• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.317-320
• /
• 2021

본 연구는 주기적인 알츠하이머 병의 중증도 모니터링을 위해 스마트 인솔을 통한 보행 특징 추출과 머신러닝 기반 중증도 분류의 성능에 대해 살펴보았다. 최근 고령화가 가속화되는 추세에 있어 치매 환자가 급증하고 있으며, 중증도가 심해질수록 필요한 치료 비용 및 노력이 급증하기 때문에 조기 진단이 최선의 치료 전략으로 보여진다. 환자 친화적이고 저비용의 관성 측정 장치가 내장된 스마트 인솔만을 사용하여 다양한 보행 실험 패러다임에서 환자의 보행 특징을 추출하고, 이를 알츠하이머 병의 중증도 진단을 위한 머신러닝 기반 분류기를 훈련시켜 성능을 평가한 결과, 숫자세기와 같이 뇌에 부하를 주는 하위 작업이 포함된 복합 보행을 측정한 데이터셋을 사용하여 훈련된 분류 모델이 일반 걷기 데이터셋을 사용한 모델보다 성능이 높게 나타나는 것이 관찰되었다. 본 연구는 안전하고 환경적 제약이 적은 방법을 사용하여 시기 적절한 진단뿐만 아니라 주기적인 중증도 모니터링 시스템의 일환으로 활용될 수 있을 것이다.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.217-230
• /
• 2019

This study was conducted to develop a customized severity-adjustment method and to evaluate their validity for acute myocardial infarction(AMI) patients to complement the limitations of the existing severity-adjustment method for comorbidities. For this purpose, the subjects of KCD-7 code I20.0 ~ I20.9, which is the main diagnosis of acute myocardial infarction were extracted using the Korean National Hospital Discharge In-depth Injury survey data from 2006 to 2015. Three tools were used for severity-adjustment method of comorbidities : CCI (charlson comorbidity index), ECI (Elixhauser comorbidity index) and the newly proposed CCS (Clinical Classification Software). The results showed that CCS was the best tool for the severity correction, and that support vector machine model was the most predictable. Therefore, we propose the use of the customized method of severity correction and machine learning techniques from this study for the future research on severity adjustment such as assessment of results of medical service.

• Phonetics and Speech Sciences
• /
• v.13 no.2
• /
• pp.57-66
• /
• 2021

This study focuses on the issue of automatic severity classification of dysarthric speakers based on speech intelligibility. Speech intelligibility is a complex measure that is affected by the features of multiple speech dimensions. However, most previous studies are restricted to using features from a single speech dimension. To effectively capture the characteristics of the speech disorder, we extracted features of multiple speech dimensions: voice quality, prosody, and pronunciation. Voice quality consists of jitter, shimmer, Harmonic to Noise Ratio (HNR), number of voice breaks, and degree of voice breaks. Prosody includes speech rate (total duration, speech duration, speaking rate, articulation rate), pitch (F0 mean/std/min/max/med/25quartile/75 quartile), and rhythm (%V, deltas, Varcos, rPVIs, nPVIs). Pronunciation contains Percentage of Correct Phonemes (Percentage of Correct Consonants/Vowels/Total phonemes) and degree of vowel distortion (Vowel Space Area, Formant Centralized Ratio, Vowel Articulatory Index, F2-Ratio). Experiments were conducted using various feature combinations. The experimental results indicate that using features from all three speech dimensions gives the best result, with a 80.15 F1-score, compared to using features from just one or two speech dimensions. The result implies voice quality, prosody, and pronunciation features should all be considered in automatic severity classification of dysarthria.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.423-431
• /
• 2023

The purpose of this study is to analyze the factors affecting the classification of the severity of contrast media side effects based on the patient's body information using artificial intelligence techniques to be used as basic data to reduce the degree of contrast medium side effects. The data used in this study were 606 examiners who had no contrast medium side effects in the past history survey among 1,235 cases of contrast medium side effects among 58,000 CT scans performed at a general hospital in Seoul. The total data is 606, of which 70% was used as a training set and the remaining 30% was used as a test set for validation. Age, BMI(Body Mass Index), GFR(Glomerular Filtration Rate), BUN(Blood Urea Nitrogen), GGT(Gamma Glutamyl Transgerase), AST(Aspartate Amino Transferase,), and ALT(Alanine Amiono Transferase) features were used as independent variables, and contrast media severity was used as a target variable. AUC(Area under curve), CA(Classification Accuracy), F1, Precision, and Recall were identified through AdaBoost, Tree, Neural network, SVM, and Random foest algorithm. AdaBoost and Random Forest show the highest evaluation index in the classification prediction algorithm. The largest factors in the predictions of all models were GFR, BMI, and GGT. It was found that the difference in the amount of contrast media injected according to renal filtration function and obesity, and the presence or absence of metabolic syndrome affected the severity of contrast medium side effects.

• Proceedings of the KAIS Fall Conference
• /
• 2012.05a
• /
• pp.22-24
• /
• 2012

The tools that classify the severity of patients based on the prediction of mortality include APACHE, SAPS, and MPM. Theses tools rely crucially on the evaluation of patients' general clinical status on the first date of their admission to ICU. Nursing activities are one of the most crucial factors influencing on the quality of treatment that patients receive and one of the contributing factors for their prognosis and safety. The purpose of this study was to identify the goodness-of-fit of CPSCS of critical patient severity classification system(CPSCS) and Glasgow coma scale(GCS) and the clinical usefulness of its death rate prediction. Data were collected from the medical records of 187 neurological patients who were admitted to the ICU of C University Hospital. The data were analyzed through $x^2$ test, t-test, Mann-Whitney, Kruskal-Wallis, goodness-of-fit test, and ROC curve. In accordance with patients' general and clinical characteristics, patient mortality turned out to be statistically different depending on ICU stay, endotracheal intubation, central venous catheter, and severity by CPSCS. Homer-Lemeshow goodness-of-fit tests were CPSCS and GCS and the results of the discrimination test using the ROC curve were $CPSCS_0$, .734, $GCS_0$,.583, $CPSCS_{24}$,.734, $GCS_{24}$, .612, $CPSCS_{48}$,.591, $GCS_{48}$,.646, $CPSCS_{72}$,.622, and $GCS_{72}$,.623. Logistic regression analysis showed that each point on the CPSCS score signifies1.034 higher likelihood of dying. Applied to neurologically ill patients, early CPSCS scores can be regarded as a useful tool.

• Journal of Trauma and Injury
• /
• v.22 no.1
• /
• pp.29-36
• /
• 2009

Purpose: The purpose of this study was to analyze the characteristics and severity of wrist injuries in snowboarding. Methods: December 2005 to February 2008, Snowboarders who experienced wrist injures were included in this study. On the basis of the medical records and radiographic evaluation, the severity of distal radius fracture was classified according to the Arbeitsgemeinschaft fur Osteosynthesefragen/Association for the Study of Internal Fixation (AO/ASIF) classification. Results: Most of the injured snowboarders were a either of the beginner (35 cases, 46.1%) or the intermediate (27 cases, 35.5%) level. The most common cause of injury in snowboarding was a slip down (60 cases, 78.9%). Comminuted and articular fractures classified as AO types A3, B, and C, which required surgical reduction, made up 42.3% of the distal radial fractures in snowboarders. When we analyzed the differences in severity between the educated and the non-educated groups, an A2 type injury in the AO classification was the most common type of injury in the educated group (20 cases, 38.5%), it means less severe fractures ocurred in the educated group (p=0.045). The most frequent injury mechanism of fractures was slip down (48 cases, 63.2%), and a slip down backwards was the dominant type of slip down (36 cases, 75.0%) (p=0.031). Conclusion: Among the snowboarders in this study who suffered self-down injury to the wrist, more fractures were associated with a backwards slip down than with a forward slip down due to over extension. For educated snowboarders the severity of fracture was lower than it was for uneducated snowboarders.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2012.04a
• /
• pp.190-193
• /
• 2012

The tools that classify the severity of patients based on the prediction of mortality include APACHE, SAPS, and MPM. Theses tools rely crucially on the evaluation of patients' general clinical status on the first date of their admission to ICU. Nursing activities are one of the most crucial factors influencing on the quality of treatment that patients receive and one of the contributing factors for their prognosis and safety. The purpose of this study was to identify the goodness-of-fit of CPSCS of critical patient severity classification system(CPSCS) and Glasgow coma scale(GCS) and the clinical usefulness of its death rate prediction. Data were collected from the medical records of 187 neurological patients who were admitted to the ICU of C University Hospital. The data were analyzed through $x^2$ test, t-test, Mann-Whitney, Kruskal-Wallis, goodness-of-fit test, and ROC curve. In accordance with patients' general and clinical characteristics, patient mortality turned out to be statistically different depending on ICU stay, endotracheal intubation, central venous catheter, and severity by CPSCS. Homer-Lemeshow goodness-of-fit tests were CPSCS and GCS and the results of the discrimination test using the ROC curve were $CPSCS_0$,.734, $GCS_0$,.583, $CPSCS_{24}$,.734, $GCS_{24}$,.612, $CPSCS_{48}$,.591, $GCS_{48}$,.646, $CPSCS_{72}$,.622, and $GCS_{72}$,.623. Logistic regression analysis showed that each point on the CPSCS score signifies1.034 higher likelihood of dying. Applied to neurologically ill patients, early CPSCS scores can be regarded as a useful tool.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.113-119
• /
• 2022

In software fault prediction, a multi classification model that predicts the fault severity category of a module can be much more useful than a binary classification model that simply predicts the presence or absence of faults. A small number of severity-based fault prediction models have been proposed, but no classifier using deep learning techniques has been proposed. In this paper, we construct MLP models with 3 or 5 hidden layers, and they have a structure with a fixed or variable number of hidden layer nodes. As a result of the model evaluation experiment, MLP-based deep learning models shows significantly better performance in both Accuracy and AUC than MLPs, which showed the best performance among models that did not use deep learning. In particular, the model structure with 3 hidden layers, 32 batch size, and 64 nodes shows the best performance.

• The Journal of the Korean dental association
• /
• v.57 no.12
• /
• pp.758-767
• /
• 2019

The classification of periodontal disease in 1999 has been widely used for determining a diagnosis, establishing a treatment plan, and evaluating the prognosis of the patient with periodontal disease. However, scientific evidence from many studies indicates the need for a new classification system for periodontal and peri-implant disease. Summary at 2017 world workshop as follows: 1) Periodontal health and peri-implant health was defined; 2) Chronic periodontitis and aggressive periodontitis were unified as periodontitis; 3) Periodontitis was further classified by staging and grading to reflect disease severity and management complexity, rate of disease progression, respectively; 4) Periodontal disease as manifestation of systemic disease is based on the International Statistical Classification of Diseases and Related Health Problems-10 (ICD-10) code; 5) Periodontal biotype and biologic width was replaced to periodontal phenotype and supracrestal tissue attachment, respectively; 6) The excessive occlusal force was replaced by a traumatic occlusal force; 7) ≥3 mm of radiographic bone loss, ≥6 mm of pocket probing depth and bleeding on probing indicates peri-implantitis in the absence of radiograph at final prosthesis delivery.

• Korean Journal of Bronchoesophagology
• /
• v.17 no.2
• /
• pp.104-107
• /
• 2011

Background and Objectives Scope classification is designed to classify acute epiglottitis according to laryngoscopic findings. There is no report about the utility of classification; the difference between the diagnosis and the prognosis by the Scope classification was not found. The aim of this study was to evaluate the utility of Scope classification in patients with acute epiglottitis. Subject and Method 127 patients who had been admitted to our hospital were diagnosed with acute epiglottitis. The patients were classified by the Scope classification. We compared demographic characteristics, clinical symptoms and signs, laboratory findings, and clinical course among the patient groups and divided the results according to the Scope classification. Results There are no significant differences among the groups in demographic characteristics, clinical symptoms and signs, laboratory findings, and clinical course. Conclusion The Scope classification of acute epiglottitis does not seem to be a method to evaluate the severity of acute epiglottitis. Thus, we need to develop multidisciplinary approaches for acute epiglottitis.