A Machine Learning Algorithm Applied to Trichoscopy for Androgenic Alopecia Staging and Severity Assessment

Marco Di Fraia; Lorenzo Tieghi; Francesca Magri; Gemma Caro; Simone Michelini; Giovanni Pellacani; Alfredo Rossi

doi:10.5826/dpc.1303a136

A Machine Learning Algorithm Applied to Trichoscopy for Androgenic Alopecia Staging and Severity Assessment

Authors

Marco Di Fraia Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy
Lorenzo Tieghi Department of Mechanical and Aerospace Engineering, Sapienza University of Rome, Roma, Italy
Francesca Magri Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy
Gemma Caro Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy
Simone Michelini Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy
Giovanni Pellacani Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy
Alfredo Rossi Dermatology Clinic, Department of Clinical Internal, Anesthesiologic and Cardiovascular Sciences, Sapienza University of Rome, Roma, Italy

Keywords:

androgenic alopecia, trichoscopy, machine learning, support vector machine, staging

Abstract

Introduction: Androgenic alopecia (AGA) staging is still based on macroscopic scales, yet the introduction of trichoscopy is gradually bringing an important change, even though it remains an eye-based method. However, recently developed artificial intelligence-assisted programs can execute automated count of trichoscopic patterns. Nevertheless, to interpret data elaborated by these programs can be complex. Machine learning algorithms might represent an innovative solution. Among them, support vector machine (SVM) models are among the best methods for classification.

Objectives: Our aim was to develop a SVM algorithm, based on three trichoscopic patterns, able to classify AGA patients and to calculate a severity index.

Methods: We retrospectively analyzed trichoscopic images from 200 AGA patients using Trichoscale Pro® software, calculating the number of vellus hair, empty follicles and single hair follicular units. Then, we elaborated a SVM model, based on these three patterns and on sex, able to classify patients as affected by mild AGA or moderate-severe AGA, and able to calculate the probability of the classification being correct, expressed as percentage (from 50% to 100%). This probability estimate is higher in patients with more AGA trichoscopic patterns and, thus, it might serve as a severity index.

Results: For training and test datasets, accuracy was 94.3% and 90.0% respectively, while the Area Under the Curve was 0.99 and 0.95 respectively.

Conclusions: We believe our SVM model could be of great support for dermatologists in the management of AGA, especially in better assessing disease severity and, thus, in prescribing a more appropriate therapy.

References

Alessandrini A, Starace M, D’Ovidio R, et al. Androgenetic alopecia in women and men: Italian guidelines adapted from European Dermatology Forum/European Academy of Dermatology and Venereology guidelines. G Ital Dermatol Venereol. 2020;155(5):622-631. DOI: 10.23736/S0392-0488.19.06399-5. PMID: 33295740.

Lolli F, Pallotti F, Rossi A, et al. Androgenetic alopecia: a review. Endocrine. 2017;57(1):9-17. DOI: 10.1007/s12020-017-1280-y. PMID: 28349362.

Norwood OT. Male pattern baldness: classification and incidence. South Med J. 1975;68(11):1359-1365. DOI: 10.1097/00007611-197511000-00009. PMID: 1188424.

Biondo S, Goble D, Sinclair R. Women who present with female pattern hair loss tend to underestimate the severity of their hair loss. Br J Dermatol. 2004;150(4):750-752. DOI: 10.1046/j.0007-0963.2003.05809.x. PMID: 15099373.

Starace M, Orlando G, Alessandrini A, Piraccini BM. Female Androgenetic Alopecia: An Update on Diagnosis and Management. Am J Clin Dermatol. 2020;21(1):69-84. DOI: 10.1007/s40257-019-00479-x. PMID: 31677111.

Gupta AK, Ivanova IA, Renaud HJ. How good is artificial intelligence (AI) at solving hairy problems? A review of AI applications in hair restoration and hair disorders. Dermatol Ther. 2021;34(2):e14811. DOI: 10.1111/dth.14811. PMID: 33496058.

Jartarkar S, Patil A, Waskiel-Burnat A, Rudnicka L, Starace M, Grabbe S, Goldust M. Artificial Intelligence in Hair and Nail Disorders. J Drugs Dermatol. 2022;21(10):1049-1052 DOI: 10.36849/JDD.6519. PMID: 36219051.

Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273–297. DOI: 10.1007/BF00994018

Hu R, Xu F, Han Y, Sheng Y, Qi S, Miao Y, Yang Q. Trichoscopic findings of androgenetic alopecia and their association with disease severity. J Dermatol. 2015;42(6):602-607. DOI: 10.1111/1346-8138.12857.. PMID: 25810236.