Early Detection and AI-Based Management of Skin-Related Neglected Tropical Diseases in Sub-Saharan Africa by Frontline Health Workers (SkincAIr)

Early Detection and Management of SKIN-related negleCted Tropical Diseases Using Artificial Intelligence in Sub-saharan afRica (SkincAIr)

Skin-related Neglected Tropical Diseases (Skin NTDs) affect about 1.8 billion people worldwide, particularly in poor and rural communities where healthcare access is limited. Many people rely on frontline health workers (FHWs) for treatment, but these workers often lack specialized training in skin diseases, making diagnosis difficult. To address this challenge, the SkincAIr project is testing whether a mobile app powered by artificial intelligence (AI) can help FHWs improve their ability to detect Skin NTDs. The study will be conducted in two arms. In the first clinical image data collection arm (36 months), dermatologists in 5 countries (Kenya, Ethiopia, Senegal, Democratic Republic of Congo and Nigeria) will collect images of skin NTD and other skin conditions that will be used for development and training of the AI model within the SkincAIr app before it is tested among FHWs. The second validation study arm will take place in 3 countries (Kenya, Ethiopia and Senegal), and will involve 50 FHWs and around 750 patients in each country over 24 months. During the first 12 months (Phase A), FHWs will diagnose patients using standard methods without the app, establishing baseline performance on key indicators including diagnostic accuracy, time to diagnosis, referral patterns, and cost implications of improved primary-level diagnosis. For the following 6 months (Phase B), FHWs will use the SkincAIr app with AI functionality activated to support diagnosis and enable real-time geolocated disease mapping and hotspot identification. In the final 6 months (Phase C), the app is withdrawn to assess whether FHWs retain their improved diagnostic skills. We will summarize the results using simple numbers and charts to show how often things happen and what the average results look like. Researchers will evaluate how well the app improves diagnosis by FHWs and whether FHWs retain their improved skills even after AI support is removed, by comparing their results with those of a skin specialist (dermatologist). Interviews and group discussions will be recorded, written down, organized into key ideas, and carefully reviewed using a computer program to understand the main themes. Study findings will be shared with National Ministries of Health, presented at local and international conferences, and reported to relevant institutional and regulatory authorities. If successful, this AI tool could boost early detection of skin diseases, enhance disease tracking, and improve healthcare in underserved areas.

Study Overview

• Status: Not yet recruiting
• Conditions: Cutaneous Leishmaniasis; Lymphatic Filariasis; Onchocerciasis; Yaws; Skin and Connective Tissue Diseases; Scabies; Leprosy; Mycetoma; Neglected Tropical Diseases; Buruli Ulcer; Podoconiosis; Tungiasis; Post Kala-Azar Dermal Leishmaniasis
• Intervention / Treatment: Device: A mobile app with AI functionality for diagnosing skin-related NTDs

Detailed Description

ABSTRACT:

Skin-related Neglected Tropical Diseases (Skin NTDs) pose a significant public health challenge, affecting 1.8 billion people globally. Skin NTDs significantly affect marginalized communities due to several factors, such as lack of trained healthcare staff and diagnostic tools. Currently, due to a scarcity of dermatologists, the majority of the rural population with skin diseases is served by frontline health workers (FHWs) with limited dermatological knowledge. The low prevalence of skin NTDs further confounds their diagnosis and recognition by FHWs. Novel innovative approaches are therefore needed to build capacity and improve diagnosis for skin NTDs. Mobile health (mHealth) interventions, particularly those incorporating artificial intelligence (AI), offer a promising solution to enhance the diagnostic capabilities of FHWs. The SkincAIr project aims to evaluate whether introducing a mobile app with AI functionality can improve the diagnostic accuracy (sensitivity and specificity) of FHWs in detecting skin NTDs, and to determine their retention of improved diagnostic skills after the AI assistance is removed, indicating potential capacity building and sustained improvement in healthcare delivery. In the clinical image data collection arm (36 months), dermatologists in 5 countries (Kenya, Ethiopia, Senegal, Democratic Republic of Congo and Nigeria) will collect images of skin NTD and other skin conditions (Image data collection phase) that will be used for training and development of the SkincAIr app, before it is evaluated among FHWs during the 24-month validation study. The validation study arm for the app will involve a within-subjects longitudinal design which will enroll 50 FHWs and will recruit about 750 patients with skin complaints from areas with high burden of skin NTDs in each of 3 countries (Kenya, Ethiopia, Senegal) over a 24-month validation study period. Data will be analyzed using R and Python, with descriptive statistics (frequency, central tendency, and dispersion) summarized in tables and charts. Diagnostic accuracy of FHWs before and after app introduction will be evaluated using sensitivity, specificity, predictive values, and percent agreement with a dermatologist. Qualitative data from interviews and FGDs will be audio-recorded, transcribed, coded, and thematically analyzed using Atlas.ti Version 7. Study findings will be shared with National Ministries of Health, presented at local and international conferences, and reported to IRBs and regulatory authorities. It is envisaged that the app will improve the diagnostic accuracy of FHWs in early detection of skin NTDs and will facilitate real-time epidemiological surveillance, contributing to improved disease mapping and hotspot identification.

INTRODUCTION/BACKGROUND:

Skin-related Neglected Tropical Diseases (MDPI, 2019) (skin NTDs) such as leprosy, Buruli ulcer, yaws (endemic treponematosis), cutaneous leishmaniasis, chromoblastomycosis, mycetoma, scabies, tungiasis, Post Kala-azar Dermal Leishmaniasis (PKDL), lymphatic filariasis, onchocerciasis, podoconiosis and sporotrichosis pose a significant public health challenge, affecting 1.8 billion people globally at any given moment (WHO, 2023). Particularly in sub-Saharan Africa (SSA), these diseases are highly prevalent and are linked to substantial health inequities, predominantly impacting marginalized communities (Kariuki et al. 2023). Kenya for instance has a significant burden of Skin NTDs, including Lymphatic filariasis at the Coastal region (Njenga et al. 2017; Ofire et al. 2025), Mycetoma in Turkana (Colom et al. 2023), Leishmaniasis in Rift Valley and Eastern parts (Baringo, Naivasha/Gilgil, Laikipia, Samburu, Nakuru, Meru, West Pokot, Elgeyo Marakwet, Isiolo, Nyandarua, and Marsabit) (Ngere et al. 2020; van Dijk et al. 2024), Tungiasis (Elson et al. 2019; Nyangacha et al. 2019) and Scabies (Schmeller and Dzikus, 2001; Mbogori 2014; Macharia et al. 2024) that have a wide distribution across the country and some pockets of cases of Leprosy in Kwale, Kilifi, Kisumu, Siaya, Homabay and Busia counties (Kenya NTLLD Program Annual Report, 2014; Wangara et al. 2019).

The prevalence of these diseases is exacerbated by factors such as poverty and a lack of adequate healthcare resources, notably insufficiently trained staff for effective management of skin NTDs (Ochola et al. 2021). The stigma surrounding skin NTDs, entrenched in societal and economic contexts, leads to isolation and discrimination, discouraging diagnosis or treatment, which in turn exacerbates disease spread and complicates control and elimination efforts, creating a self-perpetuating cycle of challenges. A high proportion of NTDs have major skin manifestations. Therefore, examination of the skin serves as an opportunity to identify multiple NTDs in a single intervention. The integrative approach, recommended by the World Health Organization (WHO) (https://www.who.int/activities/promoting-the-integrated-approach-to-skin-related-neglected-tropical-diseases), results in enhanced case detection and increased efficiency through sharing of resources and expanded programme coverage. However, there is a major barrier to the integration of skin NTD interventions: the lack of dermatologists (Schmid-Grendelmeier et al. 2019) (one dermatologist for 1-2 million inhabitants) and adequately trained healthcare staff. Currently, the majority of the rural population with skin diseases is served by frontline health workers (FHWs) with limited dermatological knowledge (Mieras et al. 2018). This challenge is further confounded by the low prevalence of skin-related NTDs, which makes them difficult to be recognized by FHWs (Mieras et al. 2018; Hotez et al. 2009). As skin NTDs rely mostly on clinical diagnosis, lack of adequate training of FHWs jeopardizes disease control programs and the attainment of the overall 2021-2030 WHO NTD roadmap target to reduce morbidity, disability and the psychosocial impact of skin NTDs by 2030. Novel innovative approaches are needed to build capacity and improve diagnosis for skin NTDs to realize the 2030 goals. In this regard, Artificial Intelligence (AI) now provides an unprecedented opportunity to use advances in medical imaging applied to the skin to tackle current barriers in the diagnosis and management of skin NTDs in SSA.

Existing AI models in dermatology often focus on diseases prevalent in developed countries and rely on homogeneous datasets, leading to models that do not generalize well to diverse populations. They typically use internal validation methods, which are insufficient for real-world deployment where models encounter varied data sources (Daneshjou et al. 2021). Whereas AI-powered algorithms have demonstrated diagnostic accuracy similar to expert clinicians in high-resource settings (Salinas et al. 2024), very few studies have explored the use of AI-powered apps for diagnosing skin NTDs in low-resource settings in SSA. This is due to the novelty of the technology which contributes to the scarcity of such research. The WHO NTD-led Global Initiative discusses progress, challenges, gaps and solutions in developing and implementing artificial augmented intelligence-based apps as a capacity building and monitoring tool for skin NTDs and selected common skin conditions in resource-limited settings. Recently, the WHO incorporated two online AI algorithms that intend to classify 12 skin NTDS and 24 common skin conditions (Quilter et al. 2024) into the WHO Skin NTDs app (mainly built as a repository of educational resources and training materials, which adhere to WHO guidelines). While the app aims to improve capacity building through AI, its "real-world" impact on disease management is still not available and upcoming studies will determine its utility. The performance of AI-algorithms is also limited by the availability of images datasets. In the AI4Leprosy study conducted in 2022 at the Brazil leprosy national referral center, although the convolutional neural networks (CNN)-based AI algorithm could contribute to the diagnosis of leprosy with high classification accuracy (90%) (AI4Leprosy), to the best of our knowledge, this has not been validated in a low-resource setting with lack of highly specialized staff. Further afield, while the technology's performance is increasingly being validated in dermatological conditions such as melanoma and other skin cancers (Patel et al. 2023), the direct evidence for its efficacy in diagnosing skin-NTDs remains limited. Overall, while these studies and initiatives demonstrate the potential of AI-powered diagnostic tools, evidence specific to their use for skin NTDs in low-resource settings is still emerging.

Our proposed validation study aims to address the aforementioned gaps by evaluating the diagnostic accuracy of an AI-powered app in diagnosing skin NTDs in Kenya, Ethiopia and Senegal, providing critical insights into its practical utility and impact on clinical practice in these settings. The intervention is the SkincAIr Research App, a unified mobile platform containing three role-specific modules: a Dermatologist Dataset eCRF for structured image collection by dermatologists across 5 countries; an FHW eCRF for clinical data collection and case documentation across all 3 study phases; and the SkincAIr Detection App - an AI-powered diagnostic decision-support feature embedded within the FHW eCRF, activated exclusively during Phase B (6 months), and withdrawn during Phase C to assess retention of improved diagnostic skills. The study measures: (SO1) diagnostic performance of FHWs with and without the app, including early detection rate, diagnostic accuracy, sensitivity and specificity against a dermatologist reference standard; (SO2) dataset quality including number, geographic diversity and image quality; (SO3) reduction in diagnostic delay; (SO4) epidemiological surveillance indicators including DHIS2 integration, case confirmation ratio and hotspot identification; (SO5) FHW knowledge gain and user satisfaction. Cost-effectiveness is assessed through primary vs secondary care cost comparison and ICER calculation.

This clinical study will provide vital data to assess the practical utility of AI in improving diagnostic accuracy and speed among non-specialist health workers. By leveraging AI and mobile technology, we can equip FHWs in low-resource settings with tools to quickly detect and manage skin NTDs.

Justification for the Study:

Neglected tropical diseases (NTDs) affect over one billion people globally, with skin NTDs such as leprosy, cutaneous leishmaniasis, and onchocerciasis contributing significantly to morbidity, disability, and stigma in affected populations. Early detection and treatment are crucial to prevent complications, reduce transmission, and improve patient outcomes. In resource-limited settings like Kenya, Ethiopia, Senegal, Nigeria and the Democratic Republic of the Congo, FHWs are often the first point of contact for patients with skin conditions. However, FHWs typically lack specialized training in dermatology, leading to misdiagnosis or delayed diagnosis of skin NTDs. Mobile health (mHealth) interventions, particularly those incorporating AI, offer a promising solution to enhance the diagnostic capabilities of FHWs. The SkincAIr project aims to evaluate whether introducing a mobile app with AI functionality can improve the diagnostic accuracy of FHWs in detecting skin NTDs. Additionally, the study seeks to determine if FHWs retain improved diagnostic skills after the AI assistance is removed, indicating potential capacity building and sustained improvement in healthcare delivery. Our project transcends the twin limitations of lack of specialized training in dermatology and availability of images datasets by collecting real clinical data from multiple geographic locations within Low-and Middle-Income Countries (LMICs), ensuring that our models are trained and externally validated on diverse datasets representative of the target populations. Inclusion of Kenya, Ethiopia, Senegal, Nigeria and the Democratic Republic of the Congo will contribute to the diversity of images that are representative of the Skin NTDs endemic in multiple geographic locations in sub-Saharan Africa. As these locations present unique challenges, including limited healthcare infrastructure and varying disease presentations, the proposed study is crucial in bridging this gap. We will implement a controlled image acquisition protocol to standardize data collection, minimizing the risk of shortcut learning - where models might rely on irrelevant features due to spurious correlations (Winkler et al. 2019). By integrating multimodal data, including clinical parameters, and ensuring robustness to missing data, our models will offer more accurate and personalized diagnostic and predictive capabilities.

Null Hypothesis:

The use of the SkincAIr AI-powered mobile application will not improve the diagnostic accuracy (sensitivity and specificity) of FHWs in detecting skin-NTDs compared to their baseline performance without the app.

General Objective:

To develop an AI supported diagnostic tool for skin NTDs (SkincAIr) and test its performance and impact among frontline health workers (FHWs) in detecting select skin NTDs.

Specific Objectives:

1. To collect image data for skin NTDs and other skin conditions by dermatologists/dermatology officers or other officers trained on skin NTDS to be used in the training and development of the SkincAIr app.
2. To quantify the impact of the SkincAIr mobile application on the diagnostic accuracy (sensitivity and specificity) of frontline health workers (FHWs) in identifying skin-neglected tropical diseases (skin-NTDs) and other skin conditions.

3. To measure the impact of SkincAIr-assisted diagnosis on key clinical and operational metrics:

   • Time to diagnosis from first visit - How long it takes for a patient to receive a diagnosis, from the time they first present to a healthcare provider
   • Time from initial presentation to definitive diagnosis - the time from any initial contact (perhaps community level or first clinic) to the final confirmed diagnosis by a specialist
   • Reduction in treatment initiation delays
   • Changes in referral patterns to specialized centers - Changes in how often and how appropriately patients are referred to specialists or higher centers
   • Cost savings in secondary care attributable to enhanced primary diagnosis (early and accurate diagnoses by FHWs)
   • New hotspots of suspected or confirmed skin NTDs during the project period (up to M60).
4. To evaluate the sustainability of improved diagnostic skills among FHWs following the withdrawal of AI assistance.

• Study Type: Interventional
• Enrollment (Estimated): 2420
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Maurice R Odiere, PhD; Phone Number: 254721845777; Email: Modiere@kemri.go.ke
• Study Contact Backup: Name: Ruth M Nyangacha, PhD; Phone Number: 254728710650; Email: RNyangacha@kemri.go.ke

Study Locations

• Democratic Republic of the Congo
  • South Kivu
    • Bukavu, South Kivu, Democratic Republic of the Congo
      • Université Catholique de Bukavu (UCB)
      • Contact: Patrick de Marie Katoto Cimusa, PhD; Phone Number: 243000000000; Email: katoto.patrick@ucbukavu.ac.cd
      • Contact: Samuel Makali Lwamushi; Phone Number: 243000000000; Email: makali.lwamushi@ucbukavu.ac.cd
      • Principal Investigator: Patrick Katoto Chimusa, PhD
• Ethiopia
  • Addis Ababa
    • Addis Ababa, Addis Ababa, Ethiopia
      • Armauer Hansen Research Institute (AHRI)
      • Contact: Kassa Haile, MD; Phone Number: 251111266385; Email: kassa.haile@ahri.gov.et
      • Contact: Amanuel Lulu; Phone Number: 251111266385; Email: amanuel.lulu@ahri.gov.et
      • Principal Investigator: Kassa Haile, MD
• Kenya
  • Nyanza
    • Kisumu, Nyanza, Kenya
      • Kenya Medical Research Institute (KEMRI)
      • Contact: Maurice Odiere, PhD; Phone Number: 254721845777; Email: Modiere@kemri.go.ke
      • Contact: Ruth Nyangacha; Phone Number: 254728710650; Email: RNyangacha@kemri.go.ke
      • Principal Investigator: Maurice Odiere, PhD
• Nigeria
  • Plateau State
    • Jos, Plateau State, Nigeria
      • Leprosy and Tuberculosis Relief Initiative Nigeria (LTR)
      • Contact: Tahir Dahiru, PhD; Phone Number: 2348036000000; Email: tahirdahiru@ltrnigeria.org
      • Contact: Shehu Yusuf; Phone Number: 2348036000000; Email: tdahiru@ltrinigeria.org
      • Principal Investigator: Tahir Dahiru, PhD
• Senegal
  • Dakar
    • Dakar, Dakar, Senegal
      • Centre Hospitalier de l'Ordre de Malte (CHOM)
      • Contact: Lahla Fall, MD; Phone Number: 221773328705; Email: hopitalsenegal@ordredemaltefrance.org
      • Principal Investigator: Lahla Fall, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

1. Frontline Health Workers (FHWs) Age Group

   • Age Range: 18 years and above o Justification: FHWs must be adults, legally eligible to provide healthcare services and consent to participate in the study Sex Distribution
   • Male and Female FHWs o Justification: Both male and female FHWs will be included to reflect the actual workforce distribution and to ensure generalizability of the results across genders.

   Inclusion criteria for FHWs:

   1. Professional Role:

      o Must be working as a FHW at one of the selected health centers at the time of the validation study.

      ▪ Justification: The study aims to assess the diagnostic performance of those directly involved in primary patient care in the targeted settings.

   2. Willingness to Participate:

      o Willing to provide written informed consent to participate in the study.

      ▪ Justification: Ethical standards require voluntary participation with informed consent.

   3. Smartphone Usage:

      o Willing and able to use a smartphone during the study.

      ▪ Justification: The SkincAIr app is smartphone-based; therefore, FHWs must be willing to use and have access to such devices.

   4. No Specialized Dermatology Training:

      • FHWs without specialised training in dermatology or extensive experience in skin disease diagnosis.

        • Justification: The study aims to evaluate the app's effectiveness among generalist healthcare workers who would benefit most from diagnostic support tools.

   Exclusion criteria for FHWs:

   1. Prior Specialised Training in dermatology:

   o FHWs with formal education or extensive experience in dermatology.

   • Justification: Including specialists could skew results, as their baseline diagnostic accuracy may already be high, reducing the observable impact of the app.

     2. Refusal or Inability to Consent:

     • FHWs unwilling or unable to provide written informed consent.
   • Justification: Ethical compliance requires informed consent for participation. 3. Inability to Use the App: o FHWs unable to use a smartphone due to technical limitations, physical impairments, or lack of familiarity with the technology.
   • Justification: Effective use of the app is essential for the intervention; inability to use it would prevent meaningful participation.

2. Patients with Skin complaints Size

   ● Total Patients: ~750 patients Age Group

   ● All Age Groups:

   o Justification: Skin-NTDs affect individuals of all ages; including all age groups enhances the generalizability of the findings and assesses the app's effectiveness across the lifespan.

   Sex Distribution

   • Male and Female Patients
   • Justification: Both sexes are included to capture the full spectrum of the disease burden and ensure the app's diagnostic accuracy is effective regardless of sex.

   Inclusion Criteria for Patients with Skin complaints:

   1. Presenting with Skin Complaints:

   o Patients presenting to participating health centres with symptoms suggestive of skin-NTDs (e.g., visible skin lesions, nodules, ulcers) but have not been diagnosed by a specialist for that specific skin condition.

   • Justification: The study aims to evaluate the app's effectiveness in real-world conditions, including all patients with potential skin-NTDs 2. Willingness to Participate: o Patients (or guardians, in the case of minors) willing to provide written informed consent for participation.

   • Justification: Ethical standards require informed consent from patients or their legal guardians.

     3. Ability to Comply with Study Procedures:

     o Patients are able to follow study instructions and attend necessary follow-up appointments.

   • Justification: Ensures complete data collection and accurate assessment of outcomes.

     4. Patients with Co-morbid conditions:

   • Justification: Immunosuppression that occurs in some comorbid conditions e.g. HIV/AIDS or severe malnutrition can reveal the Skin disease and can affect both the clinical progression and even severity of the Skin NTD. This also includes patients with multiple skin-NTDs.

   Exclusion Criteria for Patients with Skin complaints:

   1. Refusal or Inability to Consent:

      o Patients (or guardians) unwilling or unable to provide written informed consent.

      ▪ Justification: Ethical compliance requires informed consent for participation.

   2. Non-Skin-Related Complaints:

      o Patients presenting with complaints unrelated to skin conditions.

      ▪ Justification: The study focuses on skin-NTDs; including unrelated cases would not contribute to the study objectives.

   3. Previous Participation in the Study:

      o Patients who have already participated in the study.

      ▪ Justification: To avoid duplicate data and potential bias in outcomes.

      Additional Considerations:

      Diversity and Representation ● Geographical Diversity:

      o Including health centres from different regions within each country ensures that the findings are representative of various settings (urban, peri-urban, rural).

      ● Cultural and Socioeconomic Factors:

      o The study acknowledges that cultural beliefs and socioeconomic status may influence healthcare-seeking behaviour and disease presentation. By including a diverse patient population, the study aims to capture these variations.

      Ethical Justification ● Inclusivity:

      • Including all age groups and both sexes aligns with ethical principles of justice and fairness, ensuring that the benefits of the research are accessible to all segments of the population.

        • Vulnerable Populations:
      • While including minors and potentially vulnerable adults, the study will implement additional safeguards to protect their rights and well-being, following ethical guidelines and obtaining consent from guardians when necessary.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Non-Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Other: Clinical Image Data Collection; Dermatologists in 5 countries (Kenya, Ethiopia, Senegal, Nigeria and DRC) use the Dermatologist Dataset eCRF module of the SkincAIr Research App to capture and annotate high-quality clinical images of skin NTDs and other skin conditions during routine clinical activity (M12-M48, 36 months). Structured metadata including disease type, body site, age group, severity and geographic location are recorded alongside each image. Collected images are used exclusively to train and develop the SkincAIr AI model prior to its validation among frontline health workers. Target: >3,500 high-quality annotated images of skin NTDs across 11 disease categories in 5 countries (KPI 2.1).	Device: A mobile app with AI functionality for diagnosing skin-related NTDs; The SkincAIr Research App is a unified mobile platform (Android, offline-capable) containing three role-specific modules: (1) Dermatologist Dataset eCRF - used by dermatologists in 5 countries (M12-M48) to capture and annotate high-quality clinical images of skin NTDs for AI model development; (2) FHW eCRF - used by frontline health workers (FHWs) in 3 countries (M22-M45) to document clinical assessments with and without AI support; (3) SkincAIr Detection App - an AI-powered diagnostic decision-support feature embedded within the FHW eCRF, activated exclusively during Phase B (6 months), providing image-based diagnostic suggestions to assist FHWs in identifying skin NTDs. The SkincAIr Detection App is the primary intervention under validation. If proven effective, it is intended for adoption by National Ministries of Health, integration into national Health Information Systems (DHIS2), and scale-up across sub-Saharan Africa.; Other Names: SkincAIr Detection App
Experimental: SkincAIr Validation Study - Frontline Health Workers; 50 frontline health workers (FHWs) per country (Kenya, Ethiopia, Senegal) and ~750 patients with skin complaints per country participate in a 24-month within-subjects validation study using the SkincAIr Research App. FHWs complete 3 consecutive phases: Phase A (M22-M33, 12 months): baseline data collection using standard diagnostic methods without AI support, using the FHW eCRF only; Phase B (M34-M39, 6 months): AI-assisted diagnosis using the SkincAIr Detection App embedded in the FHW eCRF, activated exclusively during this phase; Phase C (M40-M45, 6 months): AI support withdrawn to assess retention of improved diagnostic skills. Each FHW serves as their own control. A reference dermatologist independently evaluates each patient to provide the gold standard diagnosis.	Device: A mobile app with AI functionality for diagnosing skin-related NTDs; The SkincAIr Research App is a unified mobile platform (Android, offline-capable) containing three role-specific modules: (1) Dermatologist Dataset eCRF - used by dermatologists in 5 countries (M12-M48) to capture and annotate high-quality clinical images of skin NTDs for AI model development; (2) FHW eCRF - used by frontline health workers (FHWs) in 3 countries (M22-M45) to document clinical assessments with and without AI support; (3) SkincAIr Detection App - an AI-powered diagnostic decision-support feature embedded within the FHW eCRF, activated exclusively during Phase B (6 months), providing image-based diagnostic suggestions to assist FHWs in identifying skin NTDs. The SkincAIr Detection App is the primary intervention under validation. If proven effective, it is intended for adoption by National Ministries of Health, integration into national Health Information Systems (DHIS2), and scale-up across sub-Saharan Africa.; Other Names: SkincAIr Detection App

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
FHW Diagnostic Accuracy Improvement (FHW-DAI)	Percentage improvement in diagnostic accuracy of frontline health workers (FHWs) when using the SkincAIr Detection App compared to baseline performance without the app. Diagnostic accuracy is measured by comparing FHW diagnoses against the reference standard diagnosis established independently by a co-located dermatologist for each patient case. A minimum improvement of 15% (KPI 1.3) is required to demonstrate clinical utility of the app. Measured across all 3 study phases: Phase A (baseline, no app, M22-M33); Phase B (app active, M34-M39); Phase C (app withdrawn, M40-M45).	Month 22 through Month 45

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Early Detection Rate of Skin NTDs by FHWs (KPI 1.1)	Percentage increase in early-stage skin NTD case detection by frontline health workers (FHWs) compared to baseline. Early detection is defined as FHW identification of a skin NTD case at an early disease stage, confirmed by the reference dermatologist. A minimum increase of 12% at 6 months of app use (Phase B) is required (KPI 1.1). Measured by comparing the proportion of early-stage confirmed cases detected by FHWs across Phase A (baseline) and Phase B (app active).	22 through Month 39
Time Reduction from FHW Suspicion to Diagnostic Confirmation (KPI 1.2)	Reduction in time (days) from the moment a FHW suspects a skin NTD to external diagnostic confirmation by a dermatologist. A reduction of more than 10% compared to baseline (Phase A) is required (KPI 1.2). Measured using timestamps recorded in the FHW eCRF across all 3 study phases.	Month 22 through Month 45
Sensitivity of FHW Diagnosis for Skin NTDs (KPI 1.4)	True Positive Rate of FHW diagnoses for skin NTDs, defined as the proportion of confirmed skin NTD cases correctly identified by FHWs. A minimum sensitivity of 80% for at least 7 skin NTD categories is required (KPI 1.4). Measured by comparing FHW diagnoses against the dermatologist reference standard across all study phases.	Month 22 through Month 45
Specificity of FHW Diagnosis for Skin NTDs (KPI 1.5)	True Negative Rate of FHW diagnoses for skin NTDs, defined as the proportion of non-skin NTD cases correctly excluded by FHWs. A minimum specificity of 80% for at least 7 skin NTD categories is required (KPI 1.5). Measured by comparing FHW diagnoses against the dermatologist reference standard across all study phases.	Month 22 through Month 45
Diagnostic Delay Reduction from First Healthcare Contact to Confirmation (KPI 3.1)	Reduction in total time (days) from a patient's first healthcare contact to external diagnostic confirmation by a dermatologist. A reduction of more than 10% compared to baseline is required (KPI 3.1). This KPI measures end-to-end diagnostic pathway efficiency and complements KPI 1.2 by capturing the full patient journey including community-level contacts prior to FHW encounter.	Month 22 through Month 45
FHW Diagnostic Knowledge Gain and Retention (KPI 5.1)	Percentage improvement in FHW diagnostic knowledge scores measured using standardised image-based clinical vignette assessments administered at 3 timepoints: pre-AI exposure (end of Phase A), post-AI exposure (end of Phase B), and post-withdrawal (end of Phase C). A minimum knowledge gain of 70% is required (KPI 5.1). This outcome also assesses whether knowledge is retained after AI support is withdrawn (Phase C).	Month 33 through Month 45
User Education Satisfaction Index (UESI) (KPI 5.2)	FHW satisfaction with the SkincAIr Detection App educational features, measured using a structured satisfaction questionnaire administered at the end of Phase B. Satisfaction is scored on a standardised scale. A minimum satisfaction index of 90% is required (KPI 5.2). Data collected via self-administered questionnaire within the SkincAIr Research App.	Month 34 through Month 39
Epidemiological Surveillance - Subjects Integrated into DHIS2 (KPI 4.1)	Cumulative number of unique subjects whose data from the SkincAIr ecosystem - including validation study eCRF records and routine app usage - are integrated into national Health Information Systems (DHIS2) by end of project. A minimum of 10,000 unique subjects integrated is required (KPI 4.1). Measured through system logs and DHIS2 integration records.	Month 22 through Month 60
Case Confirmation Ratio (CCR) (KPI 4.2)	Proportion of skin NTD cases suspected by FHWs that are subsequently confirmed by a dermatologist or laboratory test. A minimum Case Confirmation Ratio of 50% is required (KPI 4.2). This indicator measures the clinical relevance and accuracy of FHW case identification within the surveillance system.	Month 22 through Month 45
Response Time to Hotspot Identification (KPI 4.3)	Time between identification of a skin NTD hotspot by the SkincAIr system and acknowledgement by the relevant health authority. A reduction of more than 10% in response time compared to baseline is required (KPI 4.3). Measured using notification and acknowledgement timestamps from SkincAIr system logs and email records.	Month 22 through Month 60
New Skin NTD Hotspots Identified (KPI 4.4)	Number of new geographically distinct skin NTD hotspots identified through the SkincAIr surveillance system during the project period. A hotspot is defined as a spatio-temporal cluster of cases exceeding baseline levels in a defined geographic grid (5-10 km resolution). A minimum of 5 new hotspots identified is required (KPI 4.4).	Month 12 through Month 60
Cost-Effectiveness of AI-Assisted Primary Diagnosis	Cost savings achieved by shifting appropriate skin NTD case management from secondary to primary care level through improved FHW diagnostic accuracy. Measured by comparing direct and indirect costs per case at primary vs secondary care level across Phase A (baseline) and Phase B (app active). Includes calculation of the Incremental Cost-Effectiveness Ratio (ICER) to assess value for money of the SkincAIr intervention.	Month 22 through Month 45

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Skin NTD Image Dataset Size and Quality (KPI 2.1-2.4)	Total number of high-resolution annotated skin NTD images collected by dermatologists across 5 countries using the Dermatologist Dataset eCRF module of the SkincAIr Research App. Targets: >3,500 images total (KPI 2.1); geographic diversity across >4 countries (KPI 2.2); >100 images of 11 skin NTD categories (KPI 2.3); >90% of images meeting predefined quality standards (KPI 2.4).	Month 12 through Month 48

Collaborators and Investigators

• Sponsor: Kenya Medical Research Institute
• Collaborators: King's College London; Universidad Politecnica de Madrid; FACHHOCHSCHULE ZENTRALSCHWEIZ - HOCHSCHULE LUZERN; SHERWOOD HEALTHCARE SENEGAL SARL; TEACUP CONSULTING SL; MTU AUSTRALO ALPHA LAB; OMODI, AGASNA, ODIEMBO ADVOCATES LLP; OEUVRES HOSPITALIERES FRANCAISES DE L'ORDRE DE MALTE; ARMAUER HANSEN RESEARCH INSTITUTE; Leprosy and Tuberculosis Relief Initiative Nigeria; UNIVERSITE CATHOLIQUE DE BUKAVU
• Investigators: Study Chair: Gustavo H Penaloza, PhD, Polytechnic University of Madrid (UPM); Study Director: Carla Rodríguez Cuesta, MEng, SHERWOOD HEALTHCARE SENEGAL SARL

Publications and helpful links

General Publications

• Mieras LF, Taal AT, Post EB, Ndeve AGZ, van Hees CLM. The Development of a Mobile Application to Support Peripheral Health Workers to Diagnose and Treat People with Skin Diseases in Resource-Poor Settings. Trop Med Infect Dis. 2018 Sep 15;3(3):102. doi: 10.3390/tropicalmed3030102.
• Yotsu RR. Integrated Management of Skin NTDs-Lessons Learned from Existing Practice and Field Research. Trop Med Infect Dis. 2018 Nov 14;3(4):120. doi: 10.3390/tropicalmed3040120.
• Winkler JK, Fink C, Toberer F, Enk A, Deinlein T, Hofmann-Wellenhof R, Thomas L, Lallas A, Blum A, Stolz W, Haenssle HA. Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition. JAMA Dermatol. 2019 Oct 1;155(10):1135-1141. doi: 10.1001/jamadermatol.2019.1735.
• Wiese S, Elson L, Reichert F, Mambo B, Feldmeier H. Prevalence, intensity and risk factors of tungiasis in Kilifi County, Kenya: I. Results from a community-based study. PLoS Negl Trop Dis. 2017 Oct 9;11(10):e0005925. doi: 10.1371/journal.pntd.0005925. eCollection 2017 Oct.
• Wangara F, Kipruto H, Ngesa O, Kayima J, Masini E, Sitienei J, Ngari F. The spatial epidemiology of leprosy in Kenya: A retrospective study. PLoS Negl Trop Dis. 2019 Apr 22;13(4):e0007329. doi: 10.1371/journal.pntd.0007329. eCollection 2019 Apr.
• van Dijk NJ, Amer S, Mwiti D, Schallig HDFH, Augustijn EW. An epidemiological and spatiotemporal analysis of visceral leishmaniasis in West Pokot, Kenya, between 2018 and 2022. BMC Infect Dis. 2024 Oct 16;24(1):1169. doi: 10.1186/s12879-024-10053-4.
• Simundic AM. Measures of Diagnostic Accuracy: Basic Definitions. EJIFCC. 2009 Jan 20;19(4):203-11. eCollection 2009 Jan.
• Shetty VP, Pandya SS, Arora S, Capadia GD. Observations from a 'special selective drive' conducted under National Leprosy Elimination Programme in Karjat taluka and Gadchiroli district of Maharashtra. Indian J Lepr. 2009 Oct-Dec;81(4):189-93.
• Schmid-Grendelmeier P, Takaoka R, Ahogo KC, Belachew WA, Brown SJ, Correia JC, Correia M, Degboe B, Dorizy-Vuong V, Faye O, Fuller LC, Grando K, Hsu C, Kayitenkore K, Lunjani N, Ly F, Mahamadou G, Manuel RCF, Kebe Dia M, Masenga EJ, Muteba Baseke C, Ouedraogo AN, Rapelanoro Rabenja F, Su J, Teclessou JN, Todd G, Taieb A. Position Statement on Atopic Dermatitis in Sub-Saharan Africa: current status and roadmap. J Eur Acad Dermatol Venereol. 2019 Nov;33(11):2019-2028. doi: 10.1111/jdv.15972.
• Schmeller W, Dzikus A. Skin diseases in children in rural Kenya: long-term results of a dermatology project within the primary health care system. Br J Dermatol. 2001 Jan;144(1):118-24.
• Salinas MP, Sepulveda J, Hidalgo L, Peirano D, Morel M, Uribe P, Rotemberg V, Briones J, Mery D, Navarrete-Dechent C. A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis. NPJ Digit Med. 2024 May 14;7(1):125. doi: 10.1038/s41746-024-01103-x.
• Roberts W, Lyson H, Speer C, Tovar E, Paz E, Zimlichman E. Cost Savings and Improved Clinical Outcomes From a Mobile Health Cardiovascular Disease Self-Management Program. Value Health. 2025 Feb 13:S1098-3015(25)00068-3. doi: 10.1016/j.jval.2025.01.025. Online ahead of print.
• Patel RH, Foltz EA, Witkowski A, Ludzik J. Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review. Cancers (Basel). 2023 Sep 23;15(19):4694. doi: 10.3390/cancers15194694.
• Ouma FF, Mulambalah CS. Persistence and Changing Distribution of Leishmaniases in Kenya Require a Paradigm Shift. J Parasitol Res. 2021 Oct 18;2021:9989581. doi: 10.1155/2021/9989581. eCollection 2021.
• Ofire MO, Omanje V, Sempele I, Chami I, Gitahi PN, Njenga SM, Omondi WP. Lymphatic filariasis elimination in Kenya: Tracing the journey from 2002-2024 and pathways to achieving 2030 target. Int J Infect Dis. 2025 Mar;152:107839. doi: 10.1016/j.ijid.2025.107839. Epub 2025 Feb 8.
• Odiwuor S, Muia A, Magiri C, Maes I, Kirigi G, Dujardin JC, Wasunna M, Mbuchi M, Auwera GV. Identification of Leishmania tropica from micro-foci of cutaneous leishmaniasis in the Kenyan Rift Valley. Pathog Glob Health. 2012 Jul;106(3):159-65. doi: 10.1179/2047773212Y.0000000015.
• Ochola EA, Karanja DMS, Elliott SJ. The impact of Neglected Tropical Diseases (NTDs) on health and wellbeing in sub-Saharan Africa (SSA): A case study of Kenya. PLoS Negl Trop Dis. 2021 Feb 11;15(2):e0009131. doi: 10.1371/journal.pntd.0009131. eCollection 2021 Feb.
• Nyangacha RM, Odongo D, Oyieke F, Bii C, Muniu E, Chasia S, Ochwoto M. Spatial distribution, prevalence and potential risk factors of Tungiasis in Vihiga County, Kenya. PLoS Negl Trop Dis. 2019 Mar 12;13(3):e0007244. doi: 10.1371/journal.pntd.0007244. eCollection 2019 Mar.
• Nsagha DS, Bamgboye EA, Oyediran AB. Childhood leprosy in Essimbiland of Cameroon: results of chart review and school survey. Nig Q J Hosp Med. 2009 Sep-Dec;19(4):214-9.
• Njenga SM, Kanyi HM, Mutungi FM, Okoyo C, Matendechero HS, Pullan RL, Halliday KE, Brooker SJ, Wamae CN, Onsongo JK, Won KY. Assessment of lymphatic filariasis prior to re-starting mass drug administration campaigns in coastal Kenya. Parasit Vectors. 2017 Feb 22;10(1):99. doi: 10.1186/s13071-017-2044-5.
• Ngere I, Gufu Boru W, Isack A, Muiruri J, Obonyo M, Matendechero S, Gura Z. Burden and risk factors of cutaneous leishmaniasis in a peri-urban settlement in Kenya, 2016. PLoS One. 2020 Jan 23;15(1):e0227697. doi: 10.1371/journal.pone.0227697. eCollection 2020.
• Msyamboza KP, Mawaya LR, Kubwalo HW, Ng'oma D, Liabunya M, Manjolo S, Msiska PP, Somba WW. Burden of leprosy in Malawi: community camp-based cross-sectional study. BMC Int Health Hum Rights. 2012 Aug 6;12:12. doi: 10.1186/1472-698X-12-12.
• Irwig L, Bossuyt P, Glasziou P, Gatsonis C, Lijmer J. Designing studies to ensure that estimates of test accuracy are transferable. BMJ. 2002 Mar 16;324(7338):669-71. doi: 10.1136/bmj.324.7338.669. No abstract available.
• Hotez PJ, Kamath A. Neglected tropical diseases in sub-saharan Africa: review of their prevalence, distribution, and disease burden. PLoS Negl Trop Dis. 2009 Aug 25;3(8):e412. doi: 10.1371/journal.pntd.0000412.
• Gitari JW, Nzou SM, Wamunyokoli F, Kinyeru E, Fujii Y, Kaneko S, Mwau M. Leishmaniasis recidivans by Leishmania tropica in Central Rift Valley Region in Kenya. Int J Infect Dis. 2018 Sep;74:109-116. doi: 10.1016/j.ijid.2018.07.008. Epub 2018 Jul 11.
• Elson L, Wiese S, Feldmeier H, Fillinger U. Prevalence, intensity and risk factors of tungiasis in Kilifi County, Kenya II: Results from a school-based observational study. PLoS Negl Trop Dis. 2019 May 16;13(5):e0007326. doi: 10.1371/journal.pntd.0007326. eCollection 2019 May.
• Dimick JB, Ryan AM. Methods for evaluating changes in health care policy: the difference-in-differences approach. JAMA. 2014 Dec 10;312(22):2401-2. doi: 10.1001/jama.2014.16153. No abstract available.
• Daneshjou R, He B, Ouyang D, Zou JY. How to evaluate deep learning for cancer diagnostics - factors and recommendations. Biochim Biophys Acta Rev Cancer. 2021 Apr;1875(2):188515. doi: 10.1016/j.bbcan.2021.188515. Epub 2021 Jan 26.
• Colom MF, Ferrer C, Ekai JL, Ferrandez D, Ramirez L, Gomez-Sanchez N, Leting S, Hernandez C. First report on mycetoma in Turkana County-North-western Kenya. PLoS Negl Trop Dis. 2023 Aug 14;17(8):e0011327. doi: 10.1371/journal.pntd.0011327. eCollection 2023 Aug.
• Cameron HM, Gatei D, Bremner AD. The deep mycoses in Kenya: A histopathological study. 1. Mycetoma. East Afr Med J. 1973 Aug;50(8):382-95. No abstract available.

Helpful Links

• The WHO Skin NTD mobile application - a paradigm shift in leprosy diagnosis through Artificial Intelligence?
• The Burden of Neglected Tropical Diseases in Sub-Saharan Africa
• Kenya National Tuberculosis Leprosy and Lung Disease Program Annual Report, 2014
• Awareness, Attitudes, Perceptions and Practices of Scabies Infestation among Caregivers of Children under 5 Years of Age in Villages of Kwale County, Kenya
• Mbogori M. 2014 (Thesis)
• Wayne W. Daniel, Chad L. Cross, Biostatistics: A Foundation for Analysis in the Health Sciences, 2013, page 191
• WHO. Promoting the integrated approach to skin-related neglected tropical diseases
• WHO 2023. Report of the first WHO global meeting on skin-related neglected tropical diseases
• WHO 2016. Monitoring and Evaluating Digital Health Interventions: a practical guide to conducting research and assessment

Study record dates

Study Major Dates

• Study Start (Estimated): May 1, 2026
• Primary Completion (Estimated): February 28, 2029
• Study Completion (Estimated): May 31, 2030

Study Registration Dates

• First Submitted: March 27, 2026
• First Submitted That Met QC Criteria: March 27, 2026
• First Posted (Actual): April 2, 2026

Study Record Updates

• Last Update Posted (Actual): April 2, 2026
• Last Update Submitted That Met QC Criteria: March 27, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Mobile Health; Kenya; mHealth; Artificial Intelligence; Diagnostic Accuracy; Digital Health; Sub-Saharan Africa; Ethiopia; Nigeria; Senegal; Democratic Republic of the Congo; Capacity Building; Frontline Health Workers; Skin-related neglected tropical diseases; Skin NTDs; AI Diagnostic Tool
• Additional Relevant MeSH Terms: Vector Borne Diseases; Mosquito-Borne Diseases; Pathologic Processes; Disease Attributes; Infections; Protozoan Infections; Parasitic Diseases; Skin Diseases; Skin Ulcer; Lymphatic Diseases; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Gram-Negative Bacterial Infections; Spirochaetales Infections; Skin Diseases, Bacterial; Skin Diseases, Infectious; Actinomycetales Infections; Mycobacterium Infections; Mycobacterium Infections, Nontuberculous; Spirurida Infections; Secernentea Infections; Nematode Infections; Skin Diseases, Parasitic; Helminthiasis; Mycoses; Treponemal Infections; Mite Infestations; Ectoparasitic Infestations; Dermatomycoses; Lymphedema; Euglenozoa Infections; Filariasis; Flea Infestations; Pathological Conditions, Signs and Symptoms; Hemic and Lymphatic Diseases; Leishmaniasis; Nocardia Infections; Onchocerciasis; Scabies; Elephantiasis, Filarial; Elephantiasis; Leprosy; Leishmaniasis, Cutaneous; Buruli Ulcer; Tungiasis; Neglected Diseases; Skin and Connective Tissue Diseases; Yaws; Mycetoma
• Other Study ID Numbers: EC grant agreement 101190743; MGAAres(2025)3881363 (Other Grant/Funding Number: Global Health EDCTP3 Joint Undertaking - European Commission)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: Anonymised clinical images and metadata collected via the Dermatologist Dataset eCRF will be made publicly available as an open dataset following project completion (M60). Individual participant data from the validation study will be available to researchers upon reasonable request, subject to data sharing agreements and ethics committee approval. Data will be stored on AWS eu-west-1 for 10 years post-study.
• IPD Sharing Time Frame: Beginning 12 months after study completion (M60), available for 10 years
• IPD Sharing Access Criteria: Researchers must submit a data access request. Access granted subject to signing a data sharing agreement compliant with GDPR and national data protection laws of participating countries.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL

Drug and device information, study documents

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