Andrei Michael Dreyer
Research Subjects
Research Interests
Andrei Michael Dreyer has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Brink van der Merwe
Stellenbosch University
1 shared publication - Fabian Yamaguchi
Whirly Labs, Cape Town, South Africa
1 shared publication - Sedick David Baker Effendi
Department of Computer Science, Stellenbosch University, South Africa
1 shared publication - Stefan Strydom
Mast Analytics, 4th Floor, Sunclare Building, 21 Dreyer Street, Claremont, 7708, South Africa
1 shared publication - Xavier Pinho
StackGen, San Ramon, USA
1 shared publication
Latest Publications
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 36-42
Scalable Language Agnostic Taint Tracking using Explicit Data Dependencies
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 36-42
Open AccessScalable Language Agnostic Taint Tracking using Explicit Data Dependencies
- Open Access
- 28 April 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (4) , 349-373
Automatic assignment of diagnosis codes to free-form text medical note
International Classification of Disease (ICD) coding plays a significant role in classify-ing morbidity and mortality rates. Currently, ICD codes are assigned to a patient’s medical record by hand by medical practitioners or specialist clinical coders. This practice is prone to errors, and training skilled clinical coders requires time and human resources. Automatic prediction of ICD codes can help alleviate this burden. In this paper, we propose a transformer-based architecture with label-wise attention for predicting ICD codes on a medical dataset. The transformer model is first pre-trained from scratch on a medical dataset. Once this is done, the pre-trained model is used to generate representations of the tokens in the clinical documents, which are fed into the label-wise attention layer. Finally, the outputs from the label-wise attention layer are fed into a feed-forward neural network to predict appropriate ICD codes for the input document. We evaluate our model using hospital discharge summaries and their corresponding ICD-9 codes from the MIMIC-III dataset. Our experimental results show that our transformer model outperforms all previous models in terms of micro-F1 for the full label set from the MIMIC-III dataset. This is also the first successful application of a pre-trained transformer architecture to the auto-coding problem on the full MIMIC-III dataset.
- 28 April 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (4) , 349-373
Open AccessAutomatic assignment of diagnosis codes to free-form text medical note
International Classification of Disease (ICD) coding plays a significant role in classify-ing morbidity and mortality rates. Currently, ICD codes are assigned to a patient’s medical record by hand by medical practitioners or specialist clinical coders. This practice is prone to errors, and training skilled clinical coders requires time and human resources. Automatic prediction of ICD codes can help alleviate this burden. In this paper, we propose a transformer-based architecture with label-wise attention for predicting ICD codes on a medical dataset. The transformer model is first pre-trained from scratch on a medical dataset. Once this is done, the pre-trained model is used to generate representations of the tokens in the clinical documents, which are fed into the label-wise attention layer. Finally, the outputs from the label-wise attention layer are fed into a feed-forward neural network to predict appropriate ICD codes for the input document. We evaluate our model using hospital discharge summaries and their corresponding ICD-9 codes from the MIMIC-III dataset. Our experimental results show that our transformer model outperforms all previous models in terms of micro-F1 for the full label set from the MIMIC-III dataset. This is also the first successful application of a pre-trained transformer architecture to the auto-coding problem on the full MIMIC-III dataset.