{
  "abstract": "ObjectivesTo assess the feasibility and early performance of an AI-assisted workflow screening inpatient discharge summaries for potential treatment injury requiring clinician review and possible Accident Compensation Corporation (ACC) consideration in New Zealand.\n\nDesignSingle-site, six-month quality-improvement/service-evaluation pilot using a large language model as an index screening tool with clinician adjudication.\n\nSettingWairarapa Hospital, New Zealand.\n\nParticipantsAll inpatient discharge summaries produced during the pilot period (n=2,642).\n\nInterventionsThe model generated structured candidate harm signals with supporting text and certainty labels. Clinicians reviewed all flagged cases and determined whether escalation was appropriate.\n\nMain outcome measuresScreening yield, positive predictive value (PPV) for clinician-adjudicated iatrogenic harm, unsupported outputs, overlap with incident reporting and ACC claims, and clinician workload.\n\nResultsThe workflow generated 237 candidate signals (yield 9.0%, 95% CI 7.9% to 10.1%). Clinicians classified 102 as confirmed iatrogenic harm, 43 as possible harm, 81 as no harm and 11 as unsupported outputs. PPV was 43.0% for confirmed harm (95% CI 36.8% to 49.4%) and 61.2% for confirmed-or-possible harm (95% CI 54.9% to 67.1%); unsupported outputs occurred in 4.6%. Seven ACC claims were lodged following AI-assisted identification. Of 68 organisational ACC claims during the same period, 17 overlapped with AI-identified cases. The workflow required approximately 25-30 minutes of clinician time per week.\n\nConclusionsAI-assisted discharge-summary screening was operationally feasible and increased visibility of potential treatment injuries for clinician review. Further prospective evaluation should use an independent chart-review reference standard to estimate diagnostic accuracy and assess equity, workload and implementation outcomes.\n\nRegistrationNot applicable.\n\nKey messagesO_ST_ABSWhat is already known on this topicC_ST_ABSHealthcare-associated harm is systematically under-detected, with incident reporting and administrative data capturing only a fraction of treatment injuries. Structured record review methods such as the Global Trigger Tool identify substantially higher rates of adverse events but are resource-intensive and difficult to sustain at scale.\n\nWhat this study addsThis study demonstrates that an AI-assisted workflow can feasibly screen inpatient discharge summaries to identify potential treatment injuries for clinician review within routine workflows. The findings suggest that AI can function as a form of visibility infrastructure, surfacing harm signals not consistently captured by existing reporting systems while preserving clinician judgement and governance processes.\n\nHow this study might affect research, practice or policyAI-assisted screening could strengthen patient safety surveillance and support more consistent consideration of treatment injury within compensation systems. Future research should evaluate diagnostic accuracy, equity impacts, and workflow design, including whether carefully governed automation of administrative steps can improve escalation processes without displacing clinical oversight.\n\nDisclaimerThe AI system generated candidate signals of potential treatment injury only. Final determination of treatment injury status and ACC eligibility remained the responsibility of clinicians and the Accident Compensation Corporation through standard statutory processes.",
  "abstract_shown": true,
  "affiliations": [
    "Health New Zealand"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "P. Bhatnagar"
    },
    {
      "name": "W. Fearnley"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c51jk6bwee1r2.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.09.26365175",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.09.26365175v1.full",
  "id": "c51jk6bwee1r2",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.09.26365175v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7221603520",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.09.26365175v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c51jk6bwee1r2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:47Z",
      "native_id": "10.64898/2026.10.09.26365175",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.09.26365175v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "AI-assisted identification of potential treatment injury from inpatient discharge summaries: an early-stage sociotechnical evaluation in a New Zealand district hospital",
  "title_text": "AI-assisted identification of potential treatment injury from inpatient discharge summaries: an early-stage sociotechnical evaluation in a New Zealand district hospital",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:47Z",
  "url": "https://research.draconitic.com/paper/c51jk6bwee1r2",
  "venue": "medRxiv",
  "versions": []
}