Search

Abstract While ventricular shunts are the main treatment for adult hydrocephalus, shunt malfunction remains a common problem that can be challenging to diagnose. Computer vision-derived algorithms present a potential solution. We designed a feasibility study to see if such an algorithm could automatically predict ventriculomegaly indicative of shunt failure in a real-life adult hydrocephalus population. We retrospectively identified a consecutive series of adult shunted hydrocephalus patients over an eight-year period. Associated computed tomography scans were extracted and each scan was reviewed by two investigators. A machine learning algorithm was trained to identify the lateral and third ventricles, and then applied to test scans. Results were compared to human performance using Sørensen–Dice coefficients, calculated total ventricular volumes, and ventriculomegaly as documented in the electronic medical record. 5610 axial images from 191 patients were included for final analysis, with 52 segments (13.6% of total data) reserved for testing. Algorithmic performance on the test group averaged a Dice score of 0.809 ± 0.094. Calculated total ventricular volumes did not differ significantly between computer-derived volumes and volumes marked by either the first reviewer or second reviewer (p > 0.05). Algorithm detection of ventriculomegaly was correct in all test cases and this correlated with correct prediction of need for shunt revision in 92.3% of test cases. Though development challenges remain, it is feasible to create automated algorithms that detect ventriculomegaly in adult hydrocephalus shunt malfunction with high reliability and accuracy.

Abstract The emergence of generative AI technologies has led to an increasing number of people collaborating with AI to produce creative works. Across two experimental studies, in which we carefully designed and programmed state-of-the-art human–AI interfaces, we examine how the design of generative AI systems influences human creativity (poetry writing). First, we find that people were most creative when writing a poem on their own, compared to first receiving a poem generated by an AI system and using sophisticated tools to edit it (Study 1). Following this, we demonstrate that this creativity deficit dissipates when people co-create with—not edit—AI and establish creative self-efficacy as an important mechanism in this process (Study 2). Thus, our findings indicate that people must occupy the role of a co-creator, not an editor, to reap the benefits of generative AI in the production of creative works.

Abstract The use of chatbots is becoming widespread as they offer significant economic opportunities. At the same time, however, customers seem to prefer interacting with human operators when making inquiries and as a result are not as cooperative with chatbots when their use is known. This specific situation creates an incentive for organizations to use chatbots without disclosing this to customers. Will this deceptive practice harm the reputation of the organization, and the employees who work for them? Across four experimental studies, we demonstrate that prospective customers, who interact with an organization using chatbots, perceive the organization to be less ethical if the organization does not disclose the information about the chatbot to their customers (Study 1). Moreover, employees that work for an organization which requires them to facilitate the deceptive use of a chatbot exhibit greater turnover intentions (Study 2) and receive worse job opportunities from recruiters in both a hypothetical experimental setting (Study 3) and from professional job recruiters in the field (Study 4). These results highlight that using chatbots deceptively has far reaching negative effects, which begin with the organization and ultimately impact their customers and the employees that work for them.

Abstract Problem gambling levels amongst elite sportspeople are above populational baseline. We assess gambling in an elite Irish sporting population. An anonymous web-based questionnaire including the validated Problem Gambling Severity Index was distributed. Univariate and multivariate analyses were performed to evaluate predictors of moderate/high risk gambling. 608 players (mean age 24) were included. Seventy nine percent of respondents were current gamblers and 6% problem gamblers. Amongst high-risk gamblers, significantly more were male (100% vs 76%, p = 0.003), fewer completed university (52% vs 69%, p = 0.024), and more were smokers (48% vs 24%, p = 0.002). They were also more likely to avail of free online gambling offers (90% vs 44%, p

Abstract A subset of primary central nervous system lymphomas (PCNSL) are difficult to distinguish from glioblastoma multiforme (GBM) on magnetic resonance imaging (MRI). We developed a convolutional neural network (CNN) to distinguish these tumors on contrast-enhanced T1-weighted images. Preoperative brain tumor MRIs were retrospectively collected among 320 patients with either GBM (n = 160) and PCNSL (n = 160) from two academic institutions. The individual images from these MRIs consisted of a training set (n = 1894 GBM and 1245 PCNSL), a validation set (n = 339 GBM; 202 PCNSL), and a testing set (99 GBM and 108 PCNSL). Three CNNs using the EfficientNetB4 architecture were evaluated. To increase the size of the training set and minimize overfitting, random flips and changes to color were performed on the training set. Our transfer learning approach (with image augmentation and 292 epochs) yielded an AUC of 0.94 (95% CI: 0.91–0.97) for GBM and an AUC of 0.95 (95% CI: 0.92–0.98) for PCNL. In the second case (not augmented and 137 epochs), the images were augmented prior to training. The area under the curve for GBM was 0.92 (95% CI: 0.88–0.96) for GBM and an AUC of 0.94 (95% CI: 0.91–0.97) for PCNSL. For the last case (augmented, Gaussian noise and 238 epochs) the AUC for GBM was 0.93 (95% CI: 0.89–0.96) and an AUC 0.93 (95% CI = 0.89–0.96) for PCNSL. Even with a relatively small dataset, our transfer learning approach demonstrated CNNs may provide accurate diagnostic information to assist radiologists in distinguishing PCNSL and GBM.