Munich Leukemia Lab
Get email alerts
New customer deployments for Munich Leukemia Lab, straight to your inbox. No account needed.
Munich Leukemia Lab has 2 source-linked AI deployments documented in AIUseCaseHub, across 1 industry and 1 country.
2
1
1
Hyperscaler mix
See whether Munich Leukemia Lab's cases are powered by Microsoft, AWS, GCP, or multiple providers.
How Munich Leukemia Lab builds AI
Build / Buy / Compose across this company's documented cases
2 of 2 cases classified (100%) · Compare all use-case types
Use case portfolio
Use case types at Munich Leukemia Lab
Clinical analytics leads with 1 of 2 documented cases; 2 distinct types appear across the visible portfolio.
Reported outcomes
1 case reports measurable results
+82%
Quality & accuracy
median · 1 metric
Medians of results published in Munich Leukemia Lab cases, normalized for comparability. See all benchmarks →
Technology snapshot
What Munich Leukemia Lab uses across visible cases
6 named technologies are mentioned across 2 cases, led by AI-based algorithms.
Capability mix
No capability flags are attached to these cases yet.
All Use Cases (2)
MLL Munich Leukemia Laboratory uses AI on AWS to speed leukaemia/lymphoma diagnostics and automate report creation
MLL Munich Leukemia Laboratory (Germany) diagnoses blood cancers using AI on AWS and a paperless cloud architecture.The lab handles complex leukaemia and lymphoma classification, large genomic datasets, and patient-specific reporting workflows.It uses large language models and AI-based algorithms with human-in-the-loop oversight to automate report writing and questionnaire ingestion.
Munich Leukemia Lab Advances Leukemia Diagnosis with Amazon SageMaker Machine Learning
Munich Leukemia Lab (MLL) partnered with the Amazon Machine Learning Solutions Lab to build a machine learning pipeline leveraging Amazon SageMaker to classify 30 leukemia subtypes using next generation sequencing (NGS) data.Manually classifying leukemia subtypes is complex, slow, and requires expensive specialized equipment and highly skilled experts, leading to turnaround times up to ten days.MLL and AWS developed a feature extraction process transforming varied NGS data into tabular form with over 70,000 features, followed by training a LightGBM model with SageMaker Hyperparameter Optimization achieving 82% accuracy in 5-fold cross-validation.The interpretable model uses SHAP to explain feature impacts per patient, aiding clinical decision making.The solution accelerates diagnosis with high accuracy, reducing time and cost while supporting precision treatment strategies for 30 leukemia subtypes.
Ask the analyst
A question about Munich Leukemia Lab the page doesn't answer? I read every one — the good ones get answered here.