Background: The current study aims to predict the recurrence of cervical cancer patients treated with radiotherapy from radiomics features on pretreatment T1- and T2-weighted MR images. Methods: A total of 89 patients were split into model training (63 patients) and model testing (26 patients). The predictors of recurrence were selected using the least absolute shrinkage and selection operator (LASSO) regression. The machine learning used neural network classifiers. Results: Using LASSO analysis of radiomics, we found 25 features from the T1-weighted and 4 features from T2-weighted MR images, respectively. The accuracy was highest with the combination of T1- and T2-weighted MR images. The model performances with T1- or T2-weighted MR images were 86.4% or 89.4% accuracy, 74.9% or 38.1% sensitivity, 81.8% or 72.2% specificity, and 0.89 or 0.69 of the area under the curve (AUC). The model performance with the combination of T1- and T2-weighted MR images was 93.1% accuracy, 81.6% sensitivity, 88.7% specificity, and 0.94 of AUC. Conclusions: The radiomics analysis with T1- and T2-weighted MR images could highly predict the recurrence of cervix cancer after radiotherapy. The variation of the distribution and the difference in the pixel number at the peripheral and the center were important predictors.
Background: Now that the spread of COVID-19 has been controlled, it is important to investigate changes in young people’s perceptions of the vaccine and their behavior toward infection. The objectives of this study were as follows: (1) to investigate the association between Omicron strain vaccination rates among college students, their perceptions of the vaccine, and past adverse reactions to the vaccine; (2) to compare 2021 (when COVID-19 was spreading) and 2023 (when COVID-19 was strained) to identify changes in attitudes toward vaccination and motivations for vaccination and changes in infection prevention behavior. Methods: This cross-sectional survey was conducted via e-mail from 5 January to 30 January 2023. All students at Hiroshima University were sent an e-mail, which provided them access to the survey form and requested their cooperation. The questionnaire consisted of 33 items related to attributes, vaccination status, adverse reactions after vaccination, motivation for vaccination, perception of the vaccine, presence of coronavirus infection, sequelae, and infection prevention measures. Results: A total of 1083 students responded to the survey. Over 50% of the students were vaccinated with the Omicron booster. Regarding trust in vaccines, the majority of both male and female respondents said they had some trust in vaccines, although this was less than that observed in the 2021 survey. As for infection control measures, only 2% of males and 0.3% of females answered that they did not take any infection control measures. The most common response was “wear a mask”, as in the 2021 survey, with 476 men (96.6%) and 575 women (99.5%). Conclusions: The survey showed a high Omicron-responsive vaccination rate of more than 50%. In addition, more than 99% of the students were found to be taking measures to prevent infection, such as wearing masks.
Background/Introduction: When a natural or man-made disaster occurs, emergency medical teams (EMTs) are dispatched to provide medical surge capacity for injured and sick individuals. Accurate predictions of EMTs consultations during disasters can improve dispatch and withdrawal decisions. However, no published studies have yet demonstrated a method for predicting the number of consultations or patients based on EMT activity data. Objectives: This research explores an innovative yet simple and reliable method to predict the number of consultations needed by EMTs during disasters, aiming to enhance the effectiveness and efficiency of medical response. Method/Description: Data were collected using Japan-Surveillance in Post-Extreme Emergencies and Disasters (J-SPEED) and Minimum Data Set (MDS) for five disasters in Japan and one in Mozambique. For each disaster, the number of consultations was predicted from the K value and constant attenuation model, originally developed for predicting COVID-19 patient numbers. Results/Outcomes: The total number of EMT consultations per disaster ranged from 684 to 18,468. The predicted curve and actual K data were similar for each of the disasters (R2 from 0.953 to 0.997), but offset adjustments were needed for the Kumamoto earthquake and the Mozambique cyclone because their R2 values were below 0.985. For the six disasters, the difference between the number of consultations predicted from K values and the measured cumulative number of consultations ranged from ±1.0% to ±4.1%. Conclusion: The K value and constant attenuation model reliably predicted EMT consultations during six different disasters. This simple model may be useful for the coordination of future responses of EMTs during disasters.