• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.174-185
• /
• 2020

Leukemia induced death has been listed in the top ten most dangerous mortality basis for human being. Some of the reason is due to slow decision-making process which caused suitable medical treatment cannot be applied on time. Therefore, good clinical decision support for acute leukemia type classification has become a necessity. In this paper, the author proposed a novel approach to perform acute leukemia type classification using sequential neural network classifier. Our experimental result only cover the first classification process which shows an excellent performance in differentiating normal and abnormal cells. Further development is needed to prove the effectiveness of second neural network classifier.

• Journal of Biomedical Engineering Research
• /
• v.43 no.2
• /
• pp.102-108
• /
• 2022

Purpose: To propose a deep learning-based clinical decision support technique for laryngeal disease on epiglottis, tongue and vocal cords. Materials and Methods: A total of 873 laryngeal endoscopic images were acquired from the PACS database of Pusan N ational University Yangsan Hospital. and VGG16 model was applied with transfer learning and fine-tuning. Results: The values of precision, recall, accuracy and F1-score for test dataset were 0.94, 0.97, 0.95 and 0.95 for epiglottis images, 0.91, 1.00, 0.95 and 0.95 for tongue images, and 0.90, 0.64, 0.73 and 0.75 for vocal cord images, respectively. Conclusion: Experimental results demonstrated that the proposed model have a potential as a tool for decision-supporting of otolaryngologist during manual inspection of laryngeal endoscopic images.

• Journal of Oriental Neuropsychiatry
• /
• v.20 no.2
• /
• pp.143-152
• /
• 2009

Objectives : Hwabyung is one of well-known mental health problems like depression in Korea and it's concept is generated from oriental medicine. We suggest that clinical practice guideline should reflect the Hwabyung's characteristics, clinical environment and Oriental medical doctor's need. Methods : We use the general development method of clinical practice guideline and also apply the oriental medicine's properties. Results : We need to refer to the western psychiatric field, especially the clinical guideline of depression. And we should base on the clinical survey and trial with the selected core subject considering oriental medicine's character. Conclusions : From this development, we expect the application of proper clinical decision by medical team, the objectification of oriental medicine, and the improvement of medical quality in the clinical field of oriental medicine.

• Journal of Korean Medical classics
• /
• v.25 no.4
• /
• pp.39-55
• /
• 2012

Objective : In order to find the decision system in differentiation of syndromes and treatments, I paid attention to divination by Achillea sibireca. Method : I pulled out the elements of differentiation of syndromes and treatments in Zh$\bar{o}$ng y$\bar{i}$n$\grave{e}$i k$\bar{e}$ xu$\acute{e}$(中醫內科學), Uihagipmun Sanghan(醫學入門 傷寒), Donguibogam Japbyeong(東醫寶鑑 雜病) and compared them with the horoscope in The Book of Changes(周易) from the relativity of both eight principles(八綱) etc and subdivision in the entity of the cosmos (太極內 分化). Result : From this viewpoint, the decision system that has relative references in differentiation of syndromes & treatments on cold diseases(傷寒病) and complexed diseases(雜病) by eight principles etc can be compared with the decision system in divination by Achillea sibireca that the entity of the cosmos(太極) gradually can be breakdown into the positive and negative(陰陽), the positive and negative can be breakdown into four phases(四象), four phases can be breakdown into eight signs of divination(八卦), eight signs of divination can be breakdown into 64 divination signs(64卦). Conclusion : I had found that differentiation of syndromes and treatments and divination by Achillea sibireca have similarity to each other in side of decision system. Those decision systems for clinical use and telling the future has many relative references and are made of multiple structures. Clinician can easily, exactly distinguish similar syndromes of many another diseases through this way.

• Journal of Yeungnam Medical Science
• /
• v.38 no.4
• /
• pp.344-349
• /
• 2021

Background: Cancer patients have been disproportionally affected by the coronavirus disease 2019 (COVID-19) pandemic, with high rates of severe outcomes and mortality. Fever is the most common symptom in COVID-19 patients. During the COVID-19 pandemic, physicians may have difficulty in determining the cause of fever (COVID-19, another infection, or cancer fever) in cancer patients. Furthermore, there are no specific guidelines for managing cancer patients with fever during the COVID-19 pandemic. Thus, this study evaluated the clinical characteristics and outcomes of cancer patients with fever during the COVID-19 pandemic. Methods: This study retrospectively reviewed the medical records of 328 cancer patients with COVID-19 symptoms (fever) admitted to five hospitals in Daegu, Korea from January to October 2020. We obtained data on demographics, clinical manifestations, laboratory test results, chest computed tomography images, cancer history, cancer treatment, and outcomes of all enrolled patients from electronic medical records. Results: The most common COVID-19-like symptoms were fever (n=256, 78%). Among 256 patients with fever, only three (1.2%) were diagnosed with COVID-19. Most patients (253, 98.8%) with fever were not diagnosed with COVID-19. The most common solid malignancies were lung cancer (65, 19.8%) and hepatobiliary cancer (61, 18.6%). Twenty patients with fever experienced a delay in receiving cancer treatment. Eighteen patients discontinued active cancer treatment because of fever. Major events during the treatment delay period included death (2.7%), cancer progression (1.5%), and major organ dysfunction (2.7%). Conclusion: Considering that only 0.9% of patients tested for COVID-19 were positive, screening for COVID-19 in cancer patients with fever should be based on the physician's clinical decision, and patients might not be routinely tested.

• Journal of Software Engineering Society
• /
• v.25 no.2
• /
• pp.29-34
• /
• 2012

Quality control in medical is getting very important issue so that the importance of CDS(Clinical Decision Support) System has been increased. Local clinics as well as big hospitals are required to implement the CDS System. But the cost and complexity of CDS system implementation is so high since many different activities including knowledge authoring, software development, and integrating the legacy system are necessary. In this paper, we suggest the CDS system architecture to be sharable and interoperable and evaluate the availability and efficiency of this architecture.

• Electronics and Telecommunications Trends
• /
• v.35 no.2
• /
• pp.1-16
• /
• 2020

"Artificial Intelligence+" is a key strategic direction that has garnered the attention of several global medical device manufacturers and internet companies. Large hospitals are actively involved in different types of medical AI research and cooperation projects. Medical AI is expected to create numerous opportunities and advancements in areas such as medical imaging, computer aided diagnostics and clinical decision support, new drug development, personal healthcare, pathology analysis, and genetic disease prediction. On the contrary, some studies on the limitations and problems in current conditions such as lack of clinical validation, difficulty in performance comparison, lack of interoperability, adversarial attacks, and computational manipulations are being published. Overall, the medical AI field is in a paradigm shift. Regarding international standardization, the work on the top 10 standardization issues is witnessing rapid progress and the competition for standard development has become fierce.

• Toxicological Research
• /
• v.35 no.4
• /
• pp.319-330
• /
• 2019

Adverse drug reactions (ADRs) constitute key factors in determining successful medication therapy in clinical situations. Integrative analysis of electronic medical record (EMR) data and use of proper analytical tools are requisite to conduct retrospective surveillance of clinical decisions on medications. Thus, we suggest that electronic medical recording and human genetic databases are considered together in future directions of pharmacovigilance. We analyzed EMR-based ADR studies indexed on PubMed during the period from 2005 to 2017 and retrospectively acquired 1161 (29.6%) articles describing drug-induced adverse reactions (e.g., liver, kidney, nervous system, immune system, and inflammatory responses). Of them, only 102 (8.79%) articles contained useful information to detect or predict ADRs in the context of clinical medication alerts. Since insufficiency of EMR datasets and their improper analyses may provide false warnings on clinical decision, efforts should be made to overcome possible problems on data-mining, analysis, statistics, and standardization. Thus, we address the characteristics and limitations on retrospective EMR database studies in hospital settings. Since gene expression and genetic variations among individuals impact ADRs, pharmacokinetics, and pharmacodynamics, appropriate paths for pharmacovigilance may be optimized using suitable databases available in public domain (e.g., genome-wide association studies (GWAS), non-coding RNAs, microRNAs, proteomics, and genetic variations), novel targets, and biomarkers. These efforts with new validated biomarker analyses would be of help to repurpose clinical and translational research infrastructure and ultimately future personalized therapy considering ADRs.

• Journal of Computing Science and Engineering
• /
• v.6 no.1
• /
• pp.51-59
• /
• 2012

We describe the framework of a data-fuelled, interdisciplinary team-led learning system. The idea is to build models using patients from one's own institution whose features are similar to an index patient as regards an outcome of interest, in order to predict the utility of diagnostic tests and interventions, as well as inform prognosis. The Laboratory of Computational Physiology at the Massachusetts Institute of Technology developed and maintains MIMIC-II, a public deidentified high- resolution database of patients admitted to Beth Israel Deaconess Medical Center. It hosts teams of clinicians (nurses, doctors, pharmacists) and scientists (database engineers, modelers, epidemiologists) who translate the day-to-day questions during rounds that have no clear answers in the current medical literature into study designs, perform the modeling and the analysis and publish their findings. The studies fall into the following broad categories: identification and interrogation of practice variation, predictive modeling of clinical outcomes within patient subsets and comparative effectiveness research on diagnostic tests and therapeutic interventions. Clinical databases such as MIMIC-II, where recorded health care transactions - clinical decisions linked with patient outcomes - are constantly uploaded, become the centerpiece of a learning system.

• Quality Improvement in Health Care
• /
• v.14 no.1
• /
• pp.49-54
• /
• 2008

Background : This study was to reduce incidence of falls by analyzing actual problem and drawing out improvement plan applicable to the clinical practice through operation of the staff nurses-centered fall peer review group. Method : The fall peer review group was composed of 8 nurses having patient nursing experience for over 5 years, and each of fall cases was reviewed and the root cause was analyzed. As a result, it was found that the patients and their families did not fully understandthe content of the education, and the staff nurses did not completely inspect the risk factors of falls and perform immediate intervention when patient's condition changed. Based on the above-mentioned results, improvement activity was conducted for the purposes of consolidating patients education method and supplementing computerized system to support nurses' decision making as well as devices and facilities. Result : As a result of conducting improvement activity in the aspects of education for patients, support of nurse's decision-making, and devices and facilities through operation of the staff nurses-centered fall peer review group, falls decreased by 9.5% compared to before improvement activity. Conclusion : It is concluded that operation of the clinical nurses-centered fall peer review group played a role of promoter to draw out practical and applicable improvement plan to the clinical practice and apply directions of the field-centered, and increased nurses' interest in falls and ultimately, reduced incidence of falls. Therefore the Center will continue to operate the staff nurses-centered peer review group, and recommends participation of nurses who actually take the charge of nursing patients in further analysis of patients' safety accidents.