Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.23151039This dataset accompanies a scoping review of machine learning, NLP, deep learning, and spatial modeling studies applied to mental health outcomes across population-level crises: pandemics and infectious disease outbreaks, economic upheavals, natural disasters, and armed conflict or forced displacement. Following PRISMA-ScR and the Arksey and O'Malley framework as refined by Levac et al., a systematic search of PubMed/MEDLINE, Web of Science, Scopus, and IEEE Xplore (2016–2026), supplemented by citation chasing, identified 70 eligible studies from 133 screened records. Determinants extracted during charting were classified using a taxonomy adapted from the WHO Commission on Social Determinants of Health (CSDH) framework, extended with Szreter and Woolcock's social capital typology and Pearlin's stress process model. Of 343 candidate determinant items, 338 (98.5%) were coded: 81 Structural Determinants, 224 Intermediary Determinants, and 33 Cross-Cutting (bridging) items, with 5 excluded as not codeable; a further 45 items were classified separately as Outcome Measures. Two files are included: CSDH_Final_Taxonomy_v22.xlsx: factor-level extraction and CSDH classification across all included studies, with live pivot counts by tier/crisis/method, per-study metadata, a rule-based screening pass and dual-coder worksheets. screening_reconciliation_3.xlsx: title/abstract screening decisions from two independent reviewers, reconciliation of disagreements, and the Cohen's kappa calculation (κ = 0.904, "almost perfect" agreement, N=133). search_and_screening_records.zip — full search and screening audit trail: initial database search results (1.INITIAL_SEARCH.ris), deduplicated record set (2.dedup.ris/.csv), title/abstract screening decisions (3.first_screening.ris/.csv), full-text screening decisions (4.second_screening.ris/.csv), and supplementary records identified via citation chasing (5.supplement.ris).
Keyword(s):
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)