Result 1 - 10 of total 271
2020
| Keywords | covid19 |
|---|---|
| Language | English |
| Publishing date | 2020-04-30 |
| Publishing country | us |
| Document type | Thesis ; Online |
| Database | BASE - Bielefeld Academic Search Engine (life sciences selection) |
Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.
2023 Volume 55, Issue 1, Page(s) 2215540
Abstract: Background: Orofacial clefts are the most common congenital malformation, but the global burden and trends of orofacial clefts have not been comprehensively analysed. The aim of this study was to assess the global incidence, deaths and disability- ... ...
| Abstract | Background: Orofacial clefts are the most common congenital malformation, but the global burden and trends of orofacial clefts have not been comprehensively analysed. The aim of this study was to assess the global incidence, deaths and disability-adjusted life years (DALYs) of orofacial clefts by countries, regions, sex and sociodemographic index (SDI) from 1990 to 2019. Methods: The data on orofacial clefts were obtained from the Global Burden of Disease Study 2019. The incidence, deaths and DALYs were analysed by countries, regions, sex and SDI. Age-standardized rates and estimated annual percentage change (EAPC) were calculated to evaluate the burden and temporal trend of orofacial clefts. The association between EAPC and the human development index was assessed. Results: Globally, the incidence, deaths and DALYs of orofacial clefts decreased from 1990 to 2019. The high SDI region showed the biggest downward trend in incidence rate from 1990 to 2019, along with the lowest age-standardized death rate and DALY rate. Some countries, such as Suriname and Zimbabwe, experienced increased death rate and DALY rate over time. The age-standardized death rate and DALY rate were negatively associated with the level of socioeconomic development. Conclusion: Global achievement is evident in the control of the burden of orofacial clefts. The future focus of prevention should be on low-income countries, such as South Asia and Africa, by increasing healthcare resources and improving quality.KEY MESSAGESThis is the most recent estimate of the global epidemiology of orofacial clefts, with some countries not previously assessed.The global burden of orofacial clefts showed downward trends from 1990 to 2019; however, some low-income countries are still suffering from increasing burdens.Effective measures should be taken to reduce the burden of orofacial clefts in the uncontrolled regions. |
|---|---|
| MeSH term(s) | Humans ; Quality-Adjusted Life Years ; Global Burden of Disease ; Cleft Lip/epidemiology ; Global Health ; Cleft Palate/epidemiology ; Incidence |
| Language | English |
| Publishing date | 2023-05-26 |
| Publishing country | England |
| Document type | Journal Article ; Research Support, Non-U.S. Gov't |
| ZDB-ID | 1004226-x |
| ISSN | 1365-2060 ; 1651-2219 ; 0785-3890 ; 1743-1387 |
| ISSN (online) | 1365-2060 ; 1651-2219 |
| ISSN | 0785-3890 ; 1743-1387 |
| DOI | 10.1080/07853890.2023.2215540 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
| Zs.A 680: Show issues | Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (1.OG) ab Jg. 2022: Lesesaal (EG) |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
2023 Volume 15, Issue 9
Abstract: As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer ... ...
| Abstract | As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer chemistry. However, in consideration of the small datasets of chemical reactions, the data-driven model suffers from the difficulty of low accuracy in the prediction tasks of chemical reactions. In this contribution, we integrate the molecular transformer model with the strategies of data augmentation and normalization preprocessing to accomplish the three tasks of chemical reactions, including the forward predictions of chemical reactions, and single-step retrosynthetic predictions with and without the reaction classes. It is clearly demonstrated that the prediction accuracy of the molecular transformer model can be significantly raised by the use of proposed strategies for the three tasks of chemical reactions. Notably, after the introduction of the 40-level data augmentation and normalization preprocessing, the top-1 accuracy of the forward prediction increases markedly from 71.6% to 84.2% and the top-1 accuracy of the single-step retrosynthetic prediction with additional reaction class increases from 53.2% to 63.4%. Furthermore, it is found that the superior performance of the data-driven model originates from the correction of the grammatical errors of the SMILES strings, especially for the case of the reaction classes with small datasets. |
|---|---|
| Language | English |
| Publishing date | 2023-05-08 |
| Publishing country | Switzerland |
| Document type | Journal Article |
| ZDB-ID | 2527146-5 |
| ISSN | 2073-4360 ; 2073-4360 |
| ISSN (online) | 2073-4360 |
| ISSN | 2073-4360 |
| DOI | 10.3390/polym15092224 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
IEEE access : practical innovations, open solutions
2023 Volume 11, Page(s) 79480–79494
Abstract: Computer-aided Diagnosis (CADx) based on explainable artificial intelligence (XAI) can gain the trust of radiologists and effectively improve diagnosis accuracy and consultation efficiency. This paper proposes BI-RADS-Net-V2, a novel machine learning ... ...
| Abstract | Computer-aided Diagnosis (CADx) based on explainable artificial intelligence (XAI) can gain the trust of radiologists and effectively improve diagnosis accuracy and consultation efficiency. This paper proposes BI-RADS-Net-V2, a novel machine learning approach for fully automatic breast cancer diagnosis in ultrasound images. The BI-RADS-Net-V2 can accurately distinguish malignant tumors from benign ones and provides both semantic and quantitative explanations. The explanations are provided in terms of clinically proven morphological features used by clinicians for diagnosis and reporting mass findings, i.e., Breast Imaging Reporting and Data System (BI-RADS). The experiments on 1,192 Breast Ultrasound (BUS) images indicate that the proposed method improves the diagnosis accuracy by taking full advantage of the medical knowledge in BI-RADS while providing both semantic and quantitative explanations for the decision. |
|---|---|
| Language | English |
| Publishing date | 2023-07-25 |
| Publishing country | United States |
| Document type | Journal Article |
| ZDB-ID | 2687964-5 |
| ISSN | 2169-3536 |
| ISSN | 2169-3536 |
| DOI | 10.1109/access.2023.3298569 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
2023 Volume 17, Issue 3, Page(s) 190–192
Abstract: Deep learning has brought about a revolution in the field of medical diagnosis and treatment. The use of deep learning in healthcare has grown exponentially in recent years, achieving physician-level accuracy in various diagnostic tasks and supporting ... ...
| Abstract | Deep learning has brought about a revolution in the field of medical diagnosis and treatment. The use of deep learning in healthcare has grown exponentially in recent years, achieving physician-level accuracy in various diagnostic tasks and supporting applications such as electronic health records and clinical voice assistants. The emergence of medical foundation models, as a new approach to deep learning, has greatly improved the reasoning ability of machines. Characterized by large training datasets, context awareness, and multi-domain applications, medical foundation models can integrate various forms of medical data to provide user-friendly outputs based on a patien's information. Medical foundation models have the potential to integrate current diagnostic and treatment systems, providing the ability to understand multi-modal diagnostic information and real-time reasoning ability in complex surgical scenarios. Future research on foundation model-based deep learning methods will focus more on the collaboration between physicians and machines. On the one hand, developing new deep learning methods will reduce the repetitive labor of physicians and compensate for shortcomings in their diagnostic and treatment capabilities. On the other hand, physicians need to embrace new deep learning technologies, comprehend the principles and technical risks of deep learning methods, and master the procedures for integrating them into clinical practice. Ultimately, the integration of artificial intelligence analysis with human decision-making will facilitate accurate personalized medical care and enhance the efficiency of physicians. |
|---|---|
| MeSH term(s) | Humans ; Artificial Intelligence ; Deep Learning ; Physicians ; Delivery of Health Care |
| Language | English |
| Publishing date | 2023-06-30 |
| Publishing country | Japan |
| Document type | Journal Article |
| ZDB-ID | 2543899-2 |
| ISSN | 1881-7823 ; 1881-7823 |
| ISSN (online) | 1881-7823 |
| ISSN | 1881-7823 |
| DOI | 10.5582/bst.2023.01148 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
Journal of orthopaedic surgery and research
2023 Volume 18, Issue 1, Page(s) 47
Abstract: Background: This study investigated the characteristics of humeral geometric and morphological parameters in northern Chinese population by three-dimensional measurements, and compared whether there were differences in humeral morphology among ... ...
| Abstract | Background: This study investigated the characteristics of humeral geometric and morphological parameters in northern Chinese population by three-dimensional measurements, and compared whether there were differences in humeral morphology among populations from different geographical regions. Methods: Computed tomography scans of 80 humerus were obtained, reconstructed and measured. Differences in humeral morphological parameters between genders and sides were compared. Correlation analysis was used to explore possible correlations among the parameters. The differences in humeral geometric morphometric parameters between Western and East Asian populations were compared according to pool results of present and previous studies. Results: The average (and standard deviation) of humeral head radius curvature, arc angle, diameter, and thickness was 151.79 ± 6.69°, 23.36 ± 2.08 mm, 44.83 ± 3.92 mm and 17.55 ± 1.84 mm in coronal humeral head plane, and 152.05 ± 8.82°, 21.81 ± 1.88 mm, 41.77 ± 3.44 mm and 16.52 ± 1.92 mm in transversal humeral head plane. The average of the humeral head medial offset and posterior offset was 7.34 ± 2.47 mm and 0.08 ± 1.72 mm. Humeral head inclination angle, arc angle and radius curvature of humeral neck-shaft averaged 137.69 ± 4.92°, 34.7 ± 5.29° and 55.76 ± 13.43 mm. Superior, inferior, anterior, posterior concave angle of humeral anatomical neck averaged 150.41 ± 10.91°, 146.55 ± 10.12°, 146.43 ± 13.53° and 149.33 ± 14.07°. The average of height of the greater tuberosity, height of the lesser tuberosity, depth, concave angle and volume of the intertubercular groove was 14.19 ± 1.7 mm, 8.9 ± 1.54 mm, 0.92 ± 0.31 mm3, 31.28 ± 9.61 mm, 4.98 ± 1.19 mm and 89.35 ± 17.62°. The upper angle of the greater tuberosity averaged 161.04 ± 7.84°, the upper angle of the greater tuberosity was 165.94 ± 3.6°. Differences in parameters of proximal humerus between genders and sides were found. There was no correlation between parameters of proximal humerus and age. Correlations were found among humeral morphological parameters. East Asian populations differed in proximal humeral morphology from Western populations. Conclusions: This study will provide references for diagnosing and classifying shoulder disease, designing prosthesis and instrument, enhancing surgical precision and guiding patient recovery. |
|---|---|
| MeSH term(s) | Female ; Humans ; Male ; Arthroplasty, Replacement/methods ; East Asian People ; Humeral Head/diagnostic imaging ; Humeral Head/surgery ; Humerus/diagnostic imaging ; Humerus/surgery ; Shoulder/surgery ; Shoulder Joint/surgery ; Tomography, X-Ray Computed ; China |
| Language | English |
| Publishing date | 2023-01-17 |
| Publishing country | England |
| Document type | Journal Article |
| ZDB-ID | 2252548-8 |
| ISSN | 1749-799X ; 1749-799X |
| ISSN (online) | 1749-799X |
| ISSN | 1749-799X |
| DOI | 10.1186/s13018-023-03504-2 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing
2023 Volume 2023
Abstract: Despite recent medical advancements, breast cancer remains one of the most prevalent and deadly diseases among women. Although machine learning-based Computer-Aided Diagnosis (CAD) systems have shown potential to assist radiologists in analyzing medical ... ...
| Abstract | Despite recent medical advancements, breast cancer remains one of the most prevalent and deadly diseases among women. Although machine learning-based Computer-Aided Diagnosis (CAD) systems have shown potential to assist radiologists in analyzing medical images, the opaque nature of the best-performing CAD systems has raised concerns about their trustworthiness and interpretability. This paper proposes MT-BI-RADS, a novel explainable deep learning approach for tumor detection in Breast Ultrasound (BUS) images. The approach offers three levels of explanations to enable radiologists to comprehend the decision-making process in predicting tumor malignancy. Firstly, the proposed model outputs the BI-RADS categories used for BUS image analysis by radiologists. Secondly, the model employs multitask learning to concurrently segment regions in images that correspond to tumors. Thirdly, the proposed approach outputs quantified contributions of each BI-RADS descriptor toward predicting the benign or malignant class using post-hoc explanations with Shapley Values. |
|---|---|
| Language | English |
| Publishing date | 2023-10-23 |
| Publishing country | United States |
| Document type | Journal Article |
| ISSN | 2161-0363 |
| ISSN | 2161-0363 |
| DOI | 10.1109/mlsp55844.2023.10286006 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.
2023
Abstract: Activation functions play critical roles in neural networks, yet current off-the-shelf neural networks pay little attention to the specific choice of activation functions used. Here we show that data-aware customization of activation functions can result ...
| Abstract | Activation functions play critical roles in neural networks, yet current off-the-shelf neural networks pay little attention to the specific choice of activation functions used. Here we show that data-aware customization of activation functions can result in striking reductions in neural network error. We first give a simple linear algebraic explanation of the role of activation functions in neural networks; then, through connection with the Diaconis-Shahshahani Approximation Theorem, we propose a set of criteria for good activation functions. As a case study, we consider regression tasks with a partially exchangeable target function, \emph{i.e.} $f(u,v,w)=f(v,u,w)$ for $u,v\in \mathbb{R}^d$ and $w\in \mathbb{R}^k$, and prove that for such a target function, using an even activation function in at least one of the layers guarantees that the prediction preserves partial exchangeability for best performance. Since even activation functions are seldom used in practice, we designed the ``seagull'' even activation function $\log(1+x^2)$ according to our criteria. Empirical testing on over two dozen 9-25 dimensional examples with different local smoothness, curvature, and degree of exchangeability revealed that a simple substitution with the ``seagull'' activation function in an already-refined neural network can lead to an order-of-magnitude reduction in error. This improvement was most pronounced when the activation function substitution was applied to the layer in which the exchangeable variables are connected for the first time. While the improvement is greatest for low-dimensional data, experiments on the CIFAR10 image classification dataset showed that use of ``seagull'' can reduce error even for high-dimensional cases. These results collectively highlight the potential of customizing activation functions as a general approach to improve neural network performance. Comment: 13 pages. arXiv admin note: substantial text overlap with arXiv:2011.11713 |
|---|---|
| Keywords | Computer Science - Machine Learning ; Computer Science - Neural and Evolutionary Computing ; Statistics - Machine Learning ; 68T07 |
| Subject code | 006 |
| Publishing date | 2023-01-16 |
| Publishing country | us |
| Document type | Book ; Online |
| Database | BASE - Bielefeld Academic Search Engine (life sciences selection) |
Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.
Functional & integrative genomics
2024 Volume 24, Issue 2, Page(s) 33
Abstract: Non-small cell lung cancer (NSCLC) encompasses approximately 85% of all lung cancer cases and is the foremost cancer type worldwide; it is prevalent in both sexes and known for its high fatality rate. Expanding scientific inquiry underscores the ... ...
| Abstract | Non-small cell lung cancer (NSCLC) encompasses approximately 85% of all lung cancer cases and is the foremost cancer type worldwide; it is prevalent in both sexes and known for its high fatality rate. Expanding scientific inquiry underscores the indispensability of microRNAs in NSCLC. Here, we probed the impact of miR-873-5p on NSCLC development and chemoresistance. qRT‒PCR was used to measure the miR-873-5p level in NSCLC cells with or without chemoresistance. A model of miR-873-5p overexpression was constructed. The proliferation and viability of NSCLC cells were evaluated through CCK8 and colony formation experiments. Cell migration and invasion were monitored via Transwell assays. Western blotting was used to determine the levels of YWHAE, PI3K, AKT, EMT, apoptosis, and autophagy-related proteins. The sensitivity of NSCLC cells to the chemotherapeutic agent gefitinib was assessed. Additionally, the correlation of YWHAE with miR-873-5p was validated via a dual-luciferase reporter assay and RNA immunoprecipitation (RIP). Overexpressed miR-873-5p suppressed migration, proliferation, invasion, and EMT while concurrently stimulating apoptotic processes. miR-873-5p was downregulated in NSCLC cells resistant to gefitinib. Upregulating miR-873-5p reversed gefitinib resistance by inducing autophagy. YWHAE was confirmed to be a downstream target of miR-873-5p. YWHAE overexpression promoted the malignant behaviors of NSCLC cells and boosted tumor growth, while these effects were reversed following miR-873-5p overexpression. Subsequent investigations revealed that overexpressing YWHAE promoted PI3K/AKT pathway activation, with miR-873-5p displaying inhibitory effects on the YWHAE-mediated PI3K/AKT signaling cascade. miR-873-5p affects proliferation, invasion, migration, EMT, autophagy, and chemoresistance in NSCLC by controlling the YWHAE/PI3K/AKT axis. |
|---|---|
| MeSH term(s) | Male ; Female ; Humans ; Carcinoma, Non-Small-Cell Lung/drug therapy ; Carcinoma, Non-Small-Cell Lung/genetics ; Carcinoma, Non-Small-Cell Lung/metabolism ; Lung Neoplasms/drug therapy ; Lung Neoplasms/genetics ; Lung Neoplasms/metabolism ; Proto-Oncogene Proteins c-akt/genetics ; Proto-Oncogene Proteins c-akt/metabolism ; Phosphatidylinositol 3-Kinases/genetics ; Phosphatidylinositol 3-Kinases/metabolism ; Drug Resistance, Neoplasm/genetics ; Gefitinib ; Cell Line, Tumor ; MicroRNAs/genetics ; MicroRNAs/metabolism ; Autophagy/genetics ; Cell Proliferation/genetics ; 14-3-3 Proteins/genetics ; 14-3-3 Proteins/metabolism |
| Chemical Substances | Proto-Oncogene Proteins c-akt (EC 2.7.11.1) ; Phosphatidylinositol 3-Kinases (EC 2.7.1.-) ; Gefitinib (S65743JHBS) ; MicroRNAs ; YWHAE protein, human ; 14-3-3 Proteins ; MIRN873 microRNA, human |
| Language | English |
| Publishing date | 2024-02-16 |
| Publishing country | Germany |
| Document type | Journal Article |
| ZDB-ID | 2014670-X |
| ISSN | 1438-7948 ; 1438-793X |
| ISSN (online) | 1438-7948 |
| ISSN | 1438-793X |
| DOI | 10.1007/s10142-024-01295-1 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
| Zs.A 5230: Show issues | Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG) |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.
2022 Volume 207, Page(s) 3488–3498
Abstract: With the outbreak of COVID-19, Internet plus Healthcare has developed rapidly with a number of Internet plus Healthcare platforms emerging. The problem of doctor-patient trust is a key issue restricting the development of the Internet plus Healthcare, ... ...
| Abstract | With the outbreak of COVID-19, Internet plus Healthcare has developed rapidly with a number of Internet plus Healthcare platforms emerging. The problem of doctor-patient trust is a key issue restricting the development of the Internet plus Healthcare, which has aroused extensive attention of scholars. The patient's perceived trust on the Internet plus Healthcare platform has the characteristics of subjectivity, ambiguity, and high perceived risk. Therefore, existing trust calculation method becomes inapplicable because these characteristics have not been considered. In order to solve this problem, this study extracts influencing factors of patient trust on the Internet plus Healthcare platform, gives a trust calculation method based on intuitionistic fuzzy set theory, and added a risk preference coefficient in order to integrate the characteristics of patients' high perceived risk into the proposed method. This method is conducive to the platform to provide patients with more accurate doctor recommendations. |
|---|---|
| Language | English |
| Publishing date | 2022-10-19 |
| Publishing country | Netherlands |
| Document type | Journal Article |
| ZDB-ID | 2557358-5 |
| ISSN | 1877-0509 |
| ISSN | 1877-0509 |
| DOI | 10.1016/j.procs.2022.09.407 |
| Database | MEDical Literature Analysis and Retrieval System OnLINE |
This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.