Search

Background: The damage that may be caused to the operating table and patients under general anaesthesia when a large earthquake occurs is unclear. We aimed to evaluate the movement and damage to operating tables and patients under general anaesthesia during an earthquake. Methods: An operating table with a manikin resembling a patient on it was placed on a shaking table, and seismic waves were input into the shaking table. The effects of seismic waves were evaluated by altering surgical positions (supine and head-down positions), operating tables, flooring material, seismic waves, and output. We observed the movement of the operating table and measured the acceleration of the operating table and manikin head. Results: Under 90% output of long-period seismic waves, the operating table with the supine manikin was overturned. Under experimental conditions that did not cause rocking, shaking such as tilting of the operating table caused stronger acceleration in the manikin's head than in the operating table. There was no clear relationship between operating table rocking and maximum acceleration as a result of programmed seismic waves. In long-period earthquakes, rocking and overturning occurred >60 s after the onset of shaking, whereas in direct earthquakes, rocking occurred within 10 s. Conclusions: An earthquake could cause strong acceleration of the patient's head under general anaesthesia, and operating tables may overturn or shake violently. Regarding patient safety, further measures to prevent overturning should be considered.

Purpose: Natural language processing using language models has yielded promising results in various fields. Language models can help improve the workflow of radiologists. This retrospective study aimed to construct and evaluate language models for automatic summarization of radiology reports. Methods: Two radiology report datasets from the MIMIC Chest X-ray (MIMIC-CXR) database and the Japan Medical Image Database (JMID) were included in this study. The MIMIC-CXR is an open database comprising chest radiograph reports. The JMID is a large database comprising computed tomography and magnetic resonance imaging reports from 10 academic medical centers in Japan. A total of 128,032 and 1,101,271 reports were included in this study from the MIMIC-CXR database and JMID, respectively. Four Text-to-Text Transfer Transformer (T5) models were constructed. Recall-Oriented Understudy for Gisting Evaluation (ROUGE), a quantitative metric, was used to evaluate the quality of the text summarized from 19,205 and 58,043 test sets from the MIMIC-CXR and JMID, respectively. The Wilcoxon signed-rank test was used to evaluate the differences among the ROUGE values of the four T5 models. Moreover, the subsets of automatically summarized text in the test sets were manually evaluated by two radiologists. The best T5 models were selected for automatic summarization using the Wilcoxon signed-rank test. Results: The quantitative metrics of the best T5 models were as follows: ROUGE-1 = 57.75 ± 30.99, ROUGE-2 = 49.96 ± 35.36, and ROUGE-L = 54.07 ± 32.48 in the MIMIC-CXR; and ROUGE-1 = 50.00 ± 29.24, ROUGE-2 = 39.66 ± 30.21, and ROUGE-L = 47.87 ± 29.44 in the JMID. The radiologists’ evaluations revealed 86% and 85% of the texts automatically summarized from the MIMIC-CXR and JMID, respectively, to be clinically useful. Conclusion: The T5 models constructed in this study were able to perform automatic summarization of the radiology reports. The radiologists’ evaluations demonstrated most of the automatically summarized texts to be clinically valuable.

BackgroundHospital bed management is an important resource allocation task in hospital management, but currently, it is a challenging task. However, acquiring an optimal solution is also difficult because intraorganizational information asymmetry exists. Signaling, as defined in the fields of economics, can be used to mitigate this problem. ObjectiveWe aimed to develop an assignment process that is based on a token economy as signaling intermediary. MethodsWe implemented a game-like simulation, representing token economy–based bed assignments, in which 3 players act as ward managers of 3 inpatient wards (1 each). As a preliminary evaluation, we recruited 9 nurse managers to play and then participate in a survey about qualitative perceptions for current and proposed methods (7-point Likert scale). We also asked them about preferred rewards for collected tokens. In addition, we quantitatively recorded participant pricing behavior. ResultsParticipants scored the token economy–method positively in staff satisfaction (3.89 points vs 2.67 points) and patient safety (4.38 points vs 3.50 points) compared to the current method, but they scored the proposed method negatively for managerial rivalry, staff employee development, and benefit for patients. The majority of participants (7 out of 9) listed human resources as the preferred reward for tokens. There were slight associations between workload information and pricing. ConclusionsSurvey results indicate that the proposed method can improve staff satisfaction and patient safety by increasing the decision-making autonomy of staff but may also increase managerial rivalry, as expected from existing criticism for decentralized decision-making. Participant behavior indicated that token-based pricing can act as a signaling intermediary. Given responses related to rewards, a token system that is designed to incorporate human resource allocation is a promising method. Based on aforementioned discussion, we concluded that a token economy–based bed allocation system has the potential to be an optimal method by mitigating information asymmetry.

We aimed to evaluate a computer-aided diagnosis (CADx) system for lung nodule classification focussing on (i) usefulness of the conventional CADx system (hand-crafted imaging feature + machine learning algorithm), (ii) comparison between support vector machine (SVM) and gradient tree boosting (XGBoost) as machine learning algorithms, and (iii) effectiveness of parameter optimization using Bayesian optimization and random search. Data on 99 lung nodules (62 lung cancers and 37 benign lung nodules) were included from public databases of CT images. A variant of the local binary pattern was used for calculating a feature vector. SVM or XGBoost was trained using the feature vector and its corresponding label. Tree Parzen Estimator (TPE) was used as Bayesian optimization for parameters of SVM and XGBoost. Random search was done for comparison with TPE. Leave-one-out cross-validation was used for optimizing and evaluating the performance of our CADx system. Performance was evaluated using area under the curve (AUC) of receiver operating characteristic analysis. AUC was calculated 10 times, and its average was obtained. The best averaged AUC of SVM and XGBoost was 0.850 and 0.896, respectively; both were obtained using TPE. XGBoost was generally superior to SVM. Optimal parameters for achieving high AUC were obtained with fewer numbers of trials when using TPE, compared with random search. Bayesian optimization of SVM and XGBoost parameters was more efficient than random search. Based on observer study, AUC values of two board-certified radiologists were 0.898 and 0.822. The results show that diagnostic accuracy of our CADx system was comparable to that of radiologists with respect to classifying lung nodules.

We developed a computer-aided diagnosis (CADx) method for classification between benign nodule, primary lung cancer, and metastatic lung cancer and evaluated the following: (i) the usefulness of the deep convolutional neural network (DCNN) for CADx of the ternary classification, compared with a conventional method (hand-crafted imaging feature plus machine learning), (ii) the effectiveness of transfer learning, and (iii) the effect of image size as the DCNN input. Among 1240 patients of previously-built database, computed tomography images and clinical information of 1236 patients were included. For the conventional method, CADx was performed by using rotation-invariant uniform-pattern local binary pattern on three orthogonal planes with a support vector machine. For the DCNN method, CADx was evaluated using the VGG-16 convolutional neural network with and without transfer learning, and hyperparameter optimization of the DCNN method was performed by random search. The best averaged validation accuracies of CADx were 55.9%, 68.0%, and 62.4% for the conventional method, the DCNN method with transfer learning, and the DCNN method without transfer learning, respectively. For image size of 56, 112, and 224, the best averaged validation accuracy for the DCNN with transfer learning were 60.7%, 64.7%, and 68.0%, respectively. DCNN was better than the conventional method for CADx, and the accuracy of DCNN improved when using transfer learning. Also, we found that larger image sizes as inputs to DCNN improved the accuracy of lung nodule classification.

Woman-centered antenatal care necessitates Electronic Medical Record (EMR) systems that respect women’s preferences. However, women’s preferences regarding EMR systems in antenatal care remain unknown. This work aims to understand the EMR-related experiences that pregnant Japanese women want. First, we conducted a field-based observational study at an antenatal care clinic at a Japanese university hospital. We analyzed the data following a thematic analysis approach and found multiple EMR-related experiences that pregnant women encounter during antenatal care. Based on the observations’ findings, we administered a web survey to 413 recently pregnant Japanese women to understand their attitudes regarding the EMR-related experiences. Our results show that pregnant Japanese women want accessible, exchangeable, and biopsychosocial EMRs. They also want EMR-enabled explanations and summaries. Interestingly, differences in their demographics and stages of pregnancy affected their attitudes towards some EMR-related experiences. To respect their preferences, we propose amplifying the roles of EMR systems as tools that promote communication and woman-centeredness in antenatal care. We also propose expanding the EMR design mindset from a biomedical to a biopsychosocial-oriented one. Finally, to accommodate the differences in individual needs and preferences, we propose the design of adaptable person-centered EMR systems.