* If you want to update the article please login/register
BackgroundArtificial intelligence is gradually emerging and evolving the health care and Primary Care domains. Physicians' perspectives on the potential effects of digital public health on key tasks in PC have been reviewed in this series. Results of an online poll (depending on the Technology Readiness and Acceptance Model): Respondents with a high score in innovativeness had a greater likelihood to use AI-based technologies in PCs during the coronavirus pandemic. We recommend, in two separate digital health care ecosystems, that we encourage the usability of digital public health services and accelerate patient AI adoption.
Source link: https://doi.org/10.3389/fpubh.2022.931225
Smart Agriculture is replacing conventional farming methods by adopting emerging technologies such as the Internet of Things, Artificial Intelligence, and Machine Learning to ensure greater productivity and precise agriculture management to meet food demand. Previous literature reviews have also conducted similar bibliometric studies; however, there is still no study in Operations Research findings into Smart Agriculture. This paper presents a bibliometric analysis of recent research findings in OR knowledge, which has been carried out over the past two decades in Agriculture 4. 0 to find the trends and the gaps. Researchers and decision makers will be able to see how newer advanced OR theories are being used and how they can help solve certain research gaps highlighted in this review paper. Countries with arid climate conditions would be notified how satellite imagery and mapping can help them in locating newer irrigation lands to help them with their limited agricultural resources.
Source link: https://doi.org/10.3389/fsufs.2022.1053921
In the last decade, the field of cancer neoantigen research has flourished quickly. Artificial Intelligence or Machine Learning in biomedicine applications has contributed to the growing computational pipeline for neoantigen prediction. ML algorithms are a powerful way to identify the multidimensional nature of the omics results and subsequently extract the key neoantigen properties that aid in the successful finding of new neoantigens. The present study aims to outline machine learning's significant technology advances, especially the recently embedded learning algorithms and pipelines that were recently used in neoantigen estimation. The standard procedure includes identifying tumor and blood samples, determining the binding affinity between mutated peptide, MHC, and T cell receptors, as well as quantifying tumor epitopes' immunogenicity. In typical ML models, we highlight the outstanding feature extraction tools and multi-layer neural network architectures. More specifically, we highlight the best feature extraction techniques and multi-layer neural network architectures.
Source link: https://doi.org/10.3389/fonc.2022.1054231
The opportunities offered by the development of artificial intelligence techniques such as machine learning are appealing in addressing several of the current healthcare challenges. This report aims to investigate AI's most recent advancements in the field of hematopoietic cell transplantation. The literature reviewed found that AI integration in the field of HCT has grown dramatically in the last decade and provides promising avenues in diagnosis and prognosis in HCT populations facing both pre- and post-transplant challenges. Several key areas of AI integration in HCT include poorly developed algorithms, a lack of generalizability, and limited use of various AI technologies. Machine learning methods in HCT are a complex area of study that needs a lot of expansion and wide acceptance from hematology and HCT societies and organizations globally, as we predict that this will be the future practice paradigm.
Source link: https://doi.org/10.4274/tjh.2018.0123
Any country in the World wants food security as one of their top priorities. Food security and artificial intelligence are two of the new techniques that are being used in various stages of the food industry, as shown by various researchers. The application of artificial intelligence in the entire food production process, including crop production, livestock raising, harvesting/slaughtering, postharvest management, food processing, food distribution, and food waste management is explored in this paper. This report is designed to determine the usage of artificial intelligence technologies in all of the phases of food processing.
Source link: https://doi.org/10.1016/j.jafr.2023.100502
Purpose Abstract Purpose Abstract Purpose Abstract Purpose: With the artificial intelligence iterative reconstruction algorithm in total-body PET/CT imaging, it was possible to investigate the reusability of ultra-low-dose CT reconstructed. The total-body PET/CT scan was used in the clinical part to determine 52 patients with malignant tumors. Results The image quality of ULDCT-HIRphantom was inferior to that of SDCT-HIRphantom, but no significant difference was found between the two groups, but no significant difference was found between the ULDCT-AIIRphantom and SDCT-HIRphantom. The change rates of CTmean in thyroid, neck muscle, lung, mediastinum, back muscle, liver, lumbar muscle, first lumbar spine, and sigmoid colon were lower than those of SDCT-HIR, respectively, on the first lumbar spine and sigmoid colon, alongside the head and lower limb, were lower than that of SDCT-HIR. Except for the brain, the CNR of ULDCT-AIIR was the same as the SDCT-HIR, but the SNR was higher, but the SNR was higher.
Source link: https://doi.org/10.1186/s40658-022-00521-8
Abstract In many nations, global climate change is impacting water resources and other aspects of life. Accurate monthly and seasonal estimates of this rain are crucial for agricultural planning since all agricultural production and subsequent national crop production are dependent on the amount and distribution of rainfall. Rainfall forecast is also useful for non-governmental, and private organizations in making long-term decisions and planning in several areas, including farming, early warning of potential hazards, drought mitigation, disaster mitigation, and insurance policy. Using geographical and periodicity component data collected from 2011 to 2021, the applicability of Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System models in forecasting long-term monthly precipitation was investigated. The experimental results show that the ANFIS model outperforms the ANN model in all assessment criteria across all testing stations. ANFIS' efficiency coefficients were 0. 995 for ANFIS and 0. 935 for ANN over testing stations, according to Nash.
Source link: https://doi.org/10.1186/s40537-022-00683-3
Abstract Background: Artificial intelligence is gaining traction in medicine and surgery. Tools to analyze high-volume data in order to enable predictive analytics that supports complex decision-making processes can be provided by AI-based applications. Time-sensitive trauma and emergency situations are often stressful. The aim of the investigation is to look at trauma and emergency surgeons' use of AI-based technologies in clinical decision-making processes. Methods An online survey based on literature regarding AI-enabled surgical decision-making aids was commissioned by a multidisciplinary committee and accepted by the World Society of Emergency Surgery. Through the society's website and Twitter profile, the survey was sent to 917 WSES members. Discussion This includes people who are 100% confident in the benefits of AI as well as those who don't fully believe in AI and those that do not know or trust AI-enabled surgical decision-making aids. A foundational, working knowledge of clinical AI should be promoted by academic societies and surgical training programs in order to foster a foundational, working knowledge of clinical AI.
Source link: https://doi.org/10.1186/s13017-022-00467-3
However, the use of artificial intelligence -predicted age using ECGs remains uncertain. Methods: We developed an AI-enabled ECG based on a single-center database, and we simulated chronological age with a convolutional neural network that gives AI-predicted age. For all ECGs, using the 5-fold cross validation scheme, an AI-predicted age deriving from the test data was established. For all patients and CA and AI-predicted age, respectively, the areas under the curve were 0. 673 and 0. 679, respectively; 0. 700 for younger patients CA; and 0. 700 for younger patients.
Source link: https://doi.org/10.1016/j.ijcha.2023.101172
* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions