Building an Electronic Medical Record Retrieval System Using Natural Language Processing Technology and Blockly-based Visualization Tools

The application of Electronic Medical Record (EMR) systems has become a key tool for recording and managing patient data. EMR systems can store a vast amount of patient information, including all details of examinations and treatments, and integrate medical records and reports generated by different departments. This not only enables doctors to easily access medical records to support medical decision-making but also improves the quality of clinical decisions in high-pressure environments, such as emergency rooms. However, when the data in electronic medical records is too cumbersome and not properly organized, doctors may encounter cognitive overload, especially in the face of congestion in emergency rooms caused by too many patients, increasing the risk of medical errors. In light of this, this project proposes to use Natural Language Processing (NLP) technology for the automated processing of electronic medical records at Landseed International Hospital, and to implement and validate it across three clinical settings. Since most electronic medical records are composed of unstructured natural language, the application of natural language processing technology becomes crucial. Using NLP technology can help mine and mark important medical concepts, thereby improving the efficiency of information filtering. Furthermore, the system developed in this project can utilize the concept of block-based programming, allowing clinical experts to convert complex clinical rules into computable forms without the assistance of technical personnel. This not only lowers the threshold for clinical application but also allows various units to establish their own sets of clinical rules with minimal training costs, applying them in actual medical fields. The system developed in this project not only demonstrates the value of combining artificial intelligence technology with clinical expertise but also shows potential in improving patient care quality and efficiency.