Frontiers in Pediatrics (Dec 2022)
Revealing the impact of lifestyle stressors on the risk of adverse pregnancy outcomes with multitask machine learning
- Martin Becker,
- Martin Becker,
- Martin Becker,
- Martin Becker,
- Jennifer Dai,
- Jennifer Dai,
- Jennifer Dai,
- Alan L. Chang,
- Alan L. Chang,
- Alan L. Chang,
- Dorien Feyaerts,
- Ina A. Stelzer,
- Miao Zhang,
- Miao Zhang,
- Miao Zhang,
- Eloise Berson,
- Eloise Berson,
- Eloise Berson,
- Geetha Saarunya,
- Geetha Saarunya,
- Geetha Saarunya,
- Davide De Francesco,
- Davide De Francesco,
- Davide De Francesco,
- Camilo Espinosa,
- Camilo Espinosa,
- Camilo Espinosa,
- Yeasul Kim,
- Yeasul Kim,
- Yeasul Kim,
- Ivana Marić,
- Ivana Marić,
- Ivana Marić,
- Samson Mataraso,
- Samson Mataraso,
- Samson Mataraso,
- Seyedeh Neelufar Payrovnaziri,
- Seyedeh Neelufar Payrovnaziri,
- Seyedeh Neelufar Payrovnaziri,
- Thanaphong Phongpreecha,
- Thanaphong Phongpreecha,
- Thanaphong Phongpreecha,
- Neal G. Ravindra,
- Neal G. Ravindra,
- Neal G. Ravindra,
- Sayane Shome,
- Sayane Shome,
- Sayane Shome,
- Yuqi Tan,
- Yuqi Tan,
- Melan Thuraiappah,
- Melan Thuraiappah,
- Melan Thuraiappah,
- Lei Xue,
- Lei Xue,
- Lei Xue,
- Jonathan A. Mayo,
- Cecele C. Quaintance,
- Ana Laborde,
- Lucy S. King,
- Firdaus S. Dhabhar,
- Firdaus S. Dhabhar,
- Firdaus S. Dhabhar,
- Firdaus S. Dhabhar,
- Ian H. Gotlib,
- Ronald J. Wong,
- Martin S. Angst,
- Gary M. Shaw,
- David K. Stevenson,
- Brice Gaudilliere,
- Brice Gaudilliere,
- Nima Aghaeepour,
- Nima Aghaeepour,
- Nima Aghaeepour
Affiliations
- Martin Becker
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Martin Becker
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Martin Becker
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Martin Becker
- Chair for Intelligent Data Analytics, Institute for Visual and Analytic Computing, Department of Computer Science and Electrical Engineering, University of Rostock, Rostock, Germany
- Jennifer Dai
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Jennifer Dai
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Jennifer Dai
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Alan L. Chang
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Alan L. Chang
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Alan L. Chang
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Dorien Feyaerts
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Ina A. Stelzer
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Miao Zhang
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Miao Zhang
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Miao Zhang
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Eloise Berson
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Eloise Berson
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Eloise Berson
- Department of Pathology, Stanford University, Palo Alto, CA, United States
- Geetha Saarunya
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Geetha Saarunya
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Geetha Saarunya
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Davide De Francesco
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Davide De Francesco
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Davide De Francesco
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Camilo Espinosa
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Camilo Espinosa
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Camilo Espinosa
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Yeasul Kim
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Yeasul Kim
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Yeasul Kim
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Ivana Marić
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Ivana Marić
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Ivana Marić
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Samson Mataraso
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Samson Mataraso
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Samson Mataraso
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Seyedeh Neelufar Payrovnaziri
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Seyedeh Neelufar Payrovnaziri
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Seyedeh Neelufar Payrovnaziri
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Thanaphong Phongpreecha
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Thanaphong Phongpreecha
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Thanaphong Phongpreecha
- Department of Pathology, Stanford University, Palo Alto, CA, United States
- Neal G. Ravindra
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Neal G. Ravindra
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Neal G. Ravindra
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Sayane Shome
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Sayane Shome
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Sayane Shome
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Yuqi Tan
- Department of Microbiology & Immunology, Stanford University, Palo Alto, CA, United States
- Yuqi Tan
- Baxter Laboratory for Stem Cell Biology, Stanford University, Palo Alto, CA, United States
- Melan Thuraiappah
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Melan Thuraiappah
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Melan Thuraiappah
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Lei Xue
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Lei Xue
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Lei Xue
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Jonathan A. Mayo
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Cecele C. Quaintance
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Ana Laborde
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Lucy S. King
- Department of Psychology, Stanford University, Palo Alto, CA, United States
- Firdaus S. Dhabhar
- Department of Psychiatry & Behavioral Science, University of Miami, Miami, FL, United States
- Firdaus S. Dhabhar
- 0Department of Microbiology & Immunology, University of Miami, Miami, FL, United States
- Firdaus S. Dhabhar
- 1Sylvester Comprehensive Cancer Center, University of Miami, Miami, FL, United States
- Firdaus S. Dhabhar
- 2Miller School of Medicine, University of Miami, Miami, FL, United States
- Ian H. Gotlib
- Department of Psychology, Stanford University, Palo Alto, CA, United States
- Ronald J. Wong
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- Martin S. Angst
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Gary M. Shaw
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- David K. Stevenson
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Brice Gaudilliere
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Brice Gaudilliere
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Nima Aghaeepour
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, United States
- Nima Aghaeepour
- Department of Pediatrics, Stanford University, Palo Alto, CA, United States
- Nima Aghaeepour
- Department of Biomedical Data Science, Stanford University, Palo Alto, CA, United States
- DOI
- https://doi.org/10.3389/fped.2022.933266
- Journal volume & issue
-
Vol. 10
Abstract
Psychosocial and stress-related factors (PSFs), defined as internal or external stimuli that induce biological changes, are potentially modifiable factors and accessible targets for interventions that are associated with adverse pregnancy outcomes (APOs). Although individual APOs have been shown to be connected to PSFs, they are biologically interconnected, relatively infrequent, and therefore challenging to model. In this context, multi-task machine learning (MML) is an ideal tool for exploring the interconnectedness of APOs on the one hand and building on joint combinatorial outcomes to increase predictive power on the other hand. Additionally, by integrating single cell immunological profiling of underlying biological processes, the effects of stress-based therapeutics may be measurable, facilitating the development of precision medicine approaches.ObjectivesThe primary objectives were to jointly model multiple APOs and their connection to stress early in pregnancy, and to explore the underlying biology to guide development of accessible and measurable interventions.Materials and MethodsIn a prospective cohort study, PSFs were assessed during the first trimester with an extensive self-filled questionnaire for 200 women. We used MML to simultaneously model, and predict APOs (severe preeclampsia, superimposed preeclampsia, gestational diabetes and early gestational age) as well as several risk factors (BMI, diabetes, hypertension) for these patients based on PSFs. Strongly interrelated stressors were categorized to identify potential therapeutic targets. Furthermore, for a subset of 14 women, we modeled the connection of PSFs to the maternal immune system to APOs by building corresponding ML models based on an extensive single cell immune dataset generated by mass cytometry time of flight (CyTOF).ResultsJointly modeling APOs in a MML setting significantly increased modeling capabilities and yielded a highly predictive integrated model of APOs underscoring their interconnectedness. Most APOs were associated with mental health, life stress, and perceived health risks. Biologically, stressors were associated with specific immune characteristics revolving around CD4/CD8 T cells. Immune characteristics predicted based on stress were in turn found to be associated with APOs.ConclusionsElucidating connections among stress, multiple APOs simultaneously, and immune characteristics has the potential to facilitate the implementation of ML-based, individualized, integrative models of pregnancy in clinical decision making. The modifiable nature of stressors may enable the development of accessible interventions, with success tracked through immune characteristics.
Keywords
- adverse pregnancy outcomes (APO)
- psychosocial and stress-related factors
- prediction
- multitask machine learning
- immune states
- single-cell
