Clinical Report: AI-Assisted Pedigree Mapping for Hereditary Gynecologic Tumors

Overview

The study describes the development and pilot validation of an AI-assisted pedigree mapping system based on a gynecologic oncology specialty large language model. Designed with input from clinicians, genetic counselors, nurses, and patient representatives, the system uses preconsultation dialogue to extract personal and family history and generate standardized visual pedigrees. The supplied material does not report pilot performance results or numerical validation outcomes.

Background

Hereditary gynecologic tumors are reported to account for 15% to 20% of gynecologic malignancies, and genetic counseling supports risk assessment, screening, and personalized treatment decisions. Pedigree mapping is an initial component of counseling, but manual history collection and chart construction can be difficult in multigenerational families or those with complex relationships. The article identifies omissions, inaccuracies, and consultation time as practical challenges that may limit access and standardization. It also notes that general-purpose language models can produce inaccurate or unsupported medical content, motivating development of a specialty-specific system.

Data Highlights

Key Findings

• The study aimed to develop and pilot-validate an AI-assisted pedigree mapping system for hereditary gynecologic tumors.
• The system was grounded in a gynecologic oncology specialty large language model, in response to concerns about clinical hallucinations from general-purpose models.
• Participatory design included senior gynecologic oncologists, genetic counselors, clinical research nurses, and patient representatives.
• The system was designed to collect personal and family history through preconsultation multiturn dialogue and convert it into structured information.
• Its stated output includes real-time standardized visual pedigree charts.
• The supplied excerpt describes the rationale and design but does not provide accuracy, usability, or other pilot validation results.

Clinical Implications

The system is presented as an auxiliary tool for pedigree collection and visualization within genetic counseling workflows, not as a replacement for clinical assessment. The supplied material does not establish its diagnostic accuracy, effect on counseling efficiency, or impact on patient outcomes.

Conclusion

This pilot study describes a participatory, specialty-specific AI system intended to support pedigree mapping for hereditary gynecologic tumors. Further conclusions about performance or clinical impact cannot be drawn from the information provided.

Related Resources & Content

1. JMIR Medical Informatics, 2026 — Construction of an AI-Assisted Pedigree Mapping System for Hereditary Gynecological Tumors: Algorithm Development and Pilot Validation Study
2. NCCN, 2026 — NCCN Guidelines® Insights: Genetic/Familial High-Risk Assessment: Breast, Ovarian, Pancreatic, and Prostate, Version 2.2026
3. ASCO Publications — Development and validation of an AI model for predicting germline BRCA1/2 mutations from HR+/HER2- breast cancer histology images.
4. ASCO Publications — Identifying gaps in hereditary germline testing for breast cancer patients through AI-driven clinical decision support.
5. ASCO Publications — Identifying gaps in hereditary germline testing for breast cancer patients through AI-driven clinical decision support.
6. ASCO Publications — Identifying gaps in hereditary germline testing for breast cancer patients through AI-driven clinical decision support.
7. Construction of an AI-Assisted Pedigree Mapping System for Hereditary Gynecological Tumors: Algorithm Development and Pilot Validation Study
8. NCCN Guidelines® Insights: Genetic/Familial High-Risk Assessment: Breast, Ovarian, Pancreatic, and Prostate, Version 2.2026
9. NCCN Guidelines® Insights: Genetic/Familial High-Risk Assessment: Breast, Ovarian, Pancreatic, and Prostate, Version 2.2026.
10. 54P Shared hereditary pathways in colorectal and endometrial cancers: A Lynch syndrome-focused systematic review and meta-analysis - Annals of Oncology
11. JMIR Medical Informatics - Construction of an AI-Assisted Pedigree Mapping System for Hereditary Gynecological Tumors: Algorithm Development and Pilot Validation Study