIERS-ML and fullPIERS models: A multicountry prospective observational study
In this study, we have evaluated the performance of the fullPIERS and PIERS-ML models for consecutive prediction. We observed deteriorating performance of both models over time. We recommend using the models for consecutive prediction with greater caution and interpreting predictions with increasing uncertainty as the pregnancy progresses. For clinical practice, models should be adapted to retain accuracy when deployed serially. The performance of future models can be compared with the results of this study to quantify their added value.
Authors
- Wessel Ganzevoort (ORCID: https://orcid.org/0000-0002-7243-2115)
- Paul Murray (ORCID: https://orcid.org/0000-0002-6980-9276)
- Henk Groen (ORCID: https://orcid.org/0000-0002-6629-318X)
- Sanne J. Gordijn (ORCID: https://orcid.org/0000-0003-3915-8609)
- Laura Ann Magee (ORCID: https://orcid.org/0000-0002-1355-610X)
- Kimberley Kavanagh (ORCID: https://orcid.org/0000-0002-2679-5409)
- Peter von Dadelszen (ORCID: https://orcid.org/0000-0003-4136-3070)
- Tünde Montgomery-Csobán
- Guiyou Yang (ORCID: https://orcid.org/0000-0002-1976-9683)
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
- University of Strathclyde (GB)
- King's College London (GB)
- Amsterdam University Medical Centers (NL)
Publication Details
- Journal
- PLoS Medicine
- Published
- 2025-02-04
- DOI
- https://doi.org/10.1371/journal.pmed.1004509
- Citations
- 4
- Primary Topic
- Pregnancy and preeclampsia studies
- Type
- article
- Field-Weighted Citation Impact
- 8.23
Funders
- University of Strathclyde
- Bill and Melinda Gates Institute for Population and Reproductive Health
- Institute of Human Development, Child and Youth Health