Gene expression has great potential to be used as a clinical diagnostic tool. Researchers have discovered a wealth of patterns in gene expression that are predictive of a wide range of conditions, from liver disease to infectious disease, oncological relapse risk to stratifying autoimmune patients. Despite the progress in identifying these gene expression signatures, clinical translation has been hampered by a lack of purpose-built, readily deployable testing platforms. Deploying these tests to the clinic has relied on expensive, specialized machines, like sequencers, or laborious PCR protocols that require running a dozen or more reactions in parallel. We have developed Competitive Amplification Networks (CANs) to enable analysis of an entire gene expression signature in a single PCR reaction. CANs consist of natural and synthetic amplicons that compete for shared primers during amplification, forming a reaction network that leverages the molecular machinery of PCR. These reaction components are tuned such that the final fluorescent signal from the assay is exactly calibrated to the conclusion of a statistical model. In essence, the reaction acts as a biological computer, simultaneously detecting the RNA targets, interpreting their level in the context of the gene expression signature, and aggregating their contributions to the final diagnosis. We demonstrate the clinical validity of this technique by designing a CAN around a gene expression signature for discriminating between fevers of viral origin and bacterial origin. When tested against twenty patient blood samples, our assay achieved perfect diagnostic agreement with the gold-standard approach of measuring each gene independently. At the same time, the CAN assay was faster and easier to use. Crucially, CAN assays are compatible with existing qPCR instruments and workflows. CANs hold the potential to enable rapid deployment and massive scalability of gene expression analysis to clinical laboratories around the world, in highly developed and low-resource settings alike.