Decision-analysis modeling indicates the potential cost-effectiveness of [18F]2-fluoro-2-deoxy-D-glucose (FDG)-PET in the management of SPN. Furthermore, the decision trees developed can be used to model various features of the management of SPN, including modeling the cost-effectiveness of other newly emerging technologies.

ObjectiveTo determine whether the use of [18F]2-fluoro-2-deoxyglucose positron emission tomography (FDG PET) in addition to computed axial tomography (CT) is helpful in managing recurrent colorectal cancer (CRC). Summary Background DataThere is no consensus on a management algorithm for CRC. However, when recurrence is suspected, CT is generally used for further evaluation and staging of disease. MethodsThe authors used decision trees based on theoretical models to assess the cost-effectiveness of a CT ϩ FDG PET strategy for the diagnosis and management of recurrent CRC compared with a CT-alone strategy. These theoretical models focus on patients with hepatic recurrence who are potentially curable through surgical hepatic resection. The population entering the decision trees consisted of patients with CRC who had undergone surgical resection of their primary CRC and who were suspected of having recurrence based on elevated levels of carcinoembryonic antigen. ResultsThe CT ϩ FDG PET strategy was found to be cost-effective for managing patients with elevated carcinoembryonic antigen levels who were candidates for hepatic resection. The CT ϩ FDG PET strategy was higher in mean cost by $429 per patient but resulted in an increase in the mean life expectancy of 9.527 days per patient. ConclusionsThese results show, through rigorous decision tree analysis, the potential cost-effectiveness of FDG PET in the management of recurrent CRC. The decision trees can be used to model various features of the management of recurrent CRC, including the cost-effectiveness of other newly emerging technologies.In the United States, the number of new cases of colorectal cancer (CRC) was estimated at 129,400 in 1999.

No abstract

No abstract

Ultrasonic vocalizations (USVs) are known to reflect emotional processing, brain neurochemistry, and brain function. Collecting and processing USV data is manual, time-intensive, and costly, creating a significant bottleneck by limiting researchers’ ability to employ fully effective and nuanced experimental designs and serving as a barrier to entry for other researchers. In this report, we provide a snapshot of the current development and testing of Acoustilytix™, a web-based automated USV scoring tool. Acoustilytix implements machine learning methodology in the USV detection and classification process and is recording-environment-agnostic. We summarize the user features identified as desirable by USV researchers and how these were implemented. These include the ability to easily upload USV files, output a list of detected USVs with associated parameters in csv format, and the ability to manually verify or modify an automatically detected call. With no user intervention or tuning, Acoustilytix achieves 93% sensitivity (a measure of how accurately Acoustilytix detects true calls) and 73% precision (a measure of how accurately Acoustilytix avoids false positives) in call detection across four unique recording environments and was superior to the popular DeepSqueak algorithm (sensitivity = 88%; precision = 41%). Future work will include integration and implementation of machine-learning-based call type classification prediction that will recommend a call type to the user for each detected call. Call classification accuracy is currently in the 71–79% accuracy range, which will continue to improve as more USV files are scored by expert scorers, providing more training data for the classification model. We also describe a recently developed feature of Acoustilytix that offers a fast and effective way to train hand-scorers using automated learning principles without the need for an expert hand-scorer to be present and is built upon a foundation of learning science. The key is that trainees are given practice classifying hundreds of calls with immediate corrective feedback based on an expert’s USV classification. We showed that this approach is highly effective with inter-rater reliability (i.e., kappa statistics) between trainees and the expert ranging from 0.30–0.75 (average = 0.55) after only 1000–2000 calls of training. We conclude with a brief discussion of future improvements to the Acoustilytix platform.