Integration of blood protein-metabolic profiles via machine learning to enable the accurate early detection of non-small cell lung cancer
Blood proteins and metabolites combined through AI can spot early lung cancer accurately, opening a path toward simpler screening approaches.
This study demonstrates that combining blood serum proteomic and metabolomic signatures through machine learning yields an accurate diagnostic classifier for early-stage NSCLC detection. The SHAP-based approach provides model interpretability to support clinical translation.
What the study was
- Study design
- ML classification study using serum proteomics + metabolomics
- Population
- NSCLC patients and controls
- Category
- Early Detection
- Maturity
- Exploratory
- Journal
- Respiratory Research
Why it surfaced
ML integration of multi-omic blood data for NSCLC early detection directly addresses liquid biopsy and early detection watchlist priority. Score capped at 6 due to absent sample size metadata.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.