胃癌切除术复发预测标准数据集

本数据集专为原发性胃癌术后复发风险智能预测任务构建，旨在通过机器学习技术突破传统TNM分期在预后评估中的局限，解决其难以精准预判个体化复发模式及辅助化疗获益的关键问题。数据采用高维结构化特征格式，适配主流预测模型的通用训练框架，支持多维度特征融合与复杂模式识别。
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三甲胃肠肿瘤专科中心的脱敏病例库，未引入任何合成数据，以确保真实世界数据的复杂性与异质性。全量数据经由“病理专家复核+医生双盲校验”的严格质检，是训练高精度复发预测模型、辅助医生制定个体化术后辅助化疗与随访策略的高质量核心科研语料。

This dataset is specifically constructed for the intelligent prediction task of postoperative recurrence risk of primary gastric cancer. It aims to break through the limitations of traditional TNM staging in prognostic assessment via machine learning technologies, and address the critical issue that traditional staging fails to accurately predict individual recurrence patterns and the benefits of adjuvant chemotherapy.
The data adopts a high-dimensional structured feature format, which is compatible with the general training frameworks of mainstream prediction models, and supports multi-dimensional feature fusion and complex pattern recognition.
Input (Features): Combines demographic information, hospitalization information, diagnostic information, pathological information, laboratory test information, follow-up information, and other relevant data.
Output (Labels): Recurrence status labels strictly determined based on the long-term follow-up results of patients, covering recurrence time points and clinical outcomes.
The dataset adopts a full-scale real-world clinical data architecture. All data are sourced from de-identified case databases of authoritative provincial-level top-tier tertiary hospitals specializing in gastrointestinal oncology, and no synthetic data is introduced, ensuring the complexity and heterogeneity of real-world clinical data.
All data have undergone strict quality inspection via pathological expert review and double-blinded physician verification, making this dataset a high-quality core scientific research corpus for training high-precision recurrence prediction models and assisting clinicians in formulating individualized postoperative adjuvant chemotherapy and follow-up strategies.

搜集汇总

背景与挑战

背景概述

该数据集专为原发性胃癌术后复发风险智能预测任务设计，旨在通过机器学习技术提升预后评估的精准性。它包含来自福建省肿瘤医院的高维结构化临床真实数据，涵盖多维度特征和严格质控的复发标签，适用于训练预测模型以辅助个体化治疗决策。