重庆市预后情况分析辅助诊断模型训练数据

通过对样本的数据处理和数据加工，提供给辅助诊断人工智能模型进行训练，帮助人工智能模型更好地理解重庆市样本场景下的预后情况分析，提取特征，发现规律，最终提高诊断人工智能模型的准确性、鲁棒性和泛化能力。1数据采集：通过正式合作协议，从医疗机构取得匿名化的样本临床数据，包括是否有术后病理结果、术后ER(雌性激素受体)、术后PR(孕激素受体)、术后Fish，同时还要获取系统内术后Her2阴性阳性标记；2数据处理：对数据进行检查核对，确保所有数据去标志化，处于完全匿名化状态且不可还原的状态，将没有病理结果的数据去除，对异常数据进行清洗去除，对部分缺失数据进行生成式补充；3数据加工：基于数据加工规则判断规则，生成预后情况分析，具体规则为：如果ER为阳性（即ER＞0），同时满足PR>20，同时满足HER2为阴性，则预后情况判断为预后最好，反之为其他，需要更多数据分析。

This dataset is prepared through sample data processing and curation, and is provided for training auxiliary diagnostic artificial intelligence models. It aims to assist the AI models in better understanding prognostic analysis within the Chongqing clinical sample scenario, extracting features, identifying underlying patterns, and ultimately improving the accuracy, robustness, and generalization ability of the diagnostic AI models.
1. Data Collection: Anonymized clinical sample data was obtained from medical institutions through formal cooperative agreements, including the availability of postoperative pathological results, postoperative ER (Estrogen Receptor), postoperative PR (Progesterone Receptor), postoperative Fish assay results, as well as in-system markers for postoperative Her2 status (negative or positive).
2. Data Processing: The collected data was inspected and verified to ensure all records were fully de-identified, anonymized and irreversibly unlinkable. Data without postoperative pathological results was removed, abnormal data was cleaned and eliminated, and generative imputation was conducted for partially missing data.
3. Data Curation: Prognostic analysis results were generated based on standardized data processing and prognostic stratification rules. Specifically, if ER was positive (defined as ER > 0), PR > 20, and HER2 was negative, the case was classified as having the best prognosis; otherwise, it was categorized as other and required further data analysis.

搜集汇总

数据集介绍

特点

该数据集包含150条记录，主要用于训练辅助诊断人工智能模型，涉及重庆市样本的预后情况分析。数据包括受试者信息、术后病理结果、激素受体状态等，每年更新，旨在提高诊断模型的准确性和泛化能力。