METHOD: This is a prospective, observational study. The preintervention Sodergren scores of subjects with internal haemorrhoidal disease were recorded and blinded to the surgeon in charge. Sodergren scores of subjects in the two arms were unblinded and compared at the end of the study.
RESULTS: The results for 290 patients were available for final analysis. The median scores of those offered surgery and those who underwent successful rubber band ligation differed significantly [4 (interquartile range 3-10) vs 0 (interquartile range 0-4), P = 0.001]. In predicting treatment, the Sodergren score had an area under the receiver operating characteristic curve of 0.735 (95% CI 0.675-0.795).
CONCLUSION: There is a significant difference in scores between patients who were offered surgery and patients with successful rubber band ligation. Our study suggests that the Sodergren score has an acceptable discrimination in predicting the need for surgery in internal haemorrhoidal disease. We propose that patients with a Sodergren score of 6 or more be considered for upfront surgery. This score could potentially be used to standardize outcomes of future haemorrhoid trials.
MATERIALS AND METHODS: Seven hundred fifty-four radiomics-based features were extracted from 1732 scans derived from the TICH-2 multicentre clinical trial. Features were harmonised and a correlation-based feature selection was applied. Different elastic-net parameterisations were tested to assess the predictive performance of the selected radiomics-based features using grid optimisation. For comparison, the same procedure was run using radiological signs and clinical factors separately. Models trained with radiomics-based features combined with radiological signs or clinical factors were tested. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) score.
RESULTS: The optimal radiomics-based model showed an AUC of 0.693 for haematoma expansion and an AUC of 0.783 for poor functional outcome. Models with radiological signs alone yielded substantial reductions in sensitivity. Combining radiomics-based features and radiological signs did not provide any improvement over radiomics-based features alone. Models with clinical factors had similar performance compared to using radiomics-based features, albeit with low sensitivity for haematoma expansion. Performance of radiomics-based features was boosted by incorporating clinical factors, with time from onset to scan and age being the most important contributors for haematoma expansion and poor functional outcome prediction, respectively.
CONCLUSION: Radiomics-based features perform better than radiological signs and similarly to clinical factors on the prediction of haematoma expansion and poor functional outcome. Moreover, combining radiomics-based features with clinical factors improves their performance.
KEY POINTS: • Linear models based on CT radiomics-based features perform better than radiological signs on the prediction of haematoma expansion and poor functional outcome in the context of intracerebral haemorrhage. • Linear models based on CT radiomics-based features perform similarly to clinical factors known to be good predictors. However, combining these clinical factors with radiomics-based features increases their predictive performance.
RESULTS: Pose prediction experiments indicate that chaos-embedded algorithms outperform AutoDock Vina and PSOVina in ligand pose RMSD, success rate, and run time. In virtual screening experiments, Singer map-embedded PSOVina[Formula: see text] achieved a very significant five- to sixfold speedup with comparable screening performances to AutoDock Vina in terms of area under the receiver operating characteristic curve and enrichment factor. Therefore, our results suggest that chaos-embedded PSOVina methods might be a better option than AutoDock Vina for docking and virtual screening tasks. The success of chaotic maps in protein-ligand docking reveals their potential for improving optimization algorithms in other search problems, such as protein structure prediction and folding. The Singer map-embedded PSOVina[Formula: see text] which is named PSOVina-2.0 and all testing datasets are publicly available on https://cbbio.cis.umac.mo/software/psovina .
SUBJECTS: Patients who were admitted to the University of Malaya Medical Centre due to cardiac events.
METHODS: Eight different machine learning models were evaluated. The models included 3 different sets of features: full features; significant features from multiple logistic regression; and features selected from recursive feature extraction technique. The performance of the prediction models with each set of features was compared.
RESULTS: The AdaBoost model with the top 20 features obtained the highest performance score of 92.4% (area under the curve; AUC) compared with other prediction models.
CONCLUSION: The findings showed the potential of using machine learning models to predict return to work after cardiac rehabilitation.
METHODS: From inception to July 24, 2021, relevant records were retrieved from PubMed, Embase, Scopus, Web of Science, and the Cochrane Library. The quality of studies was determined using the QUADAS-2 tool. The pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and hierarchical summary receiver operating characteristic (HSROC) curve for NAAT's diagnostic performance were evaluated using an HSROC model.
RESULTS: Eight studies comprising 424 samples evaluated NAAT accuracy for Staphylococcus aureus (SA) identification, while four studies comprising 317 samples evaluated methicillin-resistant Staphylococcus aureus (MRSA) identification. The pooled NAAT summary estimates for detection of both SA (sensitivity: 0.35 (95% CI 0.19-0.55), specificity: 0.95 (95% CI 0.92-0.97), PLR: 7.92 (95% CI 4.98-12.59), NLR: 0.44 (95% CI 0.14-1.46), and DOR: 24.0 (95% CI 6.59-87.61) ) and MRSA (sensitivity: 0.45 (95% CI 0.15-0.78), specificity: 0.93 (95% CI 0.89-0.95), PLR: 10.06 (95% CI 1.49-67.69), NLR: 0.69 (95% CI 0.41-1.15), and DOR: 27.18 (95% CI 2.97-248.6) ) were comparable. The I2 statistical scores for MRSA and SA identification sensitivity were 13.7% and 74.9%, respectively, indicating mild to substantial heterogeneity. PCR was frequently used among NAA tests, and its diagnostic accuracy coincided well with the overall summary estimates. A meta-regression and subgroup analysis of country, setting, study design, patient selection, and sample condition could not explain the heterogeneity (meta-regression P = 0.66, P = 0.46, P = 0.98, P = 0.68, and P = 0.79, respectively) in diagnostic effectiveness.
CONCLUSIONS: Our study suggested that the diagnostic accuracy of NAA tests is currently inadequate to substitute culture as a principal screening test. NAAT could be used in conjunction with microbiological culture due to the advantage of faster results and in situations where culture tests are not doable.
DESIGN: We prospectively recruited 496 patients with non-alcoholic fatty liver disease who underwent VCTE by both M and XL probes within 1 week before liver biopsy.
RESULTS: 391 (78.8%) and 433 (87.3%) patients had reliable liver stiffness measurement (LSM) (10 successful acquisitions and IQR:median ratio ≤0.30) by M and XL probes, respectively (p<0.001). The area under the receiver operating characteristic curves was similar between the two probes (0.75-0.88 for F2-4, 0.83-0.91 for F4). When used in the same patient, LSM by XL probe was lower than that by M probe (mean difference 2.3 kPa). In contrast, patients with BMI ≥30 kg/m2 had higher LSM regardless of the probe used. When M and XL probes were used in patients with BMI <30 and ≥30 kg/m2, respectively, they yielded nearly identical median LSM at each fibrosis stage and similar diagnostic performance. Severe steatosis did not increase LSM or the rate of false-positive diagnosis by XL probe.
CONCLUSION: High BMI but not severe steatosis increases LSM. The same LSM cut-offs can be used without further adjustment for steatosis when M and XL probes are used according to the appropriate BMI.
METHODS: This is a retrospective study involving 416 women who presented to a tertiary urogynecology unit with symptoms of pelvic floor dysfunction. Genital hiatus and Pb were measured at rest and on maximal Valsalva. The strength of association between binary markers of POP and measurements of Gh/Pb was estimated using logistic regression analysis. Receiver operator characteristic statistics were used to compare predictive values of Gh and Pb measurements obtained at rest and on Valsalva.
RESULTS: A total of 451 women were seen during the study period. Thirty-five were excluded owing to missing data, leaving 416. Fifty-four percent (n = 223) complained of POP symptoms. On examination, 80% (n = 332) had significant POP (stage 2+ in anterior or posterior compartments or stage 1+ in the central compartment). On imaging, significant POP was diagnosed in 66% (n = 275). Mean hiatal area was 22 cm (SD, 7; range, 5-49 cm) at rest and 30 cm (SD, 10; range, 11-69 cm) on Valsalva. Genital hiatus and Pb measured on Valsalva were consistently stronger predictors of prolapse symptoms and objective prolapse (by clinician examination and by ultrasound) than at Gh and Pb measured at rest. The corresponding area under the curve values were significantly larger for Gh/Pb measures on Valsalva after adjusting for multiple confounders.
CONCLUSIONS: Genital hiatus/Pb measured on maximal Valsalva is a superior predictor of symptoms and signs of POP compared with Gh/Pb at rest.