Cardiovascular disease (CVD) remains a leading cause of global morbidity and mortality, with self-management playing a pivotal role in improving outcomes. Voice-assisted artificial intelligence (AI) technologies such as virtual assistants and voice-controlled applications have emerged as innovative tools for healthcare delivery. While the technologies show promise in areas like primary prevention and chronic disease management, their effectiveness in supporting self-management for patients with CVD remains underexplored. This study aims to evaluate the impact of voice-assisted AI technologies on CVD self-management, specifically focusing on cardiovascular-related mortality, health-related quality of life (HRQoL) and adherence to lifestyle modifications.

A systematic review and meta-analysis will be conducted following the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols. A comprehensive search will be performed across databases such as MEDLINE, Scopus, Embase and Cochrane Central Register of Controlled Trials (CENTRAL), from 2010 to 2025. The review will include randomised controlled trials (RCTs), non-RCTs and observational studies that evaluate voice-assisted AI interventions (eg, voice-controlled fitness apps, smart health assistants) aimed at CVD self-management. The primary outcome will be cardiovascular-related mortality. Secondary outcomes will include HRQoL, clinical outcomes (eg, high blood pressure), lipid profiles (eg, cholesterol and glucose levels) and lifestyle modifications (eg, dietary habits and levels of physical activity). Data management and analysis will be conducted using Comprehensive Meta-Analysis software V.2.0. The methodological quality of the included studies will be assessed using the Cochrane Risk of Bias tool for RCTs and the Newcastle-Ottawa Scale for observational studies. The meta-analysis will use random-effects models, with heterogeneity assessed using Q and I² statistics. Subgroup analyses and meta-regression will be conducted to explore potential sources of heterogeneity.

No formal ethical assessment is required, as this study involves analysis of publicly available secondary data. Findings will be disseminated through publications in peer-reviewed scientific journals, conference presentations and media coverage to inform healthcare providers, policymakers and patients.

CRD42024568702.

Maternal and child health remains a critical public health challenge in developing countries. Annually, an estimated 250 000–280 000 maternal deaths occur, with up to 95% attributed to inadequate access to timely, effective and quality healthcare. While digital health interventions have demonstrated significant potential in improving maternal health services, education and support in high-income settings, their effectiveness, feasibility and broader impact in resource-limited contexts remain understudied.

This systematic review will assess the effectiveness, feasibility and impact of digital health interventions for pregnant women and new mothers in resource-limited settings across developing countries. We will conduct a comprehensive search of MEDLINE (via PubMed), Embase, Scopus, Google Scholar and grey literature sources to identify randomised controlled trials, quasi-experimental studies and observational studies published in any language. The quality of included studies will be assessed using the Cochrane‘s risk of bias tools, RoB 2 for randomised trials and the ROBINS-I tool for non-randomised studies. A standardised data extraction form will be developed, piloted and used to systematically collect study data. We will employ the web-based CADIMA platform to facilitate screening, data extraction and evidence synthesis while minimising bias. Data will be synthesised narratively by summarising study characteristics and, where appropriate, through meta-analysis using random-effects models to calculate pooled effect sizes. Finally, we will evaluate the strength of the evidence for each outcome using the Grading of Recommendations Assessment, Development and Evaluation approach to assess confidence in the findings.

No ethical approval was required for this systematic review, as it uses only previously published data. The findings will be submitted for publication in a peer-reviewed journal and presented at relevant international conferences to disseminate them to the broader academic community. To ensure practical application of our results, we will develop a policy brief summarising key findings and recommendations.

This protocol is registered to PROSPERO, and the registration number is CRD42025631164.