• Asian Pacific Journal of Cancer Prevention
• /
• 제15권13호
• /
• pp.5123-5126
• /
• 2014

Background: To evaluate the diagnostic performance of IOTA simple rules in differentiating between benign and malignant ovarian tumors. Materials and Methods: A study of diagnostic performance was conducted on women scheduled for elective surgery due to ovarian masses between March 2007 and March 2012. All patients underwent ultrasound examination for IOTA simple rules within 24 hours of surgery. All examinations were performed by the authors, who had no any clinical information of the patients, to differentiate between benign and malignant adnexal masses using IOTA simple rules. Gold standard diagnosis was based on pathological or operative findings. Results: A total of 398 adnexal masses, in 376 women, were available for analysis. Of them, the IOTA simple rules could be applied in 319 (80.1%) including 212 (66.5%) benign tumors and 107 (33.6%) malignant tumors. The simple rules yielded inconclusive results in 79 (19.9%) masses. In the 319 masses for which the IOTA simple rules could be applied, sensitivity was 82.9% and specificity 95.3%. Conclusions: The IOTA simple rules have high diagnostic performance in differentiating between benign and malignant adnexal masses. Nevertheless, inconclusive results are relatively common.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권9호
• /
• pp.3835-3838
• /
• 2015

Objective: To evaluate the diagnostic performance of IOTA simple rules in predicting malignant adnexal tumors by non-expert examiners. Materials and Methods: Five obstetric/gynecologic residents, who had never performed gynecologic ultrasound examination by themselves before, were trained for IOTA simple rules by an experienced examiner. One trained resident performed ultrasound examinations including IOTA simple rules on 100 women, who were scheduled for surgery due to ovarian masses, within 24 hours of surgery. The gold standard diagnosis was based on pathological or operative findings. The five-trained residents performed IOTA simple rules on 30 patients for evaluation of inter-observer variability. Results: A total of 100 patients underwent ultrasound examination for the IOTA simple rules. Of them, IOTA simple rules could be applied in 94 (94%) masses including 71 (71.0%) benign masses and 29 (29.0%) malignant masses. The diagnostic performance of IOTA simple rules showed sensitivity of 89.3% (95%CI, 77.8%; 100.7%), specificity 83.3% (95%CI, 74.3%; 92.3%). Inter-observer variability was analyzed using Cohen's kappa coefficient. Kappa indices of the four pairs of raters are 0.713-0.884 (0.722, 0.827, 0.713, and 0.884). Conclusions: IOTA simple rules have high diagnostic performance in discriminating adnexal masses even when are applied by non-expert sonographers, though a training course may be required. Nevertheless, they should be further tested by a greater number of general practitioners before widely use.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권9호
• /
• pp.4377-4380
• /
• 2016

Background: To compare diagnostic performance in differentiating benign from malignant ovarian masses between IOTA (the International Ovarian Tumor Analysis) simple rules and subjective sonographic assessment. Materials and Methods: Women scheduled for elective surgery because of ovarian masses were recruited into the study and underwent ultrasound examination within 24 hours of surgery to apply the IOTA simple rules by general gynecologists and to record video clips for subjective assessment by an experienced sonographer. The diagnostic performance of the IOTA rules and subjective assessment for differentiation between benign and malignant masses was compared. The gold standard diagnosis was pathological or operative findings. Results: A total of 150 ovarian masses were covered, comprising 105 (70%) benign and 45 (30%) malignant. Of them, the IOTA simple rules could be applied in 119 (79.3%) and were inconclusive in 31 (20.7%) whereas subjective assessment could be applied in all cases (100%). The sensitivity and the specificity of the IOTA simple rules and subjective assessment were not significantly different, 82.9% vs 86.7% and 94.0% vs 94.3% respectively. The agreement of the two methods in prediction was high with a Kappa index of 0.835. Conclusions: Both techniques had a high diagnostic performance in differentiation between benign and malignant ovarian masses but the IOTA rules had a relatively high rate of inconclusive results. The IOTA rules can be used as an effective screening technique by general gynecologists but when the results are inconclusive they should consult experienced sonographers.

• 산학경영연구
• /
• 제5권
• /
• pp.295-326
• /
• 1992

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.387-394
• /
• 1995

With respect to the effectiveness of types of knowledge on human diagnostic performance, the results of several experiments claimed that training with diagnostic rules (procedural knowledge) is more effective than training that provides theoretical knowledge (principle knowledge). However, we usually have the idea that understanding the principles of system dynamics is necessary for diagnosis in some situations. In this study, we pointed out some problems in the previous experiments that force to reinterpret their experimental conclusions. Accordingly, we conducted an experiment to reinvestigate the value of theoretical knowledge in two problem situations. A simulator system, which is named DLD, that is to diagnose an electronic device was created for this purpose. It is a context-free digital logic circuit which includes forty-one gates of three basic types. Our experiment investigated the marginal effects of theoretical knowledge over common diagnostic rules. The experimental results showed that the effectiveness of the instruction in theoretical knowledge is dependent on the complexity of diagnostic situations. This adds up an experimental evidence against the presumed ineffectiveness of theoretical knowledge and forward reasoning in fault diagnosis. Furthermore, the result suggests the source of the use of theoretical knowledge.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권11호
• /
• pp.515-524
• /
• 2017

본 논문에서는 ADHD 진단을 해주는 전문가시스템을 설계 및 구현한다. DSM-IV-TR을 이용하여 ADHD 진단기준을 연령대에 따라 단어를 바꾸어 구체화한다. 이 진단지를 가지고 오브젝트와 해당 값을 설정하고 규칙을 생성한다. 그리고 'ADHD 진단 시스템 엔진'과 '사용자 질의응답 프로그램'으로 구성된 진단시스템을 설계한다. 'ADHD 진단 시스템 엔진'은 규칙 기반 추론 엔진으로 Prolog 언어로 구현하여, INPUT을 '사용자 질의응답 프로그램'으로부터 받는다. INPUT에 의해 규칙은 ADHD 진단기준을 기반으로 점화되며 진단결과를 추론해서 OUTPUT을 다시 '사용자 질의응답 프로그램'으로 보낸다. '사용자 질의응답 프로그램'은 Python 언어로 구현하여 사용자와의 대화를 처리하는 인터페이스 역할을 한다. 'ADHD 진단 시스템 엔진'과 '사용자 질의응답 프로그램'의 중간다리 역할을 Pyswip 라이브러리를 통해서 수행한다. 결과적으로 ADHD 진단 전문가시스템을 통해 진단비용 절감과 간편한 이용으로 치료계획에 도움을 주고자한다.

• Tuberculosis and Respiratory Diseases
• /
• 제64권4호
• /
• pp.266-271
• /
• 2008

연구배경: 급성 폐색전증의 발생을 예측하는 Wells 및 Geneva 예측 모형은 서구에서 잘 확립되어 있다. 폐색전증의 역학이 서구와 다를 것으로 보이는 국내에서의 예측모형의 유용성에 대해서 평가 하고자 한다. 방법: 단일 의료기관에서 폐색전증 의심 하에 multi-detector computed tomography (MDCT)를 시행한 환자 210명을 대상으로 후향적으로 조사하였다. 성별 구성은 남자 90명(42.9%), 여자 120명(57.1%)이었고, 평균 연령은 $63.3{\pm}15.9$세였다. 의무기록을 바탕으로 Wells 및 개정된 Geneva 예측 모형으로 폐색전증의 가능성에 대해 저위험군, 중등도 위험군, 고위험군으로 분류하였다. 결과: 폐색전증으로 진단된 환자는 210명 중 41명(19.5%)이었다. Wells 예측 모형을 적용한 폐색전증 발병 가능성 평가에서는, 2명(1%)이 저위험군, 137명(62.5%)이 중등도 위험군, 71명(3.8%)이 고위험군으로 분류되었고, 각 군에서 폐색전증의 발생률은 10%, 18.2%, 19.7%였다. 개정된 Geneva 예측 모형을 적용할 경우 44명(21%)이 저위험군, 160명(76.2%)이 중등도 위험군, 6명(2.8%)이 고위험군으로 분류되었고, 각 군에서 폐색전증의 발생률은 4.5%, 2.5%, 50%로 나타났다. Receiver operating characteristic (ROC) 곡선 분석에서 개정된 Geneva 예측 모형이 Wells 예측 모형에 비해 정확도가 높았다. 두 예측 모형 사이의 일치율은 불량했다($\kappa$ coefficient=0.06). 결론: 본 연구에서는 폐색전증이 의심되는 환자에서 개정된 Geneva 예측모형과 Wells 예측 모형으로 평가하여 두 모형 사이에 일치율이 불량하였으며, 개정된 Geneva 모형이 Wells 모형에 비해 폐색전증 진단 예측이 더 정확하였다.

• 지능정보연구
• /
• 제4권1호
• /
• pp.115-131
• /
• 1998

Customer service process is one of the most important processes in today's competitive business environment. Among the various activities of customer service process, equipment malfunction diagnosis activity should be performed fast and accurately. When a customer calls the service center and reports the observed symptoms, he/she describes them in layman's terms. Therefore, the customer-reported symptoms have not been considered helpful information for service representatives. However, in order to perform diagnosis activity fast and accurately, we need to make use of the customer-reported symptoms actively. In this research, we developed three systems called R-EMD (Rule-based Equipment Malfunction Diagnostic system), C-EMD (Case-based Equipment Malfunction Diagnostic system) and R&C-EMD (Rule & Case-based Equipment Malfunction Diagnostic system), each of which diagnoses equipment malfunctions using the customer-reported symptoms. R&C-EMD is a hybrid system that utilizes both rule-based and case-based technologies. The diagnosis rules used in R&C-EMD and R-EMD were not acquired from service manuals or interviews with service representatives. Rater, we extracted them directly from the past diagnosis cases based on symptoms' frequencies. By this way, we were able to overcome the knowledge acquisition bottleneck. Using the real 100 malfunction diagnosis cases, we evaluated the performances of R&C-EMC, R-EMD and C-EMD in terms of speed and accuracy. In diagnosis time, R&C-EMD took longer than R-EMD and shorter than C-EMD. However, R&C-EMC was the best in accuracy.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제9권3호
• /
• pp.63-71
• /
• 2001

This paper presents a model-based method for detecting and diagnosing some faults in the cooling tower of healing, ventilating, and air-conditioning systems. A simple model for the cooling tower is employed. Faults in cooling tower operation are detected through the deviations in the values of system characteristic parameters such as the heat transfer coefficient-area product, the tower approach, the tower effectiveness, and fan power. Three distinct faults are considered: cooling tower inlet water temperature sensor fault, cooling tower pump fault, and cooling tower fan fault. As a result, most values of the system characteristics parameter variations due to a fault are much higher or lower than the values without faults. This allows the faults in a cooling tower to be detected easily using above methods. The diagnostic rules for the faults were also developed through investigating the changes in the different parameter due to each faults.

• International Journal of Contents
• /
• 제5권3호
• /
• pp.65-70
• /
• 2009

This paper describes ongoing work on the correction of adverb errors committed by Korean learners studying English as a foreign language (EFL), using an automated English writing assessment system. Adverb errors are commonly found in learners 'writings, but handling those errors rarely draws an attention in natural language processing due to complicated characteristics of adverb. To correctly detect the errors, adverbs are classified according to their grammatical functions, meanings and positions within a sentence. Adverb errors are collected from learners' sentences, and classified into five categories adopting a traditional error analysis. The error classification in conjunction with the adverb categorization is implemented into a set of mal-rules which automatically identifies the errors. When an error is detected, the system corrects the error and suggests error specific feedback. The feedback includes the types of errors, a corrected string of the error and a brief description of the error. This attempt suggests how to improve adverb error correction method as well as to provide richer diagnostic feedback to the learners.