تشخیص غیر طبیعی از تریاژ کاوش شده بخش اورژانس با تکنولوژی داده کاوی: بخش اورژانس در یک مرکز پزشکی در تایوان به عنوان مثال گرفته شده است
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|22180||2010||9 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 4631 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 37, Issue 4, April 2010, Pages 2733–2741
Triage helps to classify patients at emergency departments to make the most effective use of resources distributed. What is more important is that accuracy in carrying out triage matters greatly in terms of medical quality, patient satisfaction and life security. As the numbers of patients in emergency departments increase, learning from the examples of abnormal diagnosis of triage in order to make modifications, constitutes a significant issue. The researcher worked with the Emergency Department of a Taiwan Medical Center to build a model to view abnormal diagnoses in the database from the establishment of a flow path and the selection of parameters for sampling. Data on patients were derived from the database. Two-stage cluster analysis (Ward’s method and K-means) and decision tree analysis were made on 501 abnormal diagnoses in an emergency department. It was found that nursing personnel make more frequent triage diagnoses than physicians do. Most of abnormal diagnoses stems from patients rather than the diagnosis on the day. Pulse and temperature have greater distinction. The researcher proposes seven correlation laws based on confidence and support proportions, derived from sample point conforming to correlation law that abnormal diagnosis is most likely in diseases of pneumonia and cirrhosis, etc. Through data mining technology, the researcher’s triage expert system is written in simulation. After periodic updates, it can improve the system and education training without the influence of the subjective factor.
Emergency departments are the front lines facing patients in emergency medical conditions. The department covers: physicians, nursing personnel, technicians, social workers, first aid technicians, administration personnel, janitors, and volunteers in 24-h operation for first aid, observation or surgery. It is a small hospital within a hospital. Process of emergency department: triage and consulting rooms of each department for treatment. According to statistics (Fig. 1) by the Department of Health (Brillman, Doezema, & Tandberg, 1996), the number of service personnel at emergency medical treatment centers has continued to grow, from 4,350,000 in 1994 to 6,870,000 in 2004, for a 58% increase in numbers. This has caused chaos at emergency departments due to a lack of knowledge regarding the procedures and department medical systems.A triage system helps patients in critical conditions. Weiner and Edwards (1964) believed that proper triage is expected to reduce the high economic price for patients in non-critical conditions. Triage consistency to physicians’ classification affects the satisfaction of patients and the waiting time (VanBoxel, 1995). Over triage will entail a waste of medical resources while under triage endangers the rights of patients and medical distribution. Triage significantly affects medical quality, patient satisfaction and life security. In accordance with hospital Emergency Department assessment standards (1995), emergency patient triage can be divided into four levels: Level I (requiring immediate treatment), Level II (to be treated in 10 minutes), Level III (to be treated in 30 minutes), and Level IV (treatment can be delayed). Decisions of the triage in current domestic emergency departments are mostly made by senior nursing personnel. Estrada (1981) held that senior experienced nursing personnel could also do the job well. Decision-making may be affected by job complications, conflicts, nursing experience, education and professional knowledge (Brillman et al., 1996). Triage nursing personnel (hereafter nursing personnel) may be perplexed in regard to triage levels. Finding the hidden rules of triage from patients’ data will help nursing personnel engaging in triage. With the demand of businesses, data application has evolved from database and data storage to data mining. Data mining refers to a: “process to locate non-obvious, unknown, and potential possible usable information from data” ( Frawley, Paitetsky-Shapiro, & Matheus, 1991); Reinschmidt, Gottschalk, Kim, and Zwietering (1999) stated that the aim of: “data mining is to extract effective, useful and unknown comprehensible information to serve as foundation of decision-making for enterprises.” Appropriate use of information will provide businesses with greater wisdom and decision information. Data mining has been successfully applied in industries, commerce and medicine. Huang and Chen (2005) used various data mining technologies to help machines learn to distinguish types of glaucoma; Abdelfattah et al. (2006), with data mining and serum examination and radioactive treatment, predicted whether Type C pneumonia pathologically changed to cirrhosis. The researcher explored abnormal diagnoses in emergency medicine with data mining, in cooperation with an Emergency Department of a Taiwan Medical Center (hereafter Emergency Department) to understand current triage operation and obtain basic statistics and patient data from the database. The study is made on medical management and nursing, with the knowledge of the administrative head at the Emergency Department, in the hope to effectively improve consistency of triage with the combination of data mining theories and practice. The purposes are as follows: (1) Based on information management, the information system is applied in triage of the Emergency Department to generate patients’ data. (2) Exploration of correlation between triage and abnormal diagnosis; cluster analysis conducted on variables with clinical meanings (Lee, Kim, Kwon, Han, & Kim, 2008). (3) Establishing triage abnormal diagnosis clusters with hierarchical clustering (Ward’s method) and partitioning clustering (K-means algorithm); obtaining correlation law of abnormal diagnosis with decision trees ( Piramuthu, 2008). (4) Improving consistency of triage with data mining; offering quantified and scientific rules for triage decision-making in the hope of serving as a foundation for future researchers and clinical examination.
نتیجه گیری انگلیسی
Triage classifies patients at emergency departments in order to distribute resources most effectively. Most important is that triage accuracy matters greatly in medical quality, patient satisfaction and life security. As the number of patients in emergency departments keeps increasing, learning from abnormal diagnoses of triage and making the required modifications become even more significant issues. The researcher worked with the Emergency Department of Taiwan Medical Center to explore rules of abnormal diagnosis in triage from flow path suggestions, parameter selection to sampling, to build a model of database abnormal diagnoses (Fig. 2). Patients data are from the database. Two-stage cluster analysis (Ward’s method and K-means) and decision tree analysis ( Yang, Lim, & Tan, 2005) was made on 501 pieces of abnormal diagnosis in emergency departments. Best number of clusters was calculated with Kappa value; Cluster center was arranged into cluster tendency ( Fig. 4). It was found that nursing personnel have more frequent triage than physicians’ diagnoses. Most of abnormal diagnoses stem from patients not diagnosed on the day. Pulse and temperature have greater distinction. Triage conditions are more serious in Clusters 2, 3 and 4 not on the day. These patients have been in and out of ICUs many times. Recurring conditions may also cause triage abnormal diagnosis. After clustering, sample points in the same cluster have similar abnormal diagnosis characteristics. Analysis is made on four clusters respectively. Patients with lower temperature or higher systolic pressure in Cluster 1 may cause abnormal diagnosis. Patients with lower pulse in Cluster 2 may cause abnormal diagnosis. Patients with lower systolic and diastolic pressure may cause abnormal diagnosis. Patients with higher pulse and temperature in Cluster 4 may cause abnormal diagnosis. The researcher proposes seven correlation laws based on confidence and support proportion and 186 samples are picked up from 7 rules for simple statistics based on c/o. Patients with pneumonia, upper GI bleeding, septicemia, fever and cirrhosis, etc are most likely to cause abnormal diagnosis. Based on the patient data of case medical center, the researcher proposes a study structure with data mining for scholars’ reference. To understand general principles of triage abnormal diagnosis in Taiwan and Asia, more samples are required in exact methods. In addition to vital sign parameters, c/o of patients has to be considered. C/o includes: case history, general appearance, symptoms and signs, and body evaluation. The researcher suggests that scholars take c/o into consideration in future research. It is suggested that when patients are under triage with temperature higher than 40.7 °C or lower than 35.6 °C, pulse no less than 105 or less than 52 times per minute, systolic pressure exceeding 210 mm Hg or less than 68 mm Hg, or diastolic pressure less than 90 mm Hg, triage levels shall be determined based on c/o, case history and other parameters. Patients with GI bleeding or pneumonia may face deteriorating situations and should be placed under more cautious triage levels. Cautious evaluation of triage is required. The researcher extracts decision experience of nursing personnel in the past as useful information and laws with data mining simulated triage expert system. The system is like a senior triage nursing person. What is really different is that it can, with periodical update, improve the system and education training, and will not be affected by emotions.