Abstract A018: Identifying and integrating global ovarian cancer patient priorities to guide artificial intelligence (AI) research in ovarian cancer
Notice bibliographique
Résumé
Abstract Background: Ovarian Cancer Research Alliance (OCRA; USA), Ovarian Cancer Action (OCA; UK), Ovarian Cancer Canada (OCC; Canada) and the Ovarian Cancer Research Foundation (OCRF; Australia) have launched the Global Ovarian Cancer Research Consortium. The Consortium unites four leading ovarian cancer research funding organizations to combine resources, expertise and determination to accelerate progress where it’s desperately needed. The Consortium’s inaugural joint initiative is a $1M (USD) international research grant program to harness the power of Artificial Intelligence (AI) to improve ovarian cancer outcomes. To ensure this program aligns with patient needs, the Consortium sought to understand research priorities from individuals with lived experience of ovarian cancer, the results of which will help inform this funding call. Objectives: To understand priorities from people with lived experience of ovarian cancer, in the context of applying AI to improve outcomes, and to support direction of the AI Accelerator Grant funding round. Methods: Each organization conducted a survey to collect qualitative data from their respective patient and public involvement (PPI) networks. In total, there were 657 respondents: 62% diagnosed with ovarian cancer, 19% caregivers, and 19% others affected. Responses were pooled and thematically analyzed to identify shared priorities. Results: Consistent research priorities emerged across all geographies: Early detection: reliable early detection tools or screening tests, biomarker research, symptom awareness to support earlier clinical intervention. Better treatments: more effective and less toxic options, targeted therapies, immunotherapy, alternatives to chemotherapy, personalized medicine. Disease recurrence: recurrence drivers, methods to detect, delay or prevent recurrence, supportive care for those living with recurrent or incurable disease. Risk & prevention: improved risk prediction for those with a family history or known genetic mutation, expanding preventative strategies. Respondents in the UK were additionally asked about the use of AI in ovarian cancer research. Between 75-80% expressed positive or broadly supportive views. Perceived benefits included the ability to analyze large, complex patient datasets, identify recurrence risk or treatment responses faster, and pattern recognition that may not be identifiable to the human eye. The most common concern expressed was that AI should not replace compassionate care or clinical judgment. Conclusions: People affected by ovarian cancer are broadly supportive of the use of AI in ovarian cancer research to accelerate progress in a cancer type with limited treatment options and poor survival rates. While broadly optimistic, patients emphasized that AI must complement, not replace, human oversight in clinical settings. Embedding lived experience into research funding strategies, including emerging fields like AI, ensures that innovation is patient-informed, ethically grounded, and directed toward the areas of greatest need. Citation Format: Sarah DeFeo, Faye Hobbs, David Hunt, Jessica Lawson, Kristin McGowan, Marie-Claire Platt, Alicia Tone, Amy Wilson. Identifying and integrating global ovarian cancer patient priorities to guide artificial intelligence (AI) research in ovarian cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Ovarian Cancer Research; 2025 Sep 19-21; Denver, CO. Philadelphia (PA): AACR; Cancer Res 2025;85(18_Suppl):Abstract nr A018.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,052 | 0,067 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,003 | 0,003 |
| Études des sciences et des technologies | 0,007 | 0,004 |
| Communication savante | 0,009 | 0,008 |
| Science ouverte | 0,002 | 0,014 |
| Intégrité de la recherche | 0,002 | 0,005 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,007 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».