{
  "slug": "eb-vae-for-joint-tumor-growth-and-dropout-modeling-713984",
  "title": "EB-VAE for Joint Tumor Growth and Dropout Modeling",
  "dek": "Abstract-only summary of an EB-VAE extension for joint tumor growth, dropout hazards, semi-mechanistic decoders, and genomic priors.",
  "summary": "EB-VAE for joint tumor growth and dropout modeling with hazard decoding, semi-mechanistic variants, and genomic prior conditioning.",
  "tags": [
    "eb-vae",
    "empirical-bayes",
    "variational-autoencoder",
    "pharmacometrics",
    "tumor-growth-modeling",
    "joint-modeling",
    "time-to-event-modeling",
    "informative-dropout",
    "hazard-model",
    "oncology",
    "genomic-covariates",
    "semi-mechanistic-modeling"
  ],
  "published_at": "2026-07-19T04:11:34.779+00:00",
  "grade": 8.8,
  "agent_utility": 8.7,
  "price_usdc": 0.304,
  "stats": {
    "claims": 17,
    "entities": 26,
    "faq": 9,
    "downloads": 0,
    "paid_downloads": 0
  },
  "preview": {
    "faq_questions": [
      "What is the main contribution described in the abstract?",
      "How does the model represent individual variability?",
      "How is dropout modeled?",
      "What is the difference between the neural and hybrid decoder results?",
      "What role do genomic covariates play?",
      "Which genetic indicators are mentioned?",
      "What numerical performance results are available from the abstract?",
      "Does the abstract establish clinical readiness?",
      "Can the bibliographic metadata be verified from the abstract?"
    ],
    "entity_names": [
      {
        "name": "Empirical Bayes variational autoencoder",
        "type": "framework"
      },
      {
        "name": "EB-VAE",
        "type": "model framework"
      },
      {
        "name": "Longitudinal tumor measurements",
        "type": "data source"
      },
      {
        "name": "Dropout information",
        "type": "data source"
      },
      {
        "name": "Genetic covariates",
        "type": "data source"
      },
      {
        "name": "Treatment response",
        "type": "outcome concept"
      },
      {
        "name": "Population modeling framework",
        "type": "modeling context"
      },
      {
        "name": "Latent individual effects",
        "type": "latent variable"
      },
      {
        "name": "Covariate-conditioned empirical Bayes prior",
        "type": "prior model"
      },
      {
        "name": "Decoder",
        "type": "model component"
      },
      {
        "name": "Tumor-volume trajectories",
        "type": "model output"
      },
      {
        "name": "Hazard model",
        "type": "time-to-event component"
      },
      {
        "name": "Time to dropout",
        "type": "model output"
      },
      {
        "name": "Fully neural decoder",
        "type": "model variant"
      },
      {
        "name": "Hybrid semi-mechanistic decoder",
        "type": "model variant"
      },
      {
        "name": "Treatment-effect parameters",
        "type": "model parameter"
      },
      {
        "name": "Nonlinear mixed-effects estimates",
        "type": "reference estimates"
      },
      {
        "name": "Genetics-conditioned prior adaptation",
        "type": "model component"
      },
      {
        "name": "Cutaneous melanoma experiments",
        "type": "evaluation setting"
      },
      {
        "name": "Breast cancer experiments",
        "type": "evaluation setting"
      },
      {
        "name": "Stability selection",
        "type": "feature-selection method"
      },
      {
        "name": "BRAF alterations",
        "type": "genetic indicator"
      },
      {
        "name": "NRAS alterations",
        "type": "genetic indicator"
      },
      {
        "name": "NF1 alterations",
        "type": "genetic indicator"
      },
      {
        "name": "MDM2 alterations",
        "type": "genetic indicator"
      },
      {
        "name": "Pharmacometric applications",
        "type": "domain"
      }
    ],
    "related_work_titles": [
      "Variational autoencoder methods",
      "Joint longitudinal and time-to-event modeling",
      "Nonlinear mixed-effects pharmacometric modeling",
      "Semi-mechanistic tumor-growth modeling",
      "Genomic covariate selection in oncology models"
    ],
    "application_industries": [
      "pharma R&D",
      "clinical trial analytics",
      "precision oncology research",
      "pharmacometrics software",
      "regulatory science research"
    ],
    "glossary_terms": [
      "Empirical Bayes variational autoencoder",
      "EB-VAE",
      "Empirical Bayes",
      "Variational autoencoder",
      "Latent individual effects",
      "Covariate-conditioned empirical Bayes prior",
      "Covariates",
      "Longitudinal data",
      "Time-to-event data",
      "Joint longitudinal and time-to-event model",
      "Hazard model",
      "Dropout",
      "Informative dropout",
      "Decoder",
      "Fully neural decoder",
      "Hybrid semi-mechanistic decoder",
      "Semi-mechanistic model",
      "Tumor-volume trajectory",
      "Tumor growth model",
      "Nonlinear mixed-effects model",
      "Treatment-effect parameters",
      "Prior predictive performance",
      "Genetics-conditioned prior adaptation",
      "Genomic covariates",
      "Stability selection",
      "Genetic indicator",
      "Pharmacometrics",
      "Cutaneous melanoma",
      "Breast cancer",
      "BRAF, NRAS, NF1, and MDM2"
    ]
  },
  "purchase": {
    "protocol": "x402",
    "version": 2,
    "network": "eip155:8453",
    "asset": "USDC",
    "price": 0.304,
    "full_markdown_url": "https://x402.disruptive-concepts.com/api/public/article/eb-vae-for-joint-tumor-growth-and-dropout-modeling-713984/full",
    "full_json_url": "https://x402.disruptive-concepts.com/api/public/article/eb-vae-for-joint-tumor-growth-and-dropout-modeling-713984/full?format=json"
  }
}