Can AI reassure you of your post plastic surgery appearance

Have you ever considered plastic surgeries? Have you ever thought about changing your appearance but were afraid of how it might turn out? Even if your plastic surgery is not optional like in the case of unpredictable accidents and you are forced to have a plastic surgery you have the right to know the outcome of your surgery. The question is can AI reassure you of your post-opearation appearance? Let's discuss it and see if we can find out the answer!

Artificial intelligence (AI) is an advanced technology that simulates humankind's cognition, including analyzing and interpreting complex data in order to solve problems. AI has been utilized in speech conversion and face recognition. Over the last decades, the use of AI in healthcare and medicine is increasing significantly (1).

Plastic surgery, as a creative discipline, can treat diseases similar to other surgery departments and enhance the appearance of our bodies. However, how AI can influence this type of intervention? AI can be utilized in pre-surgical consultations, disease diagnosis, therapeutic options and decisions, evaluating postsurgical patients, and follow-up. The aforementioned features can be beneficial in reducing medical errors, promoting work efficiency, as well as decreasing source waste (2).

Complex models created by AI apply histopathological information, imaging, and clinical data to choose the optimal treatment methods and assess outcomes. Let’s discuss some examples. The first model of predicting outcomes was used in wound healing in plastic surgery. The RReliefF algorithm was applied to predict the rate of wound healing depending on the patient’s age, the wound area, and the time between wound appearance and starting the treatment (3). Also, artificial neural network (ANN) can predict burn healing time by analyzing the burn spectra of the third day using a reflectance spectrometer. The accuracy of this method is approximately 86% which is clearly better than the accuracy of using the direct visual examination. ANN is able to predict the survival rate of burn patients based on the observations of whole body surface area, surgery, inhalation injury, and admission and rescue time ( with an accuracy of 90%) (4, 5). In addition, ANN can effectively predict possible infection of the surgical site in patients with free-flap reconstruction after receiving an operation for neck and head cancer. This prediction leads to better and more reasonable management strategies for patients (6).

Can AI play a role in cosmetic surgeries as well? Aesthetic prediction and evaluation are significantly subjective in facial aesthetic surgeries. AI prepares objective evaluation standards to evaluate the efficacy of aesthetic surgeries. AI, with the use of deep learning methods and convolutional neural networks (CNN), is able to extract facial features, as well as evaluate facial attractiveness and apparent age (7, 8). Machine learning (ML) is utilized to assess facial beauty depending on facial proportions in accordance with features like shape, color, texture, and the golden ratio. These methods prepare an objective assessment of patient aesthetic enhancement after surgery. For instance, algorithms found that approximately 66.7% of patients were younger in apparent age and their attractiveness improved after jaw surgery (8, 9).  Increases in facial attractiveness and reversing signs of facial aging were evaluated by using CNN in patients after rhinoplasty (10, 11). Emotion expression can also be analyzed by AI applying facial images analyzing the effect of operation from the view of emothional aesthetics. In a study, AI emotion detection software realized that patients with facial paralysis express more negative emotions and less joy in their smiles compared to normal people (12). These strategies make a way to quantify alternations in facial emotions before and after the operation objectively.

Despite all the encouraging results that AI has achieved in medicine, can AI replace physicians completely? The answer is, there are some limitations to be considered as follows: 1) ML algorithms need training with a large amount of data to gain satisfactory performance. But medical-related data is sensitive and it is important to protect the ownership and privacy of the data (13), 2) Algorithmic procedures of AI requires to ensure accurate medical ethical values (14), 3) AI is not able to wholly replace healthcare and physicians in decision-making and diagnosis (15).

In conclusion, the application of AI in plastic surgery is in its infancy yet. However, the development of AI algorithms in this field can show a promising perspective in evaluating post-operative appearance, decision-making, and patient management. In addition, it is crucial for plastic surgeons to completely understand and efficiently apply this technology to solve clinical problems and to provide a more effective and safer medical service for patients in the future. However, all aforementioned limitations must be considered as well.

Kimia Kazemzadeh

1. Buch VH, Ahmed I, Maruthappu M. Artificial intelligence in medicine: current trends and future possibilities. Br J Gen Pract. 2018;68(668):143-4.
2. Qin F, Gu J. Artificial intelligence in plastic surgery: current developments and future perspectives. Plastic and Aesthetic Research. 2023;10(1):3.
3. Robnik-Sikonja M, Cukjati D, Kononenko I. Comprehensible evaluation of prognostic factors and prediction of wound healing. Artif Intell Med. 2003;29(1-2):25-38.
4. Yeong EK, Hsiao TC, Chiang HK, Lin CW. Prediction of burn healing time using artificial neural networks and reflectance spectrometer. Burns. 2005;31(4):415-20.
5. Estahbanati HK, Bouduhi N. Role of artificial neural networks in prediction of survival of burn patients-a new approach. Burns. 2002;28(6):579-86.
6. Artificial neural network approach to predict surgical site infection after free-flap reconstruction in patients receiving surgery for head and neck cancer. Oncotarget. 2018;9(17):13768-82.
7. Liao H, Yan Y, Dai W, Fan P. Age estimation of face images based on CNN and divide-and-rule strategy. Mathematical Problems in Engineering. 2018;2018.
8. Patcas R, Bernini DAJ, Volokitin A, Agustsson E, Rothe R, Timofte R. Applying artificial intelligence to assess the impact of orthognathic treatment on facial attractiveness and estimated age. Int J Oral Maxillofac Surg. 2019;48(1):77-83.
9. T JI, K R, Nersisson R, Zhuang Z, Joseph Raj AN, Refayee I. Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors. Comput Intell Neurosci. 2021;2021:4423407.
10. Khetpal S, Peck C, Parsaei Y, Duan K, Gowda AU, Pourtaheri N, et al. Perceived Age and Attractiveness Using Facial Recognition Software in Rhinoplasty Patients: A Proof-of-Concept Study. J Craniofac Surg. 2022;33(5):1540-4.
11. Patcas R, Timofte R, Volokitin A, Agustsson E, Eliades T, Eichenberger M, et al. Facial attractiveness of cleft patients: a direct comparison between artificial-intelligence-based scoring and conventional rater groups. Eur J Orthod. 2019;41(4):428-33.
12. Dusseldorp JR, Guarin DL, van Veen MM, Jowett N, Hadlock TA. In the Eye of the Beholder: Changes in Perceived Emotion Expression after Smile Reanimation. Plast Reconstr Surg. 2019;144(2):457-71.
13. Kayaalp M. Patient Privacy in the Era of Big Data. Balkan Med J. 2018;35(1):8-17.
14. Keskinbora KH. Medical ethics considerations on artificial intelligence. J Clin Neurosci. 2019;64:277-82.
15. Maddox TM, Rumsfeld JS, Payne PRO. Questions for Artificial Intelligence in Health Care. Jama. 2019;321(1):31-2.