慢性阻塞性肺病分布人群分析数据

基于温州市医疗公共数据，获取患者的诊断、年龄、性别、检验报告、既往用药史等数据。依据慢性阻塞性肺病临床研究项目的入选和排除标准，构建慢性阻塞性肺病患者群体的用户画像，对所属医院、科室、诊断、年龄、首次就诊时间和复查时间的数据进行分组和对比分析，以更好地了解精准病症患者群体在时间和空间上的分布，帮助企业寻找合作临床研究机构，加快临床项目患者的入组进程。数据处理
1.年龄
公式：年龄标签值=(x-min)/(max-min)，其中x为患者当前年龄，min和max为临床试验要求的最小和最大年龄，如40岁和85岁，因此标签值会位于0到1之间，与计算z-score（标准分数）的思路类似。
2.诊断
诊断标签值赋值：详见其他情况说明。
3.首次就诊时间和最近复查时间
公式：首次就诊时间标签值=1-(当前日期-首次就诊时间)/最大时间窗口。分子和分母都以天数为单位进行计算，类似于时间序列分析中对最近数据点的加权处理。
4.检验报告
检验报告标签值赋值：赋值查看其他说明。
5.既往用药
检验报告标签值赋值：赋值详情查看其他说明。基于患者对历史用药的反应情况，判断适应性与安全性。
算法加工
基于各项标签值的相关性分配权重，初筛得分加权计算公式为：初筛得分=年龄标签值×0.15+诊断标签值×0.35+首次就诊时间标签值×0.10+检验报告标签值×0.25+既往用药标签值×0.15。

Based on the public medical data of Wenzhou City, data including patients' diagnoses, ages, genders, laboratory test reports, and past medication histories are collected. According to the inclusion and exclusion criteria of chronic obstructive pulmonary disease (COPD) clinical research projects, user profiles of COPD patient groups are constructed, and grouping and comparative analysis are performed on data such as affiliated hospitals, departments, diagnoses, ages, first visit time, and follow-up review time, so as to better understand the temporal and spatial distribution of COPD patient groups, and help enterprises identify cooperating clinical research institutions to accelerate patient enrollment for clinical trials.

### Data Processing
1. Age
Formula: Age label value = (x - min)/(max - min), where x is the patient's current age, min and max are the minimum and maximum age required by the clinical trial (e.g., 40 years old and 85 years old). Thus, the label value ranges from 0 to 1, which is consistent with the logic of calculating z-score (standard score).

2. Diagnosis
The assignment of diagnosis label values is detailed in other scenario descriptions.

3. First Visit Time and Latest Follow-up Review Time
Formula: First visit time label value = 1 - (current date - first visit time)/maximum time window. Both the numerator and denominator are calculated in days, which is similar to the weighting treatment of recent data points in time series analysis.

4. Laboratory Test Report
The assignment of laboratory test report label values is detailed in other instructions.

5. Past Medication
The assignment of past medication label values is detailed in other instructions. The adaptability and safety are evaluated based on the patient's response to historical medications.

### Algorithm Processing
Weights are assigned based on the correlation of each label value. The weighted calculation formula for the preliminary screening score is:
Preliminary Screening Score = Age Label Value × 0.15 + Diagnosis Label Value × 0.35 + First Visit Time Label Value × 0.10 + Laboratory Test Report Label Value × 0.25 + Past Medication Label Value × 0.15.

搜集汇总

数据集介绍

特点

该数据集包含529条温州市慢性阻塞性肺病患者的医疗数据，每日更新，用于分析患者群体的时间和空间分布，帮助企业寻找合作临床研究机构。数据涵盖患者的基本信息、诊断、用药记录等，并通过特定算法计算初筛得分以评估患者适应性。