Professor Basky Thilaganathan writes about the importance of digital innovation in improving maternity care. He introduces the Tommy's App, a clinical decision tool developed for women and maternity staff. Through individualised AI risk assessment, the tool aims to prevent stillbirths and premature births.
As an academic and a practicing obstetrician, I am aware of the enormous advances in research into the management of stillbirth and preterm birth, juxtaposed with a healthcare system seemingly devoid of those advances.
A consequence of this paradox is a failure of the current system to identify women at higher chance of developing pregnancy complications, which means missed opportunities for early intervention and/or appropriate monitoring.
The resulting adverse outcomes and incurred health complications of mother and baby in later life leave a lasting legacy on the family unit and a cost incurred in terms of potentially avoidable healthcare requirements in future.
The Tommy’s National Centre for Maternity Improvement is led jointly by the Royal College of Obstetricians and Gynaecologists and Royal College of Midwives, and is a collaboration of women and leading academics. We are putting evidenced clinical effectiveness methodology and digital innovation into practice to do better for our pregnant women and birthing people, for our maternity workforce and for the maternity healthcare system.
In collaboration with our Women’s Voices Involvement Group, we have co-developed a first version of the Tommy’s App: A clinical decision tool.
What we believe:
- Each pregnant woman and birthing person has the right to a safe pregnancy and birth, no matter where they live
- Each pregnant woman and birthing person needs to be supported with a care pathway that is personalised to their individual psychosocial and medical needs
- Each maternity care professional requires access to the right information at the right time, to offer appropriate and personalised care recommendations in line with national clinical guidelines
- Getting maternity care right, through improved accuracy in assessment and better decision support, is one way we can reduce the burden on an over-stretched healthcare system and improve outcomes
What we know:
There are 25,000 cases of pre-eclampsia, 3,000 stillbirths and 60,000 preterm births per year in the UK[1-3] and rates of stillbirth and preterm birth vary widely, by up to ±20% across the UK. This variation persists after adjustment for socio-economic/demographic characteristics of the population, which confirms our suspicions that there is significant variation in care.
All recent national reports have identified that staff struggle with lack of information, support and resources to provide best care. The Each Baby Counts 2020 final report states that in half (45%) of cases with affected babies, our national guidelines were not followed with reasons cited including gaps in training, failure to recognise developing complications, heavy workload, limited staffing levels and local guidelines not in line with latest evidence.
Targeted intervention relies on accurate assessment of a pregnant woman's chance of developing complications and appropriate monitoring. Our current method for antenatal risk assessment remains the same as it was in the 70s: a checklist that asks for the presence of certain risk factors, first adopted into antenatal care some 50 years ago.
This checklist does not weigh nor assess the interaction between risk factors, and it does not allow for risk reduction in the absence of these factors. Most telling is that we rely on a risk assessment system that actually is incapable of estimating a numerical risk, thereby precluding personalisation of care. This results in poor triage into care pathways and inefficient use of limited medical and staffing resources. Furthermore, it worsens health inequalities for disadvantaged groups that we are battling to tackle.
The current approach to risk assessment is out-dated, inefficient and counterproductive, making our primary aims as healthcare professionals much harder to achieve.
The way forward
Head-to-head clinical studies have demonstrated superior accuracy of artificial intelligence-(AI)-based risk prediction models.This advantage leverages 15-years of research involving data from more than 120,000 pregnancies to create regression models that assess the likelihood of placental dysfunction in pregnancy[6 and 7].
Putting the research into practice, our app (a CE-marked medical device) uses clinically validated machine learning algorithms to provide a more accurate risk assessment and generate personalised care recommendations in line with national clinical guidelines.
The Tommy’s App is a dual-interface web application shared by women and maternity staff.
It uses AI to process the data routinely gathered during antenatal appointments to assess individual risk of potential complications developing during pregnancy. Thus enabling early identification and timed intervention.
It also engages women by offering direct access to their own maternity care information, consistent with their maternity record but in accessible language and style to better support discussion with maternity care providers in the antenatal period, and informed decision-making about their care.
Women have a right to demand the best healthcare and we have the capability to deliver this care. It’s time we embrace new technologies and hit fast-forward on maternity care.
1. Grobman WA, Rice MM, Reddy UM, et al. Labor Induction versus Expectant Management in Low-Risk Nulliparous Women. N Engl J Med 2018;379(6):513-23. doi: 10.1056/NEJMoa1800566 [published Online First: 2018/08/09]
2. Lawn JE, Blencowe H, Waiswa P, et al. Stillbirths: rates, risk factors, and acceleration towards 2030. Lancet 2016;387(10018):587-603. doi: 10.1016/s0140-6736(15)00837-5 [published Online First: 2016/01/23]
3. Mol BWJ, Roberts CT, Thangaratinam S, et al. Pre-eclampsia. Lancet 2016;387(10022):999-1011. doi: 10.1016/s0140-6736(15)00070-7 [published Online First: 2015/09/08]
4. Healthcare Quality Improvement Partnership (HQIP). National Maternity and Perinatal Audit. Clinical Report 2019. Based on births in NHS maternity services between 1 April 2016 and 31 March 2017, 2019.
5. Tan MY, Wright D, Syngelaki A, et al. Comparison of diagnostic accuracy of early screening for pre-eclampsia by NICE guidelines and a method combining maternal factors and biomarkers: results of SPREE. Ultrasound Obstet Gynecol 2018;51(6):743-50. doi: 10.1002/uog.19039 [published Online First: 2018/03/15]
6. Wright D, Syngelaki A, Akolekar R, et al. Competing risks model in screening for preeclampsia by maternal characteristics and medical history. Am J Obstet Gynecol 2015;213(1):62.e1-62.e10. doi: 10.1016/j.ajog.2015.02.018 [published Online First: 2015/03/01]
7. Guy G, Leslie K, Diaz Gomez D, et al. Implementation of routine first trimester combined screening for pre-eclampsia: a clinical effectiveness study. BJOG: An International Journal of Obstetrics & Gynaecology;n/a(n/a) doi: https://doi.org/10.1111/1471-0528.16361