{
  "abstract": "Alcohol use disorder is a chronic, relapsing condition. Individuals must monitor risk and take proactive steps to manage and reduce it indefinitely to prevent lapse. Smartphone sensing and machine learning offer promise as scalable tools for automating risk monitoring and delivering personalized support during recovery. Research has demonstrated that machine learning models using ecological momentary assessment can generate highly accurate predictions of immediate lapse risk (e.g., within the next hour or day). However, many risks require supports that are not immediately available. These supports may need to be planned or involve coordination with others. In such cases, individuals may benefit from advance warning about changes in their lapse risk and the contributing factors. To meet this need, we developed machine learning models to predict future alcohol lapses within 24-hour prediction windows, lagged by 1 day, 3 days, 1 week, and 2 weeks from the prediction timepoint. We engineered features from 4x daily ecological momentary assessments from individuals (N = 151; 51% male; mean age = 41; 87% non-Hispanic White) in early recovery (≤ 8 weeks of abstinence) from alcohol use disorder over a three-month period. We trained and evaluated models using nested cross-validation. Median posterior auROC values were high (0.85–0.89) across models, though performance decreased modestly with longer lag time. Models performed worse for non-advantaged groups (non-White and/or Hispanic, income below federal poverty line, female) compared to advantaged groups (non-Hispanic White, income above federal poverty line, male). Past alcohol use, abstinence self-efficacy, and craving were the most important features, with the magnitude of their importance varying meaningfully by lag time. These findings demonstrate the feasibility of predicting alcohol lapses up to two weeks in advance. Embedding these models within a recovery monitoring and support system could enable adaptive, personalized care with enough warning to implement recovery supports not immediately available. Improving model fairness and optimizing the delivery of model feedback to sustain engagement remain critical next steps.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Psychology, University of Wisconsin-Madison, Madison, Wisconsin, United States of America",
    "Department of Psychiatry and Behavioral Sciences, Medical University of South Carolina, Charleston, South Carolina, United States of America"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Kendra Wyant"
    },
    {
      "affs": [
        1
      ],
      "name": "Gaylen E. Fronk"
    },
    {
      "name": "Jiachen Yu"
    },
    {
      "name": "Claire E. Punturieri"
    },
    {
      "name": "John J. Curtin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2kgcppc441b5b.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0356893",
  "fulltext_url": null,
  "id": "2kgcppc441b5b",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0356893",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2713|Substance Abuse Treatment and Outcomes"
    ],
    [
      "plos",
      "/Biology and life sciences/Ecology/Community ecology/Ecological risk"
    ],
    [
      "plos",
      "/Biology and life sciences/Nutrition/Diet/Alcohol consumption"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Machine learning algorithms"
    ],
    [
      "plos",
      "/Ecology and environmental sciences/Ecology/Community ecology/Ecological risk"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology/Medical risk factors"
    ],
    [
      "plos",
      "/Medicine and health sciences/Nutrition/Diet/Alcohol consumption"
    ],
    [
      "plos",
      "/People and places/Population groupings/Ethnicities/Hispanic people"
    ],
    [
      "plos",
      "/Physical sciences/Chemistry/Chemical compounds/Organic compounds/Alcohols"
    ],
    [
      "plos",
      "/Physical sciences/Chemistry/Organic chemistry/Organic compounds/Alcohols"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Applied mathematics/Algorithms/Machine learning algorithms"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Statistical methods/Forecasting"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Statistical methods/Forecasting"
    ],
    [
      "plos",
      "/Research and analysis methods/Simulation and modeling/Algorithms/Machine learning algorithms"
    ]
  ],
  "openalex": "W7211930066",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0356893&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-08",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/2kgcppc441b5b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:56Z",
      "native_id": "10.1371/journal.pone.0356893",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0356893"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:ecology",
      "subfield": "ecology"
    },
    {
      "field": "mathematics",
      "origin": "plos:statistical methods",
      "subfield": "statistics"
    },
    {
      "field": "medicine",
      "origin": "plos:nutrition",
      "subfield": "nutrition"
    }
  ],
  "title": "Forecasting alcohol lapse risk up to two weeks in advance using time-lagged machine learning models",
  "title_text": "Forecasting alcohol lapse risk up to two weeks in advance using time-lagged machine learning models",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:56Z",
  "url": "https://research.draconitic.com/paper/2kgcppc441b5b",
  "venue": "PLOS One",
  "versions": []
}