• 인터넷정보학회논문지
• /
• 제22권6호
• /
• pp.59-69
• /
• 2021

의료기기의 오작동이나 고장은 인명 피해나 큰 상해가 발생할 수 있으므로 안전성 확보가 필수적인 분야이다. 이를 위해 국제표준을 제정하고 준수하도록 하고 있지만 이들 표준은 상호의존적이고 특히, 안전성 분석 활동의 경우 시간, 노력, 비용이 많이 소요되어 표준 활동을 통합하고 커스터마이징할 필요가 있다. 따라서 본 논문에서는 의료기기 소프트웨어 개발 단계별 수행 활동과 안전성 프로세스의 활동을 통합하였다. 통합된 프로세스를 통해 하나의 프로세스로 체계적인 관리가 가능하며, STPA 기법을 기반으로 하는 프로세스 단계별로 가이드가 제공되어 안전성 활동을 효과적으로 수행할 수 있다.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• 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.

• Medical Lasers
• /
• 제9권2호
• /
• pp.150-158
• /
• 2020

Background and Objectives Low-level laser therapy (LLLT) is used widely to promote hair growth in androgenetic alopecia (AGA). This study examined the clinical efficacy and safety of a home-use LLLT device with a newly designed array of light sources and software optimized for individual types of AGA. Materials and Methods The study was a randomized, double-blind, sham device-controlled trial. Forty-eight subjects (39 men and nine women) were assigned randomly in a 2:1 ratio to use either the test device (LG Pra'L HGN1, LG electronics, Korea) or sham device. The subjects used the LLLT device three times a week for 16 weeks. Phototrichogram was used to measure the hair density and hair thickness at 0, 8, and 16-weeks. Adverse events were closely monitored. Results After 16 weeks of using the device, the test group showed a significant increase in hair density and hair thickness compared to the control. In the test group, the hair density increased 6.96 counts/cm² at eight weeks and 13.67 counts/cm² at 16 weeks from the baseline. The hair thickness increased 7.21 ㎛ at eight weeks and 11.80 ㎛ at 16 weeks compared to the baseline. Conclusion The home-use LLLT device with a novel array of light sources and an individualized program according to the types of hair loss appears to be an effective and safe treatment modality for both male and female AGA patients.

• 산업기술연구
• /
• 제24권A호
• /
• pp.83-90
• /
• 2004

Generally, electronic appliances are used on the basis of normal power source supply. The power source inevitably includes the abnormal condition, such as, sudden voltage sagging, power interrupt, and induced noises. As the electronic appliances which include micro-controller-based circuits are being increased recently, the controller circuit sometimes malfunctions by the abnormal condition of the power source. This situation causes serious problems such as hitch of electric appliance, fire and medical instrument glitch, which produces serious situations. In this paper, development of power interrupt tester which is highly suitable for an endurance test device under abnormal power source to microprocessor-based circuits is proposed 89C2051 microcontroller is performed to make power interrupt signal, and software controls peripheral hardwares and built-in functions. Experimental results of this study will offer a good application to electronic appliance maker as a test device of hardware and software debugging use.

• Journal of Information Processing Systems
• /
• 제13권6호
• /
• pp.1602-1612
• /
• 2017

Since rapidly disseminating of Internet of Things (IoT) as the new communication paradigm, a number of studies for various applications is being carried out. Especially, interest in the smart medical system is rising. In the smart medical system, a number of medical devices are distributed in popular area such as station and medical center, and this high density of medical device distribution can cause serious performance degradation of communication, referred to as the coexistence problem. When coexistence problem occurs in smart medical system, reliable transmitting of patient's biological information may not be guaranteed and patient's life can be jeopardized. Therefore, coexistence problem in smart medical system should be resolved. In this paper, we propose a distributed coexistence mitigation scheme for IoT-based smart medical system which can dynamically avoid interference in coexistence situation and can guarantee reliable communication. To evaluate the performance of the proposed scheme, we perform extensive simulations by comparing with IEEE 802.15.4 MAC protocol which is a traditional low-power communication technology.

• 디지털융복합연구
• /
• 제14권11호
• /
• pp.283-288
• /
• 2016

본 연구는 IoT기반의 의료정보 처리를 위한 시스템 및 네트워크 기술 구현에 관련한 것이다. 본 연구의 구성환경은 IoT의 기본구성으로 센서노드, 게이트웨이, 서버노드의 구성이다. 센서노드로서의 의료단말이 게이트웨이에 연결요청을 하면 서버에 미리 등록된 의료장치일 경우 서버는 등록을 허가한다. 착용형 의료장치는 주기적으로 센싱정보를 수집하여 서버에 전달하고 서버는 이를 시각화하거나 미래사용을 위해 저장한다. 본 논문에서는 이에 필요한 전체 절차와 알고리즘을 기술하였고 소프트웨어 구조를 제안하였다.

• 한국임상약학회지
• /
• 제19권1호
• /
• pp.65-68
• /
• 2009

Disposal infusion device is known to be useful for chemotherapy. Anti-cancer drug can be released by the force of carbon dioxide or balloon. In this study, we compared the$Anapa^{(R)}$ (LC0020) with B Company (LV2 ml) in terms of infusion rate and stability. Infusion rate was determined every six minute using software, MSI08IH. Stability of 5-fluorouracil was examined periodically using a High Performance Liquid Chromatography. Infusion rates of gas-derived $Anapa^{(R)}$ device were 2.29, 1.86, 1.98 ml/hr and those of balloon-derived B Company device were 1.71, 1.58, 1.37 ml/min. There were no significant differences in stability of 5-fluorouracil between $Anapa^{(R)}$ and B Company devices. In summary, gas-derived $Anapa^{(R)}$ device is thought to be comparable or superior to balloon-derived B Company device as far as infusion rate and stability are concerned. We expect that $Anapa^{(R)}$ as a home infusion device can be employed to improve a quality of life and compliance of cancer patients.

• 대한영상의학회지
• /
• 제85권4호
• /
• pp.693-704
• /
• 2024

흉부 X선은 인공지능 기술이 활발히 적용되고 있는 대표적인 영상 검사이다. 흉부 X선 영상에서 다양한 이상 소견을 자동으로 검출하여 의사의 판독을 보조하는 인공지능 기반 소프트웨어 의료기기들이 국내에서 시판되고 있고, 임상 적용이 활발히 이루어지고 있다. 이러한 흉부 X선 인공지능 검출 보조 의료기기의 임상 도입에 있어, 도입 전 성능 및 유효성 평가, 적용 대상, 분석 결과 제공의 대상 및 방식, 도입 후 모니터링, 법적 책임 문제 등 다양한 현실적인 사항에 대한 고려가 필요하고, 각 의료기관의 상황에 따른 적절한 의사결정이 필요하다. 인공지능 검출 보조 의료기기의 안전하고 효율적인 도입 및 운영을 위해서는 전문 지식을 갖춘 영상의학과 전문의의 적극적인 역할이 필수적이다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제38권4호
• /
• pp.389-394
• /
• 2015

의료영상 검사는 정보기술 및 의료장비의 발달로 인체의 해부학적 구조를 묘사하는 능력이 날로 발전하고 있다. 그러나 상지회전이 필요한 어깨관절 의료영상 검사에서는 인체구조의 복잡성으로 정확한 자세유지가 의료영상의 진단적 가치에 매우 중요하다. 자기공명검사의 경우 긴 검사시간과 고정된 자세가 필요해 검사자의 노력과 환자의 의지만으로 재현성 있는 검사가 불가능하다. 이에 상지회전과 정량적 각도가 가능한 보조기구를 개발하여 진단적 가치가있는 의료영상 검사를 하고자하였다. 본 연구는 선행 연구의 결과를 바탕으로 보조기구를 제작하였으며, 공학용 프로그램인 CATIA 프로그램으로 3차원 모델링을 설계하여, 3D프린터로 최종 완성된 보조기구를 제작하였다. 사용된 3D 프린터는 Stratasys Objet350 Connex 모델이며, 재질은 광경화성 수지를 사용하였다. 완성된 보조기구의 크기는 $120{\times}150{\times}190mm$이며, 손잡이부의 내경은 125.9 mm 로 디자인되었다. 보조기구는 총 4개의 부품으로 바디부(외부), 손잡이부(내부), 고정단자, 연결부로 구성되었으며 바디부와 손잡이부는 원활한 회전이 가능하도록 2.1 mm의 유격이 유지되도록 하였다. 손잡이부에는 360o 눈금선을 표시하여 환자마다 관찰에 필요한 회전각도를 기록할 수 있도록 하여 추적검사나 양쪽검사에 적용할 수 있도록 하였다.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2003년도 제27회 추계학술대회
• /
• pp.63-63
• /
• 2003

Purpose: Planning target volume (PTV) for tumors in abdomen or thorax includes enough margin for breathing-related movement of tumor volumes during treatment. We developed a simple and handy method, which can reduce PTV margins in patients with moving tumors, respiratory motion reduction device system (RMRDs). Materials and Methods: The patients clinical database was structured for moving tumor patients and patient setup error measurement and immobilization device effects were investigated. The system is composed of the respiratory motion reduction device utilized in prone position and abdominal presser (strip device) utilized in the supine position, moving phantom and the analysis program, which enables the analysis on patients setup reproducibility. It was tested for analyzing the diaphragm movement and CT volume differences from patients with RMRDs, the magnitude of PTV margin was determined and dose volume histogram (DVH) was computed using a treatment planning software. Dose to normal tissue between patients with RMRDs and without RMRDs was analyzed by comparing the fraction of the normal liver receiving to 50% of the isocenter dose(TD50). Results: In case of utilizing RMRDs, which was personally developed in our hospital, the value was reduced to $5pm1.4 mm$, and in case of which the belt immobilization device was utilized, the value was reduced to 3$pm$0.9 mm. Also in case of which the strip device was utilized, the value was proven to reduce to $4pm.3 mm$0. As a result of analyzing the TD50 is irradiated in DVH according to the radiation treatment planning, the usage of the respiratory motion reduction device can create the reduce of 30% to the maximum. Also by obtaining the digital image, the function of comparison between the standard image, automated external contour subtraction, and etc were utilized to develop patients setup reproducibility analysis program that can evaluate the change in the patients setup. Conclusion: Internal organ motion due to breathing can be reduced using RMRDs, which is simple and easy to use in clinical setting. It can reduce the organ motion-related PTV margin, thereby decrease volume of the irradiated normal tissue.