The spread of infectious diseases in crowded spaces such as shopping malls, markets, and hospitals is a growing concern. In order to mitigate this risk, it is crucial to develop a method that leverages the power of distributed crowd to learn, de- tect, and alert individuals about potential health hazards. Hence, the integration of federated learning (FL), and blockchain (BC) to provide intelligent platforms that facilitate pervasive AI and trust amongst IoT devices and smart phones can play a significant role in achieving this goal. In this study, we propose a new technique named BC-FL Location-Based, which utilizes smart applications installed on IoT devices and smart phones to detect and predict imminent health risks. The technique works by using algorithms such as maximal clique to detect individuals in close proximity and sharing their health data through a blockchain network. A smart contract then triggers a node with sufficient resources to gather users' learning experiences from the blockchain, aggregate it, and run a model to determine if any of the individuals present in the area are infected. To demonstrate the effectiveness of the proposed technique, we conducted simulation experiments using Ethereum-based private blockchain network, where nodes represent individuals in different locations. We used the maximal clique algorithm to simulate the movement of individuals and compared the results of the model run on individual data versus aggregated data. Experiments showed promising results, with accuracy of detection increasing to 99% when using iid data and 90% when using non-iid data.