Biosensors play a central role in the early detection of abnormal glucose levels in individuals with diabetes; therefore, the development of less invasive systems is essential. Herein, a 3D-printed colorimetric biosensor combining microneedles and chitosan nanoparticles was developed for glucose detection in sweat using machine learning. Briefly, hollow 3D-printed polylactic acid microneedles were constructed and loaded with chitosan nanoparticles encapsulating glucose oxidase, horseradish peroxidase, and the chromogenic substrate 2,2'-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid), resulting in the formation of the chitosan nanoparticle-microneedle patches. Glucose detection was performed colorimetrically by first incubating the chitosan nanoparticle-microneedle patches with glucose samples of varying concentrations and then by using photographs of the top side of each microneedle and a color recognition application on a smartphone. The Random Sample Consensus algorithm was used to train a simple linear regression model to predict glucose concentrations in unknown samples. The developed biosensor system exhibited a good linear response range toward glucose (0.025-0.375 mM), a low limit of detection (0.023 mM), a limit of quantification (0.078 mM), high specificity, and recovery rates ranging between 86-112%. Lastly, the biosensor was applied to glucose detection in spiked artificial sweat samples, confirming the potential of the proposed methodology for glucose detection in real samples.