💖💖作者：计算机毕业设计小明哥
💙💙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！
💜💜
💕💕文末获取源码
慢性肾病可视化系统-系统功能
基于大数据的慢性肾病数据可视化分析系统是一套融合现代大数据处理技术与医疗数据分析的综合性平台，系统采用Hadoop分布式存储架构结合Spark大数据处理引擎，实现对海量慢性肾病医疗数据的高效存储、处理与分析。系统后端基于Python语言开发，采用Django框架构建RESTful API接口，同时支持Java版本的Spring Boot框架实现，通过Spark SQL进行复杂的数据查询与统计分析，结合Pandas和NumPy进行科学计算处理，数据持久化采用MySQL数据库管理。前端采用Vue.js框架配合ElementUI组件库构建现代化用户界面，通过Echarts图表库实现丰富的数据可视化展示效果，辅以传统的HTML、CSS、JavaScript和jQuery技术确保系统的兼容性和交互体验。系统核心功能涵盖六大分析模块：慢性肾病患病情况统计分析模块通过多维度统计患病率分布、血压水平关联性和高血压合并症情况；肾功能指标深度分析模块深入评估血尿素、血清肌酐、尿比重、白蛋白等核心指标的分布特征与相关性；血液生化指标综合评估模块全面分析血红蛋白、白细胞、红细胞及电解质平衡状况；多指标联合诊断价值分析模块通过机器学习算法识别关键指标组合；疾病进展与严重程度评估模块建立分级诊断体系；临床特征模式识别分析模块挖掘疾病发展规律，为临床诊疗决策提供科学依据和数据支撑。
慢性肾病可视化系统-技术选型
大数据框架：Hadoop+Spark（本次没用Hive，支持定制）
开发语言：Python+Java（两个版本都支持）
后端框架：Django+Spring Boot(Spring+SpringMVC+Mybatis)（两个版本都支持）
前端：Vue+ElementUI+Echarts+HTML+CSS+JavaScript+jQuery
详细技术点：Hadoop、HDFS、Spark、Spark SQL、Pandas、NumPy
数据库：MySQL
慢性肾病可视化系统-背景意义
选题背景 慢性肾病已成为全球重要的公共卫生问题，据国际肾脏病学会统计，全球慢性肾病患病率约为8%-16%，我国慢性肾病患病率达到10.8%，患者总数超过1.3亿人，而知晓率仅为12.5%，这意味着大量患者未能得到及时诊断和治疗。随着人口老龄化加剧和糖尿病、高血压等慢性疾病发病率上升，慢性肾病的患病人数持续增长，预计到2030年将增至2亿人。传统的医疗数据分析方法面临着数据量庞大、处理速度缓慢、分析维度单一等挑战，难以满足现代医疗诊断的需求。医疗机构每天产生的检验数据、影像数据、病历数据呈指数级增长，仅一个三甲医院每年产生的医疗数据就达到数TB规模，而传统的数据库和分析工具已无法有效处理如此海量的信息。大数据技术在医疗领域的应用为解决这一难题提供了新的思路，通过分布式存储和并行计算，能够实现对海量医疗数据的快速处理和深度挖掘，为慢性肾病的早期筛查、精准诊断和个性化治疗提供强有力的技术支撑。 选题意义 本系统的构建具有重要的实际应用价值和社会意义。从临床诊疗角度来看，系统能够通过大数据分析技术识别慢性肾病的早期征象和发展规律，帮助医生快速准确地评估患者病情，提高诊断效率和准确性，特别是对于那些症状不明显的早期患者，系统可以通过多维度数据关联分析发现潜在风险，实现疾病的早发现、早诊断、早治疗。从疾病预防层面，系统通过对大量患者数据的统计分析，能够识别高危人群特征和危险因素组合，为制定针对性的预防策略提供科学依据，有效降低慢性肾病的发病率。从医疗资源配置方面，系统提供的数据可视化功能能够直观展示不同地区、不同人群的患病分布情况，帮助卫生管理部门合理配置医疗资源，优化医疗服务体系。从患者治疗效果来看，系统建立的疾病分期体系和严重程度评估模型，能够为临床医生制定个性化治疗方案提供参考，提高治疗的精准性和有效性，减少患者的医疗费用负担。同时，系统产生的研究数据还能为医学科研提供宝贵的数据资源，推动慢性肾病相关领域的学术研究发展。
慢性肾病可视化系统-演示视频
慢性肾病可视化系统-演示图片
慢性肾病可视化系统-代码展示
def analyze_ckd_prevalence_statistics(spark_session, mysql_conn):
ckd_df = spark_session.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/ckd_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").load()
total_patients = ckd_df.count()
ckd_patients = ckd_df.filter(ckd_df.Class == "ckd").count()
healthy_patients = ckd_df.filter(ckd_df.Class == "notckd").count()
prevalence_rate = (ckd_patients / total_patients) * 100
bp_ckd_analysis = ckd_df.groupBy("Bp").agg({"Class": "count"}).withColumnRenamed("count(Class)", "total_count")
bp_ckd_rate = ckd_df.filter(ckd_df.Class == "ckd").groupBy("Bp").agg({"Class": "count"}).withColumnRenamed("count(Class)", "ckd_count")
bp_analysis_result = bp_ckd_analysis.join(bp_ckd_rate, "Bp", "left_outer").fillna(0)
bp_analysis_result = bp_analysis_result.withColumn("ckd_rate", (bp_analysis_result.ckd_count / bp_analysis_result.total_count) * 100)
htn_ckd_analysis = ckd_df.filter(ckd_df.Htn == "yes").filter(ckd_df.Class == "ckd").count()
htn_total = ckd_df.filter(ckd_df.Htn == "yes").count()
htn_ckd_rate = (htn_ckd_analysis / htn_total) * 100 if htn_total > 0 else 0
bp_grade_conditions = [
(ckd_df.Bp == "normal", "normal"),
(ckd_df.Bp == "high", "prehypertension"),
(ckd_df.Bp == "very_high", "stage1_hypertension")
]
bp_grade_df = ckd_df.select("*", when(bp_grade_conditions[0][0], bp_grade_conditions[0][1]).when(bp_grade_conditions[1][0], bp_grade_conditions[1][1]).when(bp_grade_conditions[2][0], bp_grade_conditions[2][1]).otherwise("unknown").alias("bp_grade"))
bp_grade_stats = bp_grade_df.groupBy("bp_grade").agg({"Class": "count"}).withColumnRenamed("count(Class)", "total")
bp_grade_ckd = bp_grade_df.filter(bp_grade_df.Class == "ckd").groupBy("bp_grade").agg({"Class": "count"}).withColumnRenamed("count(Class)", "ckd_cases")
bp_grade_result = bp_grade_stats.join(bp_grade_ckd, "bp_grade", "left_outer").fillna(0)
bp_grade_result = bp_grade_result.withColumn("risk_rate", (bp_grade_result.ckd_cases / bp_grade_result.total) * 100)
analysis_result = {
"total_patients": total_patients,
"ckd_patients": ckd_patients,
"healthy_patients": healthy_patients,
"prevalence_rate": round(prevalence_rate, 2),
"bp_analysis": bp_analysis_result.collect(),
"htn_ckd_rate": round(htn_ckd_rate, 2),
"bp_grade_risk": bp_grade_result.collect()
}
cursor = mysql_conn.cursor()
cursor.execute("INSERT INTO analysis_results (analysis_type, result_data, created_at) VALUES (%s, %s, NOW())", ("prevalence_statistics", json.dumps(analysis_result)))
mysql_conn.commit()
return analysis_result
def analyze_kidney_function_indicators(spark_session, mysql_conn):
kidney_df = spark_session.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/ckd_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").load()
bu_stats = kidney_df.select("Bu", "Class").filter(kidney_df.Bu.isNotNull())
bu_normal = bu_stats.filter((bu_stats.Bu >= 10) & (bu_stats.Bu <= 50)).count()
bu_mild_abnormal = bu_stats.filter((bu_stats.Bu > 50) & (bu_stats.Bu <= 100)).count()
bu_severe_abnormal = bu_stats.filter(bu_stats.Bu > 100).count()
sc_stats = kidney_df.select("Sc", "Class").filter(kidney_df.Sc.isNotNull())
sc_normal = sc_stats.filter((sc_stats.Sc >= 0.6) & (sc_stats.Sc <= 1.2)).count()
sc_mild_abnormal = sc_stats.filter((sc_stats.Sc > 1.2) & (sc_stats.Sc <= 3.0)).count()
sc_severe_abnormal = sc_stats.filter(sc_stats.Sc > 3.0).count()
urine_indicators = kidney_df.select("Sg", "Al", "Su", "Rbc", "Class").filter(kidney_df.Sg.isNotNull() & kidney_df.Al.isNotNull() & kidney_df.Su.isNotNull() & kidney_df.Rbc.isNotNull())
sg_abnormal_rate = (urine_indicators.filter((urine_indicators.Sg < 1.005) | (urine_indicators.Sg > 1.025)).count() / urine_indicators.count()) * 100
al_abnormal_rate = (urine_indicators.filter(urine_indicators.Al != "normal").count() / urine_indicators.count()) * 100
su_abnormal_rate = (urine_indicators.filter(urine_indicators.Su != "normal").count() / urine_indicators.count()) * 100
rbc_abnormal_rate = (urine_indicators.filter(urine_indicators.Rbc != "normal").count() / urine_indicators.count()) * 100
correlation_df = kidney_df.select("Bu", "Sc", "Al", "Sg").filter(kidney_df.Bu.isNotNull() & kidney_df.Sc.isNotNull())
bu_sc_correlation = correlation_df.stat.corr("Bu", "Sc")
damage_grade_conditions = [
((kidney_df.Bu <= 50) & (kidney_df.Sc <= 1.2), "mild"),
((kidney_df.Bu > 50) & (kidney_df.Bu <= 100) & (kidney_df.Sc > 1.2) & (kidney_df.Sc <= 3.0), "moderate"),
((kidney_df.Bu > 100) | (kidney_df.Sc > 3.0), "severe")
]
damage_grade_df = kidney_df.select("*", when(damage_grade_conditions[0][0], damage_grade_conditions[0][1]).when(damage_grade_conditions[1][0], damage_grade_conditions[1][1]).when(damage_grade_conditions[2][0], damage_grade_conditions[2][1]).otherwise("unknown").alias("damage_grade"))
damage_stats = damage_grade_df.groupBy("damage_grade").agg({"Class": "count"}).withColumnRenamed("count(Class)", "patient_count")
proteinuria_analysis = kidney_df.select("Al", "Bu", "Sc", "Class").filter(kidney_df.Al.isNotNull() & kidney_df.Bu.isNotNull() & kidney_df.Sc.isNotNull())
proteinuria_severe = proteinuria_analysis.filter(proteinuria_analysis.Al == "abnormal").select("Bu", "Sc")
proteinuria_avg_bu = proteinuria_severe.agg({"Bu": "avg"}).collect()[0][0] if proteinuria_severe.count() > 0 else 0
proteinuria_avg_sc = proteinuria_severe.agg({"Sc": "avg"}).collect()[0][0] if proteinuria_severe.count() > 0 else 0
glucose_kidney_relation = kidney_df.filter(kidney_df.Su.isNotNull() & kidney_df.Class.isNotNull())
glucose_positive_ckd = glucose_kidney_relation.filter((glucose_kidney_relation.Su != "normal") & (glucose_kidney_relation.Class == "ckd")).count()
glucose_positive_total = glucose_kidney_relation.filter(glucose_kidney_relation.Su != "normal").count()
glucose_ckd_association = (glucose_positive_ckd / glucose_positive_total) * 100 if glucose_positive_total > 0 else 0
kidney_function_result = {
"bu_distribution": {"normal": bu_normal, "mild_abnormal": bu_mild_abnormal, "severe_abnormal": bu_severe_abnormal},
"sc_distribution": {"normal": sc_normal, "mild_abnormal": sc_mild_abnormal, "severe_abnormal": sc_severe_abnormal},
"urine_abnormal_rates": {"sg": round(sg_abnormal_rate, 2), "al": round(al_abnormal_rate, 2), "su": round(su_abnormal_rate, 2), "rbc": round(rbc_abnormal_rate, 2)},
"bu_sc_correlation": round(bu_sc_correlation, 3),
"damage_grades": damage_stats.collect(),
"proteinuria_analysis": {"avg_bu": round(proteinuria_avg_bu, 2), "avg_sc": round(proteinuria_avg_sc, 2)},
"glucose_ckd_association": round(glucose_ckd_association, 2)
}
cursor = mysql_conn.cursor()
cursor.execute("INSERT INTO analysis_results (analysis_type, result_data, created_at) VALUES (%s, %s, NOW())", ("kidney_function_analysis", json.dumps(kidney_function_result)))
mysql_conn.commit()
return kidney_function_result
def analyze_multi_indicator_diagnostic_value(spark_session, mysql_conn):
diagnostic_df = spark_session.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/ckd_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").load()
key_indicators = ["Bu", "Sc", "Al", "Hemo"]
complete_data = diagnostic_df.select(*key_indicators, "Class").filter(diagnostic_df.Bu.isNotNull() & diagnostic_df.Sc.isNotNull() & diagnostic_df.Al.isNotNull() & diagnostic_df.Hemo.isNotNull())
bu_abnormal_threshold = 50
sc_abnormal_threshold = 1.2
al_abnormal_condition = diagnostic_df.Al != "normal"
hemo_abnormal_threshold = 12.0
abnormal_combinations = complete_data.withColumn("bu_abnormal", when(complete_data.Bu > bu_abnormal_threshold, 1).otherwise(0)).withColumn("sc_abnormal", when(complete_data.Sc > sc_abnormal_threshold, 1).otherwise(0)).withColumn("al_abnormal", when(complete_data.Al != "normal", 1).otherwise(0)).withColumn("hemo_abnormal", when(complete_data.Hemo < hemo_abnormal_threshold, 1).otherwise(0))
abnormal_combinations = abnormal_combinations.withColumn("abnormal_count", abnormal_combinations.bu_abnormal + abnormal_combinations.sc_abnormal + abnormal_combinations.al_abnormal + abnormal_combinations.hemo_abnormal)
combination_stats = abnormal_combinations.groupBy("abnormal_count").agg({"Class": "count"}).withColumnRenamed("count(Class)", "total_patients")
combination_ckd = abnormal_combinations.filter(abnormal_combinations.Class == "ckd").groupBy("abnormal_count").agg({"Class": "count"}).withColumnRenamed("count(Class)", "ckd_patients")
combination_analysis = combination_stats.join(combination_ckd, "abnormal_count", "left_outer").fillna(0)
combination_analysis = combination_analysis.withColumn("ckd_rate", (combination_analysis.ckd_patients / combination_analysis.total_patients) * 100)
ckd_patients = complete_data.filter(complete_data.Class == "ckd")
healthy_patients = complete_data.filter(complete_data.Class == "notckd")
ckd_bu_avg = ckd_patients.agg({"Bu": "avg"}).collect()[0][0]
healthy_bu_avg = healthy_patients.agg({"Bu": "avg"}).collect()[0][0]
ckd_sc_avg = ckd_patients.agg({"Sc": "avg"}).collect()[0][0]
healthy_sc_avg = healthy_patients.agg({"Sc": "avg"}).collect()[0][0]
ckd_hemo_avg = ckd_patients.agg({"Hemo": "avg"}).collect()[0][0]
healthy_hemo_avg = healthy_patients.agg({"Hemo": "avg"}).collect()[0][0]
multiple_abnormal_patients = abnormal_combinations.filter(abnormal_combinations.abnormal_count >= 2)
two_abnormal = multiple_abnormal_patients.filter(multiple_abnormal_patients.abnormal_count == 2).count()
three_abnormal = multiple_abnormal_patients.filter(multiple_abnormal_patients.abnormal_count == 3).count()
four_abnormal = multiple_abnormal_patients.filter(multiple_abnormal_patients.abnormal_count == 4).count()
total_patients = complete_data.count()
severity_grading = abnormal_combinations.withColumn("severity_grade", when(abnormal_combinations.abnormal_count == 0, "normal").when(abnormal_combinations.abnormal_count == 1, "mild").when(abnormal_combinations.abnormal_count == 2, "moderate").when(abnormal_combinations.abnormal_count >= 3, "severe"))
severity_stats = severity_grading.groupBy("severity_grade").agg({"Class": "count"}).withColumnRenamed("count(Class)", "patient_count")
severity_ckd = severity_grading.filter(severity_grading.Class == "ckd").groupBy("severity_grade").agg({"Class": "count"}).withColumnRenamed("count(Class)", "ckd_count")
severity_analysis = severity_stats.join(severity_ckd, "severity_grade", "left_outer").fillna(0)
severity_analysis = severity_analysis.withColumn("diagnostic_accuracy", (severity_analysis.ckd_count / severity_analysis.patient_count) * 100)
bu_diagnostic_value = abs(ckd_bu_avg - healthy_bu_avg) / healthy_bu_avg * 100
sc_diagnostic_value = abs(ckd_sc_avg - healthy_sc_avg) / healthy_sc_avg * 100
hemo_diagnostic_value = abs(ckd_hemo_avg - healthy_hemo_avg) / healthy_hemo_avg * 100
diagnostic_ranking = [("Bu", bu_diagnostic_value), ("Sc", sc_diagnostic_value), ("Hemo", hemo_diagnostic_value)]
diagnostic_ranking.sort(key=lambda x: x[1], reverse=True)
multi_diagnostic_result = {
"combination_analysis": combination_analysis.collect(),
"normal_value_ranges": {
"ckd_averages": {"Bu": round(ckd_bu_avg, 2), "Sc": round(ckd_sc_avg, 3), "Hemo": round(ckd_hemo_avg, 2)},
"healthy_averages": {"Bu": round(healthy_bu_avg, 2), "Sc": round(healthy_sc_avg, 3), "Hemo": round(healthy_hemo_avg, 2)}
},
"multiple_abnormal_distribution": {
"two_abnormal": two_abnormal,
"three_abnormal": three_abnormal,
"four_abnormal": four_abnormal,
"total_patients": total_patients
},
"severity_grading": severity_analysis.collect(),
"diagnostic_value_ranking": [(indicator, round(value, 2)) for indicator, value in diagnostic_ranking]
}
cursor = mysql_conn.cursor()
cursor.execute("INSERT INTO analysis_results (analysis_type, result_data, created_at) VALUES (%s, %s, NOW())", ("multi_indicator_diagnostic", json.dumps(multi_diagnostic_result)))
mysql_conn.commit()
return multi_diagnostic_result
慢性肾病可视化系统-结语
💕💕
💟💟如果大家有任何疑虑，欢迎在下方位置详细交流，也可以在主页联系我。
