<![CDATA[Background: Malaria causes significant diagnostic bottlenecks during tropical outbreaks due to the limitations of light microscopy and rapid diagnostic tests (RDTs). Rapid parasite identification is essential for effective outbreak surveillance and military medical readiness, particularly in resource-constrained settings where delayed diagnosis can lead to hyperparasitaemia and ongoing transmission. This study evaluates the diagnostic precision of advanced computational modalities and conceptualizes the Malaria Outbreak Surveillance with Artificial Intelligence and Collaboration (MOSAIC) framework to strengthen counter-malaria strategies. Methods: Following PRISMA 2020 guidelines, a systematic literature search was conducted across six electronic databases (PubMed, Scopus, Google Scholar, Cochrane Library, EBSCO, and ScienceDirect). From 125 identified records, fifteen studies published between 2015 and 2026 met predefined eligibility criteria and were assessed for methodological quality. Discussion: wing to substantial methodological heterogeneity, a qualitative narrative synthesis was performed. The review examined key diagnostic metrics, including sensitivity, specificity, accuracy, and F1-score, reported by deep learning and vision-transformer models applied to digital blood smears. Findings were integrated into the tri-layered MOSAIC framework, which proposes that automated diagnostic performance must operate alongside interdisciplinary collaboration to enable timely outbreak detection, resource allocation, and field response. Conclusion: While AI offers immense potential to overcome diagnostic gridlocks through high-throughput analysis, isolated computational prowess lacks epidemiological impact. Successful outbreak mitigation depends upon the harmonised, intersectoral orchestration proposed within the MOSAIC framework, necessitating prospective field trials and standardised reporting protocols for clinical implementation. Keywords: Artificial intelligence, Malaria, Outbreak surveillance, Convolutional neural networks, Interdisciplinary collaboration.]]>
