Development and operation of a digital platform for sharing pathology image data.

BACKGROUND: Artificial intelligence (AI) research is highly dependent on the nature of the data available. With the steady increase of AI applications in the medical field, the demand for quality medical data is increasing significantly. We here describe the development of a platform for providing and sharing digital pathology data to AI researchers, and highlight challenges to overcome in operating a sustainable platform in conjunction with pathologists. METHODS: Over 3000 pathological slides from five organs (liver, colon, prostate, pancreas and biliary tract, and kidney) in histologically confirmed tumor cases by pathology departments at three hospitals were selected for the dataset. After digitalizing the slides, tumor areas were annotated and overlaid onto the images by pathologists as the ground truth for AI training. To reduce the pathologists' workload, AI-assisted annotation was established in collaboration with university AI teams. RESULTS: A web-based data sharing platform was developed to share massive pathological image data in 2019. This platform includes 3100 images, and 5 pre-processing algorithms for AI researchers to easily load images into their learning models. DISCUSSION: Due to different regulations among countries for privacy protection, when releasing internationally shared learning platforms, it is considered to be most prudent to obtain consent from patients during data acquisition. CONCLUSIONS: Despite limitations encountered during platform development and model training, the present medical image sharing platform can steadily fulfill the high demand of AI developers for quality data. This study is expected to help other researchers intending to generate similar platforms that are more effective and accessible in the future.

MobileMed: a PDA-based mobile clinical information system.

Patient clinical data are distributed and often fragmented in heterogeneous systems, and therefore the need for information integration is a key to reliable patient care. Once the patient data are orderly integrated and readily available, the problems in accessing the distributed patient clinical data, the well-known difficulties of adopting a mobile health information system, are resolved. This paper proposes a mobile clinical information system (MobileMed), which integrates the distributed and fragmented patient data across heterogeneous sources and makes them accessible through mobile devices. The system consists of four main components: a smart interface, an HL7 message server (HMS), a central clinical database (CCDB), and a web server. The smart interface and the HMS work in concert to generate HL7 messages from the existing legacy systems, which essentially send the patient data in HL7 messages to the CCDB to be stored and maintained. The CCDB and the web server enable the physicians to access the integrated up-to-date patient data. By proposing the smart interface approach, we provide a means for effortless implementation and deployment of such systems. Through a performance study, we show that the HMS is reliable yet fast enough to be able to support efficient clinical data communication.

MobileNurse: hand-held information system for point of nursing care.

Healthcare information travels with patients and clinicians and therefore the need for information to be ubiquitously available is key to reliable patient care and reliable medical systems. We have implemented MobileNurse, a prototype point-of-care system using PDA. MobileNurse has four modules each of which performs: (1) patient information management; (2) medical order check; (3) nursing recording; and (4) nursing care plan. MobileNurse provides easy input interface and various outputs for nursing records. The system consists of PDAs and a mobile support system (MSS) which supports clinical data exchange between PDAs and hospital information system. Two synchronization modules have been developed to keep the patient data consistent between PDAs and MSS. Clinical trials were performed with six volunteered nurses. They tried MobileNurse for 1-day caring-simulated patients. According to the survey after the trials, most of volunteers agreed that MobileNurse is more helpful and convenient than other non-mobile care systems to check medical orders and retrieve the results of recent clinical tests at the bedside. Through the involvement, we found out that ease-to-use interface is the most critical successful factor for mobile patient care systems.

Realization of real-time clinical data integration using advanced database technology.

As information & communication technologies have advanced, interest in mobile health care systems has grown. In order to obtain information seamlessly from distributed and fragmented clinical data from heterogeneous institutions, we need solutions that integrate data. In this article, we introduce a method for information integration based on real-time message communication using trigger and advanced database technologies. Messages were devised to conform to HL7, a standard for electronic data exchange in healthcare environments. The HL7 based system provides us with an integrated environment in which we are able to manage the complexities of medical data. We developed this message communication interface to generate and parse HL7 messages automatically from the database point of view. We discuss how easily real time data exchange is performed in the clinical information system, given the requirement for minimum loading of the database system.

The knowledge modeling for chronic urticaria assessment in clinical decision support system with PDA.

The benefits of a clinical information system would be enhanced by a clinical decision support system (CDSS). We have developed urticaria diagnosis knowledge model for clinical practice. In order to construct a more accurate, evidenced-based and comprehensive knowledge base for urticaria, we arranged and integrated knowledge from literatures-based knowledge, as provided by; The Korean Academy of Asthma and Allergy [1], the American Allergy Association based on an algorithm of chronic urticaria assessment. We presented this knowledge in a Boolean cross table frame and implemented these guidelines using the developed CDSS.

Optimizing query response with XML user profile in mobile clinical systems.

Improvements of modern mobile technology, have created a need for a mobile clinical environment. In the field of mobile clinical systems, getting information on time is as important as mission critical aspects. However, web access time with the mobile device is still not feasible clinically. Therefore, the optimisation of query response becomes an important issue. We have developed a query optimising method using a user profile. We analysed user (clinician) specific queries in the medical field. Most of the data retrieval in the medical field is focused on the clinical test results, and the patient inverted exclamation mark s demographic information. Sometimes the information requested in the medical field places a heavy load on the database, since such information may require full database scanning and much joining of tables in the databases. In such cases, constructing profile data and employing it for data retrieval would help to improve the response time. The use of a predefined profile avoids the multiple joining process, and shortens the total response time. The object of our research is to improve query response by creating user profiles and using this profile information for patient data retrieval.