CDMO: Chaotic Dwarf Mongoose Optimization Algorithm for feature selection.

In this paper, a modified version of Dwarf Mongoose Optimization Algorithm (DMO) for feature selection is proposed. DMO is a novel technique of the swarm intelligence algorithms which mimic the foraging behavior of the Dwarf Mongoose. The developed method, named Chaotic DMO (CDMO), is considered a wrapper-based model which selects optimal features that give higher classification accuracy. To speed up the convergence and increase the effectiveness of DMO, ten chaotic maps were used to modify the key elements of Dwarf Mongoose movement during the optimization process. To evaluate the efficiency of the CDMO, ten different UCI datasets are used and compared against the original DMO and other well-known Meta-heuristic techniques, namely Ant Colony optimization (ACO), Whale optimization algorithm (WOA), Artificial rabbit optimization (ARO), Harris hawk optimization (HHO), Equilibrium optimizer (EO), Ring theory based harmony search (RTHS), Random switching serial gray-whale optimizer (RSGW), Salp swarm algorithm based on particle swarm optimization (SSAPSO), Binary genetic algorithm (BGA), Adaptive switching gray-whale optimizer (ASGW) and Particle Swarm optimization (PSO). The experimental results show that the CDMO gives higher performance than the other methods used in feature selection. High value of accuracy (91.9-100%), sensitivity (77.6-100%), precision (91.8-96.08%), specificity (91.6-100%) and F-Score (90-100%) for all ten UCI datasets are obtained. In addition, the proposed method is further assessed against CEC'2022 benchmarks functions.

Postacute COVID-19 Syndrome: 129Xe MRI Ventilation Defects and Respiratory Outcomes 1 Year Later.

Background In individuals with postacute COVID-19 syndrome (PACS) and normal pulmonary function, xenon 129 (129Xe) MRI ventilation defects, abnormal quality-of-life scores, and exercise limitation were reported 3 months after infection; the longitudinal trajectory remains unclear. Purpose To measure and compare pulmonary function, exercise capacity, quality of life, and 129Xe MRI ventilation defect percent (VDP) in individuals with PACS evaluated 3 and 15 months after COVID-19 infection. Materials and Methods In this prospective study, participants with PACS aged 18-80 years were enrolled between July 2020 and August 2021 from two quaternary care centers. 129Xe MRI VDP, diffusing capacity of lung for carbon monoxide (Dlco), spirometry, oscillometry, 6-minute walk distance (6MWD), and St George Respiratory Questionnaire (SGRQ) scores were evaluated 3 months and 15 months after COVID-19 infection. Differences between time points were evaluated using the paired t test. Multivariable models were generated to explain exercise capacity and quality-of-life improvement. Odds ratios (ORs) were used to evaluate potential treatment influences. Results Overall, 53 participants (mean age, 55 years ± 18 [SD]; 27 women) attended both 3- and 15-month visits and were included in the analysis. The mean values for 129Xe MRI VDP (5.8% and 4.2%; P = .003), forced expiratory volume in the 1st second of expiration percent predicted (84% and 90%; P = .001), Dlco percent predicted (86% and 99%; P = .002), and SGRQ score (35 and 25; P < .001) improved between the 3- and 15-month visit. VDP measured 3 months after COVID-19 infection predicted the change in 6MWD (ß = -0.643, P = .006), while treatment with respiratory medication at 3 months predicted an improved quality-of-life score at 15 months (OR, 4.0; 95% CI: 1.2, 13.8; P = .03). Conclusion Pulmonary function, gas exchange, exercise capacity, quality of life, and 129Xe MRI ventilation defect percent (VDP) improved in participants with postacute COVID-19 syndrome at 15 months compared with 3 months after infection. VDP measured at 3 months after infection correlated with improved exercise capacity, while treatment with respiratory medication was associated with an improved quality-of-life score 15 months after infection. ClinicalTrials.gov registration no. NCT05014516 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Vogel-Claussen in this issue.

A Predictive Model for Postembolization Syndrome after Transarterial Hepatic Chemoembolization of Hepatocellular Carcinoma.

Purpose To develop and validate a predictive model for postembolization syndrome (PES) following transarterial hepatic chemoembolization (TACE) for hepatocellular carcinoma. Materials and Methods In this single-center, retrospective study, 370 patients underwent 513 TACE procedures between October 2014 and September 2016. Seventy percent of the patients were randomly assigned to a training data set and the remaining 30% were assigned to a testing data set. Variables included demographic, laboratory, clinical, and procedural details. PES was defined as pain and/or nausea beyond 6 hours after TACE that required intravenous medication for symptom control. The predictive model was developed by using conditional inference trees and Lasso regression. Results Demographics, laboratory data, performance, tumor characteristics, and procedural details were statistically similar for the training and testing data sets. Overall, 83 of 370 patients (22.4%) after 107 of 513 TACE procedures (20.8%) met the predefined criteria. Factors identified at univariable analysis included large tumor burden (P = .004), drug-eluting embolic TACE (P = .03), doxorubicin dose (P = .003), history of PES (P < .001) and chronic pain (P < .001), of which history of PES, tumor burden, and drug-eluting embolic TACE were identified as the strongest predictors by the multivariable analysis and were used to develop the predictive model. When applied to the testing data set, the model demonstrated an area under the curve of 0.62, sensitivity of 79% (22 of 28), specificity of 44.2% (53 of 120), and a negative predictive value of 90% (53 of 59). Conclusion The model identified history of postembolization syndrome, tumor burden, and drug-eluting embolic chemoembolization as predictors of protracted recovery because of postembolization syndrome. © RSNA, 2018.

Yttrium-90 Radioembolization for Unresectable Combined Hepatocellular-Cholangiocarcinoma.

PURPOSE: Combined hepatocellular-cholangiocarcinoma (cHCC-CC) is a rare mixed cell type primary liver cancer with limited data to guide management. Transarterial radioembolization with yttrium-90 microspheres (RE) is an emerging treatment option for both hepatocellular carcinoma and intrahepatic cholangiocarcinoma. This study explored the safety and efficacy of RE for unresectable cHCC-CC. METHODS: Patients with histopathologically confirmed cHCC-CC treated with RE were retrospectively evaluated. Clinical and biochemical toxicities were assessed using the Common Toxicity Criteria for Adverse Events v4.03. Radiological response was analyzed using the Response Criteria in Solid Tumors (RECIST) v1.1 and modified RECIST criteria. Survival times were calculated and prognostic variables identified. RESULTS: Ten patients (median age 59 years; six men, four women) with unresectable cHCC-CC underwent 14 RE treatments with resin (n = 6 patients) or glass (n = 4 patients) microspheres. Clinical toxicities were limited to grade 1-2 fatigue, anorexia, nausea, or abdominal pain. No significant biochemical toxicities were observed. Median overall survivals from the first RE treatment and from initial diagnosis were 10.2 and 17.7 months, respectively. Six of seven patients with elevated tumor biomarker levels before RE showed decreased levels after treatment (median decrease of 72%, range 13-80%). Best hepatic radiological response was 60% partial response and 40% stable disease by modified RECIST, and 100% stable disease by RECIST v1.1. Poor performance status and the presence of macrovascular invasion were identified as predictors of reduced survival after RE. CONCLUSION: RE appears to be a safe and promising treatment option for patients with unresectable cHCC-CC. LEVEL OF EVIDENCE: Level 4.

Assessing the Risk of Hemorrhagic Complication following Transjugular Liver Biopsy in Bone Marrow Transplantation Recipients.

PURPOSE: To determine if recipients of bone marrow transplants (BMTs) are at increased risk of hemorrhagic complications following transjugular liver biopsy (TJLB). MATERIALS AND METHODS: TJLBs in BMT and non-BMT patients between January 2007 and July 2014 were reviewed. Patient demographic and pre- and postprocedural laboratory data were reviewed. Mean platelet count and International Normalized Ratio were 174,300 × 10(3)/µL ± 107.3 (standard deviation) and 1.2 ± 0.4, respectively, for BMT recipients, compared with 88,100 × 10(3)/µL ± 70.9 and 1.2 ± 0.5, respectively, for non-BMT. Patients in whom hemoglobin level decreased by > 1 g/dL and/or required transfusion within 15 days of TJLB were reviewed to determine the presence of a biopsy-related hemorrhagic complication. RESULTS: A total of 1,600 TJLBs in 1,120 patients were analyzed. Of these, 183 TJLBs in 159 BMT recipients and 1,417 TJLBs in 961 patients non-BMT patients were performed. Thirteen TJLBs were complicated by hemorrhage: five in BMT (2.9%) and eight in the non-BMT cohorts (0.6%; P < .01). Preprocedural platelet counts were within normal range (57-268 × 10(3)/µL) in all but one patient (8 × 10(3)/µL). BMT recipients had an odds ratio of 4.9 (95% confidence interval, 1.25-17.3) for post-TJLB bleeding/hemorrhage compared with those without BMTs (P < .01). CONCLUSIONS: TJLB continues to be a safe procedure in the vast majority of patients. However, hemorrhagic complications occurred at a rate of 2.9% in BMT recipients, compared with 0.6% in patients without BMTs, and therefore caution should be exercised when performing TJLB in this group.