Thomsen Kenneth, Jalaboi Raluca, Winther Ole, Lomholt Hans Bredsted, Lorentzen Henrik F, Høgsberg Trine, Egekvist Henrik, Hedelund Lene, Jørgensen Sofie, Frost Sanne, Bertelsen Trine, Iversen Lars
Department of Dermatology and Venereology, Aarhus University, Aarhus, Denmark.
Department of Dermatology and Venereology, Aarhus University Hospital, Aarhus, Denmark.
Lasers Surg Med. 2025 Jan;57(1):80-87. doi: 10.1002/lsm.23843. Epub 2024 Sep 22.
Hirsutism is a widespread condition affecting 5%-15% of females. Laser treatment of hirsutism has the best long-term effect. Patients with nonpigmented or nonterminal hairs are not eligible for laser treatment, and the current patient journey needed to establish eligibility for laser hair removal is problematic in many health-care systems.
In this study, we compared the ability to assess eligibility for laser hair removal of health-care professionals and convolutional neural network (CNN)-based models.
The CNN ensemble model, synthesized from the outputs of five individual CNN models, reached an eligibility assessment accuracy of 0.52 (95% CI: 0.42-0.60) and a κ of 0.20 (95% CI: 0.13-0.27), taking a consensus expert label as reference. For comparison, board-certified dermatologists achieved a mean accuracy of 0.48 (95% CI: 0.44-0.52) and a mean κ of 0.26 (95% CI: 0.22-0.31). Intra-rater analysis of board-certified dermatologists yielded κ in the 0.32 (95% CI: 0.24-0.40) and 0.65 (95% CI: 0.56-0.74) range.
Current assessment of eligibility for laser hair removal is challenging. Developing a laser hair removal eligibility assessment tool based on deep learning that performs on a par with trained dermatologists is feasible. Such a model may potentially reduce workload, increase quality and effectiveness, and facilitate equal health-care access. However, to achieve true clinical generalizability, prospective randomized clinical intervention studies are needed.
多毛症是一种普遍存在的病症，影响着5% - 15%的女性。激光治疗多毛症具有最佳的长期效果。非色素性或非终毛的患者不符合激光治疗条件，而目前在许多医疗系统中，确定激光脱毛资格所需的患者就医流程存在问题。
在本研究中，我们比较了医疗保健专业人员和基于卷积神经网络（CNN）的模型评估激光脱毛资格的能力。
由五个单独的CNN模型输出合成的CNN集成模型，以共识专家标签为参考，达到了0.52的资格评估准确率（95%置信区间：0.42 - 0.60）和0.20的κ值（95%置信区间：0.13 - 0.27）。相比之下，获得委员会认证的皮肤科医生的平均准确率为0.48（95%置信区间：0.44 - 0.52），平均κ值为0.26（95%置信区间：0.22 - 0.31）。对获得委员会认证的皮肤科医生进行的评分者内分析得出的κ值在0.32（95%置信区间：0.24 - 0.40）和\(0.65\)（95%置信区间：0.56 - 0.74）范围内。
目前对激光脱毛资格的评估具有挑战性。开发一种基于深度学习的激光脱毛资格评估工具，使其性能与经过培训的皮肤科医生相当是可行的。这样的模型可能会减少工作量，提高质量和有效性，并促进平等的医疗保健获取。然而，要实现真正的临床普遍性，需要进行前瞻性随机临床干预研究。
