Identifying women with postdelivery posttraumatic stress disorder using natural language processing of personal childbirth narratives.

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.

Traumatic childbirth during COVID-19 triggers maternal psychological growth and in turn better mother-infant bonding.

BACKGROUND: Although posttraumatic psychological growth (PTG) occurs following stressful events, knowledge of maternal psychological growth as a result of giving birth during the novel coronavirus (COVID-19) pandemic is lacking. METHODS: We assessed PTG associated with recent childbirth (Posttraumatic Growth Inventory) in a sample of 2205 women who gave birth during the pandemic and 540 who gave birth before. They also provided information about birth-related traumatic stress (Peritraumatic Distress Inventory; PTSD Checklist), mother-infant bonding (Maternal Attachment Inventory), and breastfeeding. RESULTS: Close to two thirds (60.45 %) of participants reported childbirth-related PTG with greater appreciation of life endorsed most frequently. No group differences in PTG prevalence were noted between deliveries during or before COVID-19 (χ2 = 0.35, p = 0.84). A multigroup mediation model revealed that in deliveries during the pandemic, childbirth-related acute stress was linked with elevated PTG (ß = 0.07, p < 0.01); in turn, PTG was associated with lower posttraumatic stress symptoms (ß = -0.06, p < 0.05) and better mother-infant bonding (ß = 0.22, p < 0.001). These indirect paths via PTG were not significant in deliveries before the pandemic. LIMITATIONS: Reliance on a convenient sample, self-reports, and cross-sectional design may introduce bias. CONCLUSIONS: Perceived positive maternal psychological changes as a result of childbirth are endorsed by a significant portion of women during the pandemic and can ensue in response to traumatic childbirth. Maternal growth is further implicated in successful postpartum adjustment and positive mother-infant interactions during an important period. Hence, directing clinical attention to opportunities of maternal psychological growth may have benefits especially for women at risk for the adverse outcomes of exposure to traumatic experiences of childbirth.

COVID-19 positivity associated with traumatic stress response to childbirth and no visitors and infant separation in the hospital.

As the novel coronavirus (COVID-19) has spread globally, a significant portion of pregnant and delivering women were infected with COVID-19. While emerging studies examined birth outcomes in COVID-19 positive women, knowledge of the psychological experience of childbirth and maternal wellness remains lacking. This matched-control survey-based study included a sample of women recruited during the first wave of the pandemic in the US who gave birth in the previous six months. Women reporting confirmed/suspected COVID-19 (n = 68) during pregnancy or childbirth were matched on background factors with women reporting COVID-19 negativity (n = 2,276). We found nearly 50% of COVID positive women endorsed acute traumatic stress symptoms at a clinical level in response to childbirth. This group was more than twice as likely to endorse acute stress and to have no visitors during maternity hospitalization than COVID negative women; they were also less likely to room-in with newborns. The COVID positive group reported higher levels of pain in delivery, lower newborn weights, and more infant admission to neonatal intensive care units. Our findings suggest COVID-19 affected populations are at increased risk for traumatic childbirth and associated risk for psychiatric morbidity. Attention to delivering women's wellbeing is warranted during the pandemic.

COVID-19 is associated with traumatic childbirth and subsequent mother-infant bonding problems.

BACKGROUND: Knowledge of women's experience of childbirth in the outbreak of the coronavirus (COVID-19) pandemic and associated maternal health outcomes is scarce. METHODS: A sample of primarily American women who gave birth around the height of COVID-19 (n = 1,611) and matched controls, i.e., women who gave birth before COVID-19 (n = 640), completed an anonymous Internet survey about recent childbirth, birth-related traumatic stress (peritraumatic distress inventory; PTSD-checklist), maternal bonding (maternal attachment inventory; mother-to-infant bonding scale) and breastfeeding status. Groups (n = 637 in each) were matched on demographics, prior mental health/trauma and childbirth factors to determine the unique contribution of COVID-19 to the psychological experience of childbirth. RESULTS: Mothers in COVID-19-exposed communities endorsed more clinically acute stress response to childbirth than matched controls (Z = 2.65, p = .008, OR= 1.38). A path mediation model revealed that acute stress mediated the relationship between study group and postpartum outcomes. Specifically, higher acute stress response in birth was associated with more childbirth-related posttraumatic stress disorder symptoms (ß = .42, p < .001) and less bonding with the infant (ß = .26, p < .001), including breastfeeding problems (ß = .10, p < .01). LIMITATIONS: Use of a convenient internet sample introduces bias towards more educated women and reliance on retrospective self-report assessments may entail recall bias. CONCLUSIONS: COVID-19 is a major stressor for delivering women. It can heighten traumatic childbirth experiences and interfere with successful postpartum adjustment. Clinical attention to traumatic stress in childbirth and problems with caring for the young during this pandemic is important.