Search papers, labs, and topics across Lattice.
This paper presents a cloud-edge collaborative architecture designed for multimodal clinical screening in resource-constrained rural settings, where traditional medical AI solutions often fail due to limited bandwidth and compute resources. By utilizing lightweight, domain-specific models at the edge to process raw medical data and a cloud-based LLM to synthesize clinical summaries, the system dynamically selects diagnostic tools based on patient context, ensuring comprehensive modality coverage. Evaluation across 20 clinical cases demonstrates that this hybrid approach achieves 98-99% diagnostic tool recall and 92-96% precision, outperforming cloud-only baselines while maintaining low latency and cost.
A hybrid cloud-edge system achieves near-perfect diagnostic recall while slashing operational costs and latency in rural healthcare settings.
Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific models on the edge transform raw medical data into compact structured outputs, while a cloud LLM synthesizes these outputs into clinical summaries. An LLM-based orchestrator dynamically selects diagnostic tools based on patient context, promoting comprehensive modality coverage without processing irrelevant inputs. We evaluate on 20 multimodal clinical cases spanning cardiac, obstetric, trauma, and screening scenarios under three simulated network profiles (500,kbps--5,Mbps). The hybrid system achieves 98--99% diagnostic tool recall with 92--96% precision, matches or exceeds cloud-only baselines on clinical accuracy, and maintains bandwidth-invariant latency (25--35,s) at 4--15x lower token cost. These results highlight the role of architectural design in enabling efficient multimodal integration and improving factual grounding compared to cloud-only approaches under deployment constraints.
