卵巢癌切除术复发预测标准数据集

本数据集专为原发性卵巢癌术后复发风险的智能预测任务构建，旨在通过整合多维度临床数据，建立科学、可靠的复发风险评估模型，辅助临床决策。数据采用结构化表格形式存储，便于高效管理与分析。
输入端（Features）： 结合人口信息、住院信息、诊断信息、病理信息、检验信息、随访信息等。输出端（Labels）： 严格基于患者长期随访结果判定的复发状态标签，涵盖复发的时间节点与结局。
数据源采用全量“临床真实数据”架构。所有数据均源自权威省级妇科恶性肿瘤精准治疗临床医学研究中心的脱敏病例库，未引入任何合成数据，以确保真实世界数据的异质性与临床代表性。全量数据经所有病例均经过病理专家复核，复发诊断基于影像学证据或病理活检结果，保证标签准确性。本数据集可为机器学习模型提供高质量训练样本，支持复发风险评分系统开发、预后因素分析等研究，有助于推动卵巢癌个体化治疗策略的优化，改善患者长期生存结局。

This dataset is constructed specifically for the intelligent prediction task of postoperative recurrence risk of primary ovarian cancer, aiming to integrate multi-dimensional clinical data to establish a scientific and reliable recurrence risk assessment model and assist clinical decision-making. The data is stored in structured tabular format, facilitating efficient management and analysis.

Input (Features): Covers demographic information, hospitalization information, diagnostic information, pathological information, laboratory test information, follow-up information, etc.
Output (Labels): The recurrence status labels, strictly determined based on the long-term follow-up results of patients, cover the time point and outcome of recurrence.

The data source adopts a full-scale "real-world clinical data" architecture. All data are derived from the anonymized case database of the authoritative provincial clinical research center for precise treatment of gynecological malignancies, and no synthetic data is introduced, so as to ensure the heterogeneity and clinical representativeness of real-world data. All cases in the full dataset have been reviewed by pathological experts, and the recurrence diagnosis is based on imaging evidence or pathological biopsy results, ensuring the accuracy of the labels. This dataset can provide high-quality training samples for machine learning models, support researches such as the development of recurrence risk scoring systems and prognostic factor analysis, and help promote the optimization of individualized treatment strategies for ovarian cancer and improve the long-term survival outcomes of patients.

搜集汇总

背景与挑战

背景概述

该数据集专为原发性卵巢癌术后复发风险的智能预测而构建，整合了多维度临床真实数据，包括人口、住院、诊断、病理、检验和随访信息，并基于长期随访结果提供精准的复发状态标签。数据源自权威医疗机构的脱敏病例库，经过专家复核，可用于机器学习模型训练和复发风险评估研究。