Pulse.

a daily field guide to health research that matters

◆ Console

‹ Sat · 14 Nov 2026
Promising but preliminary

Routine CBC-based machine learning for individualized correction of lipemia-induced hemoglobin bias.

Machine learning can correct measurement errors in blood tests caused by sample cloudiness, improving accuracy.

BACKGROUND: Lipemia can interfere with photometric hemoglobin (HGB) measurement, causing spurious elevation and distortion of HGB-derived erythrocyte indices. RESULTS: In the 283-specimen analysis cohort, the model achieved an OOF coefficient of determination (R2) of 0.848 for Bias_PR prediction (MAE, 1.20 percentage points; root mean square error [RMSE], 2.06).

What the study was

Study design
Cohort study
Population
patients
Sample size
283
Category
Diagnostics
Maturity
Exploratory
Journal
Frontiers in medicine

Why it surfaced

Score 6/10 [PROMISING_PRELIMINARY]: Cohort study (Journal Article) matched 'CBC-based diagnostics and machine learni'. Components — novelty:1/3, relevance:2/3, design:1/2, population:2/2. Confidence: high. Conservative scoring applied per v1.3 rubric.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.