气象风险预报数据集

专病诊断名称分类模型：通过分析医学文献、临床数据和专家知识，建立一个诊断数据库。经过分词和打乱顺序的预处理后，使用 train_supervised 函数进行训练（迭代200次，学习率0.1，词N-grams长度为1，损失函数为"hs"）。模型性能通过 classification_report 方法评估，表现良好。参数更新通过命令同步模型、标签和标签名，从而快速、准确地诊断专病类型
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。

Specialized Disease Diagnosis Name Classification Model: A diagnostic database was established by analyzing medical literature, clinical data, and expert knowledge. After preprocessing including word segmentation and data shuffling, the model was trained using the `train_supervised` function with 200 training iterations, a learning rate of 0.1, word N-grams of length 1, and the loss function set to "hs". The model's performance was evaluated using the `classification_report` method, achieving excellent results. Parameter updates are synchronized across the model, labels, and label names via specified commands, enabling fast and accurate specialized disease diagnosis.

Specialized Disease Treatment Plan Classification Model: This model identifies and classifies treatment plans related to specific specialized diseases by analyzing large volumes of clinical data and medical literature. The dataset contains 13 categories, and the class imbalance issue was addressed through data cropping and oversampling with replication. The dataset was split into training and test sets at an 8:2 ratio. Raw data was preprocessed using GloVe. The model was trained using a CNN architecture consisting of convolutional layers, pooling layers, and fully connected layers. After model tuning, the optimal parameter combination was selected based on accuracy and recall metrics. Parameter updates are completed via specified commands to ensure synchronization between the model, labels, and label names.

搜集汇总

数据集介绍

特点

气象风险预报数据集包含医疗领域的诊断名称、性别、年龄分布等字段，规模为300000条，每月更新，用于建立疾病气象风险预报模型。