1
|
Kim J, Oh I, Lee YN, Lee JH, Lee YI, Kim J, Lee JH. Predicting the severity of postoperative scars using artificial intelligence based on images and clinical data. Sci Rep 2023; 13:13448. [PMID: 37596459 PMCID: PMC10439171 DOI: 10.1038/s41598-023-40395-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Accepted: 08/09/2023] [Indexed: 08/20/2023] Open
Abstract
Evaluation of scar severity is crucial for determining proper treatment modalities; however, there is no gold standard for assessing scars. This study aimed to develop and evaluate an artificial intelligence model using images and clinical data to predict the severity of postoperative scars. Deep neural network models were trained and validated using images and clinical data from 1283 patients (main dataset: 1043; external dataset: 240) with post-thyroidectomy scars. Additionally, the performance of the model was tested against 16 dermatologists. In the internal test set, the area under the receiver operating characteristic curve (ROC-AUC) of the image-based model was 0.931 (95% confidence interval 0.910‒0.949), which increased to 0.938 (0.916‒0.955) when combined with clinical data. In the external test set, the ROC-AUC of the image-based and combined prediction models were 0.896 (0.874‒0.916) and 0.912 (0.892‒0.932), respectively. In addition, the performance of the tested algorithm with images from the internal test set was comparable with that of 16 dermatologists. This study revealed that a deep neural network model derived from image and clinical data could predict the severity of postoperative scars. The proposed model may be utilized in clinical practice for scar management, especially for determining severity and treatment initiation.
Collapse
Affiliation(s)
- Jemin Kim
- Department of Dermatology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Gyeonggi-do, South Korea
- Scar Laser and Plastic Surgery Center, Yonsei Cancer Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Inrok Oh
- LG Chem Ltd., Seoul, South Korea
| | - Yun Na Lee
- Department of Dermatology and Cutaneous Biology Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Joo Hee Lee
- Department of Dermatology and Cutaneous Biology Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Young In Lee
- Scar Laser and Plastic Surgery Center, Yonsei Cancer Hospital, Yonsei University College of Medicine, Seoul, South Korea
- Department of Dermatology and Cutaneous Biology Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Jihee Kim
- Department of Dermatology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin-si, Gyeonggi-do, South Korea
- Scar Laser and Plastic Surgery Center, Yonsei Cancer Hospital, Yonsei University College of Medicine, Seoul, South Korea
| | - Ju Hee Lee
- Scar Laser and Plastic Surgery Center, Yonsei Cancer Hospital, Yonsei University College of Medicine, Seoul, South Korea.
- Department of Dermatology and Cutaneous Biology Research Institute, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.
| |
Collapse
|
2
|
Kim YH, Kim HK, Choi JW, Kim YC. Photobiomodulation therapy with an 830-nm light-emitting diode for the prevention of thyroidectomy scars: a randomized, double-blind, sham device-controlled clinical trial. Lasers Med Sci 2022; 37:3583-3590. [PMID: 36045183 DOI: 10.1007/s10103-022-03637-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Accepted: 08/22/2022] [Indexed: 10/14/2022]
Abstract
This randomized, double-blind, and sham device-controlled trial aimed to evaluate the efficacy and safety of home-based photobiomodulation therapy using an 830-nm light-emitting diode (LED)-based device for the prevention of and pain relief from thyroidectomy scars. Participants were randomized to receive photobiomodulation therapy using an LED device or a sham device without an LED from 1 week postoperatively for 4 weeks. Scars were assessed using satisfaction scores, the numeric rating scale (NRS) score for pain, Global Assessment Scale (GAS), and Vancouver Scar Scale (VSS) scores. The scars were also assessed using a three-dimensional (3D) skin imaging device to detect color, height, pigmentation, and vascularity. Assessments were performed at the 1-, 3-, and 6-month follow-ups. Forty-three patients completed this trial with 21 patients in the treatment group and 22 patients in the control group. The treatment group showed significantly higher patient satisfaction and GAS scores and lower NRS and VSS scores than the control group at 6 months. Improvements in color variation, height, pigmentation, and vascularity at 6 months were greater in the treatment group than in the control group, although the differences were not significant. In conclusion, early application of 830-nm LED-based photobiomodulation treatment significantly prevents hypertrophic scar formation and reduces postoperative pain without noticeable adverse effects.
Collapse
Affiliation(s)
- Yul Hee Kim
- Department of Dermatology, School of Medicine, Ajou University, 164, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea.,Department of Medical Sciences, Graduate School of Ajou University, Suwon, Korea
| | - Hyeung Kyoo Kim
- Department of Surgery, School of Medicine, Ajou University, Suwon, Korea
| | - Jee Woong Choi
- Department of Dermatology, School of Medicine, Ajou University, 164, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea
| | - You Chan Kim
- Department of Dermatology, School of Medicine, Ajou University, 164, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea.
| |
Collapse
|