Medical activity requires responsibility not only based on knowledge and clinical skills, but also in managing a vast amount of information related to patient care. It is through the appropriate treatment of information that experts can consistently build a strong policy of welfare. The primary goal of decision support systems (DSSs) is to give information to the experts where and when it is needed. These systems provide knowledge, models, and data processing tools to help the experts make better decisions in several situations. They aim to resolve several problems in health services to help patients and their families manage their health care by providing better access to these services. This paper presents a deep review of the state of the art of smart DSSs. It also elaborates on the latest developments in intelligent systems to support decision-makers in health care. The most promising findings brought in literature are analyzed and summarized according to their taxonomy, application area, year of publication, and the approaches and technologies used. Smart systems can assist decision-makers to improve the effectiveness of their decisions using the integration of data mining techniques and model-based systems. It significantly improves the current approaches, enabling the combination of knowledge from experts and knowledge extracted from data.

A Comprehensive Review on Smart Decision Support Systems for Health Care

Using clinical reasoning ontologies to make smarter clinical decision support systems: a systematic review and data synthesis

Simulation of Patient Flow in Multiple Healthcare Units using Process and Data Mining Techniques for Model Identification

Spatiotemporal and semantic information extraction from web news reports about natural hazards

Treatment of type 2 diabetes mellitus (T2DM) is a complex problem. A clinical decision support system (CDSS) based on massive and distributed electronic health record data can facilitate the automation of this process and enhance its accuracy. The most important component of any CDSS is its knowledge base. This knowledge base can be formulated using ontologies. The formal description logic of ontology supports the inference of hidden knowledge. Building a complete, coherent, consistent, interoperable, and sharable ontology is a challenge. This paper introduces the first version of the newly constructed Diabetes Mellitus Treatment Ontology (DMTO) as a basis for shared-semantics, domain-specific, standard, machine-readable, and interoperable knowledge relevant to T2DM treatment. It is a comprehensive ontology and provides the highest coverage and the most complete picture of coded knowledge about T2DM patients’ current conditions, previous profiles, and T2DM-related aspects, including complications, symptoms, lab tests, interactions, treatment plan (TP) frameworks, and glucose-related diseases and medications. It adheres to the design principles recommended by the Open Biomedical Ontologies Foundry and is based on ontological realism that follows the principles of the Basic Formal Ontology and the Ontology for General Medical Science. DMTO is implemented under Protege 5.0 in Web Ontology Language (OWL) 2 format and is publicly available through the National Center for Biomedical Ontology’s BioPortal at . The current version of DMTO includes more than 10,700 classes, 277 relations, 39,425 annotations, 214 semantic rules, and 62,974 axioms. We provide proof of concept for this approach to modeling TPs. The ontology is able to collect and analyze most features of T2DM as well as customize chronic TPs with the most appropriate drugs, foods, and physical exercises. DMTO is ready to be used as a knowledge base for semantically intelligent and distributed CDSS systems.

/pdf/dmto-a-realistic-ontology-for-standard-diabetes-mellitus-24xwqsatj6.pdf

DMTO: a realistic ontology for standard diabetes mellitus treatment

Integrating HL7 RIM and ontology for unified knowledge and data representation in clinical decision support systems

Clinical Pathways (CP) enhance the quality of patient care, and are thus important in health management. However, there is a need to address the challenge of adaptation of treatment procedures in CP—that is, the treatment schemes must be re-modified once the clinical status and other care conditions of patients in the healthcare setting change, which happen frequently. In addition, the widespread and frequent use of Electronic Medical Records (EMR) implies an increasing need to combine CP with other healthcare information systems, especially EMR, in order to greatly improve healthcare quality and efficiency. This study proposed an ontology-based method to model CP: ontology was used to model CP domain terms; Semantic Web Rule language was used to model domain rules. In this way, the CP could reason over the rules, knowledge, and information collected, and provides automated error checking for the next steps of the treatment in runtime, which is adaptive to treatment procedures. To evaluate our method, we built a Lobectomia Pulmonalis CP and realized it based on an EMR system.

Ontology-based clinical pathways with semantic rules.

Although data mining and knowledge discovery techniques have been used to clinical medicine frequently, little research has been conducted on hospital decision-making. Decision-making is a crucial part of hospital management, and it goes the whole process of medical behavior. Medical data in Hospital Information System is always complicated and especial, and this consequently aggravates burden on data analysis. In this paper, we explore how data mining and knowledge discovery can be applied to hospital management, and propose a modified data mining method that is appropriate for mass data in Hospital Information System. We first build a model based on inpatient fees theme, and then analyze it in three aspects: medical insurance fee, department annual fee and fee compositions. The knowledge discovery and analysis is based on Intersystem BI tool DeepSee.

Data mining analysis of inpatient fees in Hospital Information System

Interoperability among healthcare information systems is one of the most challenging problems in healthcare domain. In this paper, we propose a structure of Interoperable Medical Information System based on SOA (Service-Oriented Architecture) and Web 2.0 under the framework of Regional Health Information Network. Various components are described in detail, including authentication, data access, and services management and so on. Services for medical information getting are registered and published by the system; users then access the system to search and fetch demanded services and value-added applications. All of the heterogeneous and distributed data and applications are converted to independent services according to international standards. As a result of the use of SOA, the system is levels clearly demarcated with good universality and maintainability.

Design and implementation of Interoperable Medical Information System based on SOA

EMR benefits medical staffs by facilitating the order entry and prescribing errors. It can improve the safety and effectiveness of medical services, but can not manage the whole medical process and the quality of medical services. So we apply PDCA, the famous quality management cycle to the EMR. EMR with PDCA can record every state of the orders to monitor the whole medical process. This extends the safety from planning the treatment to fulfilling the treatment. By analyzing the records, doctors and hospital managers can perfect the medical process and improve the quality of medical services. The ordering system we designed with PDCA can display all the information intuitively and real-timely by changing colors of the orders.

Tian-shu Zhou

Papers

Integrating HL7 RIM and ontology for unified knowledge and data representation in clinical decision support systems

Ontology-based clinical pathways with semantic rules.

Data mining analysis of inpatient fees in Hospital Information System

Design and implementation of Interoperable Medical Information System based on SOA

Medical Process Management by Applying PDCA to EMR