Purpose With the advancement of deep neural networks in biosignals processing, the performance of automatic sleepstaging algorithms has improved significantly. However, sleep staging using only non-electroencephalogram features hasnot been as successful, especially following the current American Association of Sleep Medicine (AASM) standards. Thisstudy presents a fine-tuning based approach to widely generalizable automatic sleep staging using heart rate and movementfeatures trained and validated on large databases of polysomnography. Methods A deep neural network is used to predict sleep stages using heart rate and movement features. The model is optimizedon a dataset of 8731 nights of polysomnography recordings labeled using the Rechtschaffen & Kales scoring system,and fine-tuned to a smaller dataset of 1641 AASM-labeled recordings. The model prior to and after fine-tuning is validated ontwo AASM-labeled external datasets totaling 1183 recordings. In order to measure the performance of the model, the outputof the optimized model is compared to reference expert-labeled sleep stages using accuracy and Cohen’s κ as key metrics. Results The fine-tuned model showed accuracy of 76.6% with Cohen’s κ of 0.606 in one of the external validation datasets,outperforming a previously reported result, and showed accuracy of 81.0% with Cohen’s κ of 0.673 in another externalvalidation dataset. Conclusion These results indicate that the proposed model is generalizable and effective in predicting sleep stages usingfeatures which can be extracted from non-contact sleep monitors. This holds valuable implications for future developmentof home sleep evaluation systems.