• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.442-453
• /
• 2021

Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.

• Journal of the Korea Convergence Society
• /
• v.11 no.4
• /
• pp.95-108
• /
• 2020

A coronavirus disease 2019 (COVID-19) is a new global health problem. The Korean government is pursuing to gain its future growth engines and promoting short-term economic stimulation by investing in research and development (R&D) to improve national technological capabilities that can respond to the spread of the global epidemic. It is required to need knowledge information to establish the direction of future national planning thru understanding the status quo of R&D investment in terms of research fields. Four corona-related R&D fields were drawn on the basis of analyzing major nations' R&D funding data (USA, EU etc.) and two differentiated R&D fields were added through comparative analysis with domestic R&D projects. Domestic and foreign research organization-the research title-the scale of the research funding-the project period were presented in terms of the suggested 6(7 details) R&D research fields. Meanwhile R&D projects that have featured in the convergence of interdisciplinary were provided. This study proved the excellence of coronavirus detection and on-site diagnostic capabilities that are currently globally highlighted by deriving differentiated research fields from the domestic competitive advantage fields related to corona viruses and also suggested intensive investment research fields.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.744-756
• /
• 2002

The transient acoustic fields formed by a 3.5 ㎒ curved linear array transducer which is commonly used in ultrasonic medical imaging system for diagnosis of abdomen are systematically analyzed to obtain new design parameters for the better acoustic image. In the analysis with an assumption of radiating waveform, element size, radius of curvature, amplitude apodization are considered as parameters giving constitutive relations with the fields. As simulation results, appropriate new parameters with the reduced curvature and elevation aperture and the apodization of Hamming window, which make an improved acoustic beam with lower side lobe levels than a conventional typical transducer, are obtained.

• Geomechanics and Engineering
• /
• v.13 no.1
• /
• pp.99-117
• /
• 2017

Rock physics modeling of sandstone reservoir from gas fields of Krishna-Godavari basin represents the link between reservoir parameters and seismic properties. The rock physics diagnostic models such as contact cement, constant cement and friable sand are chosen to characterize reservoir sands of two wells in this basin. Cementation is affected by the grain sorting and cement coating on the surface of the grain. The models show that the reservoir sands in two wells under examination have varying cementation from 2 to more than 6%. Distinct and separate velocity-porosity and elastic moduli-porosity trends are observed for reservoir zones of two wells. A methodology is adopted for generation of Rock Physics Template (RPT) based on fluid replacement modeling for Raghavapuram Shale and Gollapalli Sandstones of Early Cretaceous. The ratio of P-wave velocity to S-wave velocity (Vp/Vs) and P-impedance template, generated for this above formations is able to detect shale, brine sand and gas sand with varying water saturation and porosity from wells in the Endamuru and Suryaraopeta gas fields having same shallow marine depositional characters. This RPT predicted detection of water and gas sands are matched well with conventional neutron-density cross plot analysis.

• Journal of The Korean Astronomical Society
• /
• v.36 no.3
• /
• pp.105-110
• /
• 2003

Recent observations of galaxy clusters in radio and X-ray indicate that cosmic rays and magnetic fields may be energetically important in the intracluster medium. According to the estimates based on theses observational studies, the combined pressure of these two components of the intracluster medium may range between $10\%{\~}100\%$ of gas pressure, although their total energy is probably time dependent. Hence, these non-thermal components may have influenced the formation and evolution of cosmic structures, and may provide unique and vital diagnostic information through various radiations emitted via their interactions with surrounding matter and cosmic background photons. We suggest that shock waves associated with cosmic structures, along with individual sources such as active galactic nuclei and radio galaxies, supply the cosmic rays and magnetic fields to the intracluster medium and to surrounding large scale structures. In order to study 1) the properties of cosmic shock waves emerging during the large scale structure formation of the universe, and 2) the dynamical influence of cosmic rays, which were ejected by AGN-like sources into the intracluster medium, on structure formation, we have performed two sets of N-body /hydrodynamic simulations of cosmic structure formation. In this contribution, we report the preliminary results of these simulations.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.33 no.6
• /
• pp.311-321
• /
• 2019

In this paper, we try to define and classify the concepts of Convergent Research of Korean-Western Medicine (CRKWM) to clarify the goals of research. In addition, some suggestions that are necessary to promote the CRKWM were made. The results are as follows. First, the CRKWM should be used as a concept that refers to 'interdisciplinary research' jointly conducted by experts in both Korean and Western medicines beyond their own fields. Second, True CRKWM is an "eclectic combination of East-West" that combines the advantages of traditional Korean medicine and western medicine to create a new field; it is necessary to redefine the concept of 'Integrative medicine', which is used in different context by the traditional Korean medicine and western fields in Korea, as an "eclectic combination of East-West" type. Third, In order to promote the CRKWM, it is necessary to convert the current dual medical system of relativism to one of pluralism. Forth, In order for CRKWM to be promoted, methodologies, theories, and models that become the backbones of convergence should be developed. As of now, systems medicine and network science are the best fit. Fifthly, In order to promote convergent clinical research, the development of Korean-Western diagnostic model that integrates the pathologies of Western medicine and symptoms of Korean medicine is urgent. Lastly, Mutual understanding between Korean and Western medicine fields should be preceded in order for CRKWM to be stimulated.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.8 no.2
• /
• pp.64-75
• /
• 2003

Aptamers are functional nucleic acids that can specially bind to proteins, peptides, amino acids. nucleotides, drugs, vitamins and other organic and inorganic compounds. The aptamers are identified from random DNA or RNA libraries by a SELEX (systematic evolution of ligands by exponential amplification) process. As aptamers have the advantage, and potential ability to be released from the limitations of antibodies, they are attractive to a wide range of therapeutic and diagnostic applications. Aptamers, with a high-affinity and specificity, could fulfil molecular the recognition needs of various fields in biotechnology. In this work, we reviewed some aptamer Selection techniques, properties, medical applications of their molecules and their biotechnological applications, such as ELONA (enzyme linked oligonucleotide assay), flow cytometry, biosensors, electrophoresis, chromatography and microarrays.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.9 no.2
• /
• pp.69-75
• /
• 2004

In recent years, the importance of proteomic works, such as protein expression, detection and identification, has grown in the fields of proteomic and diagnostic research. This is because complete genome sequences of humans, and other organisms, progress as cellular processing and controlling are performed by proteins as well as DNA or RNA. However, conventional I protein analyses are time-consuming; therefore, high throughput protein analysis methods, which allow fast, direct and quantitative detection, are needed. These are so-called protein microarrays or protein chips, which have been developed to fulfill the need for high-throughput protein analyses. Although protein arrays are still in their infancy, technical development in immobilizing proteins in their native conformation on arrays, and the development of more sensitive detection methods, will facilitate the rapid deployment of protein arrays as high-throughput protein assay tools in proteomics and diagnostics. This review summarizes the basic technologies that are needed in the fabrication of protein arrays and their recent applications.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1205-1210
• /
• 2004

The 4-20mA analog signal used in the various industrial fields to interface sensor in distributed process control has been replaced with relatively simple digital networks, called "fieldbus, and recently by Ethernet. Significant advances in Internet and computer technology have made it possible to develop an Internet based control, monitoring, and operation scheduling system for heating, ventilation and air-conditioning (HVAC) systems. The seamless integration of data networks with control networks allows access to any control point from anywhere. Field compatible field devices become so-called "smart" devices, capable of executing simple control, diagnostic and maintenance functions and providing bidirectional serial communication to higher level controller. The most important HVAC of BAS has received nationwide attention because of higher portion of more than 40% in building sector energy use and limited resources. This paper presents the Internet-based monitoring and control architecture and development of LonWorks control modules for AHU (air handling units) of HVAC in viewpoint of configuring BAS network. This article addresses issues in architecture section, electronics, embedded processors and software, and internet technologies.

• Genomics & Informatics
• /
• v.15 no.4
• /
• pp.162-169
• /
• 2017

Metal binding proteins or metallo-proteins are important for the stability of the protein and also serve as co-factors in various functions like controlling metabolism, regulating signal transport, and metal homeostasis. In structural genomics, prediction of metal binding proteins help in the selection of suitable growth medium for overexpression's studies and also help in obtaining the functional protein. Computational prediction using machine learning approach has been widely used in various fields of bioinformatics based on the fact all the information contains in amino acid sequence. In this study, random forest machine learning prediction systems were deployed with simplified amino acid for prediction of individual major metal ion binding sites like copper, calcium, cobalt, iron, magnesium, manganese, nickel, and zinc.