Intelligent medicine and beyond

With the developments of medical artificial intelligence (AI), meta-data analysis, intelligence-aided drug design and discovery, surgical robots and image-navigated precision treatments, intelligent medicine (IM) as a new era evolved from ancient medicine and biomedical medicine, has become an emerging topic and important criteria for clinical applications. It is fully characterized by fundamental research-driven, new-generation technique-directed as well as state-of-the-art paradigms for advanced disease diagnosis and therapy leading to an even broader future of modern medicine. As a fundamental subject and also a practice-oriented field, intelligent medicine is highly trans-disciplinary and cross-developed, which has emerged the knowledge of modern medicine, basic sciences and engineering. Basically, intelligent medicine has three domains of intelligent biomaterials, intelligent devices and intelligent techniques. Intelligent biomaterials derive from traditional biomedical materials, and currently are endowed with multiple functionalities for medical uses. For example, micro-/nanorobots, smart responsive biomaterials and digital drugs are representative intelligent biomaterials which have been already commercialized and applied to clinical uses. Intelligent devices, such as surgical robots, rehabilitation robots and medical powered exoskeleton, are an important majority in the family of intelligent medicine. Intelligent biomaterials and intelligent devices are more and more closely integrated with each other especially on the occasions of intelligence acquisition, remote transmission, AI-aided analysis and management. In comparison, intelligent techniques are internalized in the former two domains and are playing a critical role in the development of intelligent medicine. Representative intelligent techniques of telemedicine, image-navigated surgery, virtual/augmented reality and AI-assisted image analysis for early-stage disease assessments have been employed in nowadays clinical operations which to a large extent relieved medical labors. In the past decades, China has been in the leading groups compared to international colleagues in the arena of intelligent medicine, and a series of eminent research has been clinically translated for practical uses in China. For instance, the first 5G-aided remote surgery has been realized in Fujian Province in January 2019, which for the first time validated their applicability for human uses. The surgical robots have found China as the most vigorous market, and more than 10 famous Chinese companies are developing versatile surgical robots for both Chinese people and people all over the world. China also applied AI techniques to new drug developments especially in early 2020 when COVID-19 epidemic roared, and several active molecules and drug motifs have been discovered for early-stage COVID-19 screening and treatments. Based on the significance of intelligent medicine and its rapid developments in both basic research and industrials, this review summarized the comprehensive viewpoints of the Y6 Xiangshan Science Conferences titled with Fundamental Principles and Key Technologies of Intelligent Medicine, and gave an in-depth discussion on main perspectives of future developments of the integration of biomaterial and devices, the integration of bioinformatics and medical hardware, and the synergy of biotechnology and intelligence information. It is expected that this featuring article will further promote intelligent medicine to an even broader community not only for scientists but also for industrials, and in the long run embrace a perspective future for its blooming and rich contributions in China in the coming 5 years. © 2023 Chinese Academy of Sciences. All rights reserved.

Discovering AI-enabled convergences based on BERT and topic network

Various aspects of artificial intelligence (AI) have become of significant interest to academia and industry in recent times. To satisfy these academic and industrial interests, it is necessary to comprehensively investigate trends in AI-related changes of diverse areas. In this study, we identified and predicted emerging convergences with the help of AI-Associated research s collected from the SCOPUS database. The bidirectional encoder representations obtained via the transformers-based topic discovery technique were subsequently deployed to identify emerging topics related to AI. The topics discovered concern edge computing, biomedical algorithms, predictive defect maintenance, medical applications, fake news detection with block chain, explainable AI and COVID-19 applications. Their convergences were further analyzed based on the shortest path between topics to predict emerging convergences. Our findings indicated emerging AI convergences towards healthcare, manufacturing, legal applications, and marketing. These findings are expected to have policy implications for facilitating the convergences in diverse industries. Potentially, this study could contribute to the exploitation and adoption of AI-enabled convergences from a practical perspective. © 2023 Korean Society for Internet Information. All rights reserved.

Energy-based Domain Adaption with Active Learning for Emerging Misinformation Detection

Classifying whether collected information related to emerging topics and domains is fake/incorrect is not an easy task because we do not have enough labeled data in the domains. Given labeled data from source domains (e.g., gossip and health) and limited labeled data from a newly emerging target domain (e.g., COVID-19 and Ukraine war), simply applying knowledge learned from source domains to the target domain may not work well because of different data distribution. To solve the problem, in this paper, we propose an energy-based domain adaptation with active learning for early misinformation detection. Given three real world news datasets, we evaluate our proposed model against two baselines in both domain adaptation and the whole pipeline. Our model outperforms the baselines, improving at least 5% in the domain adaptation task and 10% in the whole pipeline, showing effectiveness of our proposed approach. © 2022 IEEE.

Influencing supply chain practice: the action principles approach applied to pandemic risk management

Purpose: This paper offers a novel approach for conducting impactful research on emerging topics or practices. This method is particularly relevant in the face of emerging phenomena and new dynamics, such as the impact of the COVID-19 pandemic on supply chain risks. Because these new phenomena and dynamics are relatively unexplored, little prior knowledge exists in literature and industry, and they represent a large opportunity and/or challenge to practitioners. Design/methodology/approach: The action principles research (APR) approach, as a newer version of critically engaged research (CER), offers comparison against more traditional empirical or intervention-based research. The authors illustrate the approach with a pandemic risk-management study. Findings: The APR approach originated in the information technology field. It is highly applicable for researchers who are seeking to more expeditiously support decision making and actioning on new dynamics and emerging topics and practice in supply chain management than is allowed by traditional methods and longitudinal CER. Originality/value: In the context of ongoing calls for relevance, impact and actionable findings on pandemic risk management, this paper describes an approach to developing timely findings that are actionable for practitioners and that advance science around dynamic and emerging topics or practices. We hope this will grow societal value of research, particularly in the face of the COVID-19 pandemic and the new dynamics and uncertainties that managers face in modern supply chains. © 2022, Emerald Publishing Limited.