Related Experiment Video
Updated: Sep 28, 2025
Postconditioning with Lactate-enriched Blood for Cardioprotection in ST-segment Elevation Myocardial Infarction
Published on: May 28, 2019
Machine learning predicts blood lactate levels in children after cardiac surgery in paediatric ICU
Koichi Sughimoto1,2, Jacob Levman3,4, Fazleem Baig4
1Department of Cardiovascular Surgery, Chiba Kaihin Municipal Hospital, Chiba, Japan.
Insights
Machine learning accurately predicts pediatric blood lactate levels non-invasively using arterial waveforms. This offers a continuous, real-time assessment of hemodynamic instability, potentially improving patient care.
Area of Science:
- Biomedical Engineering
- Machine Learning in Medicine
- Critical Care Medicine
Background:
- Serum lactate levels are standard markers for hemodynamic instability.
- Continuous, non-invasive methods for assessing hemodynamic stability are needed.
- Machine learning may predict blood lactate using arterial waveforms and patient data.
Purpose of the Study:
- To investigate the feasibility of predicting blood lactate levels in pediatric ICU patients.
- To utilize machine learning algorithms applied to arterial waveforms and perioperative characteristics.
- To develop a non-invasive method for continuous hemodynamic instability monitoring.
Main Methods:
- Included 48 post-operative children with median age 4 months.
- Acquired and analyzed morphological arterial waveform characteristics.
- Employed regression-based supervised learning algorithms with hold-out cross-validation.
- Assessed algorithms using mean absolute error (MAE).
Main Results:
- A tuned random forest algorithm achieved the best performance.
- The random forest model yielded a mean absolute error of 3.38 mg/dL.
- Prediction accuracy was based on updated ground truth from the most recent blood draw.
Conclusions:
- Random forest models can predict serum lactate levels by analyzing perioperative variables and arterial pressure waveforms.
- Machine learning offers a non-invasive, continuous, and accurate method for predicting blood lactate levels.
- This approach shows potential clinical utility for monitoring hemodynamic instability in pediatric patients.
Background:
Although serum lactate levels are widely accepted markers of haemodynamic instability, an alternative method to evaluate haemodynamic stability/instability continuously and non-invasively may assist in improving the standard of patient care. We hypothesise that blood lactate in paediatric ICU patients can be predicted using machine learning applied to arterial waveforms and perioperative characteristics.
Methods:
Forty-eight post-operative children, median age 4 months (2.9-11.8 interquartile range), mean baseline heart rate of 131 beats per minute (range 33-197), mean lactate level at admission of 22.3 mg/dL (range 6.3-71.1), were included. Morphological arterial waveform characteristics were acquired and analysed. Predicting lactate levels was accomplished using regression-based supervised learning algorithms, evaluated with hold-out cross-validation, including, basing prediction on the currently acquired physiological measurements along with those acquired at admission, as well as adding the most recent lactate measurement and the time since that measurement as prediction parameters. Algorithms were assessed with mean absolute error, the average of the absolute differences between actual and predicted lactate concentrations. Low values represent superior model performance.
Results:
The best performing algorithm was the tuned random forest, which yielded a mean absolute error of 3.38 mg/dL when predicting blood lactate with updated ground truth from the most recent blood draw.
Conclusions:
The random forest is capable of predicting serum lactate levels by analysing perioperative variables, including the arterial pressure waveform. Thus, machine learning can predict patient blood lactate levels, a proxy for haemodynamic instability, non-invasively, continuously and with accuracy that may demonstrate clinical utility.
