Table 2 Characteristics of the Projects
From: Spotlighting healthcare frontline workers´ perceptions on artificial intelligence across the globe
Name | Type | Aim | Country | End-Users Context | Languages Used |
|---|---|---|---|---|---|
UFMG | Maternal and Child health | Evaluating and finetuning large language models (LLMs) responses to Maternal and Child health inquiries. | Brazil, Pakistan, USA | Frontline health care workers (HCWs), Patients | Portuguese, Urdu, English |
NoHarm | Diagnosis and Treatment Data | AI-assisted clinical treatment procedures (diagnosis, discharge summaries, follow-up) in clinical settings. | Brazil | Patients, Frontline HCWs, Patients | Portuguese |
Susastho.ai | Sexual and Reproductive Health (SRH) Information | Using AI-powered (LLM & Speech-based conversational AI) platforms to provide patients with secure & private access to SRH related information and services | Bangladesh | Adolescents, At-risk populations | Bangla |
Intelsurv | Health Training, Information & Supervision | Using GPT-4 to augment structured supervisions and training for community health care workers (CHWs) | Malawi | Community healthcare workers (CHWs) | Chichewa |
EHA Clinics | Health Training & Supervision | Nigeria | English | ||
Boresha | Health Communication & Information | AI-mediated Health Messaging for community Health promotion and education | Tanzania | At-risk populations (Women & Youth) | Swahili |
