Artificial intelligence and amniotic fluid multiomics: prediction of perinatal outcome in asymptomatic women with short cervix

Abstract

Objective To evaluate the application of artificial intelligence (AI), i.e. deep learning and other machine‐learning techniques, to amniotic fluid (AF) metabolomics and proteomics, alone and in combination with sonographic, clinical and demographic factors, in the prediction of perinatal outcome in asymptomatic pregnant women with short cervical length (CL). Methods AF samples, which had been obtained in the second trimester from asymptomatic women with short CL (< 15 mm) identified on transvaginal ultrasound, were analyzed. CL, funneling and the presence of AF ‘sludge’ were assessed in all cases close to the time of amniocentesis. A combination of liquid chromatography coupled with mass spectrometry and proton nuclear magnetic resonance spectroscopy‐based metabolomics, as well as targeted proteomics analysis, including chemokines, cytokines and growth factors, was performed on the AF samples. To determine the robustness of the markers, we used six different machine‐learning techniques, including deep learning, to predict preterm delivery < 34 weeks, latency period prior to delivery < 28 days after amniocentesis and requirement for admission to a neonatal intensive care unit (NICU). Omics biomarkers were evaluated alone and in combination with standard sonographic, clinical and demographic factors to predict outcome. Predictive accuracy was assessed using the area under the receiver–operating characteristics curve (AUC) with 95% CI, sensitivity and specificity. Results Of the 32 patients included in the study, complete omics, demographic and clinical data and outcome information were available for 26. Of these, 11 (42.3%) patients delivered ≥ 34 weeks, while 15 (57.7%) delivered < 34 weeks. There was no statistically significant difference in CL between these two groups (mean ± SD, 11.2 ± 4.4 mm vs 8.9 ± 5.3 mm, P = 0.31). Using combined omics, demographic and clinical data, deep learning displayed good to excellent performance, with an AUC (95% CI) of 0.890 (0.810–0.970) for delivery < 34 weeks' gestation, 0.890 (0.790–0.990) for delivery < 28 days post‐amniocentesis and 0.792 (0.689–0.894) for NICU admission. These values were higher overall than for the other five machine‐learning methods, although each individual machine‐learning technique yielded statistically significant prediction of the different perinatal outcomes. Conclusions This is the first study to report use of AI with AF proteomics and metabolomics and ultrasound assessment in pregnancy. Machine learning, particularly deep learning, achieved good to excellent prediction of perinatal outcome in asymptomatic pregnant women with short CL in the second trimester. Copyright © 2018 ISUOG. Published by John Wiley & Sons Ltd.

Amniotic fluid cell-free transcriptome: a glimpse into fetal development and placental cellular dynamics during normal pregnancy

“…Among the omics platforms used to study AF (see Kamath-Rayne et al [88] for a review), the analysis of cell-free mRNA (cfRNA) has the advantage of being easier to profile than its proteomics [45,89,90] and metabolomics [91][92][93][94][95][96] counterparts. The AF cfRNAs are thought to be contributed directly by the fetus and by apoptotic amniocytes [97] and have been shown to be altered by physiologic and pathologic factors such as gestational age [83,85,98], fetal sex [83], maternal obesity [99], genetic syndromes [100][101][102], and neonatal comorbidities [85] (see Zwemer and Bianchi for a review [97]).…”

Machine Learning in Fetal Cardiology: What to Expect

“…Prenatal diagnosis of fetal abnormalities has greatly benefited from advances in US technology and, in the last years, also from the advances in ML. ML algorithms have been used in different applications within fetal US medicine such as to predict preterm births [43,44], the risk of euploidy, trisomy 21, and other chromosomal aneuploidies [45] or prediction of perinatal outcomes on asymptomatic short cervical length [46] among others. Regarding fetal cardiology, one of the subfields in which ML has been extensively applied in the last decades is improvement of the diagnosis of fetal hypoxia or acidemia based on the analysis of CTG.…”

Artificial Intelligence: A New Paradigm in Obstetrics and Gynecology Research and Clinical Practice

“…Innovative research by Singh et al studied the combination of AI and amniotic fluid (AF) proteomics and metabolomics, in conjunction or independently with imaging, demographic, and clinical factors, to predict perinatal outcomes in asymptomatic women with short cervix length [14]. The type of AI they used was called deep learning (DL).…”