ObjectiveThe continuous uninterrupted feedback system is the essential part of any well-organized system. We propose aLYNX concept that is a possibility to use an artificial intelligence algorithm or a neural network model in decision-making system so as to avoid possible mistakes and to remind the doctors to review tactics once more in selected cases.MethodaLYNX system includes: registry with significant factors, decisions and results; machine learning process based on this registry data; the use of the machine learning results as the adviser. We show a possibility to build a computer adviser with a neural network model for making a choice between coronary aortic bypass surgery (CABG) and percutaneous coronary intervention (PCI) in order to achieve a higher 5-year survival rate in patients with angina based on the experience of 5107 patients.ResultsThe neural network was trained by 4679 patients who achieved 5-year survival. Among them, 2390 patients underwent PCI and 2289 CABG. After training, the correlation coefficient (r) of the network was 0.74 for training, 0.67 for validation, 0.71 for test and 0.73 for total. Simulation of the neural network function has been performed after training in the two groups of patients with known 5-year outcome. The disagreement rate was significantly higher in the dead patient group than that in the survivor group between neural network model and heart team [16.8% (787/4679) vs. 20.3% (87/428), P = 0.065)].ConclusionThe study shows the possibility to build a computer adviser with a neural network model for making a choice between CABG and PCI in order to achieve a higher 5-year survival rate in patients with angina.
Introduction. Treatment with MRI-guided focused ultrasound (MRgFUS) is a new, non-invasive surgical technique for treating extrapyramidal movement disorders. This article presents the first use of MRgFUS in Russia for treating patients with essential tremor (ET). Materials and methods. Patients (n = 26; 17 men and 9 women) aged 2182 years (median age 46.0 years) and with severe and refractory ET, underwent MRgFUS thalamotomy (ExAblate 4000, Insightec). One side was treated in 22 patients (left thalamus in 18 and right thalamus in 6), both sides were treated concurrently in two patients, and both sides were treated consecutively in two patients. Tremor was assessed using the Clinical Rating Scale for Tremor (CRST). Because international clinical specialists could not visit Russia due to the COVID-19 pandemic, MRgFUS was performed via telehealth on May 5, 2020, in a world first. Results. A satisfactory result was achieved in 25 (96%) out of 26 patients. CRST scores improved by 64.7% on the side of the operation, by 10.2% on the control side, and by 37.5% overall. Intraoperative side effects included headache during sonication (42.3%), vertigo (15.4%), nausea (11.5%), vomiting (7.7%), numbness (3.8%), ataxia (3.8%), and pathological response to cold exposure (3.8%). The symptoms resolved immediately after surgery. Unstable gait was noted in five patients, which completely resolved two weeks after surgery. Median postoperative follow-up duration was 109 days [53; 231], with a maximum of 625 days. No relapses (if the hyperkinesia had completely disappeared) or increased tremor (if reduced after surgery) were observed. Conclusion. The efficacy of MRgFUS for ET was 96%, with no long-term complications. Both bilateral concurrent and bilateral consecutive MRgFUS thalamotomy is possible, but its efficacy and safety should be assessed in a randomized study. In a world first, MRgFUS was successfully implemented using telehealth.
Introduction. The widespread adoption of Artificial Intelligence (AI) technologies forms the core of the so-called Industrial Revolution 4.0.The aim of this study is to examine qualitative changes occurring over the last two years in the development of AI through an examination of trends in PubMed publications.Materials. All abstracts with keyword “artificial intelligence” were downloaded from PubMed database https://www.ncbi.nlm.nih.gov/pubmed/ in the form of .txt files. In order to produce a generalisation of topics, we classified present applications of AI in medicine. To this end, 78,420 abstracts, 5558 reviews, 304 randomised controlled trials, 247 multicentre studies and 4137 other publication types were extracted. (Figure 1). Next, the typical applications were classified.Results. Interest in the topic of AI in publications indexed in the PubMed library is increasing according to general innovation development principles. Along with English publications, the number of non-English publications continued to increase until 2018, represented especially by Chinese, German and French languages. By 2018, the number of non-English publications had started to decrease in favour of English publications. Implementations of AI are already being adopted in contemporary practice. Thus, AI tools have moved out of the theoretical realm to find mainstream application.Conclusions. Tools for machine learning have become widely available to working scientists over the last two years. Since this includes FDA-approved tools for general clinical practice, the change not only affects to researchers but also clinical practitioners. Medical imaging and analysis applications already approved for the most part demonstrate comparable accuracy with the human specialist. A classification of developed AI applications is presented in the article.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.