AI_PREMie: saving lives of mothers and babies using AI

  • 1 March 2022
  • Professor Patricia Maguire
  • Academic, Health, Social, Technological


Preeclampsia is a serious pregnancy complication typically characterised by the development of high blood pressure and protein in the urine, and it affects one in every 10 pregnancies. Every year it claims the lives of 50,000 mothers and 500,000 babies, making it one of the world’s deadliest pregnancy complications.

Diagnosis remains a serious challenge, and pre-term delivery of the baby is the only cure and the safest option for the mother. Therefore, an additional 5 million babies are born prematurely each year – sometimes very prematurely – which poses its own risks for the survival chances and long-term health of the child. Accurate risk stratification, where patients are assigned health risk statuses to help inform care, is urgently required to reduce these enormous competing risks.

Professor Maguire and her team have drawn upon cutting-edge biomedical, clinical and machine-learning knowhow to develop a prototype risk stratification tool, AI_PREMie, for preeclampsia. Their solution will be able to assist clinical decision making in real-time, hopefully enabling more accurate diagnosis and personalised treatment that will save lives.

Research description

Using their knowledge of platelets (tiny blood cells that help the body form clots and stop bleeding), Professor Maguire and her team have spent the past six years developing a new platelet-based technology platform called PALADINTM to reinvent how to find diagnostics in the blood.

They have used PALADINTM to uncover a combination of patent-pending ”biomarkers” (molecules in the blood)  that have shown great promise in diagnosing preeclampsia, one of the world’s deadliest pregnancy complications. This test also includes markers which may be useful in separating women who will progress to severe disease from those who will remain stable.

Recently, using powerful machine-learning algorithms, they have combined these unique biochemical signals with clinical data to develop a new prototype test, AI_PREMie.

In preliminary findings, the team have compelling evidence that AI_PREMie can accurately diagnose preeclampsia, which can be incredibly challenging even for experienced medical staff. AI_PREMie may also be useful towards predicting whether a woman will progress to severe, permitting a more accurate timing of delivery, and potentially allowing a baby to remain in utero for several more precious hours or days, impacting their survival chances and long-term health.

In the future, by performing their analysis using standard equipment in the hospital lab as well as ‘in the cloud’, the team believe that AI_PREMie will return an easily interpretable risk score within a few hours, aiding clinical decision-making in real-time. Furthermore, as they plan to use advanced cloud technology, AI_PREMie will continually learn and evolve once it is implemented into widespread clinical practice.

It is hoped that AI_PREMie will arm clinical care providers with an affordable risk stratification tool to closely observe pregnancies complicated by preeclampsia, and will help to prevent unnecessary adverse outcomes for mother and baby.

The impact of AI_PREMie will be a game changer in tackling preeclampsia. As a clinician, I cannot wait to use it as part of our care.

— Professor Mary Higgins, UCD School of Medicine & National Maternity Hospital, Dublin

Research team

  • Professor Patricia Maguire, UCD School of Biomolecular and Biomedical Science
    Principal Investigator / Team Lead
  • Professor Fionnuala Ní Áinle, UCD School of Medicine and Consultant Haematologist, Rotunda Hospital, Dublin
    Team Co-Lead
  • Professor Mary Higgins, UCD School of Medicine and Consultant Obstetrician, National Maternity Hospital, Dublin
    Societal Impact Champion
  • Dr Jennifer Donnelly, UCD School of Medicine and Consultant Obstetrician, Rotunda Hospital
    Clinical acumen, patient sample collection, smart data collection
  • Dr Neil O’Gorman, Consultant Obstetrician, Coombe Hospital
    Clinical acumen, patient sample collection, smart data collection
  • Dr John O’Loughlin, Laboratory Manager, Rotunda Hospital
    Hospital laboratory acumen, test design
  • Dr Paulina Szklanna, Manager, UCD AI Healthcare Hub and Research Scientist, UCD School of Biomolecular and Biomedical Science
    Biochemical analysis, data analysis, data interpretation
  • Associate Professor Brian Mac Namee, UCD School of Computer Science Artificial Intelligence, data science, data interpretation
  • Dr Suzy Whoriskey, UCD School of Mathematics and Statistics
    Statistical data analytics, data organisation, data interpretation
  • Dr Katrina Comerford, Research Scientist, UCD School of Biomolecular and Biomedical Science
    Project Management
  • Ana Le Chevelier, Research Assistant, UCD School of Biomolecular and Biomedical Science
    Biochemical analysis
  • Ella Fouhy, Research Assistant, UCD School of Biomolecular and Biomedical Science
    Smart data organisation, biochemical analysis
  • Saraswathi Rajakumar, Research Assistant, UCD School of Biomolecular and Biomedical Science
    Smart data organisation, biochemical analysis

Industry collaborators

  • John Curran, Head of Technology, SAS Ireland
    Artificial Intelligence, data integration, model deployment
  • Kevin Marshall, Head of Education, Microsoft Ireland
    Cloud framework and software integration


  • The project commenced in 2015 and was funded through the Health Research Board and Irish Research Council
  • In July 2021, the team were awarded Runner Up Prize of €500K in the SFI AI for Societal Good award


Research impact

Addressing a global health challenge

Maternal health is a significant global and national challenge. Professor Maguire and her team have combined their extensive knowledge to provide a prototype personalised treatment tool that will hopefully enable timely delivery decisions, which would transform the lives of pregnant mothers, their babies, their families and their extended communities.

Improving quality of life in this way aligns to the priorities of several Sustainable Development Goals (SDGs): SDG3 (Good Health and Well-Being), SDG5 (Gender Equality), and SDG10 (Reducing Inequality). This is not only a moral imperative but critical for maintaining international growth.

2015 WHO report acknowledges that many maternal and infant deaths are preventable and in theory could be avoided with effective and timely clinical interventions. The key is to ensure that high-risk pregnancies and complications are recognised early. Thus, new diagnostics are urgently required, and AI_PREMie will fill this gap. Any significant innovations in maternal healthcare will help reduce global maternal and newborn mortality rates.

Health impact

By providing a timely and accurate prognosis, AI_PREMie will be a game-changer for women with preeclampsia and should have a major impact on the health and mortality rates of pregnant women and their babies worldwide. Every year, preeclampsia claims the lives of 50,000 mothers and 500,000 babies. The team hope to deploy AI_PREMie globally within the few years and believe that within 5 years of deployment, the method will become part of pregnancy screening programs worldwide.

Survivors of preeclampsia have a lifelong increased risk of developing other chronic diseases, such as heart and vascular disease. In fact, preeclampsia is associated with a fourfold increased risk of developing kidney failure within 10 years after pregnancy. This risk is increased even further by having more than one preeclamptic pregnancy, a low-birthweight offspring, or a preterm delivery. Therefore, any improvement in clinical decision-making will have an enormous preventative potential on the long-term health of the population and future healthcare resource requirements.

It is difficult to sometimes know what to do: whether to deliver a baby because we fear for the mother’s safety or to keep baby in-utero for as long as possible.

— Dr Jennifer Donnelly, Consultant Obstetrician, Rotunda Hospital

Social impact

The team have raised public awareness of preeclampsia and their prototype solution through a range of public engagement activities, links to which are available in the References section below. This includes traditional media (several TV shows, articles in national papers, and opinion pieces by medical journals) as well as more modern approaches (such as reaching out directly to affected women and their families through their hashtags #myPETexperience and #AI_PREMie on Twitter).

This dual approach has received a wide response from the patients and families affected by preeclampsia who spoke of their devastating memories of the condition:

“Brilliant! As a mother who had Preeclampsia at 29 weeks and delivered 6 weeks early, this is to be commended.”

“This amazing team of women are developing a blood test to predict preeclampsia. They listened to my story about losing my daughter Aoife and made me feel a part of their research. On #WorldPreeclampsiaDay2021 I'd like to say thank you to @maguirepatr and to the UCD team.”

Academic and technological impact

The scientific innovation underlying AI_PREMie, as well as the results to date, have been well received by international clinical and scientific audiences. AI_PREMie has been selected for a myriad of oral and poster presentations at prestigious international conferences, including the International Society for Thrombosis and Haemostasis, the American Society of Hematology, the pan Canadian thrombotic Research Network, and at the iPlacenta H2020 virtual conference. AI_PREMie has also been well received by industry at the SAS UK and Ireland forum.

Furthermore, three invention disclosure forms and a patent application have been filed because of the scientific research work at the heart of AI_PREMie. The biomarkers underlying this solution were also awarded the UCD NOVA Invention of the year 2021 for their significance in preeclampsia diagnosis and the real prospect of saving lives.

Project website

UCD Institute for Discover – AI Healthcare Hub

News articles

Using platelets as little health sensors in our blood – Claire O’Connell, The Irish Times (2021)

UCD team using AI to help diagnose pre-eclampsia and save lives: diagnostic test powered by machine learning to improve outcome for pregnant women – Marie Boran, The Irish Times (2021)

University College Dublin helps save babies and mothers with help from SAS Viya – SAS, (2021)

AI_PREMie wins NovaUCD Invention of the Year Award 2021 – UCD, Discovery (2021)

AI_PREMie shortlisted for the Social Impact Award by Analytics Institute – UCD, Discovery (2021)

The diagnostic device that could save the lives of mothers and babies – Patrice Harrington The Irish Daily Mail (2020)

Opinion piece

BMJ opinion – Mary Higgins (2020)


Short Video describing AI_PREMie revolutionising preeclampsia care

RTE TV shows: 10 things to know about; The Changemakers

Research references

Twomey L, et al. (2021) A dry immersion model of microgravity modulates platelet phenotype, miRNA signature, and circulating plasma protein biomarker profile. Sci Rep 1121906.

O’Reilly D, et al. (2021) Platelets in pediatric and neonatal sepsis: novel mediators of the inflammatory cascade. Pediatr Res.

Murphy CA, et al. (2021) The role of the calibrated automated thrombogram in neonates: describing mechanisms of neonatal haemostasis and evaluating haemostatic drugs. Eur J Pediatr. Epub ahead of print.

Murphy CA, et al. (2021) Haematological parameters and coagulation in umbilical cord blood following COVID-19 infection in pregnancyEur J Obstet Gynecol Reprod Biol.  Sep 21;266:99-105. Epub ahead of print.

Cullivan S, et al. (2021). Platelets, extracellular vesicles and coagulation in pulmonary arterial hypertension. Pulmonary Circulation, 11(3).

Comer SP et al. (2021). COVID-19 induces a hyperactive phenotype in circulating platelets. Plos Biology, 19(2).

Cremer SE, et al. (2021). The canine activated platelet secretome (CAPS): A translational model of thrombin-evoked platelet activation response. Research and Practice in Thrombosis and Haemostasis, 5(1), 55-68.

Weiss L, et al. (2021) Non-valvular atrial fibrillation patients anticoagulated with rivaroxaban compared with warfarin exhibit reduced circulating extracellular vesicles with attenuated pro-inflammatory protein signatures. J Thromb Haemost.

Sklanna PB, et al. (2021) Routine haematological parameters may be predictors of COVID-19 severity. Frontiers in Medicine.

Maguire PB, et al. (2020) Comparative Platelet Releasate Proteomic Profiling of Acute Coronary Syndrome versus Stable Coronary Artery Disease. Front Cardiovasc Med. 7:101.

Murphy CA, et al. (2020) A review of the role of extracellular vesicles in neonatal physiology and pathology. Pediatr Res.

Kelliher S, et al. (2020) Pathophysiology of the Venous Thromboembolism Risk in Preeclampsia. Hamostaseologie.

Haire G, et al. (2019) Alterations in fibrin formation and fibrinolysis in early onset-preeclampsia: Association with disease severity. Eur J Obstet Gynecol Reprod Biol. 241:19-23.

Szklanna PB, et al. (2019) The Platelet Releasate is Altered in Human Pregnancy. Proteomics Clin Appl. May; 13(3):e1800162.

Parsons MEM, et al. (2018) Platelet Releasate Proteome Profiling Reveals a Core Set of Proteins with Low Variance Between Healthy Adults. Proteomics. Aug; 18(15):e1800219.

Monteith C, et al. (2017) Early onset preeclampsia is associated with an elevated mean platelet volume (MPV) and a greater rise in MPV from time of booking compared with pregnant controls: results of the CAPE study. J Perinat Med. Dec 21.

Egan K, et al. (2017) Elevated plasma TFPI activity causes attenuated TF-dependent thrombin generation in early onset preeclampsia. Thromb Haemost. 117,1549-1557.

Szklanna PB, et al. (2017) Comparative proteomic analysis of trophoblast cell models reveals their differential phenotypes, potential uses and limitations. Proteomics. 10, 1002.

Coppinger JA, et al. (2004) Proteomic characterization of the proteins released from activated platelets leads to localization of novel platelet proteins in human atherosclerotic lesions. Blood. 103, 2096-2104.

Above: Professor Mary Higgins, Professor Fionnuala Ní Áinle, Dr Paulina Szklanna and Professor Patricia Maguire. Taken January 2020.