In bankruptcy prediction, the proportion of events is very low, which is often oversampled to eliminate this bias. In this paper, we study the influence of the event rate on discrimination abilities of bankruptcy pred...
详细信息
We investigated the benefits of integrating subjective measures (e.g. verbal responses) with biometrics (e.g. eye tracking) for analyses of situation awareness (SA) in complex, high-stakes tasks. Specifically, the tec...
详细信息
Background: Pruritus is the most common initial symptom reported by patients with dermatomyositis (DM) and polymyositis (PM). However, there is limited data regarding the impact of pruritus on cancer and mortality in ...
详细信息
Background: Pruritus is the most common initial symptom reported by patients with dermatomyositis (DM) and polymyositis (PM). However, there is limited data regarding the impact of pruritus on cancer and mortality in patients with DM and PM. In this study, we aimed to investigate how pruritus is associated with cancer and mortality in patients with DM and PM. Methods: This nationwide, population-based retrospective cohort study included adult DM and PM patients from Taiwan’s National Health Insurance Research database between 2005 and 2022. Sex- and age-matched pruritic patients, identified by over 6 weeks of antipruritic medication use, and nonpruritic patients were analyzed. The primary outcome was cancer occurrence or all-cause mortality. The association between pruritus and these outcomes was estimated using Cox proportional hazards models. Results: Among 919 matched pairs of pruritic and nonpruritic patients, cancer was observed in 19.96% in the long-term pruritic group (LPG), 14.63% in the short-term pruritic group (SPG), and 10.34% in the non-pruritic group (NPG) ( p < 0.0001). All-cause mortality was documented as 30.37% in the LPG, 29.69% in the SPG, and 37.76% in the NPG ( p < 0.0001). After adjusting for sex, age, and other comorbidities, pruritus was associated with an increased risk of cancer (hazard ratio (HR) 1.708, 95% confidence interval (CI) 1.229–2.374) and a lower risk of all-cause mortality (HR 0.483, 95% CI 0.409–0.569). Conclusion: This population-based study revealed that pruritus appeared to be associated with increased risks of cancer and decreased all-cause mortality. Thus, pruritus may serve as a pragmatic factor for risk stratification and tailored treatment strategies in DM and PM. Cancer screening, particularly for nasopharyngeal and breast cancers in East Asian populations, is recommended for patients with DM or PM, especially those presenting with pruritus. Meanwhile, patients without pruritus may require vigilant management for pote
Background: Cardiogenic shock is a leading cause of mortality in patients with acute myocardial infarction. Objectives: The authors sought to compare clinical characteristics, hospital trajectory, and drug and device ...
详细信息
Background: Cardiogenic shock is a leading cause of mortality in patients with acute myocardial infarction. Objectives: The authors sought to compare clinical characteristics, hospital trajectory, and drug and device use between patients with ST-segment elevation myocardial infarction-related cardiogenic shock (STEMI-CS) and those without (non-ST-segment elevation myocardial infarction complicated by cardiogenic shock [NSTEMI-CS]). Methods: We analyzed data from 1,110 adult admissions with cardiogenic shock complicating acute myocardial infarction (AMI-CS) across 17 centers within Cardiogenic Shock Working Group. The primary end point was in-hospital mortality. Results: Our study included 1,110 patients with AMI-CS, of which 731 (65.8%) had STEMI-CS and 379 (34.2%) had NSTEMI-CS. Most patients were male (STEMI-CS: 71.6%, NSTEMI-CS: 66.5%) and White (STEMI-CS: 53.8%, NSTEMI-CS: 64.1%). In-hospital mortality was 41% and was similar among patients with STEMI-CS and NSTEMI-CS (43% vs 39%, P = 0.23). Patients with out-of-hospital cardiac arrest had higher in-hospital mortality in patients with NSTEMI-CS (63% vs 36%, P = 0.006) as compared to patients with STEMI-CS (52% vs 41%, P = 0.16). Similar results were observed for in-hospital cardiac arrest in patients with STEMI-CS (63% vs 33%, P < 0.001) and NSTEMI-CS (60% vs 32%, P < 0.001). Only 27% of patients with STEMI-CS and 12% of NSTEMI-CS received both a drug and temporary mechanical circulatory support device during the first 24 hours, which increased to 78% and 61%, respectively, throughout the course of the hospitalization (P < 0.001 for both). Conclusions: Despite increasing use of inotropic and vasoactive support and mechanical circulatory support throughout the hospitalization, both patients with STEMI-CS and NSTEMI-CS remain at increased risk for in-hospital mortality. Randomized controls trials are needed to elucidate whether timing and sequence of escalation of support improves outcomes in patients with AMI-CS.
Background: Common data models solve many challenges of standardizing electronic health record (EHR) data, but are unable to semantically integrate all the resources needed for deep phenotyping. Open Biological and Bi...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We ...
详细信息
Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad
暂无评论