Page 120 - 2023-06-中国全科医学
P. 120

2023年2月   第26卷   第6期                                 http: //www.chinagp.net   E-mail: zgqkyx@chinagp.net.cn  ·761·

           field. Methods All literature in English regarding esophageal cancer research using AI included in the Science Citation Index
           Expanded database of the Web of Science Core Collection was searched from 2000-01-01 to 2022-04-06. Microsoft Excel 2019,
           CiteSpace(5.8R3-64bit) and VOSviewer (1.6.18) were used to analyze the literature for annual number of publications,
           country,author,institution,co-citation and keywords. Results Nine hundred and eighteen studies were retrieved,with a
           total of 23 490 times of being cited. The number of studies published between 2000 and 2016 grew slowly(from 6 to 40),but
           increased rapidly between 2017 and 2022(from 62 to 216). Sixty countries,118 institutions and 5 979 authors were involved
           in the studies. China (306 articles),the United States (238 articles) and the United Kingdom (113 articles) ranked the
           top three in terms of number of studies published. The top three institutions in terms of intensity of cooperation were University of
           Amsterdam (TLS=72),Catherine Hospital (TLS=64) and Eindhoven University of Technology (TLS=53). The top three
           authors in terms of number of publications were Jacques J G H M Bergman from the Netherlands (n=16),Tomohiro Tada from
           Japan (n=12),and Fons Van Der Sommen from the Netherlands (n=12). There were 39 962 co-cited authors and 42 992
           co-cited studies. Thirty-three burst keywords were identified:the major burst keywords were p53 and mutations in 2001-2008
           (early stage),and were esophageal cancer classification,new examination techniques (tomography),differentiation,
           identification and comparison between esophageal cancer and other cancers in 2013-2018(middle stage),and were deep
           learning,convolutional neural network,and machine learning in esophageal cancer examination and diagnosis applications in
           2019-2022(late stage). Among which deep learning had the highest burst intensity (burst intensity of 13.89). Conclusion
            AI application in esophageal cancer research has entered a new phase,moving gradually from genes and mutations toward
           accurate examination,diagnosis,and treatment. The latest major burst keywords in recent years(2019-2022) are deep
           learning,convolutional neural network,and machine learning in esophageal cancer examination and diagnosis. The future
           challenges to the use of AI in esophageal cancer research may include individual data collection,data quality assurance,data
           processing specifications,AI code reproduction,and reliability assurance of AI-assisted diagnostic decision-making.
               【Key words】 Esophageal neoplasms;Artificial intelligence;Data collection;Diagnosis,differential;Visual
           analysis;CiteSpace


               食管癌包括食管腺癌和食管鳞状细胞癌,其是全球                              表 1 2000—2022 年 AI 在食管癌领域研究文献检索策略
                                                               Table 1 List of esophageal cancer studies using AI published from 2000 to
           第七大常见癌症(按发病率),第六大致死癌症(按死
                                                               2022
           亡率),新发病例死亡率高于 50%               [1] 。近 20 年,食
                                                                检索                                       文献数
           管癌在诊断、治疗、预后等方面取得了重大进展,尤其                             步骤                 检索式                  量(篇)
           新兴的人工智能(artificial intelligence,AI)逐渐被应                  esophag* (Topic) or oesophag* (Topic) or
                                                                1#  gullet (Topic) and Article OR Review (Document  103 423
           用于医疗卫生中的疾病诊断、基因组数据分析等许多领                                 Type) and English (Language)
           域 [2-3] ,这在一定程度上提高了食管癌诊断结果的准确                            cancer* (Topic) or tumour* (Topic) or tumor*
           率 [4-5] 。随着 AI 在食管癌领域研究的剧增,研究人员                      2#  (Topic) or neoplas* (Topic) or onco* (Topic)   3 272 272
                                                                    or carcinoma* (Topic) and Article OR Review
           快速了解该领域的最新发展和研究热点十分重要。因此,                                (Document Type) and English (Language)
           本研究对 2000—2022 年 AI 应用于食管癌领域的全球研                     3#  1# AND 2#                            54 077
           究进行了文献计量分析,总结 AI 在食管癌领域的应用                               "artificial intelligen*" (Topic) or computational
           和发展历程,阐明 AI 在其中的研究进展、热点和新兴                               NEAR/5 intelligence (Topic) or expert* system*
                                                                    (Topic) or intelligent learning (Topic) or feature*
           趋势,以帮助该领域研究者更好地把握未来的研究方向。                                extraction (Topic) or feature* mining (Topic) or
                                                                    feature* learning (Topic) or machine learning (Topic)
           1 资料与方法                                                  or feature* selection (Topic) or unsupervised
           1.1 资料来源及检索策略 检索 Web of Science Core                     clustering (Topic) or image* segmentation (Topic)
                                                                    or  supervised  learning  (Topic)  or  semantic
           Collection(WoSCC) 的 Science Citation Index Expanded  4#  segmentation (Topic) or deep network* (Topic)  1 068 667
           (SCI-E)数据库,检索时间 2000-01-01 至 2022-04-                    or bayes* network (Topic) or deep learning (Topic)
                                                                    or neural network* (Topic) or neural learning
           06。所有检索工作于 2022-04-06 完成,以确保没有数                          (Topic) or neural nets model (Topic) or artificial
           据更新。共检索到文献 1 074 篇,剔除非英语 2 篇、与                           neural network (Topic) or data mining (Topic) or
                                                                    graph mining (Topic) or data clustering (Topic)
           主题不相关 141 篇、文献类型不符(非研究类、综述类                              or big data (Topic) or knowledge graph (Topic)
           文章)12 篇、重复发表 1 篇,最终得到 918 篇有效文献,                         or AI (Topic) and Article OR Review (Document
                                                                    Type) and English (Language)
           具体检索策略见表 1。
                                                                5#   3# AND 4#                           1 074
           1.2 数据处理 文献数据由 2 名课题组成员分别下载
   115   116   117   118   119   120   121   122   123   124   125