In recent study, no proteins were selected to augment the clinical and demographic covariates using an elastic net model
By Elana Gotkine HealthDay Reporter
THURSDAY, July 11, 2024 (HealthDay News) — Large-scale proteomics in early pregnancy is not clinically useful for risk prediction of hypertensive disorders of pregnancy (HDP), according to a study published online July 3 in JAMA Cardiology.
Philip Greenland, M.D., from the Feinberg School of Medicine at Northwestern University in Chicago, and colleagues conducted a nested case-control study to examine the predictive ability of large-scale proteomics for prediction of HDP in early pregnancy. Nulliparous individuals during first-trimester clinical visits were included; cases were those with HDP, while controls were selected from those who delivered at or after 37 weeks without any HDP, preterm birth, or small-for-gestational-age infants. Data were included for 753 HDP cases and 1,097 controls. An aptamer-based assay that included 6,481 unique human proteins was performed on stored plasma.
The elastic net model was used to adjust protein-based models for clinical and demographic variables. Using this approach, the researchers found no proteins were selected for augmenting the clinical and demographic covariates. Modest predictive performance was seen for the resulting model, with areas under the curve of 0.64 and 0.62 for the training and test sets, respectively. Only minimal changes were yielded with further adjustment for study site.
“In this case-control study with detailed clinical data and stored plasma samples available in the first trimester, an aptamer-based proteomics panel did not meaningfully add to predictive utility over and above clinical and demographic factors that are routinely available,” the authors write.
Several authors disclosed ties to the pharmaceutical industry.
Copyright © 2024 HealthDay. All rights reserved.
