检索结果-内蒙古大学图书馆

Artificial intelligence in cardiovascular medicine: clinical applications

EUROPEAN HEART JOURNAL 2024年第40期45卷 4291-4304页

作者： Luscher, Thomas F. Wenzl, Florian A. D'Ascenzo, Fabrizio Friedman, Paul A. Antoniades, Charalambos Royal Brompton & Harefield Hosp London England Imperial Coll London Natl Heart & Lung Inst London England Kings Coll London Cardiovasc Acad Grp London England Univ Zurich Ctr Mol Cardiol Wagistr 12 CH-8952 Schlieren Zurich Switzerland NHS Natl Dis Registrat & Anal Serv London England Univ Leicester Dept Cardiovasc Sci Leicester England Karolinska Inst Dept Clin Sci Stockholm Sweden Citta Salute & Sci Hosp Cardiovasc & Thorac Dept Div Cardiol Turin Italy Mayo Clin Dept Cardiovasc Med Rochester MN USA Mayo Fdn Rochester MN USA Univ Oxford Acute Multidisciplinary Imaging & Intervent Ctr RDM Div Cardiovasc Med Oxford OX39DU England

Graphical Abstract Clinical information including patient data, laboratory parameters, and results from clinical examination, large-scale data from (multi-)national registries, imaging data, and (patient) biometrical data can all be processed by artificial intelligence. Resulting models allow for disease phenotyping, enhance diagnostics, improve prognostication, and facilitate treatment decision-making, thus ultimately contributing to a more personalized therapy of patients with cardiovascular disease. Clinical medicine requires the integration of various forms of patient data including demographics, symptom characteristics, electrocardiogram findings, laboratory values, biomarker levels, and imaging studies. Decision-making on the optimal management should be based on a high probability that the envisaged treatment is appropriate, provides benefit, and bears no or little potential harm. To that end, personalized risk-benefit considerations should guide the management of individual patients to achieve optimal results. These basic clinical tasks have become more and more challenging with the massively growing data now available;artificial intelligence and machine learning (AI/ML) can provide assistance for clinicians by obtaining and comprehensively preparing the history of patients, analysing face and voice and other clinical features, by integrating laboratory results, biomarkers, and imaging. Furthermore, AI/ML can provide a comprehensive risk assessment as a basis of optimal acute and chronic care. The clinical usefulness of AI/ML algorithms should be carefully assessed, validated with confirmation datasets before clinical use, and repeatedly re-evaluated as patient phenotypes change. This review provides an overview of the current data revolution that has changed and will continue to change the face of clinical medicine radically, if properly used, to the benefit of physicians and patients alike.

关键词： Artificial intelligence Deep learning diagnostic algorithms Face recognition ECG Imaging Outcome prediction

来源：评论

学校读者我要写书评

暂无评论

Transient/Toxic Synovitis

引用

ORTHOPEDIC CLINICS OF NORTH AMERICA 2024年第4期55卷 471-477页

作者： Pargas-Colina, Carlos D. Univ Tennessee Dept Orthopaed Surg Campbell Clin Memphis TN USA Univ Tennessee Lebonheur Childrens Hosp Campbell Clin 324 Night Sail Dr North Apartment 110 Memphis TN 38103 USA

TS of the hip is an acute inflammatory arthritis commonly triggered by infection, characterized by pain, swelling, warmth, and erythema in the affected joint. It poses a diagnostic challenge due to similarities with other hip pathologies like septic arthritis. Diagnosis relies on medical history, physical examination, blood tests, and imaging. Treatment is conservative, focusing on pain relief with analgesics and NSAIDs, while corticosteroids are reserved for severe cases after infection is ruled out. The prognosis is generally good, with spontaneous resolution, but recurrence can happen, and vigilance for complications is necessary. This condition typically has a benign course.

关键词： Acute inflammatory arthritis Transient Self-limited Septic arthritis diagnostic algorithms Ultrasounds Blood tests Medical anti-inflammatory measures

来源：评论

学校读者我要写书评

暂无评论

X-ray PCB defect automatic diagnosis algorithm based on deep learning and artificial intelligence

引用

NEURAL COMPUTING & APPLICATIONS 2023年第36期35卷 25263-25273页

作者： Liu, Yaojun Wang, Ping Liu, Jingjing Liu, Chuanyang Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing 210002 Jiangsu Peoples R China Wuhu State Owned Factory Machining Wuhu 241000 Anhui Peoples R China Chizhou Univ Coll Mech & Elect Engn Chizhou 247000 Anhui Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Nanjing 210002 Jiangsu Peoples R China

As a main electronic material, X-ray circuits are widely used in various electronic devices, and their quality has an important impact on the overall quality of electronic products. In the process of mass production of circuit boards, due to the large number of layers, tight lines and some harmful external factors, circuit board quality may be problematic. Detecting circuit board defects are important for improving the reliability of electronic products. This paper introduces deep learning and artificial intelligence technology to conduct research on the automatic detection of X-ray circuit board defects. The study used a defect detection system to study X-ray circuit boards as a detection object and obtained the structure, lighting system and composition of the detection system. The working principle of the detection system is explained, and the image is preprocessed. Testing the processing performance of the PCB defect detection system, when the number of pixels is 6526, 7028, 7530 and 8032, the time consumption ratios between the proposed detection system and image processing on a traditional PC are 35.17%, 35.4%, 35% and 35.28%, respectively. The experimental results make a certain contribution to the future artificial intelligence X-ray PCB defect automatic diagnosis algorithm.

关键词： Artificial intelligence Artificial neural networks Circuit board defects diagnostic algorithms

来源：评论

学校读者我要写书评

暂无评论

Current challenges and emerging tools in endometrial cancer diagnosis

引用

INTERNATIONAL JOURNAL OF GYNECOLOGICAL CANCER 2025年第4期35卷 100056页

作者： Aznar, Ana Luzarraga Canton, Roger Loren, Guillem Carvajal, Javier de la Calle, Irene Masferrer-Ferragutcasas, Carina Serra, Francesc Bebia, Vicente Bonaldo, Giulio Angeles, Martina Aida Cabrera, Silvia Palomar, Nuria Vilarmau, Cristina Marti, Maria Rigau, Marina Colas, Eva Gil-Moreno, Antonio Vall dHebron Univ Hosp Dept Gynecol Oncol Barcelona Spain MiMARK Diagnost SL Parc Cientif Barcelona Barcelona Spain Univ Autonoma Barcelona Vall dHebron Inst Res Biomed Res Grp Gynecol CIBERONC Barcelona Spain Hosp Santa Creu i St Pau Barcelona Spain

The diagnostic process of endometrial cancer includes imaging methods such as trans-vaginal ultrasound, along with procedures to obtain endometrial tissue for histologic evaluation. Common techniques for tissue sampling include Pipelle endometrial biopsy, hysteroscopy, and dilation and curettage, which are used to confirm the diagnosis, determine tumor histology, grade, and molecular profile. However, diagnostic algorithms for endometrial cancer differ significantly across countries, influenced by local resources, protocols, and the availability of diagnostic methods. These variations include differences in the endometrial thickness threshold for recommending a biopsy and the choice of the initial diagnostic test. Moreover, patients often have multiple tests and appointments before a definitive diagnosis, although only 5%-10% of women with post-menopausal bleeding are diagnosed with endometrial cancer. Current diagnostic techniques have limitations. Pipelle endometrial biopsy has a significant false-negative rate (10%-20%) and may fail to provide adequate diagnostic material in up to 30% of cases. Hysteroscopy, while useful, is associated with pain in up to 65% of patients and can delay diagnosis because of limited availability. Dilation and curettage is an invasive procedure requiring general anesthesia and has a higher complication rate. In response to these challenges, there is growing interest in developing new diagnostic tools that are less invasive and provide 1-step diagnoses, including liquid biopsies from urine, blood, cervico-vaginal and endometrial fluid samples by means of genomics and proteomics. This review will examine the current diagnostic algorithms in European and American guidelines, evaluate the sensitivity, specificity, and accuracy of current techniques, and explore new diagnostic tools under development.

关键词： Endometrial Cancer Diagnosis diagnostic algorithms Proteomics Genomics Pipelle

来源：评论

学校读者我要写书评

暂无评论

Contemporary imaging examinations for (suspected) stress fractures

引用

UNFALLCHIRURGIE 2023年第11期126卷 831-838页

作者： Arevalo Hernandez, Andres Mittlmeier, Thomas Weber, Marc-Andre Univ Med Rostock Inst Diagnost & Interventionelle Radiol Kinder & N Rostock Germany Univ Med Rostock Klin Unfall Hand & Wiederherstellungschirurgie Rostock Germany Univ Med Rostock Inst Diagnost & Intervent Radiol Kinder & Neurorad Ernst Heydemann Str 6 D-18057 Rostock Germany

Stress fractures belong to the group of atraumatic fractures. A low-impact and repetitive load is the underlying cause and no fracture would occur under physiological circumstances. The conventional X-ray examination remains the initial imaging modality when a stress fracture is suspected. In contrast, magnetic resonance imaging (MRI) is the gold standard and is also used to rule out other pathological changes. Computed tomography (CT) should be included if the MRI findings are unclear. New techniques, such as dual energy computed tomography (DECT) and magnetic resonance bone imaging (MR bone) should be used more frequently in practice in the future and become increasingly more important for the correct diagnosis.

关键词： Fatigue fractures CT like MR-Bone Dual energy CT diagnostic algorithms

来源：评论

学校读者我要写书评

暂无评论

Clinical Testing Guidance for Coccidioidomycosis, Histoplasmosis, and Blastomycosis in Patients With Community-Acquired Pneumonia for Primary and Urgent Care Providers

引用

CLINICAL INFECTIOUS DISEASES 2023年第6期78卷 1559-1563页

作者： Smith, Dallas J. Free, Rebecca J. Thompson III, George R. Baddley, John W. Pappas, Peter G. Benedict, Kaitlin Gold, Jeremy A. W. Tushla, Lisa A. Chiller, Tom Jackson, Brendan R. Toda, Mitsuru Ctr Dis Control & Prevent Epidem Intelligence Serv Atlanta GA USA Div Foodborne Waterborne & Environm Dis Mycot Dis Branch Atlanta GA USA Univ Calif Davis Div Infect Dis Dept Internal Med Med Ctr Sacramento CA USA Univ Calif Davis Dept Med Microbiol & Immunol Med Ctr Sacramento CA USA Univ Calif Davis Ctr Valley Fever Sacramento CA USA Univ Maryland Sch Med Div Infect Dis Baltimore MD USA Baltimore VA Med Ctr Baltimore MD USA Univ Alabama Birmingham Sch Med Dept Med Div Infect Dis Birmingham AL USA Terranova Med LLC Colorado Springs CO USA

Coccidioidomycosis, histoplasmosis, and blastomycosis are underrecognized and frequently misdiagnosed fungal infections that can clinically resemble bacterial and viral community-acquired pneumonia. This guidance is intended to help outpatient clinicians test for these fungal diseases in patients with community-acquired pneumonia to reduce misdiagnoses, unnecessary antibacterial use, and poor outcomes.

关键词： coccidioidomycosis histoplasmosis blastomycosis community-acquired pneumonia diagnostic algorithms

来源：评论

学校读者我要写书评

暂无评论

Traumatic hip dislocations in children and adolescents: diagnostic challenges and the significance of MRI imaging-a multi-center study

引用

EUROPEAN JOURNAL OF TRAUMA AND EMERGENCY SURGERY 2025年第1期51卷 1-11页

作者： Braun, Mirjam Evi Fernandez Fernandez, Francisco Riha, Lena Schmal, Hagen Schmittenbecher, Peter Schneidmueller, Dorien Struewind, Christoph Schwerk, Philipp Reineke, Sebastian Traub, Frank Ihle, Christoph Lieber, Justus Wack, Christina Ruether, Hauke Baumann, Florian Marzi, Ingo Busse, Lewin-Caspar Tueshaus, Ludger Adrian, Miriam Bergmann, Florian Graf, Alexander Kaiser, Martin M. Loose, Oliver Philipps Univ Marburg Marburg Germany Olga Hosp Klinikum Stuttgart Dept Orthopaed Stuttgart Germany Univ Tubingen Tubingen Germany Albert Ludwigs Univ Freiburg Freiburg Univ Hosp Dept Orthoped Surg & Traumatol Freiburg Germany Univ Hosp Odense Dept Orthoped Surg Odense Denmark Stadt Klinikum Karlsruhe Dept Pediat Surg Moltkestr 90 Karlsruhe Germany BG Unfallklin Murnau Dept Pediat Trauma Surg & Pediat Orthopaed Prof Kuntscher Str 8 Murnau Germany Klinikum Garmisch Partenkirchen Dept Trauma Surg Garmisch Partenkirchen Germany BG Unfallklin Murnau Dept Trauma Surg Prof Kuntscher Str 8 Murnau Germany Tech Univ Dresden Univ Hosp Dresden Dept Pediat Surg Fetscherstr 74 Dresden Germany Gesundheit Nordhessen Holding AG Clin Pediat Surg & Pediat Urol Kassel Germany Gesundheit Nordhessen Holding AG Ctr Children Severe Burn Injuries Kassel Germany Univ Med Ctr Mainz Dept Orthoped & Traumatol Mainz Germany Eberhard Karls Univ Tuebingen Dept Trauma & Reconstruct Surg BG Unfallklin Tubingen Germany Univ Childrens Hosp Dept Pediat Surg & Pediat Urol Hoppe Seyler Str 1 Tubingen Germany Philipps Univ Marburg Univ Hosp Giessen & Marburg GmbH Ctr Orthopaed & Trauma Surg Baldingerstr Marburg Germany Univ Med Ctr Gottingen Clin Trauma Surg Orthopaed & Plast Surg Gottingen Germany Regensburg Univ Med Ctr Franz Josef Straus Allee 11 D-93053 Regensburg Germany Goethe Univ Frankfurt Univ Hosp Dept Trauma Surg & Orthopaed Theodor Stern Kai 7 Frankfurt Germany Univ Med Ctr Schleswig Holstein Dept Pediat Surg Campus Lubeck Lubeck Germany Univ Hosp Mannheim Fac Heidelberg Clin Pediat Surg Mannheim Germany Ludwig Maximilians Univ Munchen Dr Von Hauner Childrens Hosp Dept Pediat Surg Lindwurmstr 4 Munich Germany Ortenau Klinikum Offenburg Dept Trauma Med & Orthopaed Special Orthopaed Surg Offenburg Kehl Germany Univ Hosp Pediat Traumatol & Pediat Surg Chief Dept Pediat Traumatol BG Trauma Ctr Bergmannstrost Merseburger Str 165 D-06112 Halle Germany

BackgroundTraumatic hip dislocations in children and adolescents are rare but can lead to severe outcomes like avascular necrosis. Delayed reductions, often due to overlooked dislocations in initial imaging, pose a major risk. The variability in symptoms and emergency care challenges early diagnosis. This multi-center study evaluates diagnostic approaches to enhance protocols for identifying traumatic hip dislocations in *** retrospective multi-center study included 76 patients (aged <= 17 years) with acute traumatic hip dislocations and open growth plates from 16 German hospitals. Patient data and imaging from 1979 to 2022 were analyzed, with statistical evaluation performed using SPSS under ethical ***-rays (single and biplanar views) were the primary diagnostic method, utilized in 85% of cases. Dislocations were missed in 12% (9 cases), primarily among children under eight years, with half of those under four. Delayed reductions (15.8%, n = 12) were linked to undetected dislocations in imaging in 9 cases. Conventional X-rays frequently missed dislocations, whereas MRI successfully identified all cases. Among the 76 patients, 54 (71%) had associated injuries, with 57.9% (n = 44) diagnosed exclusively via *** diagnosis of traumatic hip dislocations is crucial, as delays increase the risk of femoral head necrosis. An algorithmic approach is essential for young children, where dislocations may not be readily suspected. MRI is vital in the secondary diagnostic phase, providing superior visualization of associated injuries, including acetabular avulsions and soft tissue interpositions highlighting the need for integration of MRI into a unified diagnostic algorithm for children suspected of such *** of evidenceIV.

关键词： Traumatic hip dislocation Avascular necrosis MRI Concomitant injuries Children diagnostic algorithms

来源：评论

学校读者我要写书评

暂无评论

Prospects for artificial intelligence-enhanced electrocardiogram as a unified screening tool for cardiac and non-cardiac conditions: an explorative study in emergency care

引用

EUROPEAN HEART JOURNAL - DIGITAL HEALTH 2024年第4期5卷 454-460页

作者： Strodthoff, Nils Alcaraz, Juan Miguel Lopez Haverkamp, Wilhelm Carl von Ossietzky Univ Oldenburg Sch Med & Hlth Serv 6 Dept Hlth Serv Res Ammerlander Heerstr 114-118 D-26129 Oldenburg Germany Charite Univ Med Berlin Dept Cardiol & Metab Clin Cardiol Angiol & Intens Care Med Berlin Germany

Aims Current deep learning algorithms for automatic ECG analysis have shown notable accuracy but are typically narrowly focused on singular diagnostic conditions. This exploratory study aims to investigate the capability of a single deep learning model to predict a diverse range of both cardiac and non-cardiac discharge diagnoses based on a single ECG collected in the emergency *** and results In this study, we assess the performance of a model trained to predict a broad spectrum of diagnoses. We find that the model can reliably predict 253 ICD codes (81 cardiac and 172 non-cardiac) in the sense of exceeding an AUROC score of 0.8 in a statistically significant *** The model demonstrates proficiency in handling a wide array of cardiac and non-cardiac diagnostic scenarios, indicating its potential as a comprehensive screening tool for diverse medical encounters.

关键词： Artificial intelligence ECG analysis Deep learning diagnostic algorithms Clinical decision support system

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Analysis of Brain MRI for Enhanced Diagnosis of Multiple Sclerosis 5

Deep Learning-based Analysis of Brain MRI for Enhanced Diagn...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Pavani, V. Vijayalakshmi, N. Harika, N. Sowjanya, G. SriLakshmi Deepthi, V. Vignan's Nirula Institute of Technology and Science for Women Department of Information Technology Pedapalakaluru Andhra Pradesh Guntur India

ISBN: (纸本)9798350389609

A neuro degenerative disease that worsens over time, Multiple Sclerosis (MS), where early and exact diagnosis of the disease will lead to an improved treatment. In this research, a new method is introduced to diagnose MS through deep learning techniques by developing and assessing an enhanced neural network model called MS-CNN. Here, we propose MS-CNN that utilizes Deep Convolution Neural Networks (DCNNs) to automatically analyze brain MR images for improved diagnostic accuracy and efficiency. In particular we provided an end-to-end evaluation of MS-CNN on a dataset made up by MRI images divided in healthy-MS. Evaluation on CIFAR-100 dataset was carried out against two popular existing models, ResNet-50 and VGG-16 with MS-CNN. The parameters used for evaluation include sensitivity, specificity, accuracy, precision, and F1 score implemented and done with best results followed by AUC-ROC and processing time. MS-CNN does much better across the board among the models and get higher accuracy up to 94.0%, sensitivity up to 94.0% and specificity up to 95.0%. These results show that MS-CNN not only increases accuracy for diagnosing the disease, but also substantially decreases processing time to provide a feasible solution when instantaneous detection and monitoring are needed with regards to such cases in real-time possible by deep learning technology. © 2024 IEEE.

关键词： Brain MRI Deep Learning diagnostic algorithms Medical Imaging Multiple Sclerosis Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Predicting ADHD Subtypes Using Machine Learning on Brain Imaging Data

Predicting ADHD Subtypes Using Machine Learning on Brain Ima...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Baruah, Anganabha Kaur, Amanpreet Christ University Department of Psychology Bengaluru560029 India Manav Rachna international institute of research and studies Department of Applied Psychology Delhi NCR. Haryana 121003 India

ISBN: (纸本)9798331543617

The use of machine learning approaches to differentiate between various types of Attention Deficit Hyperactivity Disorder (ADHD) using information from brain imaging. Our goal is to reduce the sensitivity of the ADHD subtype evaluation by using advanced neuroimaging technologies, such as structural and functional magnetic resonance imaging (MRI), in combination with intelligent machine learning algorithms. Our methodology involves preprocessing brain MRI data, point birth, and training colored machine literacy models to categorize various forms of attention-deficit/hyperactivity disorder (ADHD). The performance of these models is assessed within the parameters of this study using attributes that are similar to recall, perfection, and delicacy. According to preliminary research, machine literacy may effectively distinguish between various forms of attention-deficit/hyperactivity disorder (ADHD), which offers a foundation for more precise and well-established therapeutic approaches. In addition to assisting people in realizing their greatest potential, this approach clarifies the brain processes underlying attention-deficit/hyperactivity disorder (ADHD). Our results suggest that the individual procedure for attention-deficit/hyperactivity disorder (ADHD) could be rewritten by combining brain imaging data with machine literacy. This would lead to better clinical concerns and more tailored remedial actions. © 2024 IEEE.

关键词： ADHD Subtypes Brain Imaging diagnostic algorithms Functional MRI Machine Learning Neuroimaging Predictive Modeling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：