Scholarlink

Objective <p>Pre-eclampsia is a cause of significant maternal morbidity and mortality, with delivery initiating resolution. The Pre-eclampsia Integrated Estimate of RiSk-machine learning (PIERS-ML) tool provides individualized risk estimates to guide joint decision-making for women with pre-eclampsia. While it has been externally validated in the UK, our objective was to test PIERS-ML performance in Kenya.</p> Design <p>Retrospective cohort validation study.</p> Setting <p>Two tertiary hospitals in Nairobi, Kenya.</p> Population <p>Women admitted with pre-eclampsia who had not experienced any element of the main outcome measure.</p> Methods <p>Test performance was assessed by stratification capacity, area under the receiver-operator curve (AUROC), area under the precision-recall curve (AUPRC), and decision curve analysis.</p> Main outcome measures <p>Any component of the PIERS primary outcome of maternal death or major maternal organ dysfunction within 48&#xa0;h of admission.</p> Results <p>Among 2,002 women with pre-eclampsia, 408 (20.4%) experienced an adverse maternal outcome within 48 h of admission (including 4 deaths) and a further 74 (3.7%) between 3–7&#xa0;days. Missingness was substantial for most laboratory variables, particularly at the public hospital. Despite this, individual level imputation enabled model assessment. PIERS-ML demonstrated good discrimination (AUROC 0.68; AUPRC 0.40) and clinically meaningful stratification: high-risk women had doubled outcome rates and the single very high-risk woman experienced an event. Decision curve analysis showed greater net benefit than treating all or none. Patterns of missingness and more severe outcomes suggested a higher risk Kenyan case mix.</p> Conclusion <p>In a high-morbidity Kenyan cohort, the PIERS-ML tool accurately identified personalised risk in women admitted with pre-eclampsia.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Performance of the Pre-Eclampsia Integrated Estimate of Risk–Machine Learning (PIERS-ML) model in a Kenyan cohort of women with pre-eclampsia- a retrospective test derivation validation study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月2日

查看全文
  • Felix Nyagaka,
  • Tünde Montgomery-Csobán,
  • Ingrid Gichere,
  • Mukaindo Mwaniki,
  • Kimberley Kavanagh,
  • Laura A. Magee,
  • Peter von Dadelszen,
  • Felix Oindi,
  • Mark A. Brown,
  • Gregory K. Davis,
  • Claire Parker,
  • Barry N. Walters,
  • Nelson Sass,
  • J. Mark Ansermino,
  • Vivien Cao,
  • Geoffrey W. Cundiff,
  • M. Joanne Douglas,
  • Guy A. Dumont,
  • Dustin T. Dunsmuir,
  • Jennifer A. Hutcheon,
  • K. S. Joseph,
  • Sayrin Lalji,
  • Tang Lee,
  • Jing Li,
  • Joanne Lim,
  • Kenneth I. Lim,
  • Sarka Lisonkova,
  • Paula Lott,
  • Jennifer M. Menzies,
  • Alexandra L. Millman,
  • Lynne Palmer,
  • Beth A. Payne,
  • Ziguang Qu,
  • James A. Russell,
  • Diane Sawchuck,
  • Dorothy Shaw,
  • D. Keith Still,
  • U. Vivian Ukah,
  • Brenda Wagner,
  • Keith R. Walley,
  • Dany Hugo,
  • Andrée Gruslin,
  • George Tawagi,
  • Graeme N. Smith,
  • Anne-Marie Côté,
  • Jean-Marie Moutquin,
  • Annie B. Ouellet,
  • Shoo K. Lee,
  • Tao Duan,
  • Jian Zhou,
  • Farizah Haniff,
  • Swati Mahajan,
  • Amanda Noovao,
  • Hanna Karjalainend,
  • Eija Kortelainen,
  • Hannele Laivuori,
  • J. Wessel Ganzevoort,
  • Henk Groen,
  • Phillipa M. Kyle,
  • M. Peter Moore,
  • Barbra Pullar,
  • Zulfiqar A. Bhutta,
  • Rahat N. Qureshi,
  • Rozina Sikandar,
  • Shereen Z. Bhutta,
  • Garth Cloete,
  • David R. Hall,
  • Erika van Papendorp,
  • D. Wilhelm Steyn,
  • Christine Biryabarema,
  • Florence Mirembe,
  • Annettee Nakimuli,
  • John Allotey,
  • Shakila Thangaratinam,
  • Kypros H. Nicolaides,
  • Olivia Ionescu,
  • Argyro Syngelaki,
  • Michael de Swiet,
  • Ranjit Akolekar,
  • James J. Walker,
  • Stephen C. Robson,
  • Fiona Broughton Pipkin,
  • Pamela Loughna,
  • Manu Vatish,
  • Christopher W. G. Redman,
  • Sarah J. E. Barry,
  • Tunde Csoban,
  • Paul Murray,
  • Chris Robertson,
  • Eleni Z. Tsigas,
  • Douglas A. Woelkers,
  • Marshall D. Lindheimer,
  • William A. Grobman,
  • Baha M. Sibai,
  • Mario Merialdi,
  • Mariana Widmer

摘要

Objective

Pre-eclampsia is a cause of significant maternal morbidity and mortality, with delivery initiating resolution. The Pre-eclampsia Integrated Estimate of RiSk-machine learning (PIERS-ML) tool provides individualized risk estimates to guide joint decision-making for women with pre-eclampsia. While it has been externally validated in the UK, our objective was to test PIERS-ML performance in Kenya.

Design

Retrospective cohort validation study.

Setting

Two tertiary hospitals in Nairobi, Kenya.

Population

Women admitted with pre-eclampsia who had not experienced any element of the main outcome measure.

Methods

Test performance was assessed by stratification capacity, area under the receiver-operator curve (AUROC), area under the precision-recall curve (AUPRC), and decision curve analysis.

Main outcome measures

Any component of the PIERS primary outcome of maternal death or major maternal organ dysfunction within 48 h of admission.

Results

Among 2,002 women with pre-eclampsia, 408 (20.4%) experienced an adverse maternal outcome within 48 h of admission (including 4 deaths) and a further 74 (3.7%) between 3–7 days. Missingness was substantial for most laboratory variables, particularly at the public hospital. Despite this, individual level imputation enabled model assessment. PIERS-ML demonstrated good discrimination (AUROC 0.68; AUPRC 0.40) and clinically meaningful stratification: high-risk women had doubled outcome rates and the single very high-risk woman experienced an event. Decision curve analysis showed greater net benefit than treating all or none. Patterns of missingness and more severe outcomes suggested a higher risk Kenyan case mix.

Conclusion

In a high-morbidity Kenyan cohort, the PIERS-ML tool accurately identified personalised risk in women admitted with pre-eclampsia.