AI and narrative embeddings detect PTSD following childbirth via birth stories
Open accessPublished version of a preprint
The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index; 12 of the 19 sources its claims cite were checked for support.
Abstract
Free-text analysis using machine learning (ML)-based natural language processing (NLP) shows promise for diagnosing psychiatric conditions. Chat Generative Pre-trained Transformer (ChatGPT) has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 (ADA) model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol. Using a sample of 1295 women who gave birth in the last six months and were 18+ years old, recruited through hospital announcements, social media, and professional organizations, we explore ChatGPT's and ADA's potential to screen for CB-PTSD by analyzing maternal childbirth narratives. The PTSD Checklist for DSM-5 (PCL-5; cutoff 31) was used to assess CB-PTSD. By developing an ML model that utilizes numerical vector representation of the ADA model, we identify CB-PTSD via narrative classification. Our model outperformed (F1 score: 0.81) ChatGPT and six previously published large text-embedding models trained on mental health or clinical domains data, suggesting that the ADA model can be harnessed to identify CB-PTSD. Our modeling approach could be generalized to assess other mental health disorders.
Overview
CoChat Summary
## TL;DR
This study tested whether childbirth narratives alone could identify probable childbirth-related PTSD (CB-PTSD) using ChatGPT and OpenAI text embeddings. The best model, built on text-embedding-ada-002, performed well and outperformed ChatGPT and six previously published domain-specific PLMs.
## Key findings
- The analyzed sample included 1,295 women who gave birth in the last six months and provided narratives of 30 words or more; narratives were collected on average 2.73 ± 1.82 months postpartum.
- The best model (Model #3, based on text-embedding-ada-002) achieved F1 = 0.81 and AUC = 0.80 for CB-PTSD classification.
- Model #3 achieved 85% sensitivity and 75% specificity in identifying CB-PTSD cases based on narrative language.
- ChatGPT zero-shot and few-shot models performed poorly; the paper reports F1 scores lower than 0.2 for all PLM models in Evaluation Method 1.
## Methods
- Design: Observational study embedded in a larger project on childbirth experience and maternal mental health; participants completed an anonymous web survey and could provide free-text birth stories.
- Sample/data: 1,295 women, age 18+, who had given birth to a live baby in the prior six months; CB-PTSD status was defined using the PCL-5 with cutoff ≥31.
- Analysis: Compared three narrative classifiers: ChatGPT zero-shot (Model #1), few-shot (Model #2), and a custom neural-network classifier using text-embedding-ada-002 embeddings (Model #3). Performance was evaluated with F1 and AUC; the embedding-based model was also compared against six PLMs (all-mpnet-base-v2, mental-roberta-base, mental-bert-base-uncased, mental-xlnet-base-cased, Bio ClinicalBERT, BioGPT).
## Limitations
- The paper states that it did not incorporate additional data sources such as self-report questionnaires beyond PCL-5, medical records, or physiological measures; this limits the model to narrative text alone.
- The sample included women who gave birth before and during the COVID-19 pandemic, and the authors note this heterogeneity may have affected language use and results.
- Clinician evaluations were not performed; CB-PTSD labels relied on the PCL-5 self-report measure. The paper also states that external validation is essential for the DFNN/text-embedding model.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
7 Valid · 1 Not valid · 2 Not checked · 23 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“minoritized women, who are at three times higher risk of experiencing post-traumatic stress symptoms60.”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Discussion
What the sources say
- Partly supportedcites [60] Iyengar, A. S. et al. Increased traumatic childbirth and postpartum depression and lack of exclusive breastfeeding in Black and Latinx individuals. Int. J. Gynecol. Obstetr. 158, 759–761 (2022). sourceExperimental — accuracy not yet measured
The Results report that Black and Hispanic/Latinx women who gave birth during the pandemic were three times more likely than matched non-Hispanic White women to report clinically relevant acute traumatic stress to childbirth. The claim broadens that finding to minoritized women generally and calls the measured outcome post-traumatic stress symptoms; the paper says the acute stress level indicates risk for post-traumatic stress disorder, not that it measured those symptoms. (LLM, conf=0.85)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Additionally, Model #3 outperforms previously established models, such as the one presented in our recent previous work47.”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Discussion
What the sources say
- Supportedcites [47] Bartal, A., Jagodnik, K. M., Chan, S. J., Babu, M. S. & Dekel, S. Identifying women with post-delivery posttraumatic stress disorder using natural language processing of personal childbirth narratives. Am. J. Obstetr. Gynecol. MFM. 5, 100834 (2023). source
The citation identifies an earlier model, rather than sourcing the citing authors’ comparison with Model #3. The source’s Materials and Methods describes its childbirth-narrative classifier, and its Results reports that model’s performance. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The analyzed sample consists of 1295 women who provided narratives of length 30 words or more”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Materials and methods > Study design
plainn = 1,295- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“These narratives were collected, on average, 2.73 ± 1.82 months post-childbirth (ranging from 0.02 to 8.34 months).”
- Also stated in: § Discussion · plain
“the childbirth narratives analyzed in our study were collected, on average, 2.73 ± 1.82 months post-childbirth (range: 0.02 to 8.34 months).”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Materials and methods > Study design
plainn = 1,295- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Discussion · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Results of Evaluation Method 2: The results show (Table 4) that our Model #3 with OpenAI’s text-embedding-ada-002 embeddings outperformed Model #3 with other embeddings of PLMs (including embeddings of PLMs trained on clinical or mental health domains) in identifying CB-PTSD using narrative data only.”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
5 more claims
Create a free account to see all 33 claims and every source verdict.
- It may state two separate claims as one. 18
- The quote only partly states this claim. 3
- Probably not a substantial claim. 9
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“Set #1: All possible pairs of sentences (C(n, r) = C(1720, 2) = 14,365) in Class 1 (CB-PTSD).”
§ AI and narrative embeddings detect PTSD following childbirth via birth stories > Materials and methods > Narrative analysis
Reported 14365 · recomputed 2956680
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Blevins, C. A., Weathers, F. W., Davis, M. T., Witte, T. K., & Domino, J. L. (2015) · Journal of Traumatic Stress · doi:10.1002/jts.22059 · Cited by 5,233 · cited 2×
“For each participant, we assessed PTSD symptoms associated with childbirth using the Posttraumatic Stress Disorder Checklist for DSM-5 (PCL-5) 34,51 , a 20-item self-report measure employed to ascertain the presence and severity of DSM-5 PTSD symptoms after a designated traumatic event over the…”
Christiane, Druml, Wolzt, & Pleiner (2001) · Acta Scientiarum Naturalium Universitatis Sunyatseni · Cited by 3,419
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.03771 · Cited by 3,347
Sallam, M. (2023) · Healthcare · doi:10.3390/healthcare11060887 · Cited by 3,126 · cited 1×
“Recently, the medical community became intrigued by its capabilities after it demonstrated its proficiency in passing medical board exams 10 , and its potential applications in medical care are wide-ranging 11–13 .”
Bergen, N., & Labonté, R. (2020) · Qualitative Health Research · doi:10.1177/1049732319889354 · Cited by 1,558
BioGPT: generative pre-trained transformer for biomedical text generation and mining
Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., & Liu, T.-Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac409 · Cited by 1,150
Wortmann, J. H., Jordan, A. H., Weathers, F. W., Resick, P. A., Dondanville, K. A., Hall-Clark, B., Foa, E. B., Young-McCaughan, S., Yarvis, J. S., Hembree, E. A., et al. (2016) · Psychological Assessment · doi:10.1037/pas0000260 · Cited by 913 · cited 1×
“The PCL-5 is widely recognized for its strong alignment with diagnostic assessments by clinicians and is used to establish a provisional PTSD diagnosis 34,52 (i.e., a presumptive disease state without a formal diagnosis), and is validated in postpartum samples 34 .”
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., & Yang, D. (2023) · arXiv · doi:10.48550/arxiv.2302.06476 · Cited by 869
Yildiz, P. D., Ayers, S., & Phillips, L. (2017) · Journal of Affective Disorders · doi:10.1016/j.jad.2016.10.009 · Cited by 768 · cited 3×
“In recent years, however, childbirth has become increasingly acknowledged as a significant PTSD trigger 30,33,34 .”
Publicly Available Clinical BERT Embeddings
Alsentzer, E., Murphy, J. R., Boag, W., Weng, W., Jin, D., Naumann, T., & McDermott, M. B. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03323 · Cited by 693
Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al. (2023) · Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.ijcnlp-main.45 · Cited by 682 · cited 1×
“In addition to its conversational abilities, ChatGPT has demonstrated remarkable performance on various other NLP tasks, including question-answering 14 , even in zero-or few-shot learning scenarios 4 .”
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., & Yang, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.85 · Cited by 504 · cited 1×
“The performance of ChatGPT in identifying suicide and depression suggests a promising future for PLMs for mental health 15,20,21 .”
ChatGPT in healthcare: A taxonomy and systematic review
Li, J., Dada, A., Puladi, B., Kleesiek, J., & Egger, J. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108013 · Cited by 452
Bang, Y., Cahyawijaya, S., Lee, N., Dai, W., Su, D., Wilie, B., Lovenia, H., Ji, Z., Yu, T., Chung, W., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.04023 · Cited by 337 · cited 1×
“In addition to its conversational abilities, ChatGPT has demonstrated remarkable performance on various other NLP tasks, including question-answering 14 , even in zero-or few-shot learning scenarios 4 .”
ChatGPT: Evolution or revolution?
Gordijn, B., & Have, H. T. (2023) · Medicine, Health Care and Philosophy · doi:10.1007/s11019-023-10136-0 · Cited by 317 · cited 1×
“Recently, the medical community became intrigued by its capabilities after it demonstrated its proficiency in passing medical board exams 10 , and its potential applications in medical care are wide-ranging 11–13 .”
Krüger-Gottschalk, A., Knaevelsrud, C., Rau, H., Dyer, A., Schäfer, I., Schellong, J., & Ehring, T. (2017) · BMC Psychiatry · doi:10.1186/s12888-017-1541-6 · Cited by 305 · cited 1×
“The clinical cutoff for this measure in non-postpartum samples is reported to be 31–33 53 , with a high specificity level using this cutoff 34 , and in accordance with this, and to reduce false negatives 34 , we used values of 31 + to define high scores for this study (potential CB-PTSD).”
Luca, D. L., Margiotta, C., Staatz, C., Garlow, E., Christensen, A., & Zivin, K. (2020) · American Journal of Public Health · doi:10.2105/ajph.2020.305619 · Cited by 303
ChatGPT: Is this version good for healthcare and research?
Vaishya, R., Misra, A., & Vaish, A. (2023) · Diabetes & Metabolic Syndrome: Clinical Research & Reviews · doi:10.1016/j.dsx.2023.102744 · Cited by 293 · cited 3×
“5-turbo-16k), manifests only modest results, confirming its previously reported non-specialized nature for clinical applications 13,22,23 .”
Forkus, S. R., Raudales, A. M., Rafiuddin, H. S., Weiss, N. H., Messman, B. A., & Contractor, A. A. (2023) · Clinical Psychology: Science and Practice · doi:10.1037/cps0000111 · Cited by 262 · cited 1×
“Additionally, while we assessed the presence of CB-PTSD using the PCL-5, which is a well validated self-report measure 34,51,64,65 and shows strong correspondence with clinical diagnostics 34 , clinician evaluations were not performed.”
MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Ji, S., Zhang, T., Ansari, L., Fu, J., Tiwari, P., & Cambria, E. (2022) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/2d7umxifj8wz · Cited by 233
Prevalence of postpartum depression and interventions utilized for its management
Anokye, R., Acheampong, E., Budu-Ainooson, A., Obeng, E. I., & Akwasi, A. G. (2018) · Annals of General Psychiatry · doi:10.1186/s12991-018-0188-0 · Cited by 224 · cited 1×
“Patients’ self-reporting of their symptoms via questionnaires may entail under-reporting due to stigma, social desirability bias, fears of infant separation, and lack of awareness that can lead to significant under-diagnoses 40,41 .”
Trauma narratives in posttraumatic stress disorder: A review
O'Kearney, R., & Perrott, K. (2006) · Journal of Traumatic Stress · doi:10.1002/jts.20099 · Cited by 210 · cited 1×
“The words in individuals’ trauma narratives may reflect post-trauma adjustment even before deep psychological analysis occurs 46 .”
Garg, R. K., Urs, V. L., Agrawal, A. A., Chaudhary, S. K., Paliwal, V., & Kar, S. K. (2023) · Health Promotion Perspectives · doi:10.34172/hpp.2023.22 · Cited by 202
Memory and narrative of traumatic events: A literature review.
Crespo, M., & Fernández-Lansac, V. (2016) · Psychological Trauma: Theory, Research, Practice, and Policy · doi:10.1037/tra0000041 · Cited by 193 · cited 1×
“Research has shown that the way in which individuals remember and describe traumatic events, encompassing the language used in the narrative, is connected to the expression of their post-traumatic stress symptoms 45 .”
Sohail, S. S., Farhat, F., Himeur, Y., Nadeem, M., Madsen, D. Ø., Singh, Y., Atalla, S., & Mansoor, W. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101675 · Cited by 192
The now and future of ChatGPT and GPT in psychiatry
Cheng, S., Chang, C., Chang, W., Wang, H., Liang, C., Kishimoto, T., Chang, J. P., Kuo, J. S., & Su, K. (2023) · Psychiatry and Clinical Neurosciences · doi:10.1111/pcn.13588 · Cited by 188 · cited 1×
“In the mental health domain, ChatGPT has been employed for a variety of applications 15–17 , and was able to identify a single patient with schizophrenia and recommend a treatment that aligns with current clinical standards of care 18 .”
McKenzie-McHarg, K., Ayers, S., Ford, E., Horsch, A., Jomeen, J., Sawyer, A., Stramrood, C., Thomson, G., & Slade, P. (2015) · Journal of Reproductive and Infant Psychology · doi:10.1080/02646838.2015.1031646 · Cited by 158
COVID-19 is associated with traumatic childbirth and subsequent mother-infant bonding problems
Mayopoulos, G. A., Ein-Dor, T., Dishy, G. A., Nandru, R., Chan, S. J., Hanley, L. E., Kaimal, A. J., & Dekel, S. (2021) · Journal of Affective Disorders · doi:10.1016/j.jad.2020.12.101 · Cited by 151 · cited 1×
“The sample includes women who gave birth before and during the COVID-19 pandemic 62,63 .”
Self-citationIs childbirth-induced PTSD associated with low maternal attachment?
Dekel, S., Thiel, F., Dishy, G. A., & Ashenfarb, A. L. (2018) · Archives of Women s Mental Health · doi:10.1007/s00737-018-0853-y · Cited by 138 · cited 1×
“Untreated CB-PTSD is associated with negative effects in the mother and, by extension, her child 35,36 , and these consequences carry significant societal costs 37,38 .”
Self-citationChildbirth and criteria for traumatic events
Boorman, R. J., Devilly, G. J., Gamble, J., Creedy, D. K., & Fenwick, J. (2014) · Midwifery · doi:10.1016/j.midw.2013.03.001 · Cited by 133
Artificial intelligence in the era of ChatGPT - Opportunities and challenges in mental health care
Singh, O. P. (2023) · Indian Journal of Psychiatry · doi:10.4103/indianjpsychiatry.indianjpsychiatry_112_23 · Cited by 131 · cited 10×
“The models that we compared were evaluated using two Evaluation Methods on the dataset published in 47 : Evaluation Method 1: We fine-tuned each of the six evaluated PLMs on a down-stream task of classifying narratives as CB-PTSD (Class 1) or not (Class 0).”
InfluentialBeyond postpartum depression: posttraumatic stress-depressive response following childbirth
Dekel, S., Ein-Dor, T., Dishy, G. A., & Mayopoulos, P. A. (2020) · Archives of Women's Mental Health · doi:10.1007/s00737-019-01006-x · Cited by 122 · cited 2×
“In recent years, however, childbirth has become increasingly acknowledged as a significant PTSD trigger 30,33,34 .”
Self-citationThe norm of the Schur product operation
Davis, C. (1962) · Numerische Mathematik · doi:10.1007/bf01386329 · Cited by 121
Linguistic predictors of trauma pathology and physical health
Alvarez‐Conrad, J., Zoellner, L. A., & Foa, E. B. (2001) · Applied Cognitive Psychology · doi:10.1002/acp.839 · Cited by 112 · cited 1×
“Alternatively, the narrative style and language that individuals use when recounting traumatic events have been suggested to provide deep insights into their mental well-being 42–44 .”
Childbirth related PTSD and its association with infant outcome: A systematic review
Sieleghem, S. V., Danckaerts, M., Rieken, R., Okkerse, J. M. E., de Jonge, E., Bramer, W. M., & den Berg, M. P. L. (2022) · Early Human Development · doi:10.1016/j.earlhumdev.2022.105667 · Cited by 101 · cited 1×
“Untreated CB-PTSD is associated with negative effects in the mother and, by extension, her child 35,36 , and these consequences carry significant societal costs 37,38 .”
Massachusetts General Hospital Comprehensive Clinical Psychiatry
(2024) · Elsevier eBooks · doi:10.1016/c2022-0-02075-4 · Cited by 97
Levis, M., Leonard Westgate, C., Gui, J., Watts, B. V., & Shiner, B. (2021) · Psychological Medicine · doi:10.1017/s0033291720000173 · Cited by 87
Changes in trauma memory and patterns of posttraumatic stress
Dekel, S., & Bonanno, G. A. (2013) · Psychological Trauma Theory Research Practice and Policy · doi:10.1037/a0022750 · Cited by 77
ChatGPT as a Complementary Mental Health Resource: A Boon or a Bane
Farhat, F. (2023) · doi:10.20944/preprints202307.1479.v1 · Cited by 76 · cited 3×
“5-turbo-16k), manifests only modest results, confirming its previously reported non-specialized nature for clinical applications 13,22,23 .”
Liu, N., Luo, K., Yuan, Z., & Chen, Y. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.772592 · Cited by 66
Preventing posttraumatic stress disorder following childbirth: a systematic review and meta-analysis
Dekel, S., Papadakis, J. E., Quagliarini, B., Pham, C. T., Pacheco‐Barrios, K., Hughes, F., Jagodnik, K. M., & Nandru, R. (2023) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2023.12.013 · Cited by 66 · cited 1×
“Early treatment for CB-PTSD facilitates improved outcomes 39 .”
Self-citationSachdeva, J., Nagle-Yang, S. M., Gopalan, P. R., Worley, L. L. M., Mittal, L. P., Shirvani, N., Spada, M. L., Albertini, E., Shenai, N., Simas, T. A. M., et al. (2022) · Journal of the Academy of Consultation-Liaison Psychiatry · doi:10.1016/j.jaclp.2022.04.005 · Cited by 58
Postpartum Help-Seeking: The Role of Stigma and Mental Health Literacy
Jones, A. (2022) · Maternal and Child Health Journal · doi:10.1007/s10995-022-03399-1 · Cited by 56
Mayopoulos, G. A., Ein-Dor, T., Li, K. G., Chan, S. J., & Dekel, S. (2021) · Scientific Reports · doi:10.1038/s41598-021-92985-4 · Cited by 55 · cited 1×
“The sample includes women who gave birth before and during the COVID-19 pandemic 62,63 .”
Self-citationRisk factors for developing posttraumatic stress disorder following childbirth
Chan, S. J., Ein-Dor, T., Mayopoulos, P. A., Mesa, M. M., Sunda, R. M., McCarthy, B. F., Kaimal, A. J., & Dekel, S. (2020) · Psychiatry Research · doi:10.1016/j.psychres.2020.113090 · Cited by 54 · cited 1×
“Importantly, this could improve the accessibility of CB-PTSD diagnosis, addressing socioeconomic, racial, and ethnic disparities associated with childbirth trauma 59,60 by helping to identify minoritized women, who are at three times higher risk of experiencing post-traumatic stress symptoms 60 .”
Self-citationEvaluation of ChatGPT for NLP-based Mental Health Applications
Lamichhane, B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.15727 · Cited by 53
Sommerlad, S., Schermelleh-Engel, K., Rosa, V. L. L., Louwen, F., & Oddo-Sommerfeld, S. (2021) · PLoS ONE · doi:10.1371/journal.pone.0256681 · Cited by 47 · cited 1×
“For approximately one-third of this population, childbirth may be a source of substantial acute stress or trauma 26–29 , and a significant minority will develop childbirth-related post-traumatic stress disorder (CB-PTSD) 30,31 .”
Bartal, A., Jagodnik, K. M., Chan, S. J., Babu, M. S., & Dekel, S. (2023) · American Journal of Obstetrics & Gynecology MFM · doi:10.1016/j.ajogmf.2022.100834 · Cited by 44
Self-citationPeritraumatic dissociation in childbirth-evoked posttraumatic stress and postpartum mental health
Thiel, F., & Dekel, S. (2019) · Archives of Women s Mental Health · doi:10.1007/s00737-019-00978-0 · Cited by 40
Self-citationAdvancing Mental Health Diagnostics: GPT-Based Method for Depression Detection
Danner, M., Hadzic, B., Gerhardt, S., Ludwig, S., Uslu, I., Shao, P., Weber, T., Shiban, Y., & Ratsch, M. (2023) · 2023 62nd Annual Conference of the Society of Instrument and Control Engineers (SICE) · doi:10.23919/sice59929.2023.10354236 · Cited by 39 · cited 1×
“In another project, ChatGPT was also successful for early depression detection 19 .”
Sohail, S. S. (2024) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03335-6 · Cited by 35
A diagnostic questionnaire for childbirth related posttraumatic stress disorder: a validation study
Arora, I. H., Woscoboinik, G. G., Mokhtar, S., Quagliarini, B., Bartal, A., Jagodnik, K. M., Barry, R. L., Edlow, A. G., Orr, S. P., & Dekel, S. (2024) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2023.11.1229 · Cited by 32
Self-citationOrovou, E., Theodoropoulou, I. M., & Antoniou, E. (2021) · PLOS ONE · doi:10.1371/journal.pone.0255689 · Cited by 31 · cited 1×
“Additionally, while we assessed the presence of CB-PTSD using the PCL-5, which is a well validated self-report measure 34,51,64,65 and shows strong correspondence with clinical diagnostics 34 , clinician evaluations were not performed.”
Sch-net: a deep learning architecture for automatic detection of schizophrenia
Fu, J., Yang, S., He, F., He, L., Li, Y., Zhang, J., & Xiong, X. (2021) · BioMedical Engineering OnLine · doi:10.1186/s12938-021-00915-2 · Cited by 31
Wang, L., Zhang, Y., Chignell, M., Shan, B., Sheehan, K., Razak, F. A., & Verma, A. A. (2022) · JMIR Medical Informatics · doi:10.2196/38161 · Cited by 31
Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT
Amin, M. M., Cambria, E., & Schuller, B. W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.03186 · Cited by 30
Galido, P. V., Butala, S., Chakerian, M., & Agustines, D. (2023) · Cureus · doi:10.7759/cureus.38166 · Cited by 29 · cited 1×
“In the mental health domain, ChatGPT has been employed for a variety of applications 15–17 , and was able to identify a single patient with schizophrenia and recommend a treatment that aligns with current clinical standards of care 18 .”
Traumatic memories of childbirth relate to maternal postpartum posttraumatic stress disorder
Thiel, F., Berman, Z., Dishy, G. A., Chan, S. J., Seth, H., Tokala, M., Pitman, R. K., & Dekel, S. (2020) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2020.102342 · Cited by 29
Self-citationDevelopmental costs associated with early maternal withdrawal
Lyons‐Ruth, K., & Yarger, H. A. (2022) · Child Development Perspectives · doi:10.1111/cdep.12442 · Cited by 26 · cited 1×
“Untreated CB-PTSD is associated with negative effects in the mother and, by extension, her child 35,36 , and these consequences carry significant societal costs 37,38 .”
Examining Symptom Clusters of Childbirth-Related Posttraumatic Stress Disorder
Thiel, F., Ein‐Dor, T., Dishy, G. A., King, A., & Dekel, S. (2018) · The Primary Care Companion For CNS Disorders · doi:10.4088/pcc.18m02322 · Cited by 24 · cited 2×
“The clinical cutoff for this measure in non-postpartum samples is reported to be 31–33 53 , with a high specificity level using this cutoff 34 , and in accordance with this, and to reduce false negatives 34 , we used values of 31 + to define high scores for this study (potential CB-PTSD).”
Self-citationValidation of childbirth-related posttraumatic stress disorder using psychophysiological assessment
Chan, S. J., Thiel, F., Kaimal, A. J., Pitman, R. K., Orr, S. P., & Dekel, S. (2022) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2022.05.051 · Cited by 24
Self-citationAdvances in virtual care for perinatal mental disorders
Vigod, S. N., & Dennis, C. (2020) · World Psychiatry · doi:10.1002/wps.20775 · Cited by 21
Vanaken, L., Smeets, T., Bijttebier, P., & Hermans, D. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.558044 · Cited by 21
Iyengar, A. S., Ein‐Dor, T., Zhang, E. X., Chan, S. J., Kaimal, A. J., & Dekel, S. (2022) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.14280 · Cited by 20
Self-citationJagodnik, K. M., Ein‐Dor, T., Chan, S. J., Ashkenazy, A. T., Bartal, A., Barry, R. L., & Dekel, S. (2023) · Journal of Affective Disorders · doi:10.1016/j.jad.2023.12.010 · Cited by 20 · cited 1×
“For approximately one-third of this population, childbirth may be a source of substantial acute stress or trauma 26–29 , and a significant minority will develop childbirth-related post-traumatic stress disorder (CB-PTSD) 30,31 .”
Self-citationSocietal Costs of Untreated Perinatal Mood and Anxiety Disorders in the United StatesPreprint
Luca, D. L., Garlow, N., Staatz, C., Margiotta, C., & Zivin, K. (n.d.) · RePEc: Research Papers in Economics · Cited by 19
Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health
Ji, S., Zhang, T., Yang, K., Ananiadou, S., Cambria, E., & Tiedemann, J. (2023) · arXiv · doi:10.48550/arxiv.2304.10447 · Cited by 16 · cited 1×
“#3 with different embeddings generated by six PLMs that were trained on different domains, including clinical and mental health domains: all-mpnet-base-v2 47 , mental-roberta-base 6 , mental-bert-base-uncased 6 , mental-xlnet-base-cased 7 , Bio ClinicalBERT 24 , and BioGPT 25 .”
Booker, J. A., Graci, M. E., Hudak, L. A., Jovanovic, T., Rothbaum, B. O., Ressler, K. J., Fivush, R., & Stevens, J. (2018) · Journal of Traumatic Stress · doi:10.1002/jts.22271 · Cited by 13
Sohail, S. S. (2023) · Research Square · doi:10.21203/rs.3.rs-3198011/v1 · Cited by 11
A call for a formal diagnosis for childbirth-related PTSD
Dekel, S. (2024) · Nature Mental Health · doi:10.1038/s44220-024-00213-5 · Cited by 7 · cited 1×
“The importance of prompt and accurate screening for CB-PTSD cannot be overstated 34,56 , as early interventions are essential to prevent the progression of this disorder to chronic stages, complicating treatment.”
Self-citationEnrichrBot: Twitter bot tracking tweets about human genes
Bartal, A., Lachmann, A., Clarke, D. J. B., Seiden, A. H., Jagodnik, K. M., & Ma’ayan, A. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa240 · Cited by 3 · cited 1×
“The analyzed sample consists of 1295 women who provided narratives of length 30 words or more, which length was selected to facilitate meaningful analysis, consistent with previous work that noted limitations in analyzing shorter narratives 47,48 .”
Self-citationMentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Ji, S., Zhang, T., Ansari, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.15621
Research works printed but not linked: 2
- Brants, T., Popat, A. C., Xu, P., Och, F. J. & Dean, J. Large language models in machine translation. In Proc. 2007 Joint Conf. Empirical Meth. Nat. Lang. Proc. Computat. Nat. Lang. Learn. Prague. 858–867 (2007).
- Belser, C. A. Comparison of natural language processing models for depression detection in chatbot dialogues. Doctoral dissertation. Massachusetts Institute of Technology. (2023).
Cited by
Moulaei, K., Yadegari, A., Baharestani, M., Farzanbakhsh, S., Sabet, B., & Reza Afrash, M. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105474 · Cited by 244
Large language models for disease diagnosis: a scoping review
Zhou, S., Xu, Z., Zhang, M., Xu, C., Guo, Y., Zhan, Z., Fang, Y., Ding, S., Wang, J., Xu, K., et al. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00011-z · Cited by 122
The Applications of Large Language Models in Mental Health: Scoping Review
Jin, Y., Liu, J., Li, P., Wang, B., Yan, Y., Zhang, H., Ni, C., Wang, J., Li, Y., Bu, Y., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/69284 · Cited by 94
“Therefore, the application of LLMs in mental health is expanding across diverse domains [13-16].”
Hipgrave, L., Goldie, J., Dennis, S., & Coleman, A. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1606291 · Cited by 51
Large Language Models in Mental Health Care: A Systematic Scoping Review (Preprint)
hua, Y., Liu, F., Yang, K., Li, Z., Sheu, Y.-H., Zhou, P., Moran, L. V., Ananiadou, S., Clifton, D. A., & Beam, A. (2024) · doi:10.2196/preprints.64088 · Cited by 46
Metadata
- Authors
- Bartal, A., Jagodnik, K. M., Chan, S. J., & Dekel, S.
- Affiliations
- Bar-Ilan University (IL)
- Harvard University (US)
- Massachusetts General Hospital (US)
- Corresponding author
- Dekel, Sharon
- Venue
- Scientific Reports
- Published
- 2024-04-11
- Volume
- 14
- Issue
- 1
- Pages
- 8336-8336
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC11009279
- OpenAlex
- W4394718458
- Cited by
- 45
- References
- 61
- Citations by year
- 2026: 15 · 2025: 25 · 2024: 5
- FWCI
- 21.29
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Scientific Reports (publishedVersion, cc-by)
- Research Square (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Data Science Institute (DSI) at Bar-Ilan University
- Mortimer B. Zuckerman STEM Leadership Program (Project Title: Assessing Risk Factors for Childbirth-Related Post-Traumatic Stress Disorder)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (R01HD108619)
- Topics
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Maternal Mental Health During Pregnancy and Postpartum
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- postpartum PTSD, childbirth, ChatGPT, text embeddings, natural language processing, PTSD screening, maternal mental health, birth narratives, PCL-5, narrative classification, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.