• Journal of KIISE
• /
• v.45 no.1
• /
• pp.61-68
• /
• 2018

The identification of genes that contribute to the prediction of prognosis in patients with cancer is one of the challenges in providing appropriate therapies. To find the prognostic genes, several classification models using gene expression data have been proposed. However, the prediction accuracy of cancer prognosis is limited due to the heterogeneity of cancer. In this paper, we integrate microarray data with biological network data using a modified PageRank algorithm to identify prognostic genes. We also predict the prognosis of patients with 6 cancer types (including breast carcinoma) using the K-Nearest Neighbor algorithm. Before we apply the modified PageRank, we separate samples by K-Means clustering to address the heterogeneity of cancer. The proposed algorithm showed better performance than traditional algorithms for prognosis. We were also able to identify cluster-specific biological processes using GO enrichment analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.383-386
• /
• 2019

4 차산업혁명의 발달은 전 세계가 건강한 삶에 관련된 스마트시티 및 맞춤형 치료에 큰 관심을 갖게 하였고, 특히 기계학습 기술은 암을 극복하기 위한 유전체 기반의 정밀 의학 연구에 널리 활용되고 있어 암환자의 예후 예측 및 예후에 따른 맞춤형 치료 전략 수립 등을 가능케하였다. 하지만 암 예후 예측 연구에 주로 사용되는 유전자 발현량 데이터는 약 17,000 개의 유전자를 갖는 반면에 샘플의 수가 200 여개 밖에 없는 문제를 안고 있어, 예후 예측을 위한 신경망 모델의 일반화를 어렵게 한다. 이러한 문제를 해결하기 위해 본 연구에서는 고차원의 유전자 발현량 데이터를 신경망 모델이 효과적으로 학습할 수 있도록 2D 이미지로 표현하는 기법을 제안한다. 길이 17,000 인 1 차원 유전자 벡터를 64×64 크기의 2 차원 이미지로 사상하여 입력크기를 압축하였다. 2 차원 평면 상의 유전자 좌표를 구하기 위해 유전자 네트워크 데이터와 Node2Vec 이 활용되었고, 이미지 기반의 암 예후 예측을 수행하기 위해 합성곱 신경망 모델을 사용하였다. 제안하는 기법을 정확하게 평가하기 위해 이중 교차 검증 및 무작위 탐색 기법으로 모델 선택 및 평가 작업을 수행하였고, 그 결과로 베이스라인 모델인 고차원의 유전자 벡터를 입력 받는 다층 퍼셉트론 모델보다 더 높은 예측 정확도를 보여주는 것을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.297-299
• /
• 2022

Malignant glioma has a poor prognosis with the reported median survival of between 6 months to 14 months. Thus, it is crucial to predict the accurate survival of patients with malignant glioma. In this paper, we propose a convolutional neural network to predict the overall survival and age of the patients. A total of four MRI modalities, T1, T1-contrast enhanced, T2, and fluid-attenuated inversion recovery, which effectively capture spatial characteristics of malignant glioma, were used as input images. Age is an important factor impacting the overall survival, thus incorporating it into the model will thereby improve the performance of the proposed model. Our model successfully predicted overall survival and age of the patients with pearson correlation coefficients of 0.1748 and 0.3056, respectively.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.2
• /
• pp.137-147
• /
• 2015

This study proposes an algorithm for predicting breast cancer prognosis based on genetic network. We identify prognosis-specific network using gene expression data and PPI(protein-protein interaction) data. To acquire the network, we calculate Pearson's correlation coefficient(PCC) between genes in all PPI pairs using gene expression data. We develop a prediction model for breast cancer patients with estrogen-receptor-negative using the network as a classifier. We compare classification performance of our algorithm with existing algorithms on independent data and shows our algorithm is improved. In addition, we make an functionality analysis on the genes in the prognosis-specific network using GO(Gene Ontology) enrichment validation.

• Korean Journal of Clinical Laboratory Science
• /
• v.50 no.2
• /
• pp.126-135
• /
• 2018

This study examined whether the difference in the middle cerebral artery (MCA) velocities can predict the prognosis of stroke and whether the prognostic impact differs among stroke subtypes. Transient ischemic attack (TIA) or acute ischemic stroke patients, who underwent a routine evaluation and transcranial Doppler (TCD), were included in this study. The MCA asymmetry index was calculated using the relative percentage difference in the mean flow velocity (MFV) between the left and right MCA: (|RMCA MFV-LMCA MFV|/mean MCA MFV)${\times}100$. The stroke subtypes were determined using the TOAST classification. Poor functional outcomes were defined as a mRS score ${\geq}3$ at 3 months after the onset of stroke. A total of 988 patients were included, of whom 157 (15.9%) had a poor functional outcome. Multivariable analysis showed that only the MCA asymmetry index was independently associated with a poor functional outcome. ROC curve analysis showed that adding the MCA asymmetry index to the prediction model improved the discrimination of a poor functional outcome from acute ischemic stroke (from 88.6% [95% CI, 85.2~91.9] to 89.2% [95% CI, 85.9~92.5]). The MCA asymmetry index has an independent prognostic value for predicting a poor short-term functional outcome after an acute cerebral infarction. Therefore, TCD may be useful for predicting a poor functional outcome in patients with acute ischemic stroke.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.701-710
• /
• 2012

Retinitis Pigmentosa(RP) is a common hereditary disease. While they have been normally living, those who have this symptom feel frustration and pain by the damage of visual acuity. At the national level, the loss of the economic activity due to the reduction of economically active population will be also greater. There is an urgent need for the base study that can provide the clinical prognosis information of RP disease. In this study, we suggest that it is possible to predict prognosis through the pattern classification of RP data. Statistical processing results through statistical software like SPSS(Statistical Package for the Social Service) were mainly applied for the conventional study in data analysis. However, machine learning and automatic pattern classification was applied to this study. SVM(Support Vector Machine) and other various pattern classifiers were used for it. The proposed method confirmed the possibility of prognostic prediction based on the result of automatically classified RP data by SVM classifier.

• Journal of the Korean Child Neurology Society
• /
• v.26 no.4
• /
• pp.240-245
• /
• 2018

Purpose: Early prediction of prognosis of children resuscitated from cardiac arrest is a major challenge. We investigated the utility of electroencephalography (EEG) and laboratory studies for predicting of neurologic outcome in children resuscitated from cardiac arrest. Methods: We retrospectively analyzed medical records of patients who were resuscitated from cardiac arrest from 2006 to 2015 at the Gil Medical Center. Patients aged one month to 18 years were included. EEG analysis included background scoring, reactivity and seizure burden. EEG background was classified score 0 (normal/organized), score 1 (slow and disorganized), score 2 (discontinuous or burst suppression), and score 3 (suppressed and featureless). Neurologic outcome was evaluated by Pediatric Cerebral Performance Category (PCPC) at least 6 months after cardiac arrest. Results: Total 26 patients were evaluated. Nine patients showed good neurologic outcome (PCPC 1, 2, 3) and 17 patients showed poor neurologic outcome (PCPC 4, 5, 6). Patients of poor neurologic outcome group showed EEG background score 3 in 88.2%, whereas 44.4% in patients of good neurologic outcome group (P=0.028). Electrographic ictal discharges except non-convulsive status epilepticus were presented in 44.4% of good neurologic outcome group and 5.9% of poor neurologic outcome group (P=0.034). Ammonia and lactate levels were higher and pH levels were lower in poor outcome group than good neurologic outcome group. Conclusion: Suppressed and featureless EEG background is associated with poor neurologic outcome and electrographic seizures are associated with good neurologic outcome.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.11 no.sup2
• /
• pp.50-58
• /
• 2008

Acute liver failure is a devastating disease in children. Most cases of acute liver failure in children are indeterminate; however, metabolic liver disease is one of the main causes in the pediatric age group. Though a major symptom of acute liver failure is hepatic encephalopathy, this is very difficult to diagnose, particularly in younger children. Liver transplantation has improved the chances of survival dramatically; however, it is not known which patients are ideal candidates for liver transplantation. Because patients may deteriorate rapidly, arranging care in a center with expertise will secure the best possible outcomes.

• Journal of Oral Medicine and Pain
• /
• v.19 no.2
• /
• pp.111-123
• /
• 1994

저자는 1990년부터 1993년 사이에 부산대학병원 구강내과에 내원하여 두 개하악장애로 진단되어 보존적 치료를 시행받은 884명의 환자를 대상으로 Solberg의 악관절장애조사 설문지를 작성케한 후, 성, 연령, 병력기간, 진단명, SCL-90-R, 치료에 대한 반응에 따라 환자군을 세분하여 각 환자군의 설문지 문항별 응답양태 및 이에 따른 예후예측을 분석한 바 다음과 같은 결론을 얻었다. 1. 악기능 및 예후악화요인 문항에서는 여성이 높은 응답수를 보인 반면, 기여요인 및 습관문항에 서는 남성이 높은 응답수를 나타내었다. 2. 고령층의 환자에서 행동 및 예후악화요인이 두드러졌다. 3. 만성군이 급성군에 비해 전 문항에서 높은 응답수를 나타내었다. 4. 혼합군 및 근육장애혼자가 관절장애환자에 비해 설문지 전 문항에서 많은 응답을 하였다. 5. SCL-90-R에서 비정상인 환자가 정상군의 환자에 비해 악기능을 제외한 전 문항에서 높은 응답수를 보였다. 6. 치료에 무반응인 환자가 성공한 환자에 비해 습관요인 문항을 제외한 설문지 전체에서 많은 응답을 하였다.