JMIR Publications

ABSTRACT

Background:

Skin Neglected Tropical Diseases (NTDs) pose significant diagnostic and management challenges in resource-limited settings due to constrained dermatological expertise, frontline health worker (FHW) training and limited access to diagnostic resources. Mobile health (mHealth) applications (apps) with AI-enabled diagnostic imaging capabilities have the potential to enhance clinical decision making and professional development at the primary care level. The World Health Organisation (WHO) skin NTD mobile app utilises convolutional neural networks to analyse images of skin lesions and generate differential diagnoses, intended to be used alongside clinical history and examination, to support FHWs in identifying 12 skin NTDs and 24 common skin conditions. Beyond clinical decision support, the app also aims to upskill FHWs in the recognition and management of these diseases. However, the success of such tools depends on understanding users’ needs and the realities of implementation in diverse clinical contexts.

Objective:

This study aimed to explore FHWs’ perspectives on the real-world use and impact of the AI-embedded WHO Skin NTD app on diagnostic workflows, dermatological understanding, clinical decision-making and FHW-patient interactions across diverse healthcare delivery settings in Kenya.

Methods:

This qualitative study involved 36 FHWs from five skin NTD-endemic counties in Kenya. Following a training workshop, FHWs integrated the app into routine clinical workflows from June to October 2024. Data were collected through 15 semi-structured interviews (each 30-45 minutes) and 4 focus group discussions (1–1.5 hours) exploring FHW experiences across diverse healthcare delivery contexts. All sessions were audio-recorded, transcribed verbatim and thematically analysed using NVivo, employing a bottom-up inductive coding approach.

Results:

FHWs reported that the app facilitated a shift from habitual referral to more proactive case management at the local-facility level, reinforcing clinical ownership and positioning them as local dermatology reference points. It was perceived to enhance diagnostic confidence, strengthen patient trust, and encourage community engagement. Some FHWs described how the app helped mitigate situations for patient stigma due to decreased reliance on public colleague consultations. However, technical limitations (e.g., internet dependency, algorithmic errors) constrained consistent use. While most FHWs used the app in line with its intended role as an assistive tool, a minority reported situations of diagnostic deferral to the AI output, highlighting potential considerations of clinical autonomy.

Conclusions:

The WHO Skin NTD app shows strong potential to strengthen frontline dermatological capacity that aligns with WHO strategies to decentralise NTD care and promote “skin health for all.” Our findings underscore the importance of embedding such tools within ethical and pedagogical frameworks that protect clinical autonomy and foster sustainable capacity building. Further research will examine real-world use in situ to guide context-specific governance, ensuring this AI-embedded tool enhances - rather than displaces – clinical reasoning and epistemic authority.