Data-Driven Modeling of Pregnancy-Related Complications. Issue 8 (August 2021)

• Record Type: Journal Article
• Authors: Espinosa, Camilo; Becker, Martin; Marić, Ivana; Wong, Ronald J.; Shaw, Gary M.; Gaudilliere, Brice; Aghaeepour, Nima; Stevenson, David K.; Stelzer, Ina A.; Peterson, Laura S.; Chang, Alan L.; Xenochristou, Maria; Phongpreecha, Thanaphong; De Francesco, Davide; Katz, Michael; Blumenfeld, Yair J.; Angst, Martin S.
• Is Part Of: Trends in molecular medicine. Volume 27:Issue 8(2021)
• Page Start: 762
• Page End: 776
• Publication Date: 2021-08
• Subjects: pregnancy -- machine learning -- multiomics -- systems biology -- multimodal learning -- multitask learning -- maternal health; Molecular biology -- Periodicals; Pathology, Molecular -- Periodicals; Physiology, Pathological -- Periodicals; 572.8
• DOI: 10.1016/j.molmed.2021.01.007
• Languages: English
• ISSNs: 1471-4914

Abstract

Abstract : A healthy pregnancy depends on complex interrelated biological adaptations involving placentation, maternal immune responses, and hormonal homeostasis. Recent advances in high-throughput technologies have provided access to multiomics biological data that, combined with clinical and social data, can provide a deeper understanding of normal and abnormal pregnancies. Integration of these heterogeneous datasets using state-of-the-art machine-learning methods can enable the prediction of short- and long-term health trajectories for a mother and offspring and the development of treatments to prevent or minimize complications. We review advanced machine-learning methods that could: provide deeper biological insights into a pregnancy not yet unveiled by current methodologies; clarify the etiologies and heterogeneity of pathologies that affect a pregnancy; and suggest the best approaches to address disparities in outcomes affecting vulnerable populations. Highlights: A multitude of clinical, biological, environmental, and demographic factors influence the trajectory of a pregnancy. Maternal genetics, environment, stress, nutrition, medical history, socioeconomic status, and racial and ethnic background all play a role in determining the success of a pregnancy. Diverse data sources are available for the study of pregnancy and prediction of adverse outcomes, including electronic health records (EHRs) and administrative claims data, high-throughput multiomics data for characterizing biological systems, and more complex sources like time series, imaging and video data, and text. Recent advances in multiview, multitask, and deep learning allow joint modeling across data sources as well as across outcomes and demonstrate the vast potential of such integrated approaches.