jcp.bmj.com


Inonu University researchers apply four machine learning algorithms—Random Forest, SVM, XGBoost and KNN—to complete blood count parameters to predict polycythaemia vera. After balancing the dataset with SMOTE and training on hemoglobin, hematocrit, white cell and platelet values, the XGBoost model attains an area under the curve of 0.99 and 94% accuracy, demonstrating AI’s potential to reduce reliance on expensive diagnostics like JAK2 mutation assays and bone marrow biopsy.

Key points

  • XGBoost model classifies PV with 0.99 AUC and 94% accuracy based on CBC features.
  • SMOTE oversampling addresses 82:1402 class imbalance before 80:20 train-test split.
  • PLT contributed 42.4% to model predictions, highlighting platelet count’s diagnostic value.

Why it matters: This study shows that machine learning on routine CBC can screen polycythaemia vera accurately, cutting diagnostic costs and invasiveness.

Q&A

  • What is the Synthetic Minority Oversampling Technique (SMOTE)?
  • How does XGBoost differ from other machine learning models?
  • Why use complete blood count (CBC) parameters for disease prediction?
  • What are the standard diagnostic tests for polycythaemia vera?
Copy link
Facebook X LinkedIn WhatsApp
Share post via...

A team from Hospital Universitario 12 de Octubre evaluates PD-L1 expression and tumor-infiltrating lymphocyte densities in early-stage NSCLC by comparing manual pathology with Navify Digital Pathology and PathAI algorithms. Their AI-assisted workflow speeds turnaround, improves reproducibility, and identifies more PD-L1–positive cases at clinically relevant cutoffs.

Key points

  • Navify Digital Pathology SP263 and PathAI AIM-PD-L1-NSCLC algorithms achieve ICC>0.98 for continuous PD-L1 TPS versus manual consensus.
  • AI tools detect significantly more cases with ≥1% PD-L1 TPS (p=0.00015), affecting immunotherapy eligibility.
  • PathAI and Navify TIL algorithms show strong correlation (r=0.49) between total H&E TILs and CD8+ cell densities.

Why it matters: AI-driven pathology scoring promises faster, more reproducible biomarker quantification in NSCLC, enabling better patient selection for immunotherapies.

Q&A

  • What is PD-L1?
  • What are tumor-infiltrating lymphocytes?
  • What is Tumor Proportion Score (TPS)?
  • How do AI algorithms improve pathology workflows?
  • Why measure turn-around time (TAT)?
Copy link
Facebook X LinkedIn WhatsApp
Share post via...