Citations

Abstract Older adults with dementia account over 15% of intensive care unit (ICU) admissions and face higher risks of functional decline and complications. We systematically evaluated the difference in ICU-related outcomes in patients with and without dementia, (e.g., mortality, resuscitation and code status decisions, complications, duration of life support and hospital stay). Searches were performed in MEDLINE, EMBASE, SCOPUS, and Web of Science between 2003 and 2024. A random-effects meta-analysis was done of odds ratios (OR) and mean differences (MD) and their corresponding 95% confidence intervals (CI) were calculated. Fifteen studies, including 1,231,037 patients (12% with dementia), met the inclusion criteria. Adjusted analysis showed that patients with dementia had a higher risk of ICU mortality (OR = 1.05, 95% CI 1.00–1.11), 30-day mortality (OR = 1.54, 95% CI 1.47–1.62) and 12-month mortality (OR = 1.95, 95% CI 1.88–2.02). They were less likely to receive mechanical ventilation (OR = 0.73, 95% CI 0.62–0.85, I2 0.0%) and more likely to develop delirium (OR = 4.80, 95% CI 1.81–12.72). In patients with dementia, ICU stays were slightly shorter (MD = –1 day, 95% CI –1.7 to –0.4), and discharge home was less common (OR = 0.40, 95% CI 0.39–0.42). Older adults with dementia experienced greater risk of mortality and delirium, alongside less aggressive intervention use and healthcare utilization (i.e., shorter ICU stays). These findings underscore the need for prospective studies to optimize ICU decision-making and post-discharge care for this vulnerable population.

Abstract Background. Quantitative radiomic features of medical images could provide clinical significance in assisting decision-making, but the existing feature selection and modeling methods are usually parameter-dependent. We aim to develop and validate a generalized radiomic method applicable to a variety of clinical outcomes. Methods and materials. A generalized methodology for radiomic feature selection and modeling (‘GRFM’ for short), including two-step feature selection and logistic regression, was proposed for studying clinical outcomes correlations. The two-step feature selection consists of Pearson correlation analysis followed by a sequential forward floating selection algorithm to identify robust feature subsets. We also applied an adaptive searching strategy to systematically determine globally optimal parameters, rather than relying on preset parameters. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of three outcomes: lymph node metastasis of gastric cancer (GC), the five-year survival status of high-grade osteosarcoma (HOS), and the pathological grade of pancreatic neuroendocrine tumors (pNETs). Results. The optimal Pearson thresholds were 0.85, 0.80 and 0.75, and the optimal feature numbers were 11, 14 and 8 in GC, HOS and pNETs, respectively. The AUC values of the three predictive models combined with the corresponding parameters were 0.9017 versus 0.9026, 0.7652 versus 0.7113, and 0.8438 versus 0.8212 for the training and validation cohorts, showing promissing generality and classifier performance . Conclusion. The proposed method was helpful in predicting different clinical outcomes, and has potential application as a general and noninvasive prediction tool to guide clinical decision-making in various cancer sites.