Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
An Update on Artificial Intelligence and Its Application in Orthopedics: A Narrative Review
0
Zitationen
1
Autoren
2024
Jahr
Abstract
Abstract Background: Prerequisites of artificial intelligence (AI) are a huge unbiased data set, linking them with different “clouds,” a powerful computer with high processing ability, and application of statistical methods to produce a complex algorithm. The concept “can machine think” developed in the early 1940s with the turning rule. The progress was slow till 2000 and then steadily increased and accelerated since 2012. Data scientists used complex statistical mathematics and computer engineers developed machines that allow machine learning, deep learning, and artificial neural network as subsets of AI. These nodes in layers can send feedback to refine its own decision. Among various fields, applications in orthopedics are in stage of validation. Clinical applications are growing fast. Use in orthopedic subfields such as joint disorders and arthroplasty, spine, fractures, sports medicine, and orthopedic oncology are promising. Aims and Objectives: Orthopedic clinicians have limited scope to be accustomed with the enmeshed statistical basis. They will be more interested in the application of AI in orthopedics in their practice. This review article is focused on some historical background and applicability of different ML models in various orthopedic domains. The future benefits and limitations are also outlined. Methodology: In this descriptive narrative exploratory review, qualitative information is collected randomly from a variety of sources. Conclusion: AI is the revolution in industrial development. It has reached the present state by the efforts and endeavors by engineers and data scientists. Its utility has been validated in orthopedic fields and is ready to use in regular practice. However, ethical issues including the “Job-Killing” effect, identification of accountable persons in situations where AI makes some mistakes, and biased data are not yet addressed. Regulating bodies are working on it.
Ähnliche Arbeiten
A survey on deep learning in medical image analysis
2017 · 13.563 Zit.
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
2020 · 7.705 Zit.
Calculation of average PSNR differences between RD-curves
2001 · 4.088 Zit.
Magnetic Resonance Classification of Lumbar Intervertebral Disc Degeneration
2001 · 3.893 Zit.
Vertebral fracture assessment using a semiquantitative technique
1993 · 3.608 Zit.