Study On Semantic-based Personalized Clinical Pathways

With the development of the healthcare system reform, more and more challenges appear for decreasing health care costs, standardizing clinical activities, improving medical quality, and optimizing patient outcomes. Clinical pathway (CP), as a cost-effective medical management schema, is considered as an important means to wrestle with these challenges. However, the utility rate of CPs remains unsatisfactory. Problems like inadequate individuation, ambiguous expression, and electronic plight restricts the implementation and development of CPs. How to improve the practicality of CPs is becoming one of the most popular research directions in the field of medical informatics. In this study, semantic web technologies were utilized to improve the practicality of CPs. Beginning with the research of pathway modeling methods, personalized CPs were customized by comprehensive considering the diversity between different patients and different hospitals. In addition, an independent CP system was designed and developed to realize the standard functions of electronic CPs. The main work is as follows:Patient-specific personalized CPs were created by constructing a semantic-based interoperability model between knowledge-based CPs and electronic health records (EHR). The status of a patient is complex and variable, likely resulting in the termination of CPs. We constructed the semantic EHR by a new semantic web framework and chosen for providing the patient information. A CP for acute appendicitis was used as an example to illustrate how to achieve CP customization and self-adaption based on the interoperability model.Hospital-specific personalized CPs was created via a data-driven, decision-making methodology by applying semantic transformation and reasoning to historical clinical data. Through the analysis of clinical data in the hospital, we can generate disease-specific treatment procedures that are frequently used by physicians. Long term order processing and error correction via semantic transforming and reasoning made the treatment procedures more consistent with clinical practice. The percentage of each pathway order with different probabilities was calculated to declare the commonality between the standard care plans and practical treatment procedures. Detailed treatment procedures with pathway orders, deduced pathway orders, and orders with probability greater than 80% were provided to efficiently customize the CPs. This will provide much more complete decision support for clinical physicians to develop more efficient and intelligent clinical procedures.An independent CP system was designed to improve the CP adaptation in the current medical information environment. An innovative knowledge base pattern was designed with separate namespaces for global knowledge, local knowledge, and real-time instances according to the knowledge stability. The interaction solution between the pathway system and the EMR system simplified the integration procedures with other hospital information systems. The independent CP system achieved standard functions of electronic CPs without modifying existing EMR systems and integration environments in hospitals.Semantic web technologies were introduced to the pathway practical research. Based on the modeling and computerization of CPs, this paper proposed the customization methods of personalized CPs considering the differences characteristics of patients and hospitals respectively, and developed an independent CP system based on the current medical information environment. We proposed the feasible solution to address the pathway practical problem from three aspects of patients, hospitals, and information environment, which lays a reliable technology foundation for the CP implementation and is beneficial to decrease health care costs, control clinical process, and improve medical quality.