AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios
Abstract Background Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obst...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Pregnancy and Childbirth |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12884-024-07095-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571230780129280 |
|---|---|
| author | Raquel M. Zimmerman Edgar J. Hernandez Mark Yandell Martin Tristani-Firouzi Robert M. Silver William Grobman David Haas George Saade Jonathan Steller Nathan R. Blue |
| author_facet | Raquel M. Zimmerman Edgar J. Hernandez Mark Yandell Martin Tristani-Firouzi Robert M. Silver William Grobman David Haas George Saade Jonathan Steller Nathan R. Blue |
| author_sort | Raquel M. Zimmerman |
| collection | DOAJ |
| description | Abstract Background Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of “explainable artificial intelligence (AI)”, as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR. Methods Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not. We also sought to identify context-specific risk relationships among inter-related variables in FGR. Performance was assessed as area under the receiver-operating characteristics curve (AUC). Results Feature selection identified the 16 most informative variables, which yielded a PGM with good overall performance in the validation cohort (AUC 0.83, 95% CI 0.79–0.87), including among “N of 1” unique scenarios (AUC 0.81, 0.72–0.90). Using the PGM, we identified FGR scenarios with a risk of perinatal morbidity no different from that of the cohort background (e.g. female fetus, estimated fetal weight (EFW) 3-9th percentile, no preexisting diabetes, no progesterone use; RR 0.9, 95% CI 0.7–1.1) alongside others that conferred a nearly 10-fold higher risk (female fetus, EFW 3-9th percentile, maternal preexisting diabetes, progesterone use; RR 9.8, 7.5–11.6). This led to the recognition of a PGM-identified latent interaction of fetal sex with preexisting diabetes, wherein the typical protective effect of female fetal sex was reversed in the presence of maternal diabetes. Conclusions PGMs are able to capture and quantify context-specific risk relationships in FGR and identify latent variable interactions that are associated with large differences in risk. FGR scenarios that are separated by nearly 10-fold perinatal morbidity risk would be managed similarly under current FGR clinical guidelines, highlighting the need for more precise approaches to risk estimation in FGR. |
| format | Article |
| id | doaj-art-4b3bbfad8b174e3cb04cf3455b305651 |
| institution | Kabale University |
| issn | 1471-2393 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Pregnancy and Childbirth |
| spelling | doaj-art-4b3bbfad8b174e3cb04cf3455b3056512025-02-02T12:46:40ZengBMCBMC Pregnancy and Childbirth1471-23932025-01-0125111410.1186/s12884-024-07095-6AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenariosRaquel M. Zimmerman0Edgar J. Hernandez1Mark Yandell2Martin Tristani-Firouzi3Robert M. Silver4William Grobman5David Haas6George Saade7Jonathan Steller8Nathan R. Blue9Department of Biomedical Informatics, University of Utah HealthUtah Center for Genetic Discovery, Department of Human Genetics, University of Utah HealthUtah Center for Genetic Discovery, Department of Human Genetics, University of Utah HealthDepartment of Pediatrics, Division of Pediatric Cardiology, University of Utah HealthDepartment of Obstetrics and Gynecology, Division of Maternal-Fetal Medicine, University of Utah HealthDepartment of Obstetrics and Gynecology, Warren Alpert Medical School, Brown UniversityDepartment of Obstetrics and Gynecology, Indiana UniversityDepartment of Obstetrics and Gynecology, Eastern Virginia Medical SchoolDepartment of Obstetrics & Gynecology, Division of Maternal Fetal Medicine, University of California, IrvineDepartment of Obstetrics and Gynecology, Division of Maternal-Fetal Medicine, University of Utah HealthAbstract Background Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of “explainable artificial intelligence (AI)”, as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR. Methods Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not. We also sought to identify context-specific risk relationships among inter-related variables in FGR. Performance was assessed as area under the receiver-operating characteristics curve (AUC). Results Feature selection identified the 16 most informative variables, which yielded a PGM with good overall performance in the validation cohort (AUC 0.83, 95% CI 0.79–0.87), including among “N of 1” unique scenarios (AUC 0.81, 0.72–0.90). Using the PGM, we identified FGR scenarios with a risk of perinatal morbidity no different from that of the cohort background (e.g. female fetus, estimated fetal weight (EFW) 3-9th percentile, no preexisting diabetes, no progesterone use; RR 0.9, 95% CI 0.7–1.1) alongside others that conferred a nearly 10-fold higher risk (female fetus, EFW 3-9th percentile, maternal preexisting diabetes, progesterone use; RR 9.8, 7.5–11.6). This led to the recognition of a PGM-identified latent interaction of fetal sex with preexisting diabetes, wherein the typical protective effect of female fetal sex was reversed in the presence of maternal diabetes. Conclusions PGMs are able to capture and quantify context-specific risk relationships in FGR and identify latent variable interactions that are associated with large differences in risk. FGR scenarios that are separated by nearly 10-fold perinatal morbidity risk would be managed similarly under current FGR clinical guidelines, highlighting the need for more precise approaches to risk estimation in FGR.https://doi.org/10.1186/s12884-024-07095-6Explainable artificial intelligencePregnancyFetal growth restrictionStillbirthPerinatal morbidity |
| spellingShingle | Raquel M. Zimmerman Edgar J. Hernandez Mark Yandell Martin Tristani-Firouzi Robert M. Silver William Grobman David Haas George Saade Jonathan Steller Nathan R. Blue AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios BMC Pregnancy and Childbirth Explainable artificial intelligence Pregnancy Fetal growth restriction Stillbirth Perinatal morbidity |
| title | AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| title_full | AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| title_fullStr | AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| title_full_unstemmed | AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| title_short | AI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| title_sort | ai based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios |
| topic | Explainable artificial intelligence Pregnancy Fetal growth restriction Stillbirth Perinatal morbidity |
| url | https://doi.org/10.1186/s12884-024-07095-6 |
| work_keys_str_mv | AT raquelmzimmerman aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT edgarjhernandez aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT markyandell aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT martintristanifirouzi aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT robertmsilver aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT williamgrobman aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT davidhaas aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT georgesaade aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT jonathansteller aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios AT nathanrblue aibasedanalysisoffetalgrowthrestrictioninaprospectiveobstetriccohortquantifiescompoundrisksforperinatalmorbidityandmortalityandidentifiespreviouslyunrecognizedhighriskclinicalscenarios |