Among patients with Coronavirus disease (COVID-19), the ability to identify patients at risk for deterioration during their hospital stay is essential for effective patient allocation and management. To predict patient risk for critical COVID-19 based on status at admission using machine-learning models. Retrospective study based on a database of tertiary medical center with designated departments for patients with COVID-19. Patients with severe COVID-19 at admission, based on low oxygen saturation, low partial arterial oxygen pressure, were excluded. The primary outcome was risk for critical disease, defined as mechanical ventilation, multi-organ failure, admission to the ICU, and/or death. Three different machine-learning models were used to predict patient deterioration and compared to currently suggested predictors and to the APACHEII risk-prediction score. Among 6995 patients evaluated, 162 were hospitalized with non-severe COVID-19, of them, 25 (15.4%) patients deteriorated to critical COVID-19. Machine-learning models outperformed the all other parameters, including the APACHE II score (ROC AUC of 0.92 vs. 0.79, respectively), reaching 88.0% sensitivity, 92.7% specificity and 92.0% accuracy in predicting critical COVID-19. The most contributory variables to the models were APACHE II score, white blood cell count, time from symptoms to admission, oxygen saturation and blood lymphocytes count. Machine-learning models demonstrated high efficacy in predicting critical COVID-19 compared to the most efficacious tools available. Hence, artificial intelligence may be applied for accurate risk prediction of patients with COVID-19, to optimize patients triage and in-hospital allocation, better prioritization of medical resources and improved overall management of the COVID-19 pandemic.
In the present study, we examined how real-world objects are represented in long-term memory. Two contrasting views exist with regard to this question: one argues that real-world objects are represented as a set of independent features, and the other argues that they form bound integrate representations. In 5 experiments, we tested the different predictions of each view, namely whether the different features of real-world items are remembered and forgotten independently from each other, in a feature-based manner, or conversely are stored and lost in an object-based manner, with all features depending upon each other. Across various stimuli, learning tasks (incidental or explicit), experimental setups (within- or between-subjects design), feature-dimensions, and encoding times, we consistently found that information is forgotten in an object-based manner. When an object ceases to be fully remembered, all of its features are lost, instead of only some of the object’s features being lost whereas other features are still remembered. Furthermore, we found support for a strong form of dependency among the different features, namely a hierarchical structure. We conclude that visual long-term memory is object-based, challenging previous findings.
Molecular probes for cellular proto-oncogenes have recently been extensively used in order to search for functional and structural alterations in tumor tissues. Variable, and sometimes contradictory, results have been obtained regarding the frequency and clinical significance of amplification of the c-myc and c-erbB-2 proto-oncogenes in different series of human solid tumors. We addressed this question by performing Southern blotting analysis on 131 primary adult solid tumors of various tissues and 5 metastases of unknown origin, using molecular probes for both genes. Amplification of c-myc was found in 5 of the primary tumors, and amplification of c-erbB-2 in 5 others. In 2 tumors of the latter group, the c-erbB-2 gene was also rearranged. The distribution of these 10 tumors with regard to clinical stage and course of the disease did not point to an association between the amplification events and specific stage or prognosis. We concluded that, in this series, the amplification of both proto-oncogenes was occasional and was not a prognostic marker.
Background: The neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) have emerged as markers of various outcomes of inflammatory and malignant diseases. The association of those markers with short-term outcomes of acute diverticulitis has been discussed in recent studies. This study aimed at evaluation of the association of NLR and PLR with long-term outcomes in patients presenting with acute diverticulitis. Methods: A retrospective single institute study included patients admitted with acute diverticulitis between 2012 and 2016. Associations were analysed of NLR and PLR values at admission with patient outcomes. Results: A total of 456 patients were included in the study. High NLR and PLR values were associated with complicated disease (P < 0.01 for both). Among patients with complicated diverticulitis, for those with high NLR, the interval to a recurrent episode of acute diverticulitis was shorter (68.3 days versus 83.7 days, P = 0.044). Patients with high NLR had higher mean number of readmissions (0.54 versus 0.34, P = 0.035). High NLR (10.06 AE 11.23 versus 7.6 AE 8.04, P = 0.012) and PLR (9.64 days AE10.56 versus 7.47 days AE8.225, P = 0.018) were associated with longer cumulative hospital stay due to acute diverticulitis. Conclusions: High NLR and PLR values were associated with recurrence in acute diverticulitis in terms of shorter interval between recurrent episodes and longer cumulative hospitalization days.
Background Neck ultrasound (US) and Technetium‐99 m Sestamibi (MIBI) scan are the most commonly used imaging studies for preoperative localization of parathyroid adenomas. The aim of this study was to determine the added value of MIBI scan and its effect on the operative plan via a hypothetical model where a stepwise approach is conducted and MIBI is considered only after the ultrasound is evaluated. Methods Patients who underwent parathyroidectomy for primary hyperparathyroidism (PHPT) between 2012 and 2019 at two tertiary centers were included. Data collected included demographic data, preoperative workup, operative findings and follow‐up. The added value of MIBI scans was determined for patients with positive ultrasound. Results A total of 513 patients with positive US result and a MIBI scan were included. If a stepwise approach was conducted then MIBI scan would not change the operative plan in 492 (95.9%). Among the remaining 21 patients, MIBI scan would correctly change the ultrasound‐based operative plan in only 12 (2.3%) patients, while incorrectly change the plan in 9 (1.8%), resulting in unnecessary exploration of the contralateral side. In patients with sonographic appearance of a parathyroid gland larger than 1.2 cm, MIBI scan would correctly change the operative plan in only 1 of the 287 (0.35%) patients. Conclusions Our study suggests that the routine use of MIBI scans may have limited added value in patients with PHPT and a positive neck ultrasound, especially in those with adenoma size larger than 1.2 cm. Positive ultrasound alone may be sufficient for the preoperative localization of parathyroid disease.
One of the most common ileostomy-related complications is high output stoma (HOS) which causes significant fluids and electrolytes disturbances. We aimed to analyze the incidence, severity, and risk factors for readmission for HOS. Methods: We reviewed all patients who underwent loop ileostomy closure in a single institution between 2010 and 2020. Patients that were readmitted for dehydration due to HOS during the time interval between the creation and the closure of the stoma were identified and divided into a study (HOS) group. The remaining patients constructed the control group. Results: A total of 307 patients were included in this study, out of which, 41 patients were readmitted 73 times (23.7% readmission rate) for the HOS group, and the remaining 266 patients constructed the control group. Multivariate analysis identified; advanced American Society of Anesthesiologists (ASA) physical status (PS) classification, elevated baseline creatinine, and open surgery as risk factors for HOS. Renal function worsened among the entire cohort between the construction of the stoma to its closure (mean creatinine of 0.82 vs. 0.96, P < 0.0001). Conclusion: Loop ileostomy formation is associated with a substantial readmission rate for dehydration as a result of HOS, and increasing the risk for renal impairment during the duration of the diversion. We identified advanced ASA PS classification, open surgery, and elevated baseline creatinine as predictors for HOS.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.