💖💖作者：计算机毕业设计江挽 💙💙个人简介：曾长期从事计算机专业培训教学，本人也热爱上课教学，语言擅长Java、微信小程序、Python、Golang、安卓Android等，开发项目包括大数据、深度学习、网站、小程序、安卓、算法。平常会做一些项目定制化开发、代码讲解、答辩教学、文档编写、也懂一些降重方面的技巧。平常喜欢分享一些自己开发中遇到的问题的解决办法，也喜欢交流技术，大家有技术代码这一块的问题可以问我！ 💛💛想说的话：感谢大家的关注与支持！ 💜💜 网站实战项目 安卓/小程序实战项目 大数据实战项目 深度学习实战项目
基于大数据的健康风险预测数据可视化分析系统介绍
基于大数据的健康风险预测数据可视化分析系统是一个集数据采集、分布式存储、智能分析与可视化展示于一体的综合性平台。系统采用Hadoop作为分布式存储基础，利用HDFS实现海量健康数据的可靠存储，通过Spark引擎进行高效的数据处理与分析计算。后端基于Spring Boot框架构建RESTful接口服务，整合Spark SQL实现复杂的健康数据查询与统计分析，结合Pandas和NumPy进行数据清洗、特征工程与风险评估建模。前端采用Vue框架搭配ElementUI组件库构建交互界面,运用Echarts图表库实现生命体征趋势图、风险画像雷达图、患者聚类散点图等多维度数据可视化展示。系统核心功能包括健康风险预测数据的录入与管理、基于生命体征指标的多维分析、用户风险画像的智能绘制、医疗资源使用情况的统计分析以及基于K-Means算法的患者聚类分组。通过大数据技术的应用,系统能够处理百万级健康记录,实现秒级响应的查询与分析,为健康管理决策提供数据支撑。
基于大数据的健康风险预测数据可视化分析系统演示视频
基于大数据的健康风险预测数据可视化分析系统演示图片
基于大数据的健康风险预测数据可视化分析系统代码展示
import org.apache.spark.sql.*;
import org.apache.spark.sql.types.*;
import org.springframework.stereotype.Service;
import javax.annotation.Resource;
import java.util.*;
@Service
public class HealthRiskAnalysisService {
private SparkSession spark = SparkSession.builder().appName("HealthRiskPrediction").master("local[*]").config("spark.sql.warehouse.dir", "/user/hive/warehouse").getOrCreate();
@Resource
private HealthDataMapper healthDataMapper;
public Map<String, Object> analyzeVitalSigns(Long userId) {
List<HealthData> dataList = healthDataMapper.selectByUserId(userId);
Dataset<Row> dataset = spark.createDataFrame(dataList, HealthData.class);
dataset.createOrReplaceTempView("vital_signs");
Dataset<Row> avgMetrics = spark.sql("SELECT AVG(heartRate) as avgHeart, AVG(bloodPressureHigh) as avgBpHigh, AVG(bloodPressureLow) as avgBpLow, AVG(bloodSugar) as avgSugar, AVG(temperature) as avgTemp FROM vital_signs");
Row metricsRow = avgMetrics.first();
double avgHeart = metricsRow.getDouble(0);
double avgBpHigh = metricsRow.getDouble(1);
double avgBpLow = metricsRow.getDouble(2);
double avgSugar = metricsRow.getDouble(3);
double avgTemp = metricsRow.getDouble(4);
Dataset<Row> trendData = spark.sql("SELECT DATE(checkTime) as date, AVG(heartRate) as dailyHeart, AVG(bloodPressureHigh) as dailyBp, AVG(bloodSugar) as dailySugar FROM vital_signs GROUP BY DATE(checkTime) ORDER BY date DESC LIMIT 30");
List<Row> trendList = trendData.collectAsList();
List<Map<String, Object>> trends = new ArrayList<>();
for (Row row : trendList) {
Map<String, Object> item = new HashMap<>();
item.put("date", row.getString(0));
item.put("heartRate", row.getDouble(1));
item.put("bloodPressure", row.getDouble(2));
item.put("bloodSugar", row.getDouble(3));
trends.add(item);
}
Dataset<Row> abnormalCount = spark.sql("SELECT COUNT(*) as total, SUM(CASE WHEN heartRate > 100 OR heartRate < 60 THEN 1 ELSE 0 END) as abnormalHeart, SUM(CASE WHEN bloodPressureHigh > 140 OR bloodPressureLow > 90 THEN 1 ELSE 0 END) as abnormalBp, SUM(CASE WHEN bloodSugar > 6.1 THEN 1 ELSE 0 END) as abnormalSugar FROM vital_signs");
Row abnormalRow = abnormalCount.first();
long totalRecords = abnormalRow.getLong(0);
long abnormalHeart = abnormalRow.getLong(1);
long abnormalBp = abnormalRow.getLong(2);
long abnormalSugar = abnormalRow.getLong(3);
Map<String, Object> result = new HashMap<>();
result.put("avgMetrics", Map.of("heartRate", avgHeart, "bloodPressureHigh", avgBpHigh, "bloodPressureLow", avgBpLow, "bloodSugar", avgSugar, "temperature", avgTemp));
result.put("trends", trends);
result.put("abnormalStats", Map.of("total", totalRecords, "abnormalHeartRate", abnormalHeart, "abnormalBloodPressure", abnormalBp, "abnormalBloodSugar", abnormalSugar));
return result;
}
public Map<String, Object> generateRiskProfile(Long userId) {
List<HealthData> dataList = healthDataMapper.selectByUserId(userId);
Dataset<Row> dataset = spark.createDataFrame(dataList, HealthData.class);
dataset.createOrReplaceTempView("health_records");
Dataset<Row> riskMetrics = spark.sql("SELECT AVG(heartRate) as avgHeart, AVG(bloodPressureHigh) as avgBpHigh, AVG(bloodPressureLow) as avgBpLow, AVG(bloodSugar) as avgSugar, AVG(bmi) as avgBmi, AVG(cholesterol) as avgChol FROM health_records");
Row metricsRow = riskMetrics.first();
double heartRate = metricsRow.getDouble(0);
double bpHigh = metricsRow.getDouble(1);
double bpLow = metricsRow.getDouble(2);
double bloodSugar = metricsRow.getDouble(3);
double bmi = metricsRow.getDouble(4);
double cholesterol = metricsRow.getDouble(5);
double heartRisk = calculateHeartRisk(heartRate);
double bpRisk = calculateBpRisk(bpHigh, bpLow);
double sugarRisk = calculateSugarRisk(bloodSugar);
double bmiRisk = calculateBmiRisk(bmi);
double cholRisk = calculateCholesterolRisk(cholesterol);
double overallRisk = (heartRisk + bpRisk + sugarRisk + bmiRisk + cholRisk) / 5.0;
String riskLevel = overallRisk >= 0.7 ? "高风险" : overallRisk >= 0.4 ? "中风险" : "低风险";
Dataset<Row> historicalRisk = spark.sql("SELECT DATE(checkTime) as date, AVG(heartRate) as hr, AVG(bloodPressureHigh) as bp, AVG(bloodSugar) as bs FROM health_records GROUP BY DATE(checkTime) ORDER BY date DESC LIMIT 90");
List<Row> historyList = historicalRisk.collectAsList();
List<Map<String, Object>> riskHistory = new ArrayList<>();
for (Row row : historyList) {
double dailyHr = row.getDouble(1);
double dailyBp = row.getDouble(2);
double dailyBs = row.getDouble(3);
double dailyRisk = (calculateHeartRisk(dailyHr) + calculateBpRisk(dailyBp, 0) + calculateSugarRisk(dailyBs)) / 3.0;
Map<String, Object> item = new HashMap<>();
item.put("date", row.getString(0));
item.put("riskScore", dailyRisk);
riskHistory.add(item);
}
Map<String, Object> result = new HashMap<>();
result.put("riskProfile", Map.of("heartRisk", heartRisk, "bloodPressureRisk", bpRisk, "bloodSugarRisk", sugarRisk, "bmiRisk", bmiRisk, "cholesterolRisk", cholRisk));
result.put("overallRisk", overallRisk);
result.put("riskLevel", riskLevel);
result.put("riskHistory", riskHistory);
return result;
}
public Map<String, Object> performPatientClustering() {
List<HealthData> allData = healthDataMapper.selectAllLatest();
Dataset<Row> dataset = spark.createDataFrame(allData, HealthData.class);
dataset.createOrReplaceTempView("all_patients");
Dataset<Row> patientFeatures = spark.sql("SELECT userId, AVG(heartRate) as avgHeart, AVG(bloodPressureHigh) as avgBp, AVG(bloodSugar) as avgSugar, AVG(bmi) as avgBmi, AVG(age) as age FROM all_patients GROUP BY userId");
List<Row> featureList = patientFeatures.collectAsList();
Map<Long, double[]> patientVectors = new HashMap<>();
for (Row row : featureList) {
Long userId = row.getLong(0);
double[] features = new double[]{row.getDouble(1), row.getDouble(2), row.getDouble(3), row.getDouble(4), row.getDouble(5)};
double[] normalized = normalizeFeatures(features);
patientVectors.put(userId, normalized);
}
int k = 3;
Map<Long, Integer> clusterAssignments = kMeansClustering(patientVectors, k);
Map<Integer, List<Long>> clusters = new HashMap<>();
for (Map.Entry<Long, Integer> entry : clusterAssignments.entrySet()) {
clusters.computeIfAbsent(entry.getValue(), key -> new ArrayList<>()).add(entry.getKey());
}
Map<Integer, Map<String, Double>> clusterCenters = new HashMap<>();
for (Map.Entry<Integer, List<Long>> entry : clusters.entrySet()) {
int clusterId = entry.getKey();
List<Long> userIds = entry.getValue();
double sumHeart = 0, sumBp = 0, sumSugar = 0, sumBmi = 0, sumAge = 0;
for (Long userId : userIds) {
double[] features = patientVectors.get(userId);
sumHeart += features[0];
sumBp += features[1];
sumSugar += features[2];
sumBmi += features[3];
sumAge += features[4];
}
int count = userIds.size();
Map<String, Double> center = new HashMap<>();
center.put("heartRate", sumHeart / count);
center.put("bloodPressure", sumBp / count);
center.put("bloodSugar", sumSugar / count);
center.put("bmi", sumBmi / count);
center.put("age", sumAge / count);
clusterCenters.put(clusterId, center);
}
Map<String, Object> result = new HashMap<>();
result.put("clusterCount", k);
result.put("clusterAssignments", clusterAssignments);
result.put("clusterSizes", clusters.entrySet().stream().collect(HashMap::new, (map, e) -> map.put(e.getKey(), e.getValue().size()), HashMap::putAll));
result.put("clusterCenters", clusterCenters);
return result;
}
private double calculateHeartRisk(double heartRate) {
if (heartRate < 60 || heartRate > 100) return 0.8;
if (heartRate < 65 || heartRate > 95) return 0.5;
return 0.2;
}
private double calculateBpRisk(double high, double low) {
if (high > 140 || low > 90) return 0.9;
if (high > 130 || low > 85) return 0.6;
if (high < 90) return 0.4;
return 0.2;
}
private double calculateSugarRisk(double bloodSugar) {
if (bloodSugar > 7.0) return 0.9;
if (bloodSugar > 6.1) return 0.6;
if (bloodSugar < 3.9) return 0.5;
return 0.1;
}
private double calculateBmiRisk(double bmi) {
if (bmi > 28) return 0.8;
if (bmi > 24) return 0.5;
if (bmi < 18.5) return 0.4;
return 0.1;
}
private double calculateCholesterolRisk(double cholesterol) {
if (cholesterol > 6.2) return 0.9;
if (cholesterol > 5.7) return 0.6;
return 0.2;
}
private double[] normalizeFeatures(double[] features) {
double[] normalized = new double[features.length];
normalized[0] = features[0] / 120.0;
normalized[1] = features[1] / 160.0;
normalized[2] = features[2] / 10.0;
normalized[3] = features[3] / 35.0;
normalized[4] = features[4] / 100.0;
return normalized;
}
private Map<Long, Integer> kMeansClustering(Map<Long, double[]> vectors, int k) {
List<Long> userIds = new ArrayList<>(vectors.keySet());
List<double[]> centroids = new ArrayList<>();
Random random = new Random(42);
for (int i = 0; i < k; i++) {
centroids.add(vectors.get(userIds.get(random.nextInt(userIds.size()))).clone());
}
Map<Long, Integer> assignments = new HashMap<>();
for (int iter = 0; iter < 100; iter++) {
for (Long userId : userIds) {
double[] vector = vectors.get(userId);
int closestCluster = 0;
double minDistance = Double.MAX_VALUE;
for (int i = 0; i < k; i++) {
double distance = euclideanDistance(vector, centroids.get(i));
if (distance < minDistance) {
minDistance = distance;
closestCluster = i;
}
}
assignments.put(userId, closestCluster);
}
List<double[]> newCentroids = new ArrayList<>();
for (int i = 0; i < k; i++) {
List<double[]> clusterVectors = new ArrayList<>();
for (Map.Entry<Long, Integer> entry : assignments.entrySet()) {
if (entry.getValue() == i) {
clusterVectors.add(vectors.get(entry.getKey()));
}
}
if (clusterVectors.isEmpty()) {
newCentroids.add(centroids.get(i));
} else {
double[] newCentroid = new double[clusterVectors.get(0).length];
for (double[] vec : clusterVectors) {
for (int j = 0; j < vec.length; j++) {
newCentroid[j] += vec[j];
}
}
for (int j = 0; j < newCentroid.length; j++) {
newCentroid[j] /= clusterVectors.size();
}
newCentroids.add(newCentroid);
}
}
centroids = newCentroids;
}
return assignments;
}
private double euclideanDistance(double[] a, double[] b) {
double sum = 0;
for (int i = 0; i < a.length; i++) {
sum += Math.pow(a[i] - b[i], 2);
}
return Math.sqrt(sum);
}
}
基于大数据的健康风险预测数据可视化分析系统文档展示
💖💖作者：计算机毕业设计江挽 💙💙个人简介：曾长期从事计算机专业培训教学，本人也热爱上课教学，语言擅长Java、微信小程序、Python、Golang、安卓Android等，开发项目包括大数据、深度学习、网站、小程序、安卓、算法。平常会做一些项目定制化开发、代码讲解、答辩教学、文档编写、也懂一些降重方面的技巧。平常喜欢分享一些自己开发中遇到的问题的解决办法，也喜欢交流技术，大家有技术代码这一块的问题可以问我！ 💛💛想说的话：感谢大家的关注与支持！ 💜💜 网站实战项目 安卓/小程序实战项目 大数据实战项目 深度学习实战项目
