Artificial intelligence is a concept that includes machine learning and deep learning. The deep learning model used in this study corresponds to DNN (deep neural network) by utilizing two or more hidden layers. In this study, MLP (multi-layer perceptron) and machine learning models (XGBoost, LGBM) were used. An MLP consists of at least three layers: an input layer, a hidden layer, and an output layer. In general, tree models or linear models using machine learning are widely used for classification. We analyzed our data by applying deep learning (MLP) to improve the performance, which showed good results. The deep learning and ML models showed differences in predictive power and disease classification patterns. We used a confusion matrix and analyzed feature importance using the SHAP value method. Here, we present a protocol to confirm that the use of deep learning can show good performance in disease classification using hospital numerical structured data (laboratory test).

This study aims to improve the efficiency of task switching in hospital laboratories. In a laboratory, several medical technicians perform multiple tasks. Technicians are not aware of the marginal amount of time it takes to switch between tasks, and this accumulation of lost minutes can cause the technician to worry more about the remaining working time than work quality. They rush through their remaining tasks, thereby rendering their work less efficient. For time optimization, we identified work changeover times to help maintain the work quality in the laboratory while reducing the number of task switching instances. We used the turnaround time (TAT) compliance rate of emergency room samples as an indicator to evaluate laboratory performance and the number of task switching instances as an index of the task performer perspective (TPP). We experimented with a monitoring system that populates the time for sample classification according to the optimal time for task switching. Through the proposed methodology, we successfully reduced not only the instances of task switching by 10% but also the TAT non-compliance rate from 4.97 to 2.66%. Consequently, the introduction of new methodology has greatly increased work efficiency.