1.山东第一医科大学第一附属医院皮肤科,山东 济南 250013
2.中国青年创业就业基金会盈康一生公益基金,北京 100005
3.山东省胸部肿瘤数字诊疗重点实验室,山东省数据开放创新应用实验室,智能外科山东省工程研究中心,山东第一医科大学第一附属医院//山东省千佛山医院,山东 济南 250013
张书成,第一作者,研究方向:皮肤科医工交叉,E-mail: shiu844213@163.com
司晓青,通信作者,教授,硕士生导师,E-mail: docsixiaoqing@163.com
收稿:2026-01-22,
修回:2026-03-04,
录用:2026-03-05,
纸质出版:2026-03-20
移动端阅览
张书成,司晓青.机器学习辅助临床决策在皮肤病中的应用进展[J].中山大学学报(医学科学版),2026,47(02):195-202.
ZHANG Shucheng,SI Xiaoqing.Application Progress of Machine Learning Assisted Clinical Decision-making in Dermatology[J].Journal of Sun Yat-sen University(Medical Sciences),2026,47(02):195-202.
张书成,司晓青.机器学习辅助临床决策在皮肤病中的应用进展[J].中山大学学报(医学科学版),2026,47(02):195-202. DOI: 10.11714/jsysu.med.YX20260019.
ZHANG Shucheng,SI Xiaoqing.Application Progress of Machine Learning Assisted Clinical Decision-making in Dermatology[J].Journal of Sun Yat-sen University(Medical Sciences),2026,47(02):195-202. DOI: 10.11714/jsysu.med.YX20260019.
机器学习(ML)在皮肤病临床决策中的应用日趋广泛,已渗透至病灶识别、多模态鉴别诊断、个体化治疗推荐、疗效预测及预后评估等多个关键环节。ML模型通过整合影像、基因组学、临床特征等多源数据,不仅能够辅助医生提高诊断准确性,还可优化治疗方案选择,实现疾病动态管理与个体化干预,展现出显著的临床应用潜力。例如,基于卷积神经网络的影像分析系统在皮肤肿瘤的识别中表现出与皮肤科专家相当甚至更优的性能。在治疗优化方面,ML可通过分析患者多维数据,推荐个性化用药方案,预测治疗反应及不良事件风险,为精准医疗提供支撑。在预后评估与长期管理层面,结合患者报告结局和时间序列数据的ML模型,可实现对疾病进展的动态监测和复发风险的个体化预测。然而,尽管技术发展迅速,ML在皮肤病临床决策中的实际转化仍面临多重瓶颈,包括数据偏差、算法泛化能力不足、临床验证缺失、系统整合困难以及伦理监管不完善等问题。本综述系统梳理了ML在皮肤病临床决策各环节中的应用现状与研究进展,深入分析其面临的关键瓶颈,从影像识别、治疗优化、预后评估及伦理挑战等方面全面综述ML辅助临床决策的应用进展,以期为相关研究与临床实践提供参考。
Machine learning (ML) is increasingly being integrated into clinical decision-making in dermatology, penetrating multiple critical stages including lesion identification, multimodal differential diagnosis, personalized treatment recommendation, efficacy prediction, and prognosis evaluation. By synthesizing multi-source data such as medical imaging, genomics, and clinical characteristics, ML models not only assist clinicians in improving diagnostic accuracy but also optimize therapeutic selection, enabling dynamic disease management and individualized intervention, thereby demonstrating substantial clinical application potential. For instance, convolutional neural network-based image analysis systems have exhibited performance comparable to or exceeding that of dermatology experts in the recognition of cutaneous neoplasms. Regarding treatment optimization, ML can recommend personalized medication regimens, predict treatment responses and adverse event risks by analyzing multidimensional patient data, thereby providing robust support for precision medicine. In the realm of prognosis assessment and long-term management, ML models incorporating patient-reported outcomes and time-series data facilitate dynamic monitoring of disease progression and individualized prediction of recurrence risk. However, despite rapid technological advances, the practical translation of ML into dermatological clinical decision-making still confronts multiple bottlenecks, including data bias, insufficient algorithmic generalization, lack of robust clinical validation, difficulties in system integration, and incomplete ethical supervision. This review systematically outlines the current applications and research progress of ML across various stages of dermatological clinical decision-making, thoroughly analyzes the key bottlenecks encountered, and comprehensively synthesizes advances in ML-assisted clinical decision support spanning image recognition, treatment optimization, prognosis evaluation, and ethical challenges, aiming to provide valuable insights for related research and clinical practice.
Kline A , Wang H , Li Y , et al . Multimodal machine learning in precision health: a scoping review [J]. NPJ Digit Med , 2022 , 5 ( 1 ): 171 .
李昂 , 崔勇 . 人工智能在皮肤科中的应用 [J]. 中国皮肤性病学杂志 , 2022 , 36 ( 8 ): 872 - 876 .
Li A , Cui Y . Application progress of artificial intelligence in dermatology [J]. Chin J Dermatoven , 2022 , 36 ( 8 ): 872 - 876 .
Ba W , Wu H , Chen WW , et al . Convolutional neural network assistance significantly improves dermatologists’ diagnosis of cutaneous tumours using clinical images [J]. Eur J Cancer , 2022 , 169 : 156 - 165 .
Winkler JK , Blum A , Kommoss K , et al . Assessment of diagnostic performance of dermatologists cooperating with a convolutional neural network in a prospective clinical study: human with machine [J]. JAMA Dermatol , 2023 , 159 ( 6 ): 621 .
Lyakhova UA , Lyakhov PA . Systematic review of approaches to detection and classification of skin cancer using artificial intelligence: development and prospects [J]. Comput Biol Med , 2024 , 178 : 108742 .
Jones OT , Matin RN , Van Der Schaar M , et al . Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review [J]. Lancet Digit Health , 2022 , 4 ( 6 ): e466 - e476 .
Groh M , Badri O , Daneshjou R , et al . Deep learning-aided decision support for diagnosis of skin disease across skin tones [J]. Nat Med , 2024 , 30 ( 2 ): 573 - 583 .
Barata C , Rotemberg V , Codella NCF , et al . A reinforcement learning model for AI-based decision support in skin cancer [J]. Nat Med , 2023 , 29 ( 8 ): 1941 - 1946 .
Cai ZR , Kim J , Rezaei SJ , et al . Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis [J]. Br J Dermatol , 2025 , 193 ( 5 ): 847 - 855 .
Liu Z , Zhang Y , Wang K , et al . Early diagnosis model of mycosis fungoides and five inflammatory skin diseases based on a multimodal data-based convolutional neural network [J]. Br J Dermatol , 2025 , 193 ( 5 ): 968 - 977 .
Tang P , Yan X , Nan Y , et al . FusionM4Net: a multi-stage multi-modal learning algorithm for multi-label skin lesion classification [J]. Med Image Anal , 2022 , 76 : 102307 .
Wang J , Zhang Y , Xie F , et al . Enhancing diagnosis of psoriasis and inflammatory skin diseases: a spatially aligned multimodal model integrating clinical and dermoscopic images [J]. J Invest Dermatol , 2025 , 145 ( 11 ): 2736 - 2744.e6 .
Wang Y , Feng Y , Zhang L , et al . Adversarial multimodal fusion with attention mechanism for skin lesion classification using clinical and dermoscopic images [J]. Med Image Anal , 2022 , 81 : 102535 .
Nielsen ML , Petersen TC , Maul JT , et al . Multivariable predictive models to identify the optimal biologic therapy for treatment of patients with psoriasis at the individual level [J]. JAMA Dermatol , 2022 , 158 ( 10 ): 1149 .
Wu S , Lei L , Hu Y , et al . Machine learning-based prediction models for atopic dermatitis diagnosis and evaluation [J]. Fundam Res , 2025 , 5 ( 3 ): 1313 - 1322 .
Liu D , Hu BD , Glickman J , et al . Artificial intelligence in atopic dermatitis: a narrative review [J]. J Allergy Clin Immunol , 2025 , 156 ( 4 ): 889 - 898 .
Chen Y , Peng C , Chen X , et al . The role of solute carriers in the metabolic reprogramming of skin diseases [J]. Clin Rev Allergy Immunol , 2025 , 68 ( 1 ): 80 .
Chia S , Wen Seow JJ , Peres Da Silva R , et al . CAN-scan: a multi-omic phenotype-driven precision oncology platform identifies prognostic biomarkers of therapy response for colorectal cancer [J]. Cell Rep Med , 2025 , 6 ( 4 ): 102053 .
Wade BSC , Pindale R , Luccarelli J , et al . Prediction of individual treatment allocation between electroconvulsive therapy or ketamine using the personalized advantage index [J]. NPJ Digit Med , 2025 , 8 ( 1 ): 127 .
Jayaraman P , Desman J , Sabounchi M , et al . A primer on reinforcement learning in medicine for clinicians [J]. NPJ Digit Med , 2024 , 7 ( 1 ): 337 .
Yap CF , Nair N , Morgan AW , et al . Identifying predictive biomarkers of response in patients with rheumatoid arthritis treated with adalimumab using machine learning analysis of whole-blood transcriptomics data [J]. Arthritis Rheumatol , 2025 , 77 ( 12 ): 1663 - 1672 .
Guo LK , Su Y , Zhang YYN , et al . Prediction of treatment response to antipsychotic drugs for precision medicine approach to schizophrenia: randomized trials and multiomics analysis [J]. Mil Med Res , 2023 , 10 ( 1 ): 24 .
Vithayathil M , Koku D , Campani C , et al . Machine learning based radiomic models outperform clinical biomarkers in predicting outcomes after immunotherapy for hepatocellular carcinoma [J]. J Hepatol , 2025 , 83 ( 4 ): 959 - 970 .
Kim SS , Codi A , Platts-Mills JA , et al . Personalized azithromycin treatment rules for children with watery diarrhea using machine learning [J]. Nat Commun , 2025 , 16 ( 1 ): 5968 .
Petzschner FH . Practical challenges for precision medicine [J]. Science , 2024 , 383 ( 6679 ): 149 - 150 .
Andrew TW , Alrawi M , Plummer R , et al . A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers [J]. NPJ Digit Med , 2025 , 8 ( 1 ): 15 .
Huttin O , Girerd N , Jobbe-Duval A , et al . Machine learning-based phenogrouping in MVP identifies profiles associated with myocardial fibrosis and cardiovascular events [J]. JACC Cardiovasc Imaging , 2023 , 16 ( 10 ): 1271 - 1284 .
Wan G , Leung BW , DeSimone MS , et al . Development and validation of time-to-event models to predict metastatic recurrence of localized cutaneous melanoma [J]. J Am Acad Dermatol , 2024 , 90 ( 2 ): 288 - 298 .
Low JSY , Teh HF , Thevarajah TM , et al . An AI-assisted microfluidic paper-based multiplexed surface-enhanced raman scattering (SERS) biosensor with electrophoretic removal and electrical modulation for accurate acute myocardial infarction (AMI) diagnosis and prognosis [J]. Biosens Bioelectron , 2025 , 270 : 116949 .
Maintz L , Welchowski T , Herrmann N , et al . Machine learning-based deep phenotyping of atopic dermatitis: severity-associated factors in adolescent and adult patients [J]. JAMA Dermatol , 2021 , 157 ( 12 ): 1414 .
Nielsen ML , Nymand LK , Pena AD , et al . Predictors of flares and disease severity in patients with atopic dermatitis using machine learning [J]. JAMA Dermatol , 2025 , 161 ( 9 ): 950 .
Tawfik SS , Thomas BR , Kelsell DP , et al . Dermatology quality of life index scores in bangladeshi patients with atopic eczema and their families in east London [J]. Br J Dermatol , 2023 , 188 ( 4 ): 524 - 532 .
Daneshjou R , Smith M P , Sun M D , et al . Lack of transparency and potential bias in artificial intelligence data sets and algorithms: a scoping review [J]. JAMA Dermatol , 2021 , 157 ( 11 ): 1362 .
Shamout F , Zhu T , Clifton D A . Machine learning for clinical outcome prediction [J]. IEEE Rev Biomed Eng , 2021 , 14 : 116 - 126 .
Daneshjou R , Vodrahalli K , Novoa RA , et al . Disparities in dermatology AI performance on a diverse, curated clinical image set [J]. Sci Adv , 2022 , 8 ( 32 ): eabq6147 .
Combalia M , Codella N , Rotemberg V , et al . Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 international skin imaging collaboration grand challenge [J]. Lancet Digit Health , 2022 , 4 ( 5 ): e330 - e339 .
Salinas MP , Sepúlveda J , Hidalgo L , et al . A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis [J]. NPJ Digit Med , 2024 , 7 ( 1 ): 125 .
Young AT , Fernandez K , Pfau J , et al . Stress testing reveals gaps in clinic readiness of image-based diagnostic artificial intelligence models [J]. NPJ Digit Med , 2021 , 4 ( 1 ): 10 .
Adlung L , Cohen Y , Mor U , et al . Machine learning in clinical decision making [J]. Med , 2021 , 2 ( 6 ): 642 - 665 .
Vasey B , Ursprung S , Beddoe B , et al . Association of clinician diagnostic performance with machine learning-based decision support systems: a systematic review [J]. JAMA Netw Open , 2021 , 4 ( 3 ): e211276 .
Krakowski I , Kim J , Cai ZR , et al . Human-AI interaction in skin cancer diagnosis: a systematic review and meta-analysis [J]. NPJ Digit Med , 2024 , 7 ( 1 ): 78 .
Warner E , Lee J , Hsu W , et al . Multimodal machine learning in image-based and clinical biomedicine: survey and prospects [J]. Int J Comput Vis , 2024 , 132 ( 9 ): 3753 - 3769 .
Liu H , Sun W , Cai W , et al . Current status, challenges, and prospects of artificial intelligence applications in wound repair theranostics [J]. Theranostics , 2025 , 15 ( 5 ): 1662 - 1688 .
Chanda T , Hauser K , Hobelsberger S , et al . Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma [J]. Nat Commun , 2024 , 15 ( 1 ): 524 .
Dovigi E , Wongvibulsin S , Lee I , et al . Augmented intelligence and dermatology - part Ⅱ: bias, benchmarks, guidelines, ethics, regulation, and future directions [J]. J Am Acad Dermatol , 2025 : S0190962225004402 .
Coorey G , Figtree GA , Fletcher DF , et al . The health digital twin to tackle cardiovascular disease—a review of an emerging interdisciplinary field [J]. NPJ Digit Med , 2022 , 5 ( 1 ): 126 .
Wilimitis D , Turer RW , Ripperger M , et al . Integration of face-to-face screening with real-time machine learning to predict risk of suicide among adults [J]. JAMA Netw Open , 2022 , 5 ( 5 ): e2212095 .
Gordon ER , Trager MH , Kontos D , et al . Ethical considerations for artificial intelligence in dermatology: a scoping review [J]. Br J Dermatol , 2024 , 190 ( 6 ): 789 - 797 .
Daneshjou R , Barata C , Betz-Stablein B , et al . Checklist for evaluation of image-based artificial intelligence reports in dermatology: CLEAR derm consensus guidelines from the international skin imaging collaboration artificial intelligence working group [J]. JAMA Dermatol , 2022 , 158 ( 1 ): 90 .
La Cava WG , Lee PC , Ajmal I , et al . A flexible symbolic regression method for constructing interpretable clinical prediction models [J]. NPJ Digit Med , 2023 , 6 ( 1 ): 107 .
Weir VR , Li Y , Gillis MC , et al . Evaluating skin tone scales for dermatologic dataset labeling: a prospective-comparative study [J]. NPJ Digit Med , 2025 , 8 ( 1 ): 787 .
Van Beek MJ , Swerlick RA , Daveluy S , et al . The 2023 annual report of DataDerm: the database of the american academy of dermatology [J]. J Am Acad Dermatol , 2024 , 91 ( 5 ): 904 - 909 .
Vodrahalli K , Ko J , Chiou AS , et al . Development and clinical evaluation of an artificial intelligence support tool for improving telemedicine photo quality [J]. JAMA Dermatol , 2023 , 159 ( 5 ): 496 .
Liu J , Jiang S , Wu Y , et al . Deep learning-based radiomics and machine learning for prognostic assessment in IDH-wildtype glioblastoma after maximal safe surgical resection: a multicenter study [J]. Int J Surg , 2025 , 111 ( 7 ): 4576 - 4585 .
Gomez Rossi J , Rojas-Perilla N , Krois J , et al . Cost-effectiveness of artificial intelligence as a decision-support system applied to the detection and grading of melanoma, dental caries, and diabetic retinopathy [J]. JAMA Netw Open , 2022 , 5 ( 3 ): e220269 .
Yu Z , Nguyen TD , Ju L , et al . Hierarchical skin lesion image classification with prototypical decision tree [J]. NPJ Digit Med , 2025 , 8 ( 1 ): 26 .
Feng J , Phillips RV , Malenica I , et al . Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare [J]. NPJ Digit Med , 2022 , 5 ( 1 ): 66 .
Lüscher TF , Wenzl FA , D’Ascenzo F , et al . Artificial intelligence in cardiovascular medicine: clinical applications [J]. Eur Heart J , 2024 , 45 ( 40 ): 4291 - 4304 .
0
浏览量
88
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
