Tag: BioData Mining

GraphRAG-ADR combines a knowledge graph with a large language model to extract adverse drug reactions from informal patient narratives, reaching ...

A retrospective cohort study developed an XGBoost model using five routine clinical indicators to estimate early pregnancy loss risk after ...

Researchers propose treating Big Five personality dimensions as tunable behavioral parameters in multi-agent AI systems, a testable framework rather than ...

A retrospective multicentre study reports that a deep learning model combining three time-point chest CT scans predicted MDR-TB treatment outcomes ...

Temporal sequence mining of linked claims and mortality data from 3.6 million Maryland residents identified 1,816 ordered diagnostic trajectories significantly ...

A new framework called EvoLatent-FS uses evolutionary feature optimization before variational encoding to learn more compact and discriminative latent representations ...

A new open-access framework called scCIF adaptively fuses single-cell multi-omics data and outperformed competing methods on eight public datasets.

A new deconvolution framework called ESMF uses single-cell reference data, negative binomial noise modeling and dual-validated marker selection to estimate ...