Novel multimodal sensing and machine learning strategies to classify cognitive workload in laparoscopic surgery

Background: Surgeons can experience elevated cognitive workload (CWL) during surgery due to various factors including operative technicalities and the environmental demands of the operating theatre. This can result in poorer outcomes and have a detrimental effect on surgeon well-being. The objective measurement of CWL provides a potential solution to facilitate classification of workload levels, however results are variable when physiological measures are used in isolation. The aim of this study is to develop and propose a multimodal machine learning (ML) approach to classify CWL levels using a bespoke sensor platform and to develop a ML approach to impute missing pupil diameter measures due to the effect of blinking or noise.

Materials and methods: Ten surgical trainees performed a simulated laparoscopic cholecystectomy under cognitive conditions of increasing difficulty, namely a modified auditory N-back task with increasing difficulty and a verbal clinical scenario. Physiological measures were recorded using a novel platform (MAESTRO). Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) were used as direct measures of CWL. Indirect measures included electromyography (EMG), electrocardiography (ECG) and pupil diameter (PD). A reference point for validation was provided by subjective assessment of perceived CWL using the SURG-TLX. A multimodal machine learning approach that systematically implements a CNN-BiLSTM, a binary version of the metaheuristic Manta Ray Foraging Optimisation (BMRFO) and a version of Fuzzy C-Means (FCM) called Optimal Completion Strategy (OCS) was used to classify the associated perceived CWL state.

Results: Compared to other state of the art classification techniques, cross-validation results for the classification of CWL levels suggest that the CNN-BLSTM and BMRFO approach provides an average accuracy of 97 % based on the confusion matrix. Additionally, OCS demonstrated a superior average performance of 9.15 % in terms of Root-Mean-Square-Error (RMSE) when compared to other PD imputation methods.

Conclusion: Perceived CWL levels were correctly classified using a multimodal ML approach. This approach provides a potential route to accurately classify CWL levels, which may have application in future surgical training and assessment programs as well as the development of cognitive support systems in the operating room.