Key result
Non-invasive PPG signals estimate hemoglobin values with ~81% accuracy using a random forest model.
Why the study?
The study was conducted to facilitate the noninvasive estimation of hemoglobin values using a machine learning model.
Does a Random Forest Regression model using PPG signals improve the accuracy of non-invasive hemoglobin estimation compared to other ML models?
Does a Random Forest Regression model using PPG signals improve the accuracy of non-invasive hemoglobin estimation compared to other ML models?
A Random Forest Regression model using PPG signals can estimate hemoglobin non-invasively with 81% accuracy and a mean absolute error of 0.88.
No takes yet. Share an insight, caveat, or question.
May support non-invasive Hb monitoring in limited settings; leaves open prospective validation against reference standards.
Jayasanthi et al. (2024) studied Hemoglobin estimation (n=3,000). Random Forest Regression model using PPG signals vs. Other ML models (LASSO, Support Vector, Ridge, and ADA-BOOST Regression) was evaluated on Hemoglobin estimation accuracy. A Random Forest Regression model using non-invasive Photo-plethysmography (PPG) signals estimated hemoglobin values with 81% accuracy and a mean absolute error of 0.88.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: