Update README.md

README.md

@@ -18,7 +18,7 @@ tags:
 
 **MADRS-BERT** is a fine-tuned `bert-base-german-cased` model that predicts depression severity scores (0–6) across individual items of the [Montgomery-Åsberg Depression Rating Scale (MADRS)](https://en.wikipedia.org/wiki/MADRS). Each prediction is based on transcribed, structured clinician–patient interview segments.
 
-- **Publication**: [https://doi.org/10.21203/rs.3.rs-6555767/v1](https://doi.org/10.21203/rs.3.rs-6555767/v1)
+- **Publication**: [https://www.nature.com/articles/s41746-025-01982-8#Sec8](https://www.nature.com/articles/s41746-025-01982-8#Sec8)
 - **Example dataset**: [https://github.com/webersamantha/MADRS-BERT/data](https://github.com/webersamantha/MADRS-BERT/data)
 - **Github Repo**: The code for data curation, finetuning and evaluation is shared in the following github repo: [https://github.com/webersamantha/MADRS-BERT](https://github.com/webersamantha/MADRS-BERT)
 
@@ -123,4 +123,4 @@ The model was evaluated on a held-out clinical validation set and achieved stron
 ## Citation
 
 If you use this model, please cite:
-> Weber, S. et al. (2025). "Using a Fine-tuned Large Language Model for Symptom-based Depression Evaluation" (https://www.nature.com/articles/s41746-025-01982-8#Sec8)
+> Weber, S. et al. (2025). "Using a Fine-tuned Large Language Model for Symptom-based Depression Evaluation" (DOI: https://doi.org/10.1038/s41746-025-01982-8)