Agentic AI for Mental Health in Africa

Voice AI plus constrained Generative AI for screening, triage, clinical reporting, and longitudinal monitoring in low-resource and post-conflict settings.

AYA is building scalable mental health infrastructure for frontline care.

Tenths of Millions Silent, Invisible, Suffering

Across Africa, an invisible crisis unfolds. Over 150 million people are undiagnosed and untreated, struggling with depression, anxiety, and trauma—and unsupported. They suffer in silence because the systems designed to help them simply don't reach them.

  • 150+ million Africans with undiagnosed mental health conditions
  • Less than 5% detection rate in primary care—most people never get screened
  • 12x shortage of mental health workers compared to WHO standards
  • Frontline workers overwhelmed without tools, training, or supervision to help
African woman experiencing mental health distress

The opportunity for change is real. With the right tools, we can close this gap.

150M+

Undiagnosed and untreated

<5%

Current detection rate

1.4:100K

Mental health workers—tenth of thousands shortage (12x below WHO standard)

60%

With AYA screening

What AI-Powered Infrastructure Can Do

  • Reach people where they are—not where healthcare happens to exist
  • Work with existing frontline workers, amplifying their impact
  • Operate in resource-constrained, disconnected, post-conflict settings
  • Turn silence into support—one conversation at a time

Agentic AI for Mental Health

AYA provides a scalable infrastructure layer that empowers frontline workers with AI-driven screening, triage, clinical reporting, and continuous monitoring—designed for low-resource and post-conflict settings.

AYA Agentic AI for Mental Health Infrastructure diagram showing Voice AI Analysis, Constrained Generative AI, Triage & Reporting, Human-in-the-Loop Review, Longitudinal Monitoring, and Secure & Offline-First capabilities

Building Compassionate, Scalable Mental Health Infrastructure

AYA empowers frontline health workers, nurses, and community counselors with intelligent AI that listens, understands, and connects patients to the care they need—all within the constraints of low-resource and post-conflict settings.

Community health worker conducting voice-based mental health screening with patient

Voice AI Screening

Listen with intelligence. Our voice AI is trained on Multilingual Multimodal Clinical Dataset from diverse populations across Africa. It detects depression, anxiety, and trauma indicators in just 30 seconds—opening the door to care for those who have been invisible in the system.

60% detection rate vs. 5% current rate in primary care

Intelligent Triage & Clinical Support

Every patient deserves appropriate care. Our agentic AI orchestrates constrained workflows to classify severity and risk, guiding clinicians and supervisors toward the right care path. 85-90% accuracy in clinical decision support, grounded in proven clinical protocols.

Empowering frontline clinicians to make confident decisions

Female clinician reviewing mental health clinical reports with data visualizations
African woman receiving supportive follow-up care and monitoring

Continuous Care & Monitoring

Recovery is a journey. Longitudinal monitoring keeps care active over time—automated check-ins, risk alerts, and outcome tracking ensure no one falls through the cracks. Patients receive timely support, and supervisors gain visibility into population mental health trends.

Care that doesn't end at one visit—it sustains healing

A Patient's Journey to Care

From a 30-second voice sample to a personalized clinical plan. Meet Amara, a woman in Ethiopia, and follow her journey through AYA's intelligent screening, analysis, and care system.

1

30-Voice Sample: Sharing Her Story

Amara visits her local health clinic. A community health worker conducts a voice-based screening in Amharic, asking open-ended questions about her emotional state and well-being. Over one minute, she shares her experience—sadness about recent loss, anxiety about her family's future, and difficulty sleeping.

The 30-second voice sample captures genuine emotional expression—the foundation for AI analysis.

African woman under stress providing voice sample
2

Voice AI Analysis: Reading the Signals

AYA's voice AI, trained on Multilingual Multimodal Clinical Dataset, analyzes Amara's voice in real-time. The system calculates a comprehensive psychiatric severity score:

Emotional Distress Index (EDI) 78 — SEVERE
Sadness 84% — SEVERE
Fear/Anxiety 71% — HIGH
Anger 38% — MODERATE

Clinical Formulation

Severe emotional dysregulation with dominant sadness and anxiety, supported by voice behavioral markers (slowed speech, reduced vocal energy, tremor). High risk for self-harm and deterioration without immediate intervention.

Voice AI algorithm visualization with waveforms and emotional metrics analysis
3

GenAI Clinical Report: Actionable Insights

The voice psychiatric severity score (EDI of 78) triggers AYA's constrained GenAI layer. The system generates a detailed clinical report—not a diagnosis, but a structured guide for clinicians—including:

  • Risk Assessment: HIGH RISK — same-day clinical review required
  • Triage Level: LEVEL 1 — immediate safety inquiry and care coordination
  • Clinical Rationale: Severe emotional dysregulation with dominant sadness and fear, clinical markers consistent with depression and trauma activation
  • Treatment Pathway: Immediate psychotropic medication consideration (preferably SSRI), trauma-informed stabilization, social protection assessment

Clinicians receive this structured report instantly—no guessing, no delays. The AI confidence is 89%, grounded in clinical protocols.

Clinician reviewing AI-generated clinical report
4

Longitudinal Monitoring: Progress Tracking

Amara starts psychiatric consultation and trauma-informed counseling. Her care doesn't end at diagnosis—it deepens through continuous monitoring.

Weekly voice check-ins measure her progress:

  • EDI trajectory tracked—AYA flags if improvement stalls after 4 weeks
  • All three emotional dimensions monitored—sadness, fear, and anger patterns show recovery
  • Behavioral voice markers reassessed—improvements in speech rate, vocal energy, and tremor signal clinical progress
  • Risk alerts triggered if warning signs emerge—enabling early escalation
Patient in follow-up care session with healthcare provider
The Impact

How AI-Powered Analysis Transforms Care

Discover how our intelligent system delivers measurable improvements across every step of the patient journey

🎯

Objective Severity Measurement

EDI, emotional dimensions, and voice behavioral markers provide quantifiable clinical data—eliminating guesswork and bias in assessment

Instant Clinical Reports

From voice sample to actionable clinical plan in seconds—triage level, risk assessment, and treatment recommendations guide immediate care decisions

📊

Continuous Progress Tracking

Longitudinal monitoring follows patients across weeks and months—EDI trajectory, emotional shifts, and voice markers reveal whether treatment is working

🌍

Built for Low-Resource Settings

Trained on Multilingual Multimodal Clinical Dataset from diverse African populations, works offline on basic phones, requires minimal supervision—scaled mental health infrastructure for Africa

Our Impact

Real Stories. Real Impact. Real Change.

In communities across Ethiopia and Uganda, AYA is transforming lives. These aren't just pilot programs—they're journeys of hope where people finally get the care they deserve.

🇪🇹

Ethiopia

Lenegewa Women's Rehabilitation and Job Training Center

Active

Empowering women survivors of trauma with AI-powered screening, connecting those with sex work, homelessness, and severe poverty experiences to healing support

Actively Serving Communities
🇪🇹

Ethiopia

EECMY-DASSC

Active

Bringing mental health screening to post-conflict communities, reaching people who've experienced violence and displacement with compassionate AI-powered care

Actively Serving Communities
🇺🇬

Uganda

Karis Medical Center

Active

Integrating voice AI into clinical care, continuously monitoring patient progress and outcomes to ensure support doesn't end at diagnosis

Actively Serving Communities
Rigorous Validation

Evidence That Builds Trust

Our work isn't based on promises—it's grounded in rigorous, peer-reviewed research proving that voice AI can accurately detect mental health conditions, support trauma recovery, and save lives. These studies validate what frontline workers and patients already know: technology guided by compassion works.

📊

An AI-enabled, trauma-informed rehabilitation protocol for Ethiopian women with complex trauma

Alemu, Y., Ohiomoba, P., Kahsay, Y., et al.

International Journal of Psychiatry Research2026

Key Findings

  • AI-enabled screening and rehabilitation protocol for trauma survivors
  • Effectiveness in addressing complex trauma from sex work, homelessness, and severe poverty
  • Integration with local mental health infrastructure
Read Study
📊

Objectively quantifying pediatric psychiatric severity using artificial intelligence, voice recognition technology, and universal emotions: Pilot study

Alemu, Y., Teshome, S., Salegh, E., Ohiomoba, P., & Vinson, S.

Annals of Research Protocols2023

Key Findings

  • Voice AI accurately quantifies psychiatric severity in pediatric populations
  • Universal emotional recognition improves diagnostic accuracy
  • Pilot validation across diverse populations
Read Study
📊

Implementing and analyzing the advantages of voice AI measurement-based care to address behavioral health treatment disparities among youth

Alemu, Y., Cardenas Bautista, E., Vinson, S., Ohiomoba, P., et al.

Telehealth and Telemedicine Today2024

Key Findings

  • Voice AI measurement-based care reduces health disparities in youth mental health
  • Implementation evidence for scaling in underserved communities
  • Improved treatment outcomes through objective severity monitoring
Read Study
📊

Objectively quantifying pediatric psychiatric severity using AI and voice recognition technology

Caulley, D., Alemu, Y., Burson, S., et al.

JMIR Research Protocols2023

Key Findings

  • Validated AI and voice recognition methodology for psychiatric assessment
  • High accuracy in identifying clinical severity levels
  • Scalable approach for global mental health screening
Read Study
Meet Our Team

Builders, Healers, Believers

Our team bridges technology and compassion. Doctors, engineers, clinicians, and advocates united by a single conviction: mental health care in Africa is possible, and it starts now.

Dr. Yared Alemu

Dr. Yared Alemu

CEO and Co-Founder

Patrick Ohiomoba

Patrick Ohiomoba

CTO and Co-Founder

Dr. Delessa Bulcha Neger

Dr. Delessa Bulcha Neger

Strategic Advisor

Dr. Selam Negussie

Dr. Selam Negussie

Psychiatrist and Director of Clinical Services

Octavian Balafel

Octavian Balafel

Lead Software Engineer

Dr. Randa Ibrahim

Dr. Randa Ibrahim

Physician-Coach-Counselor

Dr. Fikrte Teklemariam

Dr. Fikrte Teklemariam

Physician-Coach-Counselor

Dr. Yoeal Asfiaha

Dr. Yoeal Asfiaha

Physician-Coach-Counselor

Dr. Abdi Degelu

Dr. Abdi Degelu

Lead Implementation Director

Dr. Selam Abadi

Dr. Selam Abadi

Physician-Coach-Counselor

Dr. Lidya Tessema

Dr. Lidya Tessema

Team Member

Our Ecosystem

Built Together with Africa

AYA is co-designed and deployed with the leaders, healers, and innovators across Africa who understand what mental health infrastructure truly needs. From regional authorities to grassroots NGOs, these are the partners making this possible.

Oromo Science Technology Authority (OSTA)

Regional Authority

The largest region in Ethiopia, serving a population of 60 million. OSTA drives innovation and technology adoption across the region's healthcare infrastructure.

Key Contribution

Population reach: 60M

EECMY-DASSC

NGO Partner

One of the oldest and largest NGOs in Ethiopia with over 240 active projects covering all of Ethiopia's regions. Provides deep community integration and implementation support.

Key Contribution

240+ projects nationally

AASTU

Academic Institution

Addis Ababa Science and Technology University serves as the lead academic institution for science and technology research and innovation in Ethiopia.

Key Contribution

Research validation hub

Jimma University

Medical Partner

One of the largest and most advanced medical schools in Ethiopia. Provides clinical expertise, validation, and training for mental health professionals.

Key Contribution

Clinical training partner

Bule Hora University

Remote Deployment Partner

Located in a remote region of Ethiopia, serves as the testing ground for implementations in challenging environments with limited connectivity and resources.

Key Contribution

Low-resource testing site

Join Us in Closing the Gap

If your health system, NGO, research institution, or community organization believes mental health is a human right—and you're ready to bring that belief to life—let's talk. Together, we can build the infrastructure that finally reaches those who've been invisible.