Applying machine learning methods to psychosocial screening data to improve identification of prenatal depression: Implications for clinical practice and research

H Preis, PM Djurić, M Ajirak, T Chen, V Mane… - Archives of women's …, 2022 - Springer
We utilized machine learning (ML) methods on data from the PROMOTE, a novel
psychosocial screening tool, to quantify risk for prenatal depression for individual patients …

Using the PROMOTE screener to identify psychosocial risk factors for prenatal substance use

A Azeem, M Lobel, C Heiselman… - Journal of Addiction …, 2024 - journals.lww.com
Methods We conducted a retrospective chart review of 1842 patients who completed the
PROMOTE screening instrument during their first prenatal visit to outpatient clinics of a New …

Learning from Heterogeneous Data with Deep Gaussian Processes

M Ajirak, H Preis, M Lobel… - 2023 IEEE 9th …, 2023 - ieeexplore.ieee.org
Deep Gaussian processes (DGPs) are deep models represented by layers of Gaussian
processes (GPs). They are flexible Bayesian models capable of capturing highly nonlinear …

[HTML][HTML] Saving time, signaling trust: Using the PROMOTE self-report screening instrument to enhance prenatal care quality and therapeutic relationships

H Preis, C Whitney, C Kocis, M Lobel - PEC innovation, 2022 - Elsevier
Objectives Comprehensive screening of psychosocial vulnerabilities and substance use in
prenatal care is critical to promote the health and well-being of pregnant patients. Effective …

Uncertainty Quantification of Deep Generative Models Based on Gaussian Processes for Heterogeneous Incomplete Data

M Ajirak - 2023 - search.proquest.com
This dissertation focuses on the theoretical aspects of machine learning based on Gaussian
processes (GPs), aiming to tackle fundamental challenges related to the trustworthiness of …