• Journal of Yeungnam Medical Science
• /
• 제37권4호
• /
• pp.332-336
• /
• 2020

Homozygous mutations in NUDT15 R139C are known as the major factor associated with thiopurine-induced early leukopenia, particularly in Asian patients. Therefore, NUDT15 genotyping is currently recommended before thiopurine treatment to identify patients who are NUDT15 poor metabolizers and consider the use of an alternative immunomodulatory therapy. We report a case of a 12-year-old Korean girl with Crohn's disease (CD), in whom thiopurine-induced leukopenia was prevented by initiation of azathioprine (AZA) therapy at a low dose (0.5 mg/kg/day) and early detection of significant hair loss and white blood cell (WBC) count decrease at 17 days from the start of AZA treatment. The WBC count dropped from 8,970/μL to 3,370/μL in 2 weeks, and AZA treatment was stopped because of concerns of potential leukopenia in the near future. Her WBC count recovered to 5,120/μL after 3 weeks. Gene analysis later revealed that she had a homozygous mutation in NUDT15 R139C, resulting in a poor metabolizing activity of NUDT15. In situations when NUDT15 genotyping is unavailable, initiation of AZA therapy at 0.5 mg/kg/day with close observation of hair loss and WBC counts within 2 weeks may be an alternative way to prevent thiopurine-induced early leukopenia in Asian children with CD.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.290-297
• /
• 2024

We investigate the efficacy of ensemble learning methods, specifically the soft voting technique, for enhancing heart disease prediction accuracy. Our study uniquely combines Logistic Regression, SVM with RBF Kernel, and Random Forest models in a soft voting ensemble to improve predictive performance. We demonstrate that this approach outperforms individual models in diagnosing heart disease. Our research contributes to the field by applying a well-curated dataset with normalization and optimization techniques, conducting a comprehensive comparative analysis of different machine learning models, and showcasing the superior performance of the soft voting ensemble in medical diagnosis. This multifaceted approach allows us to provide a thorough evaluation of the soft voting ensemble's effectiveness in the context of heart disease prediction. We evaluate our models based on accuracy, precision, recall, F1 score, and Area Under the ROC Curve (AUC). Our results indicate that the soft voting ensemble technique achieves higher accuracy and robustness in heart disease prediction compared to individual classifiers. This study advances the application of machine learning in medical diagnostics, offering a novel approach to improve heart disease prediction. Our findings have significant implications for early detection and management of heart disease, potentially contributing to better patient outcomes and more efficient healthcare resource allocation.

• 스마트미디어저널
• /
• 제11권4호
• /
• pp.62-68
• /
• 2022

수산 양식장 질병 감염의 확산을 사전에 차단을 위해서는 양식장의 수질 환경 및 생육 어류의 상태를 실시간 모니터링하면서 어류의 질병을 예측하는 시스템이 필요하다. 어류 질병 예측의 기존 연구는 이미지 처리 기법이 대부분이었으나 최근에는 딥러닝 기법을 통한 질병 예측방법의 연구가 활발히 진행되고 있다. 본 논문에서는 수산 양식장에서 발생할 수 있는 넙치의 질병을 딥러닝 기술로 예측하는 방법에 대한 연구결과를 소개하고자 한다. 이 방법은 양식장에서 수집된 카메라 영상에 데이터 증강과 전처리 포함하여 질병 인식률의 성능을 높인다. 이것을 통해 질병 어류를 조기 발견으로 양식 어업에서 어류 집단 폐사 등 어업 재해를 예방하고 지역 수산 양식장으로 어류의 질병 확산 피해를 줄여 매출액 감소 차단될 것으로 기대한다.

• The Plant Pathology Journal
• /
• 제38권3호
• /
• pp.229-238
• /
• 2022

Fusarium wilt caused by Fusarium oxysporum f. sp. niveum (Fon) is the most serious soil-borne disease in the world and has become the main limiting factor of watermelon production. Reliable and quick detection and quantification of Fon are essential in the early stages of infection for control of watermelon Fusarium wilt. Traditional detection and identification tests are laborious and cannot efficiently quantify Fon isolates. In this work, a real-time polymerase chain reaction (PCR) assay has been described to accurately identify and quantify Fon in watermelon plants and soil. The FONRT-18 specific primer set which was designed based on identified specific sequence amplified a specific 172 bp band from Fon and no amplification from the other formae speciales of Fusarium oxysporum tested. The detection limits with primers were 1.26 pg/µl genomic DNA of Fon, 0.2 pg/ng total plant DNA in inoculated plant, and 50 conidia/g soil. The PCR assay could also evaluate the relationships between the disease index and Fon DNA quantity in watermelon plants and soil. The assay was further used to estimate the Fon content in soil after disinfection with CaCN₂. The real-time PCR method is rapid, accurate and reliable for monitoring and quantification analysis of Fon in watermelon plants and soil. It can be applied to the study of disease diagnosis, plant-pathogen interactions, and effective management.

• 대한치과의사협회지
• /
• 제52권7호
• /
• pp.396-401
• /
• 2014

Peri-implantitis is an inflammatory disease of the peri-implant tissue by bacterial infection or other factors, which results in peri-implant bone loss. Many nonsurgical treatments were tried on initial to moderate peri-implantitis lesion to reduce the inflammation. Some of these treatments made effective results, however, they were not definitively predictable. To prevent peri-implantitis and further peri-implant bone loss, early intervention is the most important. Early detection of peri-implant infection through the regular maintenance care can make it possible to do early nonsurgical intervention. Nonsurgical intervention is effective on peri-implant mucositis and can also be effective on initial peri-implantitis lesion. If the peri-implantitis is not resolves by nonsurgical treatment, surgical approach should be considered.

• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.

• 대한의용생체공학회:의공학회지
• /
• 제31권1호
• /
• pp.27-32
• /
• 2010

Noninvasive detection of patients with probable Alzheimer's disease (AD) is of great importance for assisting a medical doctor's decision for early treatment of AD patients. In the present study, we have extracted quantitative electroencephalogram (qEEG) variables, which can be potentially used to diagnose AD, from resting eyes-closed continuous EEGs of 22 AD patients and 27 age-matched normal control (NC) subjects. We have extracted qEEG variables from mean phase coherence (MPC) and EEG coherence, evaluated for all possible combinations of electrode pairs. Preliminary trials to discriminate the two groups with the extracted qEEG variables demonstrated that the use of MPC as a supplementary or alternative measure for the EEG coherence may enhance the accuracy of noninvasive diagnosis of AD.

• 수면정신생리
• /
• 제9권1호
• /
• pp.9-13
• /
• 2002

Alzheimer's disease (AD) is one of the most common and devastating dementing disorders of old age. Most AD patients showed significant alternation of sleep structure as well as cognitive deficit. Typical findings of sleep architecture in AD patients include lower sleep efficiency, higher stage 1 percentage, and greater frequency of arousals. The slowing of EEG activity is also noted. Abnormalities in REM sleep are of particular interest in AD because the cholinergic system is related to both REM sleep and AD. Several parameters representing REM sleep structure such as REM latency, the amount of REM sleep, and REM density are change in patients with AD. Especially, measurements of EEG slowing during tonic REM sleep can be used as an EEG marker for early detection of possible AD. In addition, a structural defect in the suprachiasmatic nucleus is suggested to cause various chronobiological alternations in AD. Most of alternations related to sleep make sleep disturbances common and disruptive symptoms of AD. In this article, the author reviewed the alternation of sleep structure and circadian rhythm in AD patients.

• Journal of Computing Science and Engineering
• /
• 제8권2호
• /
• pp.87-93
• /
• 2014

Coronary artery disease (CAD) is currently a prevalent disease from which many people suffer. Early detection and treatment could reduce the risk of heart attack. Currently, the golden standard for the diagnosis of CAD is angiography, which is an invasive procedure. In this article, we propose an algorithm that uses data mining techniques, a fuzzy expert system, and the imperialist competitive algorithm (ICA), to make CAD diagnosis by a non-invasive procedure. The ICA is used to adjust the fuzzy membership functions. The proposed method has been evaluated with the Cleveland and Hungarian datasets. The advantage of this method, compared with others, is the interpretability. The accuracy of the proposed method is 94.92% by 11 rules, and the average length of 4. To compare the colonial competitive algorithm with other metaheuristic algorithms, the proposed method has been implemented with the particle swarm optimization (PSO) algorithm. The results indicate that the colonial competition algorithm is more efficient than the PSO algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• 제10권3호
• /
• pp.88-97
• /
• 2018

Chronic diseases management can be effectively achieved through early detection, continuous treatment, observation, and self-management, rather than a radar approach where patients are treated only when they visit a medical facility. However, previous studies have not been able to provide integrated chronic disease management services by considering generalized services such as hypertension and diabetes management, and difficult to expand and link to other services using only specific sensors or services. This paper proposes clinical rule flow model based on medical data analysis to provide personalized care for chronic disease management. Also, we implemented that as Rule-based Smart Healthcare System (RSHS). The proposed system executes chronic diseases management rules, manages events and delivers individualized knowledge information by user's request. The proposed system can be expanded into a variety of applications such as diet and exercise service in the future.