• 대한간호학회지
• /
• 제22권4호
• /
• pp.589-603
• /
• 1992

This study investigated a process to estimate the need for nursing staff on the basis of a patient elassification system and the required care needs and activities. The investigation was carried out in the following four steps. Step 1. Patients were classified according to the amount of nursing care need on each shift as class I (mildly ill), class II (mederately ill), class III (acutely ill), and class IV (critically ill). Step 2. Measurement of the direct nursing care hours needed for each patient class, and measurement of indirect nursing care hourse and personal time of the nursing staff. Step 3. Calculation of he total nursing workload in a nursing unit. Step 4. Estimation of the nursing staff needed. The investigation was carried out from July 17th to 30th, during 24hours every other day. The subjects were the patients and the nursing staff on two units of Seoul National University Hospital, Korea. Some of the results from the investigation are as follows : 1) Distribution of patient classification On the neuro surgical (N.S.), the distribution was class I, 22 patient, 3, class II, 27 patients, class III, 26 patients, and class IV, 25 patients, For the orthopedic surgical unit(0.5.), it was class I, 43 patients, class II, 43 patients, class III, patients, and class IV, 3 patients. 2) Direct nursing care hours per day On the N.S. unit, 3.2 hours of direct nursing care were needed for class I, 3.9 hours for class II, 5.1 hours of class III, and 6.2 hours for class IV patients, while 2.0 hours for class I, 2.5 hours for class II, 3.5 hours for class III, 5.0 hours class IV patients were needed on the 0.5. units. 3) Analysis of direct nursing care activities Activities were classified into assessment and observation(47%), medication(38.7%), communiontion(5.1%), exercise(2.4%), elimination and irrigation(1.3%), treatmemt(1.1%), hygiene(0.8%), nutrition(0.8%), and hot and cold compress(0.1%). 4) Average hours of indirect nursing care per day. On the N.S. unit 4.2 hours, and on the O.S. unit, 3.5 hours of RN indirect care was needed. 5) The average personal time used by the of nursing staff was 17 minutes for both RNs and nursing assistants in the N.S. unit, and 32 minutes for both RNs and nursing assistants in the O.S. unit. 6) Estimation of nursing staff needed on two specialized units of a university hospital For the N.S. nursing unit of 43 beds, 31 nursing staff would be indicated. For the 0.5. nursing unit of the same number of beds, 19 nursing staff would be indicated.

• 해양환경안전학회지
• /
• 제24권2호
• /
• pp.146-156
• /
• 2018

선박 해도시스템은 기존의 종이해도 사용에서 ECDIS을 이용한 전자해도의 사용으로 변화하였다. 선박 항해장비의 자동화, 통합화, 디지털화를 위해서 전자해도의 등장은 필수적이지만 새로운 시스템이 해상에 도입되는 과도기적인 상황에서 예상치 못한 다양한 문제가 발생하면서 항해 안전에 큰 위협이 되고 있다. 이 논문에서는 ECDIS가 새로운 항해 장비로서 본래의 목적에 따라 선박의 안전 항해에 기여하고 있는지를 분석하기 위해서 선박에서 ECDIS를 사용했던 항해사들을 대상으로 ECDIS 사용전과 후에 대한 사용성 평가를 실시하고 대응표본 t 검증하였다. 그 결과, 업무 간소화와 비용 감소에 대한 효율성이 ECDIS 사용 후 더욱 저하된 것으로 유의미하게 분석되었다. 사용자 지침인 IMO 'MSC.1/Circ.1503 ECDIS - Guidance for good practice'를 분석하여 S/W 유지보수, ECDIS 이상현상, RCDS와 ECDIS의 차이, ECDIS 상의 다양한 정보 중첩으로 인한 식별성 저하 등이 선박 안전에 미치는 영향을 고찰하였다. 또한 식별된 이상현상을 특성 별로 분류하고 그에 맞는 개선 방안에 대해 제안하였다. 사용성 평가에서 효율성 저하의 원인은 ECDIS의 문제를 시스템적으로 해결하지 않고 사용자에게 주의를 환기시키는 것으로만 해결하려고 했기 때문으로 분석되며, 우선적으로 ECDIS의 최신 S/W 유지, 전 세계 해역을 포함하는 신뢰성 있는 ENC 발행, S-mode 개발과 같은 정보 식별성 향상이 문제 해결에 필요하다.

• Korean Journal of Radiology
• /
• 제21권7호
• /
• pp.869-879
• /
• 2020

Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, and output structured reports from computed tomography (CT) images. Materials and Methods: This study included 1079 patients (median age, 55 years; men, 718) from three hospitals, between January 2011 and January 2019, who were divided into a monocentric training set (n = 876; median age, 55 years; men, 582), five multicenter/multiparameter validation sets (n = 173; median age, 59 years; men, 118) with different slice thicknesses and image pixels, and a normal control set (n = 30; median age, 53 years; men, 18). Three classifications (fresh, healing, and old fracture) combined with fracture location (corresponding CT layers) were detected automatically and delivered in a structured report. Precision, recall, and F1-score were selected as metrics to measure the optimum CNN model. Detection/diagnosis time, precision, and sensitivity were employed to compare the diagnostic efficiency of the structured report and that of experienced radiologists. Results: A total of 25054 annotations (fresh fracture, 10089; healing fracture, 10922; old fracture, 4043) were labelled for training (18584) and validation (6470). The detection efficiency was higher for fresh fractures and healing fractures than for old fractures (F1-scores, 0.849, 0.856, 0.770, respectively, p = 0.023 for each), and the robustness of the model was good in the five multicenter/multiparameter validation sets (all mean F1-scores > 0.8 except validation set 5 [512 x 512 pixels; F1-score = 0.757]). The precision of the five radiologists improved from 80.3% to 91.1%, and the sensitivity increased from 62.4% to 86.3% with artificial intelligence-assisted diagnosis. On average, the diagnosis time of the radiologists was reduced by 73.9 seconds. Conclusion: Our CNN model for automatic rib fracture detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists' workload.