Natural language processing of multi-hospital electronic health records for public health surveillance of suicidality.


Journal

Npj mental health research
ISSN: 2731-4251
Titre abrégé: Npj Ment Health Res
Pays: England
ID NLM: 9918592488906676

Informations de publication

Date de publication:
14 Feb 2024
Historique:
received: 01 02 2023
accepted: 06 12 2023
medline: 13 4 2024
pubmed: 13 4 2024
entrez: 12 4 2024
Statut: epublish

Résumé

There is an urgent need to monitor the mental health of large populations, especially during crises such as the COVID-19 pandemic, to timely identify the most at-risk subgroups and to design targeted prevention campaigns. We therefore developed and validated surveillance indicators related to suicidality: the monthly number of hospitalisations caused by suicide attempts and the prevalence among them of five known risks factors. They were automatically computed analysing the electronic health records of fifteen university hospitals of the Paris area, France, using natural language processing algorithms based on artificial intelligence. We evaluated the relevance of these indicators conducting a retrospective cohort study. Considering 2,911,920 records contained in a common data warehouse, we tested for changes after the pandemic outbreak in the slope of the monthly number of suicide attempts by conducting an interrupted time-series analysis. We segmented the assessment time in two sub-periods: before (August 1, 2017, to February 29, 2020) and during (March 1, 2020, to June 31, 2022) the COVID-19 pandemic. We detected 14,023 hospitalisations caused by suicide attempts. Their monthly number accelerated after the COVID-19 outbreak with an estimated trend variation reaching 3.7 (95%CI 2.1-5.3), mainly driven by an increase among girls aged 8-17 (trend variation 1.8, 95%CI 1.2-2.5). After the pandemic outbreak, acts of domestic, physical and sexual violence were more often reported (prevalence ratios: 1.3, 95%CI 1.16-1.48; 1.3, 95%CI 1.10-1.64 and 1.7, 95%CI 1.48-1.98), fewer patients died (p = 0.007) and stays were shorter (p < 0.001). Our study demonstrates that textual clinical data collected in multiple hospitals can be jointly analysed to compute timely indicators describing mental health conditions of populations. Our findings also highlight the need to better take into account the violence imposed on women, especially at early ages and in the aftermath of the COVID-19 pandemic.

Identifiants

pubmed: 38609541
doi: 10.1038/s44184-023-00046-7
pii: 10.1038/s44184-023-00046-7
doi:

Types de publication

Journal Article

Langues

eng

Pagination

6

Informations de copyright

© 2024. The Author(s).

Références

Moutier, C. Suicide Prevention in the COVID-19 Era: Transforming Threat Into Opportunity. JAMA Psychiatry https://doi.org/10.1001/jamapsychiatry.2020.3746 (2020).
Dubé, J. P., Smith, M. M., Sherry, S. B., Hewitt, P. L. & Stewart, S. H. Suicide behaviors during the COVID-19 pandemic: a meta-analysis of 54 studies. Psychiatry Res. 301, 113998 (2021).
pubmed: 34022657 pmcid: 9225823 doi: 10.1016/j.psychres.2021.113998
Leske, S., Kõlves, K., Crompton, D., Arensman, E. & de Leo, D. Real-time suicide mortality data from police reports in Queensland, Australia, during the COVID-19 pandemic: an interrupted time-series analysis. Lancet Psychiatry 8, 58–63 (2021).
pubmed: 33212023 doi: 10.1016/S2215-0366(20)30435-1
Pirkis, J. et al. Suicide trends in the early months of the COVID-19 pandemic: an interrupted time-series analysis of preliminary data from 21 countries. Lancet Psychiatry 8, 579–588 (2021).
pubmed: 33862016 pmcid: 9188435 doi: 10.1016/S2215-0366(21)00091-2
Jollant, F. et al. Hospitalization for self-harm during the early months of the COVID-19 pandemic in France: A nationwide retrospective observational cohort study. Lancet Reg. Health Eur 6, 100102 (2021).
pubmed: 34557830 pmcid: 8454825 doi: 10.1016/j.lanepe.2021.100102
Gracia, R. et al. Is the COVID-19 pandemic a risk factor for suicide attempts in adolescent girls? J. Affect. Disord. 292, 139–141 (2021).
pubmed: 34119869 pmcid: 8777066 doi: 10.1016/j.jad.2021.05.044
Cousien, A., Acquaviva, E., Kernéis, S., Yazdanpanah, Y. & Delorme, R. Temporal trends in suicide attempts among children in the decade before and during the COVID-19 pandemic in Paris, France. JAMA Netw. Open 4, e2128611 (2021).
pubmed: 34618041 pmcid: 8498848 doi: 10.1001/jamanetworkopen.2021.28611
Ridout, K. K. et al. Emergency department encounters among youth with suicidal thoughts or behaviors during the COVID-19 pandemic. JAMA Psychiatry 78, 1319–1328 (2021).
pubmed: 34468724 doi: 10.1001/jamapsychiatry.2021.2457
Yard, E. et al. Emergency department visits for suspected suicide attempts among persons aged 12-25 years before and during the COVID-19 pandemic—United States, January 2019-May 2021. MMWR Morb. Mortal. Wkly. Rep. 70, 888–894 (2021).
pubmed: 34138833 pmcid: 8220953 doi: 10.15585/mmwr.mm7024e1
Bersia, M. et al. Suicide spectrum among young people during the COVID-19 pandemic: a systematic review and meta-analysis. EClinicalMedicine 54, 101705 (2022).
pubmed: 36338787 pmcid: 9621691 doi: 10.1016/j.eclinm.2022.101705
Swedo, E. Trends in U.S. emergency department visits related to suspected or confirmed child abuse and neglect among children and adolescents aged 18 years before and during the COVID-19 pandemic — United States, January 2019–September 2020. MMWR Morb. Mortal. Wkly. Rep. 69, 1841–1847 (2020).
John, A., Pirkis, J., Gunnell, D., Appleby, L. & Morrissey, J. Trends in suicide during the covid-19 pandemic. BMJ 371, m4352 (2020).
pubmed: 33184048 doi: 10.1136/bmj.m4352
Bitsko, R. H. et al. Mental health surveillance among children—United States, 2013-2019. MMWR Suppl. 71, 1–42 (2022).
pubmed: 35202359 pmcid: 8890771 doi: 10.15585/mmwr.su7102a1
Spasic, I. & Nenadic, G. Clinical text data in machine learning: systematic review. JMIR Med. Inform. 8, e17984 (2020).
pubmed: 32229465 pmcid: 7157505 doi: 10.2196/17984
Jiang, L. Y. et al. Health system-scale language models are all-purpose prediction engines. Nature 619, 357–362 (2023).
pubmed: 37286606 pmcid: 10338337 doi: 10.1038/s41586-023-06160-y
Shakeri Hossein Abad, Z. et al. Digital public health surveillance: a systematic scoping review. NPJ Digit. Med. 4, 41 (2021).
pubmed: 33658681 pmcid: 7930261 doi: 10.1038/s41746-021-00407-6
Syrowatka, A. et al. Leveraging artificial intelligence for pandemic preparedness and response: a scoping review to identify key use cases. NPJ Digit. Med. 4, 96 (2021).
pubmed: 34112939 pmcid: 8192906 doi: 10.1038/s41746-021-00459-8
Yin, Z., Sulieman, L. M. & Malin, B. A. A systematic literature review of machine learning in online personal health data. J. Am. Med. Inform. Assoc. JAMIA 26, 561–576 (2019).
pubmed: 30908576 doi: 10.1093/jamia/ocz009
Edo-Osagie, O., De La Iglesia, B., Lake, I. & Edeghere, O. A scoping review of the use of Twitter for public health research. Comput. Biol. Med. 122, 103770 (2020).
pubmed: 32502758 pmcid: 7229729 doi: 10.1016/j.compbiomed.2020.103770
Kohane, I. S. et al. What every reader should know about studies using electronic health record data but may be afraid to ask. J. Med. Internet Res. 23, e22219 (2021).
pubmed: 33600347 pmcid: 7927948 doi: 10.2196/22219
Wismüller, A. et al. Early-stage COVID-19 pandemic observations on pulmonary embolism using nationwide multi-institutional data harvesting. NPJ Digit. Med. 5, 120 (2022).
pubmed: 35986059 pmcid: 9388980 doi: 10.1038/s41746-022-00653-2
Desai, R. J. et al. Broadening the reach of the FDA Sentinel system: a roadmap for integrating electronic health record data in a causal analysis framework. NPJ Digit. Med. 4, 170 (2021).
pubmed: 34931012 pmcid: 8688411 doi: 10.1038/s41746-021-00542-0
Bittar, A., Velupillai, S., Downs, J., Sedgwick, R. & Dutta, R. Reviewing a decade of research into suicide and related behaviour using the South London and Maudsley NHS Foundation Trust Clinical Record Interactive Search (CRIS) System. Front. Psychiatry 11, 553463 (2020).
pubmed: 33329090 pmcid: 7729078 doi: 10.3389/fpsyt.2020.553463
Metzger, M.-H. et al. Use of emergency department electronic medical records for automated epidemiological surveillance of suicide attempts: a French pilot study. Int. J. Methods Psychiatr. Res. 26, e1522 (2017).
pubmed: 27634457 doi: 10.1002/mpr.1522
Xie, F., Ling Grant, D. S., Chang, J., Amundsen, B. I. & Hechter, R. C. Identifying suicidal ideation and attempt from clinical notes within a large integrated health care system. Perm. J. 26, 85–93 (2022).
pubmed: 35609162 pmcid: 9126541 doi: 10.7812/TPP/21.102
Karystianis, G. et al. Automated analysis of domestic violence police reports to explore abuse types and victim injuries: text mining study. J. Med. Internet Res. 21, e13067 (2019).
pubmed: 30860490 pmcid: 6434398 doi: 10.2196/13067
Downs, J. et al. Detection of suicidality in adolescents with autism spectrum disorders: developing a natural language processing approach for use in electronic health records. AMIA Annu. Symp. Proc. 2017, 641–649 (2017).
pubmed: 29854129
Finlayson, S. G. et al. The clinician and dataset shift in artificial intelligence. N. Engl. J. Med. 385, 283–286 (2021).
pubmed: 34260843 pmcid: 8665481 doi: 10.1056/NEJMc2104626
Angelakis, I., Gillespie, E. L. & Panagioti, M. Childhood maltreatment and adult suicidality: a comprehensive systematic review with meta-analysis. Psychol. Med. 49, 1057–1078 (2019).
pubmed: 30608046 pmcid: 6498789 doi: 10.1017/S0033291718003823
Serafini, G. et al. Life adversities and suicidal behavior in young individuals: a systematic review. Eur. Child Adolesc. Psychiatry 24, 1423–1446 (2015).
pubmed: 26303813 doi: 10.1007/s00787-015-0760-y
Lawn, R. B. & Koenen, K. C. Violence against women and girls has long term health consequences. BMJ 375, e069311 (2021).
pubmed: 34969657 doi: 10.1136/bmj-2021-069311
Sardinha, L., Maheu-Giroux, M., Stöckl, H., Meyer, S. R. & García-Moreno, C. Global, regional, and national prevalence estimates of physical or sexual, or both, intimate partner violence against women in 2018. Lancet Lond. Engl. 399, 803–813 (2022).
doi: 10.1016/S0140-6736(21)02664-7
Di Fazio, N. et al. Mental health consequences of COVID-19 pandemic period in the European population: an institutional challenge. Int. J. Environ. Res. Public. Health 19, 9347 (2022).
pubmed: 35954706 pmcid: 9367746 doi: 10.3390/ijerph19159347
Violence Against Women Prevalence Estimates. World Health Organization https://www.who.int/publications-detail-redirect/9789240022256 (2021).
RESPECT women – Preventing violence against women. World Health Organization https://www.who.int/publications-detail-redirect/WHO-RHR-18.19 (2019).
Stubbs, A. & Szoeke, C. The effect of intimate partner violence on the physical health and health-related behaviors of women: a systematic review of the literature. Trauma Violence Abuse 23, 1157–1172 (2022).
pubmed: 33541243 doi: 10.1177/1524838020985541
Jewkes, R. et al. Effective design and implementation elements in interventions to prevent violence against women and girls associated with success: reflections from the what works to prevent violence against women and girls? Global programme. Int. J. Environ. Res. Public Health 18, 12129 (2020).
Krug, E., Dahlberg, L., Mercy, J., Zwi, A. & Lozano, R. World report on violence and health. http://apps.who.int/iris/bitstream/handle/10665/42495/9241545615_eng.pdf?sequence=1 (2002).
Anderson, H. D. et al. Monitoring suicidal patients in primary care using electronic health records. J. Am. Board Fam. Med. 28, 65–71 (2015).
pubmed: 25567824 doi: 10.3122/jabfm.2015.01.140181
Fradera, M. et al. Can Routine Primary Care Records Help in Detecting Suicide Risk? A Population-Based Case-Control Study in Barcelona. Arch. Suicide Res. 26, 1395–1409 (2022).
pubmed: 33896400 doi: 10.1080/13811118.2021.1911894
Benchimol, E. I. et al. The REporting of studies Conducted using Observational Routinely-collected health Data (RECORD) statement. PLoS Med. 12, e1001885 (2015).
pubmed: 26440803 pmcid: 4595218 doi: 10.1371/journal.pmed.1001885
Durkheim, E. Suicide: A Study of Sociology (Routledge, 1897).
Zortea, T. C. et al. The impact of infectious disease-related public health emergencies on suicide, suicidal behavior, and suicidal thoughts. Crisis 42, 474–487 (2021).
pubmed: 33063542 doi: 10.1027/0227-5910/a000753
Laliotis, I., Ioannidis, J. P. A. & Stavropoulou, C. Total and cause-specific mortality before and after the onset of the Greek economic crisis: an interrupted time-series analysis. Lancet Public Health 1, e56–e65 (2016).
pubmed: 29253418 doi: 10.1016/S2468-2667(16)30018-4
Murphy, S. N. et al. Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2). J. Am. Med. Inform. Assoc. JAMIA 17, 124–130 (2010).
pubmed: 20190053 doi: 10.1136/jamia.2009.000893
Liu, Y. et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach. http://arxiv.org/abs/1907.11692 (2019). https://doi.org/10.48550/arXiv.1907.11692 .
Dura, B. et al. EDS-NLP: efficient information extraction from French clinical notes. https://doi.org/10.5281/zenodo.6818507 (2022).
Martin, L. et al. CamemBERT: a Tasty French Language Model. in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics 7203–7219 https://doi.org/10.18653/v1/2020.acl-main.645 (2020).
Dura, B. et al. Learning structures of the French clinical language:development and validation of word embedding models using 21 million clinical reports from electronic health records. http://arxiv.org/abs/2207.12940 (2022). https://doi.org/10.48550/arXiv.2207.12940 .
Cicchetti, D. V. & Feinstein, A. R. High agreement but low kappa: II. Resolving the paradoxes. J. Clin. Epidemiol. 43, 551–558 (1990).
pubmed: 2189948 doi: 10.1016/0895-4356(90)90159-M
Bernal, J. L., Cummins, S. & Gasparrini, A. Interrupted time series regression for the evaluation of public health interventions: a tutorial. Int. J. Epidemiol. 46, 348–355 (2017).
pubmed: 27283160
Galvão, P. V. M., Silva, H. R. S. E. & Silva, C. M. F. P. d. Temporal distribution of suicide mortality: a systematic review. J. Affect. Disord 228, 132–142 (2018).
pubmed: 29247901 doi: 10.1016/j.jad.2017.12.008
Seabold, S. & Perktold, J. Statsmodels: econometric and statistical modeling with python. In Proc 9th Python in Science Conference, (2010).
Davidson-Pilon, C. lifelines: survival analysis in Python. J. Open Source Softw 4, 1317 (2019).
doi: 10.21105/joss.01317
Weiskopf, N. G., Hripcsak, G., Swaminathan, S. & Weng, C. Defining and measuring completeness of electronic health records for secondary use. J. Biomed. Inform. 46, 830–836 (2013).
pubmed: 23820016 doi: 10.1016/j.jbi.2013.06.010

Auteurs

Romain Bey (R)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France.

Ariel Cohen (A)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France. ariel.cohen-ext@aphp.fr.

Vincent Trebossen (V)

Child and Adolescent Psychiatry Department, Robert Debré University Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France.

Basile Dura (B)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France.

Pierre-Alexis Geoffroy (PA)

Département de psychiatrie et d'addictologie, GHU Paris Nord, DMU neurosciences, Bichat - Claude Bernard Hospital, Assistance Publique-Hôpitaux de Paris, 75018, Paris, France.
GHU Paris - psychiatry & neurosciences, 1, rue Cabanis, 75014, Paris, France.
NeuroDiderot, Inserm, FHU I2-D2, université Paris Cité, 75019, Paris, France.
CNRS UPR 3212, Institute for cellular and integrative neurosciences, 67000, Strasbourg, France.

Charline Jean (C)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France.
Université Paris-Est Créteil, INSERM, IMRB U955, Créteil, France.
Service Santé Publique & URC, Hôpital Henri Mondor, Assistance Publique-Hôpitaux de Paris, Créteil, France.

Benjamin Landman (B)

Child and Adolescent Psychiatry Department, Robert Debré University Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France.

Thomas Petit-Jean (T)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France.

Gilles Chatellier (G)

Innovation and Data unit, IT Department, Assistance Publique-Hôpitaux de Paris, Paris, France.
Université Paris Cité, Paris, France.

Kankoe Sallah (K)

URC PNVS, CIC-EC 1425, INSERM, Bichat - Claude Bernard Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France.

Xavier Tannier (X)

Sorbonne Université, Inserm, Université Sorbonne Paris Nord, Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances pour la e-Santé (LIMICS), Paris, France.

Aurelie Bourmaud (A)

Université Paris Cité, Paris, France.
Clinical Epidemiology Unit, Robert Debré University Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France.
CIC 1426, Inserm, Paris, France.

Richard Delorme (R)

Child and Adolescent Psychiatry Department, Robert Debré University Hospital, Assistance Publique-Hôpitaux de Paris, Paris, France.
Human Genetics and Cognitive Functions, Institut Pasteur, Paris, France.

Classifications MeSH