湖北省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湖北省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 subjected to sample data processing and refinement to support the training of auxiliary diagnostic artificial intelligence (AI) models. The goal is to enable the AI models to better perform prognostic analysis in clinical sample scenarios from Hubei Province, extract features, identify underlying patterns, and ultimately enhance the accuracy, robustness, and generalization capability of the diagnostic AI models. 1. Data Collection: Anonymized clinical sample data is acquired from medical institutions through formal cooperative agreements. The collected data includes postoperative pathological results, postoperative estrogen receptor (ER) status, postoperative progesterone receptor (PR) status, postoperative FISH results, as well as in-system postoperative HER2 negative/positive markers. 2. Data Processing: Data verification and validation are conducted to ensure all data is fully de-identified and anonymized to a non-reversible state. Data without pathological results is removed, abnormal data is cleaned and excluded, and generative imputation is performed for partially missing values. 3. Data Annotation & Processing: Prognostic analysis results are generated in accordance with standardized rule-based processing criteria. The specific rules are as follows: If ER is positive (i.e., ER > 0), PR > 20, and HER2 is negative, the prognostic status is classified as "Best Prognosis"; otherwise, it is categorized as "Other" and requires further data analysis.

搜集汇总

数据集介绍

特点

该数据集包含150条湖北省患者的术后病理和预后情况数据，用于辅助诊断AI模型的训练，通过特定规则分析预后情况，旨在提高模型的准确性和泛化能力。