The University of Tokyo · Medicine
켄지 카로 연구실은 전염병 전파 메커니즘과 의료 기술 혁신을 융합한 연구를 주도하고 있습니다. 코로나19의 전파 양상과 정책 효과를 수리모델링을 통해 분석함으로써 감염병 예방 전략을 제안하며, 5G 기반 원격 진료 시스템의 도입과 그 영향에 대해서도 연구하고 있습니다. 또한 의료 현장에서의 인공지능 활용, 특히 딥러닝 기반 진단 보조 시스템의 정밀성과 해석 가능성 문제에 초점을 맞추고 있습니다.
Figures are computed from collected data and may differ slightly.
The first case of COVID-19 in Japan was reported on 16 January 2020. The total number of the infected has reached 313,844 and the number of deaths has reached 4,379 as of 16 January 2021. This article reviews the characteristics of and responses to the three waves of COVID-19 in Japan during 2020-2021 in order to provide a reference for the next step in epidemic prevention and control. The Japanese Government declared a state of emergency on 7 April 2020, which suppressed the increase in the num
To assess the effectiveness of response strategies of avoiding large gatherings or crowded areas and to predict the spread of COVID-19 infections in Japan, we developed a stochastic transmission model by extending the Susceptible-Infected-Removed (SIR) epidemiological model with an additional modeling of the individual action on whether to stay away from the crowded areas. The population were divided into three compartments: Susceptible, Infected, Removed. Susceptible transitions to Infected eve
Fifth Generation (5G) mobile communications technology became available in Japan as of the end of March 2020. The Ministry of Internal Affairs and Communications (MIC) is proceeding with a plan to use 5G for a doctor-to-doctor remote diagnosis system. This remote diagnosis offers patients the benefit of receiving advanced medical care without having to travel long distances. The provision of a remote diagnosis will provide elderly patients in rural areas with an earlier diagnosis without burdeni
In recent years, machine learning, and particularly deep learning, has shown remarkable potential in various fields, including medicine. Advanced techniques like convolutional neural networks and transformers have enabled high-performance predictions for complex problems, making machine learning a valuable tool in medical decision-making. From predicting postoperative complications to assessing disease risk, machine learning has been actively used to analyze patient data and assist healthcare pr
Background: Instead of the complete lockdown, since the outbreak of coronavirus disease 2019 (COVID-19), Japan has been trying to control the infection by self-restraint request policy. It seems that the number of infected people has subsided, however, the increasing human activities again in the resumption of economy may lead to the second wave of infections. Here, we analyzed the major factors behind the success control of the first outbreak in Japan and the potential risk of the second wave.
Neural networks have garnered attention over the past few years. A neural network is a typical model of machine learning that is used to identify visual patterns. Neural networks are used to solve a wide variety of problems, including image recognition problems and time series prediction problems. In addition, neural networks have been applied to medicine over the past few years. This paper classifies the ways in which neural networks have been applied to medicine based on the type of data used
The COVID-19 global pandemic of the past two years has changed the way humans behave, the way governments respond to crises, and placed a heavy burden on the health care systems of the countries in question. As 2022 begins, the world is experiencing a huge wave of infection with the Omicron variant of SARS-CoV-2 due […]
As the number of people with COVID-19 increases daily around the world, point-of-care testing (POCT) is gaining attention as a tool that can provide immediate test results and greatly help to deter infection and determine what to do next. POCT has several drawbacks such as a low sensitivity and specificity, but according to studies POCT has increased sensitivity on par with that of polymerase chain reaction testing. The advantage of POCT is that the results can be obtained quickly, regardless of
The comparison between the proposed model and the plain Faster R-CNN model shows that we achieved better accuracy in tumor detection, in terms of the mean precision as well as the mean sensitivity, with the proposed model.
Targeting the 9 countries with the highest cumulative number of newly confirmed cases in the past year, we analyzed the case fatality ratio (CFR) among newly confirmed cases and the vaccination rate (two or more doses of vaccine per 100 people) in the United States of America (USA), India, France, Germany, Brazil, the Republic of Korea, Japan, Italy, and the United Kingdom (UK) for the period of 2020-2022. Data reveal a decrease in the CFR among newly confirmed cases since the beginning of 2022,
In Japan, there is a growing initiative to construct centralized databases and platforms that can aggregate and manage a vast range of medical, health, and caregiving data for research and analysis. Recent advancements in artificial intelligence (AI), particularly in general-purpose models like the Segment Anything model and Chat GPT, promise significant progress towards utilizing such data-rich platforms effectively for healthcare. Traditionally, AI has displayed superior performance by learnin
As the super-aged society, Japan is facing challenges in health care system. As one of measures to cope with challenges, the Ministry of Health, Labor, and Welfare started to construct an open medical information platform, named PeOPLe, in 2016 for personalized medical care, improvement of medical services, and the redistribution of medical resources. The Ministry plans to build the platform infrastructure by 2020 and put the platform into full-scale operation by 2025. PeOPLe collects only medic
During a six-week period from July 20 to August 31, 2022, Japan experienced its highest level of COVID-19 infection ever, with an average of nearly 200,000 new infections per day nationwide. Cases requiring inpatient care peaked at 1,993,062. Twenty-seven prefectures (out of 47 prefectures) had an average hospital bed occupancy of 50% or higher, and bed occupancy in Kanagawa in particular reached 98% in mid-August. In Tokyo, bed occupancy by patients with severe COVID-19 reached 57% and peaked a
In recent years, the market for wearable devices has been rapidly growing, with much of the demand for health management. These devices are equipped with numerous sensors that detect inertial measurements, electrocardiograms, photoplethysmography signals, and more. Utilizing the collected data enables the monitoring and analysis of the user's health status in real time. With the proliferation of wearable devices, research on applications such as human activity recognition, anomaly detection, and
Open papers in the app to read, cite, and organize with AI.