Background/Objectives: Keratoconus (KC) is a chronic disease that causes progressive corneal thinning and steepening, thereby negatively impacting visual acuity. Although corneal topography and keratometry are the primary measures to diagnose KC, access to these methods can be limited by various factors. To address these limitations, this study evaluates a novel low-cost deep-learning algorithm that infers keratometric categories from smartphone-assisted Placido ring photographs. Methods: Development utilized 1240 healthy control eye images and 188 K1-labeled KC images for pretraining, without using their K1 labels. A Variational Autoencoder with KL divergence regularization (AutoEncoderKL) was trained on this pool; its encoder generated latent features for KC images (n = 535). A held-out set (n = 70) with Pentacam keratometry was labeled by K1 into 47 D. An ensemble classifier chosen via grid search and cross-validation used the encoder features. Performance was assessed for accuracy, precision, recall, and F1-score. Results: The model achieved 91% accuracy across all classes. Precision of the model was 0.77 (47 D); recall was 0.83, 0.91, and 1.00; and F1-scores were 0.80, 0.94, and 0.92, respectively. Notably, the model achieved perfect recall for the >47 D K1 category. Conclusions: A smartphone-assisted Placido ring imaging approach was able to predict K1-based keratometric categories without requiring tomographic or keratometric measurements as model inputs at inference. These findings provide preliminary proof-of-concept for the potential use of smartphone-assisted Placido ring images as a low-cost approach for K1-based stratification. Larger externally validated studies across different sites, devices, operators, printed Placido discs, acquisition conditions, and patient populations are required before clinical utility can be assessed.