EUVIMEDEUVIMED entdecken
Übersichtsarbeit

CLARITY: An Exploratory Scaffold for Educational Engagement with AI-Assisted Evidence Synthesis in Rehabilitation

Andrew M Ball, Tommy Perreault, Jan Dommerholt

Archives of Physical Medicine and Rehabilitation · 2026-06 · 107 (6) · 1231-1242

DOI: 10.1016/j.apmr.2026.02.003 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Archives of Physical Medicine and Rehabilitation, 2026-06. Verfasst von Andrew M Ball und 2 weiteren Autor:innen. Beteiligte Einrichtung: Spine and Headache Rehabilitation Lake Norman, Novant Rehabilitation, Novant Health, Charlotte, NC. Electronic address: Andrew.Ball@NovantHealth.org. Hauptthemen laut MEDLINE: Artificial Intelligence, Rehabilitation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: To describe and evaluate Clinical Literature Analysis and Review using Interpretive Transparency (CLARITY), an artificial intelligence (AI)-assisted literature synthesis scaffold designed for structured learning and hypothesis generation in rehabilitation medicine. DESIGN: Proof-of-concept case series using ScholarAI, which integrates GPT-assisted triage and fairness-aware reweighting. All outputs are exploratory and not for clinical application. SETTING: Open-access rehabilitation literature applied in academic and clinical training environments. MAIN OUTCOME MEASURES: Synthesis speed, adjudicator concordance, demographic representation, and fairness-adjusted effect sizes. RESULTS: CLARITY reduced review timelines from months to days, achieving 84.7% concordance in clinician adjudication of borderline studies. Fairness adjustments (±20%) modestly altered pooled estimates and highlighted underrepresentation trends. SHAP and LIME overlays improved transparency but did not affect inclusion outcomes. CONCLUSIONS: CLARITY is an AI-assisted educational scaffold (not yet a clinical decision aid tool), supporting efficient, reproducible, equity-conscious engagement with literature to stimulate hypothesis generation and critical dialogue. Although limited by single-reviewer design and absence of audit logs, it provides a valuable entry point for structured AI-assisted synthesis in early-stage or educational contexts. Outputs are strictly exploratory and require expert interpretation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceRehabilitationHumans

Stichwörter der Autor:innen

Algorithmic fairnessArtificial intelligenceClinical educationEvidence synthesisLIMEMeta-analysisRehabilitationSHAPTransparency

Autor:innen und Institutionen

  • Spine and Headache Rehabilitation Lake Norman, Novant Rehabilitation, Novant Health, Charlotte, NC. Electronic address: Andrew.Ball@NovantHealth.org.
  • Department of Biomedical Informatics, Wentworth-Douglass Hospital/Pinnacle Rehabilitation Network, Dover and Portsmouth, NH.
  • Myopain Seminars, Bethesda, MD.

Zitieren

APA

Ball, A. M., Perreault, T., & Dommerholt, J. (2026). CLARITY: An Exploratory Scaffold for Educational Engagement with AI-Assisted Evidence Synthesis in Rehabilitation. Archives of Physical Medicine and Rehabilitation, 107(6), 1231-1242. https://doi.org/10.1016/j.apmr.2026.02.003

Vancouver

Ball AM, Perreault T, Dommerholt J. CLARITY: An Exploratory Scaffold for Educational Engagement with AI-Assisted Evidence Synthesis in Rehabilitation. Archives of Physical Medicine and Rehabilitation. 2026;107(6):1231-1242. doi:10.1016/j.apmr.2026.02.003

BibTeX
@article{Ball2026,
  author = {Ball, Andrew M and Perreault, Tommy and Dommerholt, Jan},
  title = {CLARITY: An Exploratory Scaffold for Educational Engagement with AI-Assisted Evidence Synthesis in Rehabilitation},
  journal = {Archives of Physical Medicine and Rehabilitation},
  year = {2026},
  volume = {107},
  number = {6},
  pages = {1231--1242},
  doi = {10.1016/j.apmr.2026.02.003}
}
Kostenlos starten →