Abstract
BACKGROUND
Maternal mental disorders are considered a leading complication of childbirth and
a common contributor to maternal death. In addition to undermining maternal welfare,
untreated postpartum psychopathology can result in child emotional and physical neglect
and associated significant pediatric health costs. Some women may experience traumatic
childbirth and develop posttraumatic stress disorder symptoms after delivery (childbirth-related
posttraumatic stress disorder). Although women are routinely screened for postpartum
depression in the United States, there is no recommended protocol to inform the identification
of women who are likely to experience childbirth-related posttraumatic stress disorder.
Advancements in computational methods of free text have shown promise in informing
the diagnosis of psychiatric conditions. Although the language in narratives of stressful
events has been associated with posttrauma outcomes, whether the narratives of childbirth
processed via machine learning can be useful for childbirth-related posttraumatic
stress disorder screening is unknown.
OBJECTIVE
This study aimed to examine the use of written narrative accounts of personal childbirth
experiences for the identification of women with childbirth-related posttraumatic
stress disorder. To this end, we developed a model based on natural language processing
and machine learning algorithms to identify childbirth-related posttraumatic stress
disorder via the classification of birth narratives.
STUDY DESIGN
Overall, 1127 eligible postpartum women who enrolled in a study survey during the
COVID-19 pandemic provided short written childbirth narrative accounts in which they
were instructed to focus on the most distressing aspects of their childbirth experience.
They also completed a posttraumatic stress disorder symptom screen to determine childbirth-related
posttraumatic stress disorder. After the exclusion criteria were applied, data from
995 participants were analyzed. A machine learning-based Sentence-Transformers natural
language processing model was used to represent narratives as vectors that served
as inputs for a neural network machine learning model developed in this study to identify
participants with childbirth-related posttraumatic stress disorder.
RESULTS
The machine learning model derived from natural language processing of childbirth
narratives achieved good performance (area under the curve, 0.75; F1 score, 0.76;
sensitivity, 0.8; specificity, 0.70). Moreover, women with childbirth-related posttraumatic
stress disorder generated longer narratives (t test results: t=2.30; p=.02) and used more negative emotional expressions (Wilcoxon test: sadness: p=8.90e-04; W=31,017; anger: p=1.32e-02; W=35,005.50) and death-related words (Wilcoxon test: p=3.48e-05; W=34,538) in describing their childbirth experience than those with no childbirth-related
posttraumatic stress disorder.
CONCLUSION
This study provided proof of concept that personal childbirth narrative accounts generated
in the early postpartum period and analyzed via advanced computational methods can
detect with relatively high accuracy women who are likely to endorse childbirth-related
posttraumatic stress disorder and those at low risk. This suggests that birth narratives
could be promising for informing low-cost, noninvasive tools for maternal mental health
screening, and more research that used machine learning to predict early signs of
maternal psychiatric morbidity is warranted.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to American Journal of Obstetrics & Gynecology MFMAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Trait anxiety and unplanned delivery mode enhance the risk for childbirth-related post-traumatic stress disorder symptoms in women with and without risk of preterm birth: a multi sample path analysis.PLoS One. 2021; 16e0256681
- The effect of labor comfort on traumatic childbirth perception, post-traumatic stress disorder, and breastfeeding.Breastfeed Med. 2020; 15: 779-788
- Childbirth and criteria for traumatic events.Midwifery. 2014; 30: 255-261
- Delivery as a traumatic event: prevalence, risk factors, and treatment for postnatal posttraumatic stress disorder.Clin Obstet Gynecol. 2004; 47: 552-567
- Trauma and posttraumatic stress disorder.in: Stern TA Fava M Wilens T Rosenbaum JF Mass General Hosp Compreh Clin psych. 2nd ed. Elsevier, Philadelphia, PA2016
- Beyond postpartum depression: posttraumatic stress-depressive response following childbirth.Arch Womens Ment Health. 2020; 23: 557-564
- Childbirth induced posttraumatic stress syndrome: a systematic review of prevalence and risk factors.Front Psychol. 2017; 8: 560
- The prevalence of posttraumatic stress disorder in pregnancy and after birth: a systematic review and meta-analysis.J Affect Disord. 2017; 208: 634-645
- Delivery mode is associated with maternal mental health following childbirth.Arch Womens Ment Health. 2019; 22: 817-824
Kazato M. Screening for childbirth-related posttraumatic stress disorder using the City Birth Trauma Scale: A pilot project. Doctor of Nursing Practice Final Manuscripts. 2022. Available at: https://digital.sandiego.edu/cgi/viewcontent.cgi?article=1193&context=dnp.
- Monitoring maternal near miss/severe maternal morbidity: a systematic review of global practices.PLoS One. 2020; 15e0233697
- Cardiac disease in pregnancy: when to raise the ‘red flag.S Afr Med J. 2018; 108: 901-906
- Increased traumatic childbirth and postpartum depression and lack of exclusive breastfeeding in Black and Latinx individuals.Int J Gynaecol Obstet. 2022; 158: 759-761
- A simple model for prediction postpartum PTSD in high-risk pregnancies.Arch Womens Ment Health. 2016; 19: 483-490
- Is childbirth-induced PTSD associated with low maternal attachment?.Arch Womens Ment Health. 2019; 22: 119-122
- A prospective cohort study of post-traumatic stress disorder and maternal-infant bonding after first childbirth.J Psychosom Res. 2021; 144110424
- Risk factors for developing posttraumatic stress disorder following childbirth.Psychiatry Res. 2020; 290113090
- Association of sexual assault history with traumatic childbirth and subsequent PTSD.Arch Womens Ment Health. 2021; 24: 767-771
- Prevalence of postpartum depression and interventions utilized for its management.Ann Gen Psychiatry. 2018; 17: 18
- Treating postpartum depression with brexanolone.Nursing. 2020; 50: 48-53
- Postpartum help-seeking: the role of stigma and mental health literacy.Matern Child Health J. 2022; 26: 1030-1037
- Digital health needs of women with postpartum depression: focus group study.J Med Internet Res. 2021; 23: e18934
Boyd RL. The multifaceted measurement of the individual through language. The University of Texas at Austin. 2017. Available at: https://repositories.lib.utexas.edu/handle/2152/47328.
Wardecker BM. Correlates and predictors of emotion language and well-being in stressful and traumatic contexts. 2016. Available at: https://deepblue.lib.umich.edu/bitstream/handle/2027.42/133286/bwardeck_1.pdf?sequence=1.
- Psychological aspects of natural language use: our words, our selves.Annu Rev Psychol. 2003; 54: 547-577
- Retrieving and modifying traumatic memories: recent research relevant to three controversies.Curr Dir Psychol Sci. 2019; 28: 91-96
- Memory and forgetting.Curr Psychiatry Rep. 2018; 20: 87
- Memory and narrative of traumatic events: a literature review.Psychol Trauma. 2016; 8: 149-156
- Changes in trauma memory and patterns of posttraumatic stress.Psychol Trauma Theor Res Pract Pol. 2013; 5: 26-34
- Trauma narratives in posttraumatic stress disorder: a review.J Trauma Stress. 2006; 19: 81-93
- Natural language processing in mental health applications using non-clinical texts.Nat Lang Eng. 2017; 23: 649-685
- Automated assessment of patients’ self-narratives for posttraumatic stress disorder screening using natural language processing and text mining.Assessment. 2017; 24: 157-172
- Natural language processing and machine learning of electronic health records for prediction of first-time suicide attempts.JAMIA Open. 2021; 4: ooab011
- BERT: pre-training of deep bidirectional transformers for language understanding.Assoc Comput Linguist. 2019; : 4171-4186
- Machine Learning: a primer for child psychiatrists.J Am Acad Child Adolesc Psychiatry. 2016; 55: 835-836
- Traumatic memories of childbirth relate to maternal postpartum posttraumatic stress disorder.J Anx Disord. 2021; 77102342
- Childbirth narratives of women with posttraumatic stress symptoms in the postpartum period.J Obstet Gynecol Neonatal Nurs. 2018; 47: 333-341
- COVID-19 is associated with traumatic childbirth and subsequent mother-infant bonding problems.J Affect Disord. 2021; 282: 122-125
- Narratives in the immediate aftermath of traumatic injury: markers of ongoing depressive and posttraumatic stress disorder symptoms.J Trauma Stress. 2018; 31: 273-285
Weathers FW, Litz BT, Keane TM, Palmieri PA, Marx BP, Schnurr PP. PTSD Checklist for DSM-5 (PCL-5). US Department of Veterans. 2013. Available at: www.ptsd.va.gov. Accessed August 6, 2022.
- Psychometric analysis of the PTSD Checklist-5 (PCL-5) among treatment-seeking military service members.Psychol Assess. 2016; 28: 1392-1403
- The German version of the Posttraumatic Stress Disorder Checklist for DSM-5 (PCL-5): psychometric properties and diagnostic utility.BMC Psychiatry. 2017; 17: 379
Face H. all-mpnet-base-v2. Hugging Face. 2022. Available at: https://huggingface.co/sentence-transformers/all-mpnet-base-v2. Accessed August 11, 2022.
- Mpnet: masked and permuted pre-training for language understanding.Adv Neural Info Proc Syst. 2020; 33: 16857-16867
Sbert. Model comparisons table. 2022. Available at: https://www.sbert.net/_static/html/models_en_sentence_embeddings.html. Accessed August 11, 2022.
- EnrichrBot: twitter bot tracking tweets about human genes.Bioinformatics. 2020; 36: 3932-3934
- The development and psychometric properties of LIWC2015.University of Texas at Austin, Austin, TX2015
- The data management of the language of trauma narrative communication.IEEE EDUCON. 2021; : 1502-1508
- Research use of electronic health records: patients’ views on alternative approaches to permission.AJOB Empir Bioeth. 2020; 11: 172-186
- Detecting systemic data quality issues in electronic health records.Stud Health Technol Inform. 2019; 264: 383-387
- Electronic health records to facilitate clinical research.Clin Res Cardiol. 2017; 106: 1-9
- Machine learning methods for predicting postpartum depression: scoping review.JMIR Ment Health. 2021; 8: e29838
- Neural networks for early diagnosis of postpartum PTSD in women after cesarean section.Appl Sci. 2022; 12: 7492
- A machine learning approach to identifying pregnant women's risk for persistent post-traumatic stress following childbirth.J Affect Disord. 2022; 296: 136-149
- Effects of expressive writing and use of cognitive words on meaning making and post-traumatic growth.J Pac Rim Psychol. 2019; 13: e5
- Self-disclosure and psychological well-being.in: Maddux JE Tangney JP Social psychological foundations of clinical psychology. The Guilford Press, New York, NY2010: 212-225
- Emotional and physical health benefits of expressive writing.Adv Psychiatr Treat. 2005; 11: 338-346
- Forming a story: the health benefits of narrative.J Clin Psychol. 1999; 55: 1243-1254
- Early psychological intervention following recent trauma: a systematic review and meta-analysis.Eur J Psychotraumatol. 2019; 101695486
- Validation of childbirth-related posttraumatic stress disorder using psychophysiological assessment.Am J Obstet Gynecol. 2022; 227: 656-659
- Text messaging-based medical diagnosis using natural language processing and fuzzy logic.J Healthc Eng. 2020; 2020: 1-14
- Using state of the art speaker recognition and natural language processing technologies to detect Alzheimer's disease and assess its severity.INTERSPEECH. 2020; : 2177-2181
- A feasibility study using a machine learning suicide risk prediction model based on open-ended interview language in adolescent therapy sessions.Int J Environ Res Public Health. 2020; 17: 8187
- Psychometric properties of the PTSD Checklist for Diagnostic and Statistical Manual of Mental Disorders-Fifth Edition (PCL-5) in veterans.Psychol Assess. 2016; 28: 1379-1391
- Spotlight on maternal mental health: a prepandemic and postpandemic priority.Evid Based Nurs. 2021; 24: 29-30
- Perinatal mental health: a review of progress and challenges.World Psychiatry. 2020; 19: 313-327
Article info
Publication history
Published online: December 08, 2022
Accepted:
December 6,
2022
Received in revised form:
November 16,
2022
Received:
September 6,
2022
Footnotes
The authors report no conflict of interest.
S.D. was supported by grants from the National Institute of Child Health and Human Development (R21HD100817 and R01HD108619), and an Interim Support Funding (ISF) award from the Massachusetts General Hospital Executive Committee on Research. K.M.J. was supported by the Mortimer B. Zuckerman STEM Leadership Postdoctoral Fellowship Program. The sponsors were not involved in the study design; collection, analysis, or interpretation of data; writing of the report; or decision to submit this article for publication.
This study was presented at the Society for Reproductive and Infant Psychology 41st Annual Meeting (virtual), September 8–10, 2021; the Marce Society of North America Biennial Meeting (virtual), October 21–23, 2021; the Partnership for Maternal & Child Health of Northern New Jersey Maternal Mental Health Month (virtual), May 12, 2022; the Philadelphia Prenatal Diagnosis, Genetics, Ultrasound, Obstetrics and Maternal-Fetal Medicine 14th Annual Conference, Philadelphia, PA (virtual), June 9–11, 2022; and the North American Society for Psychosocial Obstetrics and Gynecology Biennial Meeting, Ann Arbor, MI, April 22–24, 2022.
Cite this article as: Bartal A, Jagodnik KM, Chan SJ, et al. Identifying women with postdelivery posttraumatic stress disorder using natural language processing of personal childbirth narratives. Am J Obstet Gynecol MFM 2022;XX:x.ex–x.ex.
Identification
Copyright
© 2022 Elsevier Inc. All rights reserved.
