Plastic Surgery Division, Department of Surgery, Plastic Surgery Resident PGY4, Mayo Clinic, Rochester, MN, 55905, USA.
Mayo Clinic Alix School of Medicine, Mayo Clinic, Rochester, MN, USA.
Aesthetic Plast Surg. 2021 Dec;45(6):2742-2748. doi: 10.1007/s00266-021-02430-0. Epub 2021 Sep 27.
The widespread popularity of browlifts and blepharoplasties speaks directly to the importance that patients place on the periorbital region of the face. In literature, most esthetic outcomes are based on instinctive analysis of the esthetic surgeon, rather than on patient assessments, public opinions, or other objective means. We employed an artificial intelligence system to objectively measure the impact of brow lifts and associated rejuvenation procedures on the appearance of emotion while the patient is in repose.
We retrospectively identified all patients who underwent bilateral brow lift for visual field obstruction between 2006 and 2019. Images were analyzed using a commercially available facial expression recognition software package (FaceReader™, Noldus Information Technology BV, Wageningen, Netherlands). The data generated reflected the proportion of each emotion expressed for any given facial movement and the action units associated.
A total of 52 cases were identified after exclusion. Pre-operatively, the angry, happy, sad, scared, and surprised emotion were detected on average of 13.06%, 1.68%, 13.06%, 3.53%, and 0.97% among all the patients, respectively. Post-operatively, the angry emotion average decreased to 5.42% (p=0.009). The happy emotion increased to 9.35% (p=0.0013), while the sad emotion decreased to 5.42%. The scared emotion remained relatively the same at 3.4%, and the surprised emotion increased to 2.01%; however, these were not statistically significant.
This study proposes a paradigm shift in the clinical evaluation of brow lift and other facial esthetic surgery, implementing an existing facial emotion recognition system to quantify changes in expression associated with facial surgery.
This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
广泛流行的眉提升术和眼睑成形术直接表明了患者对面部眶周区域的重视。在文献中，大多数审美结果都是基于审美外科医生的本能分析，而不是基于患者评估、公众意见或其他客观手段。我们使用人工智能系统客观地衡量眉提升术和相关年轻化手术对患者休息时表情情感的影响。
我们回顾性地确定了 2006 年至 2019 年间所有因视野受阻而行双侧眉提升术的患者。使用商业可得的面部表情识别软件包（FaceReader™，Noldus Information Technology BV，荷兰瓦赫宁根）对图像进行分析。生成的数据反映了给定面部运动和相关动作单元所表达的每种情感的比例。
排除后共确定 52 例。术前，所有患者的愤怒、高兴、悲伤、恐惧和惊讶情绪的平均检出率分别为 13.06%、1.68%、13.06%、3.53%和 0.97%。术后，愤怒情绪平均下降至 5.42%（p=0.009）。高兴情绪增加到 9.35%（p=0.0013），而悲伤情绪下降到 5.42%。恐惧情绪相对保持在 3.4%，惊讶情绪增加到 2.01%；然而，这些差异没有统计学意义。
本研究提出了眉提升术和其他面部美容手术临床评估的范式转变，采用现有的面部情绪识别系统来量化与面部手术相关的表情变化。
证据水平 IV：本杂志要求作者为每篇文章分配一个证据水平。有关这些循证医学评级的完整描述，请参考目录或在线作者指南 www.springer.com/00266 。
