Page 41 - Read Online

Brenac et al. Art Int Surg 2024;4:296-315 https://dx.doi.org/10.20517/ais.2024.49 Page 306

(2) Patients reported a greater perceived age reduction
(-6.7 years) compared to the neural network estimates
(-4.3 years)
(3) FACE-Q scores indicated high patient satisfaction
with facial appearance, quality of life, and overall
outcome
(4) A positive correlation was found between neural
network age reduction estimates and patient satisfaction
Boonipat Using artificial intelligence to 2020 Plastic and (1) Evaluate the use of ML to measure facial (1) The facial recognition application showed a greater
et al. [40] measure facial expression following Reconstructive expression before and after facial reanimation recognition of happy signals in postoperative (42%) vs.
facial reanimation surgery Surgery surgery using video data preoperative (13%) smile videos (P < 0.0001) compared
to 53% in control videos
[41]
Geisler et al. A role for artificial intelligence in 2021 Journal of (1) Develop CNN models based on the ResNet-50 (1) CNN model developed showed an overall testing
the classification of craniofacial Craniofacial architecture to classify non-syndromic CS from 2D accuracy of 90.6%, demonstrating the potential of ML to
anomalies Surgery clinical photographs detect craniofacial conditions
Knoops A machine learning framework for 2019 Scientific Reports (1) Develop the first fully automated large-scale (1) The developed 3DMM achieves a diagnostic
[42]
et al. automated diagnosis and clinical 3DMM for supervised learning in sensitivity of 95.5% and specificity of 95.2%
computer-assisted planning in diagnostics, risk stratification, and treatment (2) The model simulates surgical outcomes with a mean
plastic and reconstructive surgery simulation, and to demonstrate its potential for accuracy of 1.1 ± 0.3 mm
improving clinical decision making in orthognathic (3) The 3DMM framework automates diagnosis and
surgery provides patient-specific treatment plans from 3D scans,
improving efficiency in clinical decision making
[44]
Lim et al. Using generative artificial 2023 Journal of Clinical (1) Investigating the capacity of AI tools to (1) DALL-E-2, Midjournet and Blue Willow showed a
intelligence tools in cosmetic Medicine generate realistic images pertinent to cosmetic higher representation of females, light skin tones, and
surgery: a study on rhinoplasty, surgery with a BMI < 20
facelifts, and blepharoplasty (2) AI tools could enhance patient information but must
procedures be integrated ethically to ensure comprehensive
representation and maintain medical standards
Hand surgery Ozkaya Evaluation of an artificial 2022 European Journal of (1) Determine the diagnostic performance of ML to (1) ML demonstrated 76% sensitivity, 92% specificity,
[46]
et al. intelligence system for diagnosing Trauma and detect scaphoid fractures on anteroposterior wrist an AUC of 0.840, a Youden index of 0.680, and an F-
scaphoid fracture on direct Emergency Surgery radiographs score of 0.826 for detecting scaphoid fractures
radiography (2) The experienced orthopedic specialist had the
highest diagnostic performance based on AUC, while ML
performance was comparable to that of a less
experienced orthopedic specialist and superior to the ED
physician
[47]
Oeding et al. Diagnostic performance of artificial 2024 The Journal of (1) Determine the diagnostic efficacy of AI models (1) AI models exhibited strong diagnostic performance,
intelligence for detection of Hand Surgery for detecting scaphoid and distal radius fractures with AUROC values ranging from 0.77 to 0.96 for
scaphoid and distal radius (2) Compare the efficacy to human clinical experts scaphoid fractures and 0.90 to 0.99 for distal radius
fractures: a systematic review fractures. Accuracy ranged from 72.0% to 90.3% for
scaphoid fractures and 89.0% to 98.0% for distal radius
fractures
(2) Compared to clinical experts, 92.9% of the studies
found AI models to have comparable or better
performance. AI models generally showed poorer
performance on occult scaphoid fractures, though
models specifically trained for these types of fractures