Scholarlink

<p>Healthcare data are characterized by high volume, velocity, and variety, posing significant challenges for efficient analysis and reasoning. These challenges are amplified by the continuous generation of diverse information from multiple sources such as electronic health records (EHRs), laboratory test results, medical imaging systems, and IoT-enabled health monitoring devices. For example, blood glucose readings from diabetic patients, ECG and blood pressure signals from cardiovascular monitoring systems, and oncology data from cancer registries are often stored in incompatible formats and distributed repositories, creating major barriers to integrated analysis and diagnosis. With the growing emphasis on holistic and preventive care, it is crucial to analyze data across non-communicable diseases (NCDs), including diabetes, cardiovascular diseases, cancer, and stroke, which are interrelated and require coordinated management. However, technical barriers such as heterogeneous data formats, fragmented storage, and limited interoperability hinder effective decision-making. To address these limitations, this study proposes an ontology-driven big data analytics framework aligned with India’s National Programme for Prevention and Control of Cancer, Diabetes, Cardiovascular Diseases, and Stroke (NPCDCS). Domain-specific NCD ontologies developed using the Basic Formal Ontology (BFO) ensure structured and semantically enriched knowledge representation. Five NCD-specific EHR datasets were converted into Resource Description Framework (RDF) using R2RML mappings and analyzed using Semantic Web Rule Language (SWRL) rules derived from NPCDCS clinical guidelines. RDF data were stored in the Hadoop Distributed File System (HDFS), and a hybrid load balancing MapReduce strategy optimized SPARQL query execution. The outcomes demonstrate improved semantic interoperability, data integration accuracy, and reasoning efficiency, enabling consistent comorbidity detection, enhanced scalability, and real-time, policy-aligned decision support for large-scale NCD management. Furthermore, the framework enhances analytical transparency by enabling explainable reasoning pathways, supports incremental ontology expansion for new disease domains, and ensures reproducibility across distributed healthcare environments. The improved query performance and semantic consistency establish a foundation for scalable, intelligent, and interoperable healthcare analytics adaptable to national and global health programs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ontology-based knowledge modeling approach for big data analysis of interdependent health conditions in the diagnosis of non-communicable diseases

  • 期刊论文

  • 发表日期：

    2026年3月3日

查看全文
  • Ritesh Chandra,
  • Sonali Agarwal,
  • Navjot Singh

摘要

Healthcare data are characterized by high volume, velocity, and variety, posing significant challenges for efficient analysis and reasoning. These challenges are amplified by the continuous generation of diverse information from multiple sources such as electronic health records (EHRs), laboratory test results, medical imaging systems, and IoT-enabled health monitoring devices. For example, blood glucose readings from diabetic patients, ECG and blood pressure signals from cardiovascular monitoring systems, and oncology data from cancer registries are often stored in incompatible formats and distributed repositories, creating major barriers to integrated analysis and diagnosis. With the growing emphasis on holistic and preventive care, it is crucial to analyze data across non-communicable diseases (NCDs), including diabetes, cardiovascular diseases, cancer, and stroke, which are interrelated and require coordinated management. However, technical barriers such as heterogeneous data formats, fragmented storage, and limited interoperability hinder effective decision-making. To address these limitations, this study proposes an ontology-driven big data analytics framework aligned with India’s National Programme for Prevention and Control of Cancer, Diabetes, Cardiovascular Diseases, and Stroke (NPCDCS). Domain-specific NCD ontologies developed using the Basic Formal Ontology (BFO) ensure structured and semantically enriched knowledge representation. Five NCD-specific EHR datasets were converted into Resource Description Framework (RDF) using R2RML mappings and analyzed using Semantic Web Rule Language (SWRL) rules derived from NPCDCS clinical guidelines. RDF data were stored in the Hadoop Distributed File System (HDFS), and a hybrid load balancing MapReduce strategy optimized SPARQL query execution. The outcomes demonstrate improved semantic interoperability, data integration accuracy, and reasoning efficiency, enabling consistent comorbidity detection, enhanced scalability, and real-time, policy-aligned decision support for large-scale NCD management. Furthermore, the framework enhances analytical transparency by enabling explainable reasoning pathways, supports incremental ontology expansion for new disease domains, and ensures reproducibility across distributed healthcare environments. The improved query performance and semantic consistency establish a foundation for scalable, intelligent, and interoperable healthcare analytics adaptable to national and global health programs.