PCSK9类降脂药物评价数据集

多维诊疗数据构建患者主索引：将患者数据特征向量定义为患者性别、住址、家族遗传病、过敏原等信息，使用DBSCAN算法，基于特征向量的密度，将密度相近的数据点划为同一个簇，将患者数据点进行聚类，每个聚类可以视为一个患者群体，作为主索引的标识。
专病治疗方案分类模型：该模型通过分析大量临床数据和医学文献，识别并分类与特定专病相关的治疗方案。数据集包括13个类别，样本不平衡问题通过裁剪和复制补充解决。训练集和测试集按8:2比例划分。使用 GloVe对原始数据进行预处理。模型训练使用CNN构建卷积层、池化层和全连接层。模型调优后，判断准确率、召回率选择最佳参数组合。参数更新通过指定命令完成，确保模型、标签和标签名同步。

Constructing Patient Master Index with Multi-dimensional Medical and Diagnostic Data: Define the feature vector of patient data as information such as patient gender, residential address, family history of genetic disorders, allergens, etc. Use the DBSCAN algorithm to cluster patient data points based on the density of their feature vectors, grouping data points with similar densities into the same cluster. Each cluster can be regarded as a patient cohort, serving as the identifier for the patient master index.

Specialized Disease Treatment Scheme Classification Model: This model identifies and classifies treatment schemes related to specific diseases by analyzing large volumes of clinical data and medical literature. The dataset consists of 13 categories, and the sample imbalance issue is addressed by clipping over-represented samples and supplementing under-represented ones via copying. The dataset is split into training and test sets at an 8:2 ratio. Raw data is preprocessed using GloVe. The model training uses CNN to construct convolutional layers, pooling layers and fully connected layers. After model tuning, the optimal parameter combination is selected based on accuracy and recall metrics. Parameter updates are completed via specified commands to ensure synchronization among the model, labels and label names.

搜集汇总

数据集介绍

特点

PCSK9类降脂药物评价数据集包含30万条医疗数据，每月更新，涵盖患者住院、诊断、用药等多维度信息，适用于医疗、教学和科研领域，支持诊疗模式研究和药物经济学分析。数据集采用DBSCAN算法和CNN模型进行数据处理和分析，旨在解决ASCVD疾病特征研究问题。