An App Developed for Detecting Nurse Burnouts Using the Convolutional Neural Networks in Microsoft Excel:...

Area of Science:

• Nursing
• Healthcare Technology
• Artificial Intelligence in Medicine

Background:

• Nurse burnout is a critical issue affecting healthcare professionals' well-being and patient outcomes.
• Objective classification of burnout levels remains a challenge in existing literature.

Purpose of the Study:

• To develop a convolutional neural network (CNN) model for automatic detection and classification of nurse burnout.
• To create a mobile application for early nurse burnout assessment using the Maslach Burnout Inventory-Human Services Survey (MBI-HSS).

Main Methods:

• Recruited 1002 nurses in Taiwan and administered the 20-item MBI-HSS.
• Employed k-mean clustering and CNN for classification and predictive model development, estimating 38 parameters.
• Utilized a 70%:30% data split for training and testing the predictive model.

Main Results:

• The 20-item CNN model achieved a high accuracy rate of 0.95 and an area under the curve of 0.97.
• The predictive model demonstrated 100% accuracy in classification through a novel matching scheme.
• The model accurately predicted burnout in the testing set with 0.91 accuracy.

Conclusions:

• A 20-item CNN model effectively estimates parameters for accurate nurse burnout detection.
• An app was successfully developed to aid nurses in early self-assessment of job burnout.