• Journal of Periodontal and Implant Science
• /
• 제48권2호
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• 대한융합한의학회지
• /
• 제6권1호
• /
• pp.37-42
• /
• 2024

Objectives: This study aims to evaluate the clinical validity of the system by conducting a clinical study to assess the diagnostic agreement between the system and Korean medical doctors. Methods: This study was conducted from September 7, 2023, to December 7, 2023, across five Korean medicine institutions, involving 100 adult participants aged 20-64 who consented to participate. Participants first entered their symptoms into a web-based program, which utilized an AI-based algorithm to diagnose 36 types of pattern differentiation. Subsequently, Korean medical doctors conducted face-to-face diagnoses using the same 36 types. The diagnostic agreement between the system and the doctors' diagnoses was analyzed using descriptive statistical analysis, and the results were expressed as a percentage agreement. Results: Analysis of the diagnostic data from 100 participants revealed that the web-based diagnosis support system identified an average of 7.76±0.79 patterns per patient, while Korean medical doctors identified an average of 7.99±0.10 patterns per patient. The diagnostic agreement between the system and the doctors showed an average of 7.08±1.08 patterns per patient, with an overall diagnostic agreement rate of 88.57±13.31%. Conclusion: This study developed a web-based diagnosis support system for traditional Korean medicine and evaluated its clinical validity by assessing diagnostic agreement. Comparing the diagnoses of the system with those of Korean medical doctors for 100 patients, the system showed an approximately 89% agreement rate with the clinical diagnoses. The system holds potential for aiding Korean medical doctors in pattern differentiation diagnosis in clinical practice.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2004년도 요약집 춘계학술발표대회
• /
• pp.221-221
• /
• 2004

• Clinical and Experimental Pediatrics
• /
• 제64권2호
• /
• pp.80-85
• /
• 2021

Background: Although identifying cases in large administrative databases may aid future research studies, previous reports demonstrated that the use of the International Classification of Diseases, Tenth Revision (ICD-10) code alone for diagnosis leads to disease misclassification. Purpose: We aimed to assess the value of the ICD-10 diagnostic code for identifying potential children with biliary atresia. Methods: Patients aged <18 years assigned the ICD-10 code of biliary atresia (Q44.2) between January 1996 and December 2016 at a quaternary care teaching hospital were identified. We also reviewed patients with other diagnoses of code-defined cirrhosis to identify more potential cases of biliary atresia. A proposed diagnostic algorithm was used to define ICD-10 code accuracy, sensitivity, and specificity. Results: We reviewed the medical records of 155 patients with ICD-10 code Q44.2 and 69 patients with other codes for biliary cirrhosis (K74.4, K74.5, K74.6). The accuracy for identifying definite/probable/possible biliary atresia cases was 80%, while the sensitivity was 88% (95% confidence interval [CI], 82%-93%). Three independent predictors were associated with algorithm-defined definite/probable/possible cases of biliary atresia: ICD-10 code Q44.2 (odds ratio [OR], 2.90; 95% CI, 1.09-7.71), history of pale stool (OR, 2.78; 95% CI, 1.18-6.60), and a presumed diagnosis of biliary atresia prior to referral to our hospital (OR, 17.49; 95% CI, 7.01-43.64). A significant interaction was noted between ICD-10 code Q44.2 and a history of pale stool (P<0.05). The area under the curve was 0.87 (95% CI, 0.84-0.89). Conclusion: ICD-10 code Q44.2 has an acceptable value for diagnosing biliary atresia. Incorporating clinical data improves the case identification. The use of this proposed diagnostic algorithm to examine data from administrative databases may facilitate appropriate health care allocation and aid future research investigations.

• 전기전자학회논문지
• /
• 제23권4호
• /
• pp.1157-1165
• /
• 2019

본 논문은 전류신호와 자속신호를 이용한 유도전동기 예방진단시스템을 개발하기 위한 머신러닝 알고리즘의 개발 및 적용 결과에 대하여 논하였다. 유도전동기의 결함 종류를 판별하기 위한 최적 특징추출단계를 통하여 총 29개의 특징을 도출하였다. 특히, 전류신호의 제7차 고조파 중심으로부터 사이드밴드까지의 주파수의 차이가 부하율 증가에 따라서 증가되는 경향을 이용하여 임의의 부하율 상태를 반영할 수 있는 알고리즘을 도출하였으며, KPCA 특징 축소 기법, k-NN 판단 알고리즘에 의한 분류 정확도를 조사한 결과, 약 84.6%의 분류 정확도를 보였다.

• 드라이브 ㆍ 컨트롤
• /
• 제15권4호
• /
• pp.30-38
• /
• 2018

Electronic control units (ECUs) are currently popular, and have evolved further towards the high-end application of autonomous vehicles in the automotive industry. Such digital technologies have also become widespread, in agriculture and construction equipment. Likewise, transmission control of high-speed tracked vehicles is based on the transmission control unit (TCU), performing complex gear change control functions, and diagnostic algorithms (a TCU's self-diagnostic and reporting capability of malfunction data through CAN communication). Since all functions of TCU are implemented by embedded-software, it is hardly possible to analyze specifications by reverse engineering. In this paper a real-time transmission simulator adaptable to TCU is presented, for analysis of diagnosis algorithm and standards. Signal simulation circuits are deliberately designed considering electrical characteristics of TCU inputs and various analysis tools, such as analog input auto scan function, and global output enable switch, are implemented in software. Test results from hardware-in-the-loop simulator verify tolerance time for each error, as well as cause of fault, error reset conditions.

• 한국정보통신학회논문지
• /
• 제16권11호
• /
• pp.2446-2452
• /
• 2012

국내외의 배출가스 규제 강화에 부합하기위하여, 사용자 의도에 따른 연료 분사시기와 분사량 조절이 가능한 커먼레일 ECU를 제어할 수 있는 알고리즘 개발의 필요에 따라서 본 논문에서는 커먼레일 엔진 전용 ECU에 적용할 수 있는 노킹 판별 및 엔진 밸런스 보정이 가능한 노킹 진단 알고리즘을 구현하여 시뮬레이터로 개발하였다. 또한 운전자가 직접 차량을 진단하는 운전자 중심의 진단 서비스를 제공하고자 시뮬레이터의 결과를 OBD-II 표준에 의거하는 차량 위주의 진단기로 개발하고자 한다. 이를 위해 자동차 고장진단 신호 및 센서 출력 신호를 송수신하는 유선 시스템과 무선 시스템인 블루투스 모듈을 이용하여 실시간 통신이 제공될 수 있는 OBD-II 진단기 S/W 설계방안을 제안함으로써 차량의 연비향상 및 유해가스 저감을 통한 엔진의 효율성 향상을 실현하도록 한다.

• Tribology and Lubricants
• /
• 제16권6호
• /
• pp.461-468
• /
• 2000

In this study, a neural network based diagnostic system of a rotating spindle system supported by ball bearings was introduced. In order to create actual failure situations, two exemplary abnormal status were made. Out of several possible data source locations, ten measurement spots were chosen. In order to discriminate multiple abnormal status, a neural network system was introduced using back propagation algorithm updating connecting weight between each nodes. In order to find the optimal structure of the neural network system reducing the information sources, magnitude of the weight of the network was referred. Hinton diagram was used to visually inspect the least sensitive weight connecting between input and hidden layers. Number of input node was reduced from 10 to 7 and prediction rate was increased to 100%.

• 대한의용생체공학회:의공학회지
• /
• 제13권1호
• /
• pp.69-78
• /
• 1992

This Paper describes implementation of a remote ECG diagnostic system using telephone line. The overall system includes ECG data acquisition system, ECG terminal, system control software, automatic diagnosis system, and transmission system.'The proposed system provides various functions, which are ECG data acquisition, transmission, receiving, diagnosis and dialogue between patients and medical doctors. Thls system is very simple and convienient to use. We evaluate the performance of modem and the accuracy of automatic diagnosis algorithm. The obtained results suggest the Possibilities of a remote ECG diagnostic system using the only existed telephone line.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 춘계학술대회 논문집
• /
• pp.639-642
• /
• 2000

Chemical facility system have dangerous elements that can injure the human like an explosion and a fire, gas poisoning by a leakage of the harmful chemical material. In addition to a vibration of the machine occurs the leakage. Therefore, the chemical factory requires for periodic monitoring of the vibration. But, until now, the operator has executed a monitoring of the machine by the senses. So, the diagnostic expert system by which the operator can judge easily and expertly a condition of the machine is developed. This paper describes the structure of diagnostic system and the diagnostic algorithm using fuzzy inference