SNOMED CT-Based Standardized e-Clinical Pathways for Enabling Big Data Analytics in Healthcare

• Published in: IEEE access 2020, Vol.8, p.92765-92775
• Main Authors: Alahmar, Ayman D., Benlamri, Rachid
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Big Data; Clinical pathway; Data analysis; data analytics; Datasets; decision tree; Encoding; Health care; Health care facilities; health level 7; Hospitals; length of stay; Machine learning; Medical diagnostic imaging; Missing data; Ontologies; Patient care planning; Patient satisfaction; semantic web; SNOMED CT; Statistical analysis; Streamlining
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2994286

Automation of healthcare facilities represents a challenging task of streamlining a highly information-intensive sector. Modern healthcare processes produce large amounts of data that have great potential for health policymakers and data science researchers. However, a considerable portion of such data is not captured in electronic format and hidden inside the paperwork. A major source of missing data in healthcare is paper-based clinical pathways (CPs). CPs are healthcare plans that detail the interventions for the treatment of patients, and thus are the primary source for healthcare data. However, most CPs are used as paper-based documents and not fully automated. A key contribution towards the full automation of CPs is their proper computer modeling and encoding their data with international clinical terminologies. We present in this research an ontology-based CP automation model in which CP data are standardized with SNOMED CT, thus enabling machine learning algorithms to be applied to CP-based datasets. CPs automated under this model contribute significantly to reducing data missingness problems, enabling detailed statistical analyses on CP data, and improving the results of data analytics algorithms. Our experimental results on predicting the Length of Stay (LOS) of stroke patients using a dataset resulting from an e-clinical pathway demonstrate improved prediction results compared with LOS prediction using traditional EHR-based datasets. Fully automated CPs enrich medical datasets with more CP data and open new opportunities for machine learning algorithms to show their full potential in improving healthcare, reducing costs, and increasing patient satisfaction.