Huilong Duan

Resource behavior measure and application in business process management

Efficient resource behavior measure in business process management is a real and challenging problem. It reflects the actual situations in business process execution from resource perspective and is highly relevant for the business process performance. This paper presents an approach of measuring resource behavior from four important perspectives, i.e., preference, availability, competence and cooperation, based on process mining. Furthermore, this paper shows how business process management can benefit from resource behavior measure. In particular, four applications are addressed to demonstrate the applicability of resource behavior measure in business process management. The presented approach is evaluated based on a proof-of-concept implementation and its application to a real case form health-care. The results show that the proposed approach is possible to improve current state of business process management.

Supporting adaptive clinical treatment processes through recommendations

OBJECTIVESnEfficient clinical treatment processes is considered a key factor of medical quality control. Current IT solutions are far away from this perspective since they typically have difficulty supporting the variances occurring in clinical practices, and providing adequate flexible support of clinical processes.nnnMETHODSnThis paper proposes a hybrid approach based on rough set theory and case-based reasoning to allow physicians to rapidly adjust patients treatment processes to changes of patients clinical states. In detail, the proposed approach recommends appropriate treatment plans in clinical process execution by adopting a similarity measure to select appropriate clinical treatment plans executed on patients who presented similar features to the current one. Such clinical treatment plans are then applied to suggest which actions to perform next in clinical treatment process execution.nnnRESULTSnAs a motivating scenario, this study performs the experiments of type 2 diabetes patients treatment process. The results show that the proposed approach is feasible to recommend suitable clinical treatment plans in clinical process execution, which makes adaptive clinical treatment processes possible.

Variation prediction in clinical processes

For clinical processes, meaningful variations may be related to care performance or even the patient survival. It is imperative that the variations be predicted timely so that the patient care journey can be more adaptive and efficient. This study addresses the question of how to predict variations in clinical processes. Given the assumption that a clinical case with low appropriateness between its specific patient state and its applied medical intervention is more likely to be a variation than other cases, this paper proposes a method to construct an appropriateness measure model based on historical clinical cases so as to predict such variations in future cases of clinical processes. The proposed method is demonstrated on a real life data set from the Chinese Liberation Army General Hospital. The experimental results confirm the given assumption and indicate the feasibility of the proposed method.

Level of detail navigation and visualization of electronic health records

Clinicians usually intend to get overall health status as well as specific health care information from patients electronic health record (EHR). However, the amount of EHR data can be incredibly large, which makes it a very tedious and inefficient work for clinicians to extract valuable information. This paper first investigates the clinical relevance of EHR data content. Then it presents a Level of Detail (LOD) information navigation model, which classified patients whole EHR into different detail levels according to their clinical relevance. A novel navigation and visualization method is brought forward based on this model. Finally, an application is designed and implemented based on this method. It can guide clinicians from summarized overview to detailed contents of the EHR smoothly. Both the evolution of specific health problems and other related EHR information can be visualized and located quickly.

Radiology workflow-based monitoring dashboard in a heterogeneous environment

Radiology departments could benefit from the digital dashboards which integrate and visualize information reflecting workflow state. However, the heterogeneous environment in radiology prevents an integrated overall view of the process. The objective of this study is to design and develop a workflow-based dashboard in a heterogeneous environment to help the radiology administrators and managers monitor the state of the work flow in real time. Firstly, we propose to use workflow management method to implement the system integration. Then a real-time monitoring dashboard which analyzed data from workflow management system integrated with information in other radiology systems is designed and developed. A use case implementation is carried out in Huzhou Central hospital of China. The dashboard is well accepted by the radiology administrators and managers in the hospital who lack real-time workflow monitoring tools in a heterogeneous environment. This work presents a new perspective on radiology department management, and can be viewed as an initial endeavor for introducing workflow management technology in healthcare.

Enhancing interoperability of ECG machine to support ECG telediagnosis service

Now many remote or underserved areas have brought forward a high demand for improving the quality of ECG interpretation. Telediagnosis can provide a feasible solution. However, even communities already equipped with ECG machines cannot communicate with a remote diagnostic center, because these machines lack interoperability. It can be predicted that the applicability and popularization of ECG telediagnosis could be greatly improved via developing high interoperable ECG machines and realizing a direct interaction between the machines and a remote diagnostic center. In this paper, a detail analysis on the flow of ECG telediagnosis is represented first. Several interactive transactions and a complete and reasonable interaction workflow of ECG machine are designed on the base of the analysis. The design has realized an automatic acquisition of patient information and the transmission of a complete ECG record as well as a diagnostic report. We have created an ECG machine based on the design presented and developed a Web Service named TeleECGService, through which a direct interaction between an ECG machine and a remote diagnostic center can be achieved. An ECG remote diagnosis system based such high interoperable ECG machines has been put into use in a hospital in Shanxi Province of China.

A compound segmentation algorithm for anterior chamber angle in OCT image

Anterior chamber (AC) angle is a useful parameter in the investigation and diagnoses of angle closure glaucoma. And Optical coherence tomography (OCT) is a noninvasive and high-resolution technique for AC angle imaging. An accurate and automatic angle measurement should be based on a precise AC angle segmentation in OCT image. However, conventional segmentation algorithms can not achieve a well result because the algorithms are not robust to the dark shadow areas and speckle noise existing in the image. A new compound segmentation algorithm is proposed in this paper. The morphological method, intensity transform, gradient image, and ratio of foreground-to-background average intensity, etc., are applied in this new algorithm to improve the accuracy of segmentation. The experiments show that the presented algorithm can achieve a satisfactory segmentation result for the AC angle in OCT images.

A clinical decision support system for primary headache disorder based on hybrid intelligent reasoning

Clinical decision support system (CDSS) is an effective tool for improving healthcare quality. Since the clinical symptoms of some primary headache disorders in individual patients often overlap and that ill-defined boundaries for some headache features may be vague, current rule-based CDSS cannot perform as well as expected. In this paper, we develop a CDSS for primary headache disorder diagnosis based on rule-based and case-based reasoning in order to simulate a headache specialists thinking process. First, the new case is evaluated by rule-based reasoning, the rules come from headache clinical guideline; second, if rule-based reasoning was unable to get accurate answer, case-based reasoning will find the most similar case in case library based on similarity matching. In particular, we define a similarity calculating method for primary headaches case. The final results show that the proposed approach improves the diagnostic accuracy dramatically compared to the rule-based primary headache diagnosis systems.

A RFID-based tracking system of endoscopes

The cleaning and disinfection of the endoscopes are extremely important for reducing endoscopic transmission of infections in hospitals. There have been many such cases of medical accidents reported in the history and most are caused by poor management. According to the Technical Specifications for the Cleaning and Disinfection of Endoscopes (2004) of China, this paper has presented a tracking system based on the radio frequency identification (RFID) technology to provide a better management of the endoscopes. It can efficiently prevent the potential medical errors by recording and checking the current state of the endoscopes, and it can provide a better traceability of the daily operations of the endoscopes by saving the historical using, cleaning and disinfection records. Preliminary clinical application was tested in the endoscope center of a 2200-bed hospital in Hangzhou, China. The result has expectantly demonstrated that it can effectively standardize the operation procedures and reduce the medical errors. Further evaluation of its usefulness and the user satisfaction will be done in the future.

A problem-snapshot view of patient history data for cardiac preoperative evaluation

Preoperative risk evaluation is a very important work before a cardiac surgery. Clinicians always have to spend much time reviewing the information about operative risk factors. In this paper, we have made a few tentative attempts to help clinicians improve the efficiency of risk evaluation. First a surgery-problem network for cardiac surgeries is built to extract the associated medical problems from patient history problems. Then a set of data filter rules are defined for each medical problem to retrieve the required data, which is clustered around the problems and forms a set of snapshots. After that, we propose a multi-level-timeline method to visualize the problems and snapshots extracted. Finally, a special problem-snapshot visualization tool for cardiac preoperative evaluation is designed and developed as a result. The tool provides a quick way of reviewing the information which is helpful for cardiac preoperative risk evaluation through information visualization technology. It can save a lot of tedious work.