Key result
An extreme gradient boosting model optimized with Optuna estimated creatinine levels noninvasively using photoplethysmography signals with an accuracy of 85.2% and an ROC-AUC of 0.80.
Why the study?
Traditional creatinine measurement requires invasive blood tests associated with pain and infection risk, necessitating a noninvasive estimation method for patients with chronic kidney disease.
Can a machine learning model using photoplethysmography signals accurately estimate serum creatinine levels noninvasively?
Can a machine learning model using photoplethysmography signals accurately estimate serum creatinine levels noninvasively?
A machine learning model using PPG signals can estimate serum creatinine levels noninvasively with 85.2% accuracy, potentially reducing the need for invasive blood tests.
Answers are grounded in this paper and cite their sources.
PPG-ML creatinine estimation may reduce invasive testing in CKD; leaves open prospective validation before any practice change.
Frequent measurement of creatinine levels is vital for patients with chronic kidney disease. Traditional creatinine level measurement requires invasive blood test which has several disadvantages like discomfort, anxiety, panic, pain, risk of infection, etc. To address the issue, we propose a noninvasive machine learning (ML) model-based method to estimate creatinine level using photoplethysmography (PPG) signal. We obtained the PPG signal and gold-standard serum creatinine level of 404 patients from the Medical News Mart for Concentrated Care III (MIMIC III) database. In data preprocessing, we analyzed the PPG signal following several steps and created PPG feature set. We used multiple feature engineering methods to identify the most important features. We integrated Optuna, a hyperparameter optimization framework, with every ML model to get the optimal hyperparameters. We developed five ML models and compared their performance both with and without the application of Optuna. We found that Optuna significantly improves every model's performance. With Optuna, extreme gradient boosting (XGBoost) performed best among all five models. This XGBoost model had an accuracy of 85.2 %, an average k-fold cross validation score (k = 10) of 0.70, and a “receiver operating characteristic area under the curve” (ROC-AUC) score of 0.80. With the high performance exhibited by our developed model, the study can play a crucial role in the field of noninvasive creatinine estimation and diagnosis of chronic kidney disease. • Present machine learning (ML) model for estimating creatinine levels noninvasively using PPG signals. • Utilize the MIMIC III database, comprising PPG signals and gold-standard serum creatinine levels of patients. • Conduct data preprocessing on PPG, including feature extraction and feature engineering to identify important features. • Integrate Optuna, a hyperparameter optimization framework, to optimize models’ performance. • Employ various machine learning classification algorithms to select the best-performing model.
No takes yet. Share an insight, caveat, or question.
Sridevi et al. (2025) studied Chronic kidney disease (n=404). XGBoost machine learning model using photoplethysmography (PPG) signals vs. Invasive blood test (gold-standard serum creatinine) was evaluated on Accuracy of creatinine level estimation (ROC-AUC 0.80). An extreme gradient boosting model optimized with Optuna estimated creatinine levels noninvasively using photoplethysmography signals with an accuracy of 85.2% and an ROC-AUC of 0.80.
Synapse has enriched 10 related papers. Consider them for comparative context: