(70%) and testing (30%) sets we tested logistic regression, decision tree, random forest, linear discriminant analysis, support vector machine, naive Bayes, and neural networks (NN). The top model was then used to stratify endometrial cancer risk into low, medium, and high risk categories. Results: The NN outperformed the other methods with a test AUC of 0.88. Using the NN, we classified 57.2% of those who developed cancer within 5 years as high risk, 41.8% as medium risk, and 1.1% as low risk. For those who did not develop cancer within 5 years we classified 0.9%, 71.0%, and 28.2% as high, medium, and low risk, respectively. Conclusion: Our results indicate that the use of a NN based on personal health information can accurately discriminate between those at high risk of developing endometrial cancer and those who are not, offering a costeffective and non-invasive way to stratify endometrial cancer risk for targeted screening and prevention.
modeling, particularly for treatments with non-coplanar geometries or largely off-centered isocenters. Acquired surfaces and the CT generated body contours showed good agreement. Conclusion: Efficacy of efficient full-body surface acquisition for patientspecific collision modeling have been demonstrated. With personalized modeling, the safety of radiotherapy delivery could be ensured while achieving the full dosimetric benefit of non-coplanar beam geometries.
Meticulous monitoring for cardiovascular systems is important for postoperative patients in postanesthesia or the intensive care unit. The continuous auscultation of heart and lung sounds can provide a valuable information for patient safety. Although numerous research projects have proposed the design of continuous cardiopulmonary monitoring devices, they primarily focused on the auscultation of heart and lung sounds and mostly served as screening tools. However, there is a lack of devices that could continuously display and monitor the derived cardiopulmonary parameters. This study presents a novel approach to address this need by proposing a bedside monitoring system that utilizes a lightweight and wearable patch sensor for continuous cardiovascular system monitoring. The heart and lung sounds were collected using a chest stethoscope and microphones, and a developed adaptive noise cancellation algorithm was implemented to remove the background noise corrupted with those sounds. Additionally, a short-distance ECG signal was acquired using electrodes and a high precision analog front end. A high-speed processing microcontroller was used to allow real-time data acquisition, processing, and display. A dedicated tablet-based software was developed to display the acquired signal waveforms and the processed cardiovascular parameters. A significant contribution of this work is the seamless integration of continuous auscultation and ECG signal acquisition, thereby enabling the real-time monitoring of cardiovascular parameters. The wearability and lightweight design of the system were achieved through the use of rigid–flex PCBs, which ensured patient comfort and ease of use. The system provides a high-quality signal acquisition and real-time monitoring of the cardiovascular parameters, thus proving its potential as a health monitoring tool.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.