Harnessing Artificial Intelligence for Diagnosing Androgenetic Alopecia: A Training and Validation Study

The aim of this study is to develop and validate deep learning models in diagnosis of male and female pattern hair loss, and assessment of its severity based on clinical and trichoscopic image by handheld dermoscopy and administrative data (age and sex).

Study Overview

• Status: Not yet recruiting
• Conditions: Androgenetic Alopecia

Detailed Description

The investigators intend to develop and validate artificial intelligence (AI) and machine learning (ML) models in diagnosis of male and female pattern hair loss, and assessment of its severity based on clinical and trichoscopic image using widely available and accessible handheld dermoscopes.

Conventional androgenetic alopecia (AGA) diagnosis and severity assessment are tedious and time-consuming tasks that are prone to human errors. These challenges can be tackled using artificial intelligence (AI), namely leveraging applications of machine learning and artificial neural networks for enhancing the diagnostic accuracy of scalp disease classification systems via dermoscopic image analysis. Computer aided assessment of hair microphotographs was attempted for decades, yet it faced many technical hurdles before the onset of deep learning and neural networks; and currently available software generate inaccurate results compared with visual counting. More accurate methods of analysis are needed for trichoscopic imaging, utilising deep learning image recognition models trained with a large image dataset. A number of deep learning models have been developed in recent years using videodermoscopy that achieved reliable hair density, thickness and severity classification, yet remain limited by small non-inclusive training datasets, need for hair shaving and lack of detailed reporting. Moreover, to our knowledge all previous models depend on image acquisition from expensive standalone videodermoscopy devices that lack widespread availability, rather than handheld dermoscopes that are commonly available.

The study will enroll 400 participants (200 healthy controls and 200 AGA patients). Controls undergo history and trichoscopic exams to exclude hair disorders. Trichoscopic examination will be conducted using a handheld dermoscope (CuTechs DS175) with a specialized field spacer. Patients will be assessed for disease severity using gender-specific scales. Both groups will have standardized digital and trichoscopic images taken for analysis. Images will be used to manually count and classify hairs, assess follicle units, and identify dermoscopic signs. A structured database will store all data and link clinical and image data to support objective diagnosis. AI models, particularly CNNs using transfer learning, will be trained on preprocessed images for classification and severity scoring. Model performance will be evaluated using metrics like accuracy, precision, recall, F1-score, and AUC-ROC compared with metrics reported by expert trichologists to validate accuracy and reliability

• Study Type: Observational
• Enrollment (Estimated): 400

Contacts and Locations

• Study Contact: Name: Noura Nour, MSc, MBBch; Phone Number: 00201271451744; Email: nouraadel41929@postgrad.kasralainy.edu.eg
• Study Contact Backup: Name: Ahmed Mourad, MD; Phone Number: 00201021534245; Email: ahmedmourad@kasralainy.edu.eg

Study Locations

• Egypt
  • Cairo Governorate
    • Cairo, Cairo Governorate, Egypt, 11553
      • Faculty of Medicine Cairo University
      • Contact: Noura Nour, MSc, MBBch; Phone Number: 00201271451744; Email: nouraadel41929@postgrad.kasralainy.edu.eg

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Patients diagnosed clinically and trichoscopically with androgenetic alopecia of both genders and apparently healthy controls.

Description

for the patient group:

Inclusion criteria:

• Patients with male or female pattern hair loss diagnosed clinically or suspected clinically and confirmed trichoscopically
• Age of disease onset 12-50 years old
• Both genders
• Any grade of androgenetic alopecia
• Any duration of androgenetic alopecia
• Any skin type

Exclusion criteria by clinical and trichoscopic examination:

• Patients with patchy hair loss or Telogen effluvium only.
• Patients with cicatricial alopecia or diffuse alopecia areata
• Patients with inflammatory scalp disorders (psoriasis, seborrheic dermatitis, lichen planopilaris and frontal fibrosing alopecia in a pattern distribution)
• Lack of patient cooperation.

for the control group: apparently healthy participants not suffering from the following: AGA, patchy hair loss, cicatricial alopecia, diffuse alopecia areata, inflammatory scalp disorders (psoriasis, seborrheic dermatitis, lichen planopilaris and frontal fibrosing alopecia in a pattern distribution).

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
androgenetic alopecia; Patients diagnosed clinically and trichoscopically with androgenetic alopecia of both genders. The diagnosis of AGA requires fulfillment of the primary criterion, plus one or more of the secondary criteria, and absence of exclusion criteria: Primary criterion Hair shaft thickness heterogeneity on the frontal and/or vertex scalp, defined as proportion of hairs < 0.06 mm (including intermediate, thin, and vellus hairs) ≥20%.; Secondary criteriaProportion of single hair follicle unit on the frontal and/or vertex scalp ≥30%.Proportion of vellus hairs on the frontal and/or vertex scalp >10%.There are at least two other dermoscopic signs: brown peripilar sign, yellow dots,white dots, scalp honeycomb pigmentation; Exclusion criteria Black dots, broken hairs, exclamation mark hairs
normal controls; apparently normal participants not suffering from the following : androgenetic alopecia; patchy hair loss.; cicatricial alopecia or diffuse alopecia areata; inflammatory scalp disorders (psoriasis, seborrheic dermatitis, lichen planopilaris and frontal fibrosing alopecia in a pattern distribution)

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
assessment of diagnostic capability of AI in AGA	Assess accuracy, sensitivity, specificity and positive predictive value of the trained AI models in differentiating AGA affected from non-AGA affected subjects using their macroscopic and trichoscopic images.	1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
assessment of severity of androgenetic alopecia using AI	Assess accuracy, sensitivity, specificity and positive predictive value of the trained AI models in assessment of severity of androgenetic alopecia as regards: Clinical classification (Sinclair scale for female pattern baldness and the Hamilton-Norwood scale for male pattern baldness); Trichoscopic parameters: mean hair thickness (in micrometer, using planimetric analysis), hair density (frequency per cm2), proportion of terminal hairs, proportion of vellus hairs, number of hairs per follicular unit, presence of brown peripilar sign, yellow dots, and scalp honeycomb pigmentation.	1 year
facilitation of AI assessment using macroscopic imagies	To compare the model's diagnostic accuracy using the macroscopic versus trichoscopic images alone	1 year

Collaborators and Investigators

• Sponsor: Cairo University

Publications and helpful links

General Publications

• Sacha JP, Caterino TL, Fisher BK, Carr GJ, Youngquist RS, D'Alessandro BM, Melione A, Canfield D, Bergfeld WF, Piliang MP, Kainkaryam R, Davis MG. Development and qualification of a machine learning algorithm for automated hair counting. Int J Cosmet Sci. 2021 Nov;43 Suppl 1:S34-S41. doi: 10.1111/ics.12735.
• Wang Y, Ding W, Yao M, Li Y, Wang M, Wang L, Li Z, Sun S, Yang M, Zhu Y, Zhou N. Diagnostic and grading criteria for androgenetic alopecia using dermoscopy. Skin Res Technol. 2024 Apr;30(4):e13649. doi: 10.1111/srt.13649.
• Kuczara A, Waskiel-Burnat A, Rakowska A, Olszewska M, Rudnicka L. Trichoscopy of Androgenetic Alopecia: A Systematic Review. J Clin Med. 2024 Mar 28;13(7):1962. doi: 10.3390/jcm13071962.
• Young AT, Xiong M, Pfau J, Keiser MJ, Wei ML. Artificial Intelligence in Dermatology: A Primer. J Invest Dermatol. 2020 Aug;140(8):1504-1512. doi: 10.1016/j.jid.2020.02.026. Epub 2020 Mar 27.
• Devjani S, Ezemma O, Kelley KJ, Stratton E, Senna M. Androgenetic Alopecia: Therapy Update. Drugs. 2023 Jun;83(8):701-715. doi: 10.1007/s40265-023-01880-x. Epub 2023 May 11.
• Bokhari L, Cottle P, Grimalt R, Kasprzak M, Sicinska J, Sinclair R, Tosti A. Efficiency of Hair Detection in Hair-to-Hair Matched Trichoscopy. Skin Appendage Disord. 2022 Sep;8(5):382-388. doi: 10.1159/000524345. Epub 2022 May 12.

Study record dates

Study Major Dates

• Study Start (Estimated): April 25, 2026
• Primary Completion (Estimated): September 25, 2026
• Study Completion (Estimated): November 25, 2026

Study Registration Dates

• First Submitted: December 7, 2025
• First Submitted That Met QC Criteria: December 7, 2025
• First Posted (Actual): December 19, 2025

Study Record Updates

• Last Update Posted (Actual): March 20, 2026
• Last Update Submitted That Met QC Criteria: March 19, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Androgenetic Alopecia; deep learning; male pattern hair loss; female pattern hair loss; trichoscopy; Convoluted neural network; handheld dermoscope; hair count
• Additional Relevant MeSH Terms: Pathological Conditions, Anatomical; Skin Diseases; Hypotrichosis; Hair Diseases; Pathological Conditions, Signs and Symptoms; Skin and Connective Tissue Diseases; Alopecia
• Other Study ID Numbers: MD-192-2025

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: relevant praticipant data shall be provided to researchers who request them on reasonable basis
• IPD Sharing Time Frame: from 2027 indefintely
• IPD Sharing Access Criteria: access will be provided to deidentified data including all study parameters
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF; ANALYTIC_CODE; CSR

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No