Key result
MLP algorithm outperforms LSTM in predicting pain scores, achieving lower mean absolute error.
Why the study?
To analyze how deep learning models using heart rate variability-derived analgesia nociception index differed from medical doctors' predictions of expert assessment of pain scores during surgery.
Does a multilayer perceptron (MLP) algorithm improve the prediction of expert assessment of pain scores compared to an LSTM algorithm in surgical patients?
Observational (n=80)
No
Does a multilayer perceptron (MLP) algorithm improve the prediction of expert assessment of pain scores compared to an LSTM algorithm in surgical patients?
Effect estimate: MAE 2.490 ± 0.522 vs 2.633 ± 0.542
Absolute Event Rate: 2.49% vs 2.633%
An MLP algorithm using HRV data can continuously and non-invasively predict intraoperative pain levels with low error, potentially assisting in analgesic dosage adjustment.
MLP modestly outperformed LSTM for expert pain prediction in this small cohort; leaves open utility of ML models for real-time intraoperative monitoring pending validation.
There are many surgical operations performed daily in operation rooms worldwide. Adequate anesthesia is needed during an operation. Besides hypnosis, adequate analgesia is critical to prevent autonomic reactions. Clinical experience and vital signs are usually used to adjust the dosage of analgesics. Analgesia nociception index (ANI), which ranges from 0 to 100, is derived from heart rate variability (HRV) via electrocardiogram (ECG) signals, for pain evaluation in a non-invasive manner. It represents parasympathetic activity. In this study, we compared the performance of multilayer perceptron (MLP) and long short-term memory (LSTM) algorithms in predicting expert assessment of pain score (EAPS) based on patient's HRV during surgery. The objective of this study was to analyze how deep learning models differed from the medical doctors' predictions of EAPS. As the input and output features of the deep learning models, the opposites of ANI and EAPS were used. This study included 80 patients who underwent operations at National Taiwan University Hospital. Using MLP and LSTM, a holdout method was first applied to 60 training patients, 10 validation patients, and 10 testing patients. As compared to the LSTM model, which had a testing mean absolute error (MAE) of 2.633 ± 0.542, the MLP model had a testing MAE of 2.490 ± 0.522, with a more appropriate shape of its prediction curves. The model based on MLP was selected as the best. Using MLP, a seven-fold cross validation method was then applied. The first fold had the lowest testing MAE of 2.460 ± 0.634, while the overall MAE for the seven-fold cross validation method was 2.848 ± 0.308. In conclusion, HRV analysis using MLP algorithm had a good correlation with EAPS; therefore, it can play role as a continuous monitor to predict intraoperative pain levels, to assist physicians in adjusting analgesic agent dosage. Further studies may consider obtaining more input features, such as photoplethysmography (PPG) and other kinds of continuous variable, to improve the prediction performance.
No takes yet. Share an insight, caveat, or question.
Jean et al. (2022) conducted an observational in Surgical operations requiring general anesthesia (n=80). Multilayer perceptron (MLP) algorithm vs. Long short-term memory (LSTM) algorithm was evaluated on Mean absolute error (MAE) in predicting expert assessment of pain score (EAPS) (MAE 2.490 ± 0.522 vs 2.633 ± 0.542). The multilayer perceptron (MLP) algorithm achieved a lower mean absolute error (2.490 ± 0.522) compared to the LSTM algorithm (2.633 ± 0.542) in predicting expert assessments of pain scores.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: