{
  "abstract": "Estimating the causal effects of medical treatments is difficult when clinically important outcomes are costly to measure or require long follow-up. Short-term or inexpensive surrogate outcomes offer a potential alternative, but surrogate biomarkers may be unavailable or difficult to identify. Advances in artificial intelligence (AI) have enabled increasingly accurate prediction of clinical outcomes from inexpensive, high-dimensional measurements, which creates an opportunity to use AI predictions themselves as surrogates. To this end, we develop a framework for estimating treatment effects from paired measurements obtained before and after treatment for each treated individual. A pretrained AI model is applied to the before and after measurements, and our estimator compares the resulting outcome predictions. We characterize the technical assumptions under which this within-person contrast identifies the average treatment effect on the treated, even when clinical outcomes are never observed for treated individuals. When these assumptions cannot be justified, we use prediction-powered inference to correct bias using a small number of observed clinical outcomes and obtain valid inference. Synthetic and real-world cardio-oncology experiments demonstrate the validity and accuracy of the approach.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.27180",
  "author_total": 5,
  "authors": [
    {
      "name": "Frances Dean"
    },
    {
      "name": "Anna Neufeld"
    },
    {
      "name": "Joshua Barrios"
    },
    {
      "name": "Geoffrey H Tison"
    },
    {
      "name": "Ahmed Alaa"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/38mcg5qcqp4yh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.27180",
  "fulltext_url": null,
  "id": "38mcg5qcqp4yh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.27180",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2613|Advanced Causal Inference Techniques"
    ]
  ],
  "openalex": "W7214191654",
  "pdf_url": "https://arxiv.org/pdf/2609.27180",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/38mcg5qcqp4yh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:06Z",
      "native_id": "2609.27180",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.27180"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Artificial intelligence surrogates for treatment effect estimation with before-and-after data",
  "title_text": "Artificial intelligence surrogates for treatment effect estimation with before-and-after data",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:06Z",
  "url": "https://research.draconitic.com/paper/38mcg5qcqp4yh",
  "venue": "arXiv",
  "versions": []
}