Detection of Vigil And Fatigue States During The Execution of Laparoscopic Tasks Based On EEG Patterns

Abstract Fatigue decreases performance in several professional activities. Fatigue can lead to commit technical mistakes which consequences might be lethal, such as in health area, where a surgical error due to the absence of rest can provoke the patient death. Therefore, this study aims to detect vigil and fatigue (due to lack of sleep) states in medical students through the classification of electroencephalographic (EEG) patterns. The EEG signals of 18 physician students were analyzed within theta band (4 - 8 Hz) over front-central recording sites, and alpha band (8 - 13 Hz) rhythms over temporal and parieto-occipital recording sites during the execution of laparoscopic tasks before and after their medical duties. The EEG signal processing pipeline consisted in pre-processing based on individual component analysis, absolute band power estimates, and Support Vector Machine classification. The F-score to differ between vigil and fatigue states was 90.89%, where the first class was slightly more identifiable reaching a sensitivity of 90.18%. Based on this outcome, the detection of fatigue in medical students while their laparoscopic training seems achievable and feasible to diminish technical mistakes that could be lethal in health area. For this purpose, EEG recording are provided.

Download Full-text

Modelos de aprendizaje automático para el apoyo en la clasificación de tipos de cáncer a partir de datos estructurados y no estructurados de expedientes clínicos

10.24275/uama.6732.7811 ◽

2020 ◽

Author(s):

◽

Erick Esteven Montelongo González

Keyword(s):

Unstructured Data ◽

Classification Model ◽

Support Vector ◽

Classification Models ◽

Multi Layer Perceptron ◽

Health Area ◽

Vector Machines ◽

Clinical Records ◽

Unstructured Information

The existence of large volumes of data generated by the health area presents an important opportunity for analysis. This can obtain information to support physicians in the decisionmaking process for the diagnosis or treatment of diseases, such as cancer. The present work shows a methodology for the classification of patients with liver, lung and breast cancer, through machine learning models, to obtain the model that performs best in the classification. The methodology considers three classification models: Support Vector Machines (SVM), Multi-Layer Perceptron (MLP) and AdaBoost using both structured and unstructured information from the patient's clinical records. Results show that the best classification model is MLP using only unstructured data, obtaining 89% of precision, showing the usefulness of this type of data in the classification of cancer patients.

Download Full-text

Evaluation of the Usefulness and Convenience of the Kyoto Classification of Gastritis in the Endoscopic Diagnosis of the Helicobacter pylori Infection Status

Digestion ◽

10.1159/000502573 ◽

2019 ◽

Vol 101 (6) ◽

pp. 771-778 ◽

Cited By ~ 4

Author(s):

Hiroyuki Sakae ◽

Masaya Iwamuro ◽

Yuki Okamoto ◽

Yuka Obayashi ◽

Yuki Baba ◽

...

Keyword(s):

Helicobacter Pylori ◽

Medical Students ◽

Endoscopic Diagnosis ◽

Infection Status ◽

Point Increase ◽

Before And After ◽

H Pylori ◽

Improved Accuracy ◽

Prompt Diagnosis

Background/Aims: The Kyoto Classification of Gastritis was published in 2014. Although this classification is now widely used in Japan, its usefulness and convenience have not been sufficiently evaluated. This study aimed to evaluate the usefulness and convenience of this classification in the endoscopic diagnosis of Helicobacter pylori infection. Methods: We made a test for the endoscopic diagnosis of H. pylori infection comprising 30 cases who had representative endoscopic features of non-, active, or inactive gastritis. Thirty-eight participants took the test before and after a brief mini-lecture on the Kyoto Classification of Gastritis. Eighteen participants took the test again 3 months later. We investigated the accuracy before, just after, and 3 months after the mini-lecture. Results: The accuracy of endoscopists after the lecture was significantly improved in comparison to before the lecture (77.6 vs. 83.3%). Medical students also showed significantly improved accuracy after the lecture (56.7 vs. 71.7%). Among endoscopists, this improvement was maintained after 3 months. Before the lecture, the accuracy of diagnosing non-gastritis was 90.3%; it tended to be further improved 3 months later (96.5%). A >10% point increase was observed in diagnosing active (72.7–83.3%) and inactive gastritis (73.2–84.3%) at 3 months after the lecture in comparison to before the lecture. Conclusion: A brief mini-lecture on the Kyoto Classification of Gastritis improved the accuracy in the endoscopic diagnosis of gastritis, indicating that understanding this classification is useful for the prompt diagnosis of H. pylori infection during esophagogastroduodenoscopy.

Download Full-text