Projects
Deidentification Pipeline (M2P2)
Multilingual de-identification techniques for medical records.
Liquid Biopsy
Computational solutions to improve liquid biopsies
Single-cell multi-omics analysis
Investigating skin cancers using single-cell multi-omics
AttentionDDI
Predicting drug drug interactions for enhancing patient safety
BEDICT models
Predicting base editing efficiencies in both lab cells and living models
Drug Synergy Prediction
Predicting drug synergy for enhancing therapeutic effectiveness
Emergency care outcome prediction
ML models rapidly stratify patient cardiac risk in emergency settings
Metagenomic Mining
Training AI algorithms on metagenomic data for predicting CAS9 PAM motifs
Nursing Resource allocation
ML models for predicting patient-related nursing workload.
Prediction of lung function
Deep learning models quantify lung disease progression
PRIDICT
Predicting prime editing efficiencies and optimizing prime editing guide RNA (pegRNA) design
Systemic Sclerosis Subtype Analysis
Generative DL models patient trajectories
TEEP
TnpB editing efficiency predictor
Alignment in Spoken Interaction
Studying how conversational coordination shapes meaning in human and machine communication
Data-driven psychiatry
Modeling speech and behavior to support mental health research and assessment
Modeling Spoken Language Beyond Text
Audio-first approaches to understanding language directly from speech
Protein Design
Generative AI for protein fitness optimization
Automated Image Analysis
AI-assisted diagnosis in rheumatology
Federated Learning
Today, in every aspect of our lives, everything we do leaves a digital footprint. Health-care institutions are also increasingly …
Human Reproduction Reloaded
We are proud to be part of the UZH University Research Priority Programs (URPP) where we together with the Schwank lab investigate the …
Patient Similarity Analysis
Since the early days of computing, healthcare professionals have dreamt of using the vast storage and processing powers of computers to …
Long-read sequencing - Part I
An introduction to long-read sequencing.
MRIdle
Helping reduce idle time in the USZ Radiology department
30 days All-Cause Readmission
Comparing neural-networks versus logistic regression for predicting readmission.
autoDISCERN
Assessing the quality of online health information with AI.
Single Cell RNA Sequencing
Cancer on the cell level.
Drug-Drug Interactions
Novel computational method for drug-drug interaction predictions which are an important consideration for patient treatment.
Automated Reports from Xrays
Using deep learning for automatically generated medical reports describing radiological images.
