The effort to improve healthcare delivery by making medicine more personalized, precise and efficient, presents many challenges that require the acquisition, processing and analysis of a large variety of healthcare data. One example is how patients with a trauma injury are dispatched to trauma centers distributed in large geographic areas (Bardes et al., 2022). Another example is the identification of patients with certain cardiovascular diseases, such as coronary artery disease, which often remain undetected (Joseph et al., 2021). Using protein sequence and gene expression data coupled with state-of-the-art deep learning techniques for making predictions enables a large set of applications in digital health, like predicting human age (Ashiqur Rahman et al., 2020) (Mohamadi et al., 2021), or detecting adverse drug-drug interactions (Islam et al., 2021), which is a fundamental drug safety and surveillance problem.
- Emergency Medical Services Shock Index is the Most Accurate Predictor of Patient Outcomes After Blunt Torso Trauma Journal of Trauma and Acute Care Surgery, 2022.
- BIBMDetecting Drug-Drug Interactions using Protein Sequence-Structure Similarity Networks In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2021. Oral
- BIBMHuman Age Estimation from Gene Expression Data using Artificial Neural Networks In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2021. Oral
- Coronary artery disease phenotype detection in an academic hospital system setting Applied Clinical Informatics, 2021.
- BBDeep learning for biological age estimation Briefings in Bioinformatics, 2020.