JMIR Publications

ABSTRACT

Background:

In Lebanon, disadvantaged pregnant women suffer from poor maternal outcomes due to limited access to antenatal care (ANC) and a strained healthcare system, compounded by ongoing conflicts and a significant refugee population. Despite substantial efforts to improve maternal health, the provision of maternal health services in primary healthcare centers (PHCs) still faces significant challenges. mHealth interventions, particularly those using artificial intelligence (AI) and gamification, are proving effective in addressing gaps in maternal health services by offering scalable and accessible care.

Objective:

This study aimed to evaluate the effectiveness of an AI-based gamified intervention, Gamification and AI and mHealth Network for Maternal Health Improvement (GAIN MHI), on maternal health outcomes and access to antenatal care services among disadvantaged populations in Lebanon.

Methods:

The study was a community interventional trial with historical controls, conducted across 19 randomly allocated PHCs in five Lebanese governorates. Participants included pregnant women in their first trimester attending PHCs. The intervention utilized mHealth tools, including educational mobile-based messages, appointment reminders, and the GAIN MHI App, which provided AI-driven and gamified learning for healthcare providers. Data collection covered demographics, medical history, and maternal and neonatal health outcomes. Key outcome measures included healthcare access (e.g., ANC visits, supplement intake, ultrasound completion, lab tests) and maternal and neonatal outcomes (e.g., term delivery, normal delivery, abortion rates, neonatal morbidity, maternal complications).

Results:

3,989 participants were involved in this study, divided between the control group (n=1,993) and the intervention group (n=1,996). Separate regression models controlling for demographics, health and obstetric characteristics showed 56.9% higher likelihood of completing four or more ANC visits (OR 1.569, p<0.05) and 82.1% increase in the odds of completing the available lab tests (OR=1.821, p<0.05) in the intervention group. Results showed, as well, that the intervention group had significantly higher odds of completing two or more ultrasound images (OR=7.984, p<0.05), completing urine analysis tests (OR=4.399, p<0.05), and having better supplement intake (OR=3.508, p<0.05). Regarding maternal and neonatal outcomes, regression models showed 29.5% increase in the odds of term delivery (OR=1.295, p=0.002) and 58% increase in the odds of not facing any neonatal morbidity (OR=1.580, p=0.002) in the intervention group. On the other side, both the intervention and control groups experienced decreased odds of normal deliveries and increased odds of abortion and maternal complications.

Conclusions:

The GAIN MHI intervention effectively improved access to ANC and neonatal outcomes. These findings highlight the potential of mHealth interventions to enhance healthcare delivery. To sustain these improvements, future research should focus on integrating mHealth with other interventions that address socioeconomic and contextual factors. This approach will further optimize maternal and neonatal health outcomes among disadvantaged populations.