肝癌切除术复发预测标准数据集

本数据集专为原发性肝癌术后复发预测任务构建，旨在解决传统复发预测依赖人工经验、评估精度有限、难以提前预警的问题，适配术后复发预测模型的训练需求。
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。
数据源仅采用临床真实数据，源自权威省级三甲专科医院——福建省肿瘤医院的脱敏病例库，涵盖不同手术方式、不同分期的术后病例，确保数据的临床真实性与代表性。数据集经过临床专家严格校验、剔除无效数据，是训练原发性肝癌术后复发预测模型、实现复发风险精准评估的高质量核心语料。

This dataset is specifically constructed for the task of postoperative recurrence prediction of primary liver cancer, aiming to solve the problems of traditional recurrence prediction methods relying on manual experience, limited evaluation accuracy, and difficulty in early warning, while meeting the training requirements of postoperative recurrence prediction models.
Input (Features): Integrates demographic information, hospitalization information, diagnostic information, pathological information, laboratory test information, follow-up information, and other relevant clinical data.
Output (Labels): Recurrence status labels strictly determined based on patients' long-term follow-up results, covering the specific time points and outcomes of recurrence.
The dataset only adopts real clinical data, sourced from the anonymized case database of Fujian Provincial Cancer Hospital, an authoritative provincial-level tertiary specialized hospital. It covers postoperative cases with various surgical approaches and tumor stages, ensuring the clinical authenticity and representativeness of the data.
After strict verification by clinical experts and exclusion of invalid data, this dataset serves as a high-quality core resource for training postoperative recurrence prediction models of primary liver cancer and realizing accurate assessment of recurrence risk.

搜集汇总

背景与挑战

背景概述

该数据集是专为原发性肝癌术后复发预测模型训练而构建的高质量标准数据集。它基于福建省肿瘤医院的脱敏临床真实病例，整合了人口、住院、诊断、病理、检验及随访等多维度特征，并包含基于长期随访判定的复发状态标签。数据集经过临床专家严格校验，旨在解决传统复发预测方法精度有限、预警不足的问题，为精准评估术后复发风险提供核心数据支持。