人工智能在检验医学发展中的重要作用

检验大数据涉及全身各系统并随着疾病的变化而变化,纵横交错,导致目前我们还没有突破检验结果综合分析的瓶颈。借助人工智能,通过检验大数据处理,根据疾病特点对检验数据结果进行全面的综合分析,通过模拟、延伸和扩展将检验数据与疾病的诊断、鉴别诊断、治疗效果评价和预后判断联系起来,产生具有最高水平的智能分析,突破人脑对巨大数据同时...     

Artificial intelligence meets hematology

The application of artificial intelligence (AI) in hematology it not new at all. However, it increasingly becomes part of the measurement of hematological parameters and subsequently also influences decision making. Here some examples are provided where well established parameters could be exploited better, if data are not reduced to single values but instead the entire data generation process is considered. Furthermore applications of artificial neural networks (ANN), point of care (PoC) devices and the internet of things (IoT) are discussed. Beside all the technical advancements human judgement will remain the last decision.     

胃镜联合腹腔镜治疗胃间质瘤的围手术期护理

目的:总结胃镜联合腹腔镜治疗胃间质瘤的围手术期护理要点。方法:对5例行胃镜联合腹腔镜治疗胃间质瘤的病人术前充分评估,做好心理护理、皮肤准备;术后加强饮食、活动、管道、用药护理,密切观察病情,及早发现或预防并发症。结果:5例病人术后恢复良好,未发生并发症,均于术后1周左右出院。结论:细致周到的围手术期护理是保证胃镜联合腹腔镜治疗胃间质瘤成功的关键。     

Artificial intelligence for COVID-19 and future pandemics: A mini-review

The pandemic of severe acute respiratory syndrome coronavirus 2 has spread very quickly all over the world and has become an unparalleled public health crisis. This unforeseen and exceptional situation has instigated a wave of research to investigate the virus, track its spread, and study the disease it causes. Current methods of diagnosis and monitoring largely rely on polymerase chain reactions and enzyme-linked immunesorbent assay methods. In this hour of crisis, researchers are looking for new technologies to monitor and control such disease outbreaks. Artificial intelligence (AI) is one such technology. Being an evidence-based tool, this technology has the potential to upgrade our disease management strategies and help us to restrict the spread of such diseases. AI can play an effective role in tracking the spread of diseases, screening of the population, identifying patients and developing treatments of diseases. Through this review, we aim to analyze the role of AI in the diagnosis, monitoring and treatment of diseases like coronavirus disease 2019, with most recent updates and assess the prospects of this technology in the management of such diseases.     

Artificial intelligence ecosystem for computational psychiatry: Ideas to practice

Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms. One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable. This may help researchers develop more effective treatments and interventions for mental health problems. This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry. The artificial intelligence ecosystem for computational psychiatry includes data acquisition, preparation, modeling, application, and evaluation. This approach allows researchers to integrate data from a variety of sources, such as brain imaging, genetics, and behavioral experiments, to obtain a more complete understanding of mental health conditions. Through the process of data preprocessing, training, and testing, the data that are required for model building can be prepared. By using machine learning, neural networks, artificial intelligence, and other methods, researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors. Despite the continuous development and breakthrough of computational psychiatry, it has not yet influenced routine clinical practice and still faces many challenges, such as data availability and quality, biological risks, equity, and data protection. As we move progress in this field, it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.     

人工智能在甲状腺结节超声诊断中的应用进展

超声作为甲状腺病变的首选检查方法,可在发现病灶的同时对其生物学行为进行初步判断,具有便捷、安全等优势,但存在一定的操作者依赖性.人工智能的发展为临床工作提供了第二种意见,可辅助医师发现病灶,提高诊断准确性,减少人为因素所致的诊断偏倚.基于深度学习网络所构建的计算机辅助诊断系统,其诊断能力在一定程度上可与经验丰富的超声医...     

脑性瘫痪患儿智力水平及智力结构的探讨

目的　探讨脑性瘫痪儿童的智力水平及智力结构情况,并观察其运动障碍严重程度对患儿智力的影响。方法　采用修订版韦氏儿童智力量表(WISC CR)对45例脑性瘫痪(包括轻、中、重度患儿)患儿进行测试,并比较其智商及智力结构间的差异。结果　本组脑性瘫痪患儿的平均总智商为( 70. 02±19. 50),较正常人群偏低;语言智商(79. 80±18. 88)与操作智商( 64. 24±19. 28 )进行比较,两者间差异有统计学意义(P<0. 01);各患者Bannatyne四因素间差异有统计学意义,特别是序列因素分值较低;另外,不同严重程度的脑性瘫痪患儿智商及智力结构间差异均有统计学意义。结论　本研究结果表明,脑性瘫痪患儿智力水平滞后,其智力结构也存在不平衡现象,而且其运动功能障碍也在一定程度上影响了患儿的智力水平及智力结构。     

应用胃镜诊断胃癌160例临床分析

目的探讨胃癌的发病特点。方法我院2005年1月至2010年12月通过胃镜加活检确诊胃癌患者160例,对其临床资料进行回顾性分析。结果胃癌患者幽门螺杆菌（HP）感染率较高[71．25％（114／160）],且男性感染率较女性偏高,随年龄增长呈上升趋势（Z=2．303,P=0．021）;胃癌大体形态：≤35岁者以Borrmann Ⅲ、Ⅳ型为主（9例）,随年龄增长BorrmannⅢ、Ⅳ型减少,BorrmannⅠ、Ⅱ型增加;男女胃癌发病比例为2．26：1,但青年人中女性发病率明显高于男性,随年龄增长男性胃癌发病率明显高于女性（Z=3．599,P〈0．001）;各部位胃癌组织类型均以低分化腺癌为主,随年龄增长低分化腺癌等高度恶性癌有下降趋势（x2=9．831,P=0．042）。结论胃癌发病与HP感染有关;随年龄增长,BorrmannⅢ、Ⅳ型发病率呈下降趋势,BorrmannⅠ、Ⅱ型呈上升趋势;男性发病率高于女性;发病部位呈上移趋势;高恶性度比例呈下降趋势。     

数字人体与人工智能--生命科学与信息科学的融合

"数字人体--人体系统数字学"是在信息科学、系统科学、生物科学、生命科学、中西医学、计算机与自动化科学技术等多学科交叉、综合集成的基础上产生的新学科.将人工智能与数字人体相结合,是目前人工智能研究的新方向.该文介绍了数字人体的概念和研究方法,分析了人工智能的发展状况,指出两者之间的内在的联系,并给出了结合实例.     

Artificial intelligence and computer simulation models in critical illness

Widespread implementation of electronic health records has led to the increased use of artificial intelligence (AI) and computer modeling in clinical medicine. The early recognition and treatment of critical illness are central to good outcomes but are made difficult by, among other things, the complexity of the environment and the often non-specific nature of the clinical presentation. Increasingly, AI applications are being proposed as decision supports for busy or distracted clinicians, to address this challenge. Data driven “associative” AI models are built from retrospective data registries with missing data and imprecise timing. Associative AI models lack transparency, often ignore causal mechanisms, and, while potentially useful in improved prognostication, have thus far had limited clinical applicability. To be clinically useful, AI tools need to provide bedside clinicians with actionable knowledge. Explicitly addressing causal mechanisms not only increases validity and replicability of the model, but also adds transparency and helps gain trust from the bedside clinicians for real world use of AI models in teaching and patient care.     

基于CiteSpace知识图谱的甲状腺超声人工智能可视化分析

目的：通过对2013-2023年甲状腺超声及人工智能研究方向的中英文文献进行计量、共现及可视化分析,总结该领域近期研究进展及梳理知识结构。方法：以中国知网（CNKI）及Web of Science为来源数据库,检索关于甲状腺超声及人工智能的相关文献,利用CiteSpace分析软件进行作者、机构、关键词的图谱绘制,进行文献计量分析。结果：共纳入文献9515篇,涉及34 个机构,119 个关键词。对发文量和发文的增长速度进行分析,知识图谱显示国内发文数量整体较国际发文量高,国内及国际发文量分别自2013、2018年起逐年上升,近两年增长速度减缓。国内发表文章较多的作者为姜珏、詹维伟、罗渝昆、周琦、雷小莹、张波等人。国际发表文章较多的作者Paul、Saba、Suri等人。国内231个机构、国际上共226个机构发表了相关文献,其中国内发文量前3的机构包括上海交通大学医学院附属瑞金医院超声科（21篇）,北京协和医院超声医学科（10篇）,西安交通大学第二附属医院超声研究室（5篇）和中国医科大学附属盛京医院超声科（5篇）。国际发文量前3的机构包括Zhejiang Univ（9篇） ,Shanghai Jiao Tong Univ（7篇）,Sun Yat Sen Univ（7篇）和Huazhong Univ Sci & Technol（7篇）。机构间合作关系主要以Zhejiang Univ、Shanghai Jiao Tong Univ为核心的国内机构及以North Eastern Hill Univ为核心的国外机构。关键词分析结果显示,国内文献主要集中在多模态超声用于甲状腺结节良恶性的鉴别上,国际文献更偏向于机器深度学习,人工智能方向。结论：通过CiteSpace进行可视化分析,发现国内及国际研究人员对于甲状腺超声人工智能的关注度不断提高,但仍需加强跨机构、跨团队、跨区域的多中心协作,进一步深入研究。     

人工智能在慢性病患者健康管理中的应用进展

慢性病因其长期性、难治愈性成为威胁患者健康的重要公共卫生问题之一,人工智能为实现高效的慢性病健康管理提供了方法。该文对人工智能及其在慢性病健康管理领域中的应用现状进行综述,同时对应用中存在的问题进行总结并提出展望,以期为人工智能在慢性病健康管理中的应用提供借鉴。     

1195例胃大部切除术后残胃病变临床与内镜检查分析

目的通过分析胃大部切除术后残胃病变的临床特点及内镜表现,探讨不同手术方式对病变的影响。方法将本院1984年4月至2008年10月检出的1195例残胃患者按毕Ⅰ式和毕Ⅱ式进行分组,对其临床症状、内镜表现、病理结果及随访情况进行回顾性分析。结果胃大部切除术后残胃病变发生率高达98．08％,毕Ⅱ式术后残胃及吻合口炎（90．77％）、胆汁反流（71．59％）、残胃原发癌（4．55％）的发生率均显著高于毕Ⅰ式（51．15％、34．48％、1．72％）,P〈0．01,残胃及吻合口溃疡发生率则是毕Ⅰ式（28．45％）明显高于毕Ⅱ式（16．73％）,P〈0．01,其余残胃病变两组比较差异无统计学意义（P〉0．05）。结论胃大部切除术是治疗胃恶性肿瘤、消化性溃疡及其严重并发症的主要方法,毕Ⅱ式较毕Ⅰ式术后更易发生并发症;近年来,残胃病变发病率有下降趋势;定期复查内镜及病理是防治残胃病变尤其是残胃癌的重要措施。     

2013年上海嘉定地区胃镜筛查胃癌漏诊的临床研究

目的:分析2013年间上海市嘉定地区5所医院共24 837例门诊行胃镜筛查患者的胃癌漏诊情况。方法:由经专业培训的内镜操作者对24 837例曾行胃镜筛查的患者再次施行胃镜检查,对可疑病灶行多块、多方向活检,其中经病理诊断胃癌或癌疑者,根据不同病灶施行外科手术或内镜切除术,切除标本行系列病理切片检查。回顾性分析所有患者1年内的病史,并查阅其以往的胃镜检查资料,确定是否符合胃癌漏诊标准;胃癌漏诊者分析其漏诊原因。结果:胃镜活检病理结果提示,24 837例患者中胃癌297例(1.2%),其中99例患者在嘉定地区接受手术治疗,术后病理证实早期胃癌11例(11.1%),进展期胃癌87例(87.9%),胃黏膜相关淋巴组织淋巴瘤1例(1.0%)。99例患者中,8例(8.1%)为前次胃镜筛查漏诊,其前期平均行胃癌相关胃镜检查3.5次,活检病理结果均为慢性胃炎或伴肠腺化生,与本次胃癌相关的临床就诊至明确诊断时间平均为12.5个月。8例漏诊患者在本次胃镜活检病理检查中均证实为胃癌或癌疑,术后病理证实为早期胃癌4例,未见淋巴结转移;进展期胃癌3例,其中2例附近淋巴结转移;另1例为胃黏膜相关淋巴组织淋巴瘤。结论:99例手术治疗的胃肿瘤患者中,属前期胃镜检查漏诊的患者为8例(8.1%),漏诊原因包括未发现明确的病灶、恶性溃疡及糜烂误判为良性疾病、活检病理无肿瘤依据等,应引起临床高度重视。     

Measurement of glutathione S-transferase and its class-pi in plasma and tissue biopsies obtained after laparoscopy and endoscopy from subjects with esophagus and gastric cancer

OBJECTIVES: To develop an indirect enzyme-linked immunosorbent assay (ELISA) for measuring class-pi glutathione S-transferase (GST) in plasma, and tissue biopsies obtained from upper gastrointestinal cancer (UGI Ca) patients. METHODS: GST activity and GST-pi concentration were detected in normal human squamous esophageal epithelium, normal gastric cardia and their corresponding malignant tumor biopsies. RESULTS: Plasma GST was significantly higher (p < 0.05) in UGI Ca patients as compared to those obtained from normal individuals. Plasma GST-pi concentration in normal subjects was 6.6 +/- 1.9 ng/mg protein, whereas it was higher in UGI Ca patients (esophageal, 10.0 +/- 1.8; gastric, 10.7 +/- 1.7 ng/mL, p 相似文献   

Artificial intelligence promotes shared decision-making through recommending tests to febrile pediatric outpatients

BACKGROUND: To promote the shared decision-making(SDM) between patients and doctors in pediatric outpatient departments, this study was designed to validate artificial intelligence(AI)-initiated medical tests for children with fever.METHODS: We designed an AI model, named Xiaoyi, to suggest necessary tests for a febrile child before visiting a pediatric outpatient clinic. We calculated the sensitivity, specificity, and F1 score to evaluate the efficacy of Xiaoyi’s recommendations. The patients w...     

人工智能辅助床旁超声诊断肾创伤的基础研究

目的探讨基于卷积神经网络（CNN）构建的人工智能辅助诊断模型对肾钝性创伤超声诊断的应用价值。 方法建立不同程度动物肾创伤模型,通过床旁超声仪采集正常肾及创伤肾超声图片,分成训练集及测试集,根据造模位置和超声造影结果,手动勾画出肾轮廓,采用3折交叉验证进行分类训练及测试。绘制受试者工作特征（ROC）曲线,计算人工智能辅助诊断模型的敏感度、特异度、准确性和曲线下面积（AUC）。 结果采集正常肾图片共1737张,各级别创伤肾图片共2125张,经过对测试集的验证,该模型可自动对肾创伤有无进行分类,对肾创伤诊断的平均敏感度为73%、平均特异度为85%、平均准确性为79%、AUC为0.80,诊断价值较高。 结论基于CNN构建的深度学习模型辅助床旁超声仪在诊断肾创伤有无分类中取得了较满意的结果。     

转移性卵巢癌临床研究分析

目的探讨转移性卵巢癌疾病的诊断及治疗。方法回顾分析临床及病理明确诊断转移性卵巢癌52例。结果:转移性卵巢癌病人中有腹胀表现为42例(80.77%)、少量至中量腹水38例(73.08%),B超提示卵巢肿瘤直径小于10cm41例(78.85%),CA125小于200U/ml48例(92.31%)及CEA大于10ng/ml共47例(90.38%),CA125/CEA比值介于5-10者共有46例(88.46%)。经过手术及有效化疗5-6疗程的病人31例(59.62%)平均生存期为14.45个月,手术未行化疗及仅化疗3疗程以下的病人21例(40.38%)平均生存期为5.9个月,此两组经LogRank检验(P<0.01)有显著差别。结论:卵巢肿瘤病人,如有腹胀、腹水、B超示卵巢肿瘤直径小于10cm、CA125小于200U/ml及CEA大于10ng/ml、CA125/CEA比值介于5-10,应高度怀疑转移性卵巢癌;并应积极给予手术加有效足够的化疗以延长病人的生存时间。同时还应给予病人心理治疗。