Greater Net Benefit Research Articles

Utility of PSA free-to-total ratio for clinically significant prostate cancer in men with a PSA level of

To investigate the relationship between the prostate-specific antigen (PSA) free-to-total ratio (FTR) and International Society of Urological Pathology Grade Group ≥2, clinically significant prostate cancer (csPCa) in men with a low PSA level (≤4 ng/mL). Patients and Methods Data were obtained from the Prostate Cancer Prevention Trial. Patients with a PSA level of ≤4 ng/mL and who received a biopsy within a year of this PSA measurement were included. Associations between FTR and csPCa were investigated with logistic regression, adjusting for age and PSA, a re-scaled Brier score (index of predictive accuracy), and decision curve analysis. A total of 406 patients were analysed with 139 (34%) having csPCa and 204 (50%) having any grade PCa. For those with an FTR ≤0.15, 46% had csPCa, vs 22% for those with a ratio ≥0.20. In a regression model, the predicted probability of csPCa for a 60-year-old with a PSA of 3 ng/mL was 61% if the FTR was 0.05, falling to 18% if the FTR was 0.30. A clear negative relationship between increasing FTR and probability of csPCa was observed. A model containing FTR additional to PSA and age provides greater net benefit as per decision curve analysis and likely superior discrimination and calibration measured by a higher index of predictive accuracy. In middle-aged men with a PSA level between 1.5 and 4 ng/mL but otherwise indicated for biopsy, a low FTR is associated with higher rates of csPCa. It should be utilised as an additional, readily available and inexpensive test to improve prediction of csPCa and aid in patient counselling.

Comparison of multiple machine learning models for predicting prognosis of pancreatic ductal adenocarcinoma based on contrast-enhanced CT radiomics and clinical features.

The aim of this study was to evaluate the prognostic potential of combining clinical features and radiomics with multiple machine learning (ML) algorithms in pancreatic ductal adenocarcinoma (PDAC). A total of 116 patients with PDAC who met the eligibility criteria were randomly assigned to a training or validation cohort. Seven ML algorithms, including Supervised Principal Components, stepwise Cox, Random Survival Forest, CoxBoost, Least absolute shrinkage and selection operation (Lasso), Ridge, and Elastic network, were integrated into 43 algorithm combinations. Forty-three radiomics models were constructed separately using radiomics features extracted from arterial phase (AP), venous phase (VP), and combined arterial and venous phase (AP+VP) images. The concordance index (C-index) of each model was calculated. The model with the highest mean C-index was identified as the best model for calculating the radiomics score (Radscore). Univariate and multivariate Cox analyses were used to identify independent prognostic indicators and create a clinical model for prognosis prediction. The multivariable Cox regression was used to combine Radscore with clinical features to create a combined model. The efficacy of the model was evaluated using the C-index, calibration curves, and decision curve analysis (DCA). The model based on the Lasso+StepCox[both] algorithm constructed using AP+VP radiomics features showed the best predictive ability among the 114 radiomics models. The C-indices of the model in the training and validation cohorts were 0.742 and 0.722, respectively. Based on the results of the univariate and multivariate Cox regression analyses, sex, Tumor-Node-Metastasis (TNM) stage, and systemic inflammation response index were included to build the clinical model. The combined model, incorporating three clinical factors and AP+VP-Radscore, achieved the highest C-indices of 0.764 and 0.746 in the training and validation cohorts, respectively. In terms of preoperative prognosis prediction for PDAC, the calibration curve and DCA showed that the combined model had a good consistency and greatest net benefit. A combined model of clinical features and AP+VP-Radscore screened using multiple ML algorithms has an excellent ability to predict the prognosis of PDAC and may provide a noninvasive and effective method for clinical decision-making.

Beyond Glasgow Coma Scale: Prehospital prediction of traumatic brain injury

IntroductionEarly identification of traumatic brain injury followed by timely, targeted treatment is essential. We aimed to establish the ability of prehospital Glasgow Coma Scale score alone and combined with vital signs to predict hospital-diagnosed traumatic brain injury. MethodsThis study included adults from the 2017–2020 Trauma Quality Improvement Program data set with blunt mechanism. We calculated test characteristics of prehospital Glasgow Coma Scale score ≤12 alone and Glasgow Coma Scale score combined with heart rate and systolic blood pressure for predicting (1) any traumatic brain injury and (2) moderate to severe traumatic brain injury. Diagnostic performances were calculated in all patients and older adults (≥55 years). We used decision curve analysis to determine the net diagnostic benefit of prehospital Glasgow Coma Scale score combined with heart rate + systolic blood pressure over Glasgow Coma Scale score alone. ResultsOf 1,687,336 patients, 39.1% had any traumatic brain injury, 3.7% had moderate to severe traumatic brain injury, and 9.1% had a prehospital Glasgow Coma Scale score ≤12. Prehospital Glasgow Coma Scale score ≤12 alone had a sensitivity 83.1%, specificity 93.7%, negative predictive value 99.3%, and positive predictive value 33.7% for predicting moderate to severe traumatic brain injury. Adding prehospital heart rate <65/min and systolic blood pressure >150 mm Hg to Glasgow Coma Scale score ≤12 improved the positive predictive value for moderate to severe traumatic brain injury (55.3%), with a preserved negative predictive value of 96.4%. Decision curve analysis showed the traumatic brain injury prediction model including prehospital heart rate and systolic blood pressure had the greatest net benefit across most threshold probabilities. ConclusionLess than a third of adult blunt trauma patients with a prehospital Glasgow Coma Scale score ≤12 have moderate to severe traumatic brain injury. Supplementing Glasgow Coma Scale score with prehospital vital signs improves diagnostic accuracy, potentially by filtering out patients with altered consciousness due to shock. Future work should better identify patients for traumatic brain injury–specific treatments in prehospital settings, including triage destination.

The LTAR Grazing Land Common Experiment at Walnut Gulch Experimental Watershed.

The Walnut Gulch Experimental Watershed (WGEW) Long-Term Agroecosystem Research (LTAR) network common experiment addresses the aspirational practice of brush management (BM) to reverse the prevailing condition of woody plant encroachment (WPE) and increase perennial native grass production. Across the western United States, the decision to implement BM includes consideration of management objectives, cost, and the expected impact on a diverse suite of ecosystem services. Maintaining or restoring grass cover will help meet the LTAR sustainable production, economic, and social goals, and averting degradation will meet environmental goals. This common experiment, focused on hydrologic and erosion impacts of BM, aims to inform land management decisions on three major plant communities in the Southwestern United States: creosote bush (Larrea tridentata), mesquite (Prosopis velutina), and pinyon-juniper (PJ, Pinus and Juniperus spp.). On the WGEW, applying tebuthiuron pellets to creosote bush increased grass cover and reduced runoff and erosion. The 2016BM experiment on the Santa Rita Experimental Range applied a commonly used liquid herbicide cocktail but achieved only 7% mortality on mesquite, probably because of the timing of the aerial application. Experiments manipulating rainfall amount and intensity on plots receiving fire, chemical, or mechanical BM treatments on PJ communities aim to improve process representation in simulation models. The deliverables of these BM experiments will be to (i) improve the performance of runoff and erosion models, (ii) enhance our ability to identify areas most at risk from reduced hydrologic function and soil erosion after shrub proliferation, and (iii) better predict how landscapes will respond to BM interventions. Ranchers, land management agencies, and watershed conservation organizations will benefit from training and availability of improved tools to focus treatments on areas where greatest net benefits might be realized.

Incorporating Individual-Level Treatment Effects and Outcome Preferences Into Personalized Blood Pressure Target Recommendations.

There are no shared decision-making frameworks for selecting blood pressure (BP) targets for individuals with hypertension. This study addressed whether results from the SPRINT (Systolic Blood Pressure Intervention Trial) could be tailored to individuals using predicted risks and simulated preferences. Among 8202 SPRINT participants, Cox models were developed and internally validated to predict each individual's absolute difference in risk from intensive versus standard BP lowering for cardiovascular events, cognitive impairment, death, and serious adverse events (AEs). Individual treatment effects were combined using simulated preference weights into a net benefit, which represents a weighted sum of risk differences across outcomes. Net benefits were compared among those above versus below the median AE risk. In simulations for which cardiovascular, cognitive, and death events had much greater weight than the AEs of BP lowering, the median net benefit was 3.3 percentage points (interquartile range [IQR], 2.0-5.7), and 100% of participants had a net benefit favoring intensive BP lowering. When simulating benefits and harms to have similar weights, the median net benefit was 0.8 percentage points (IQR, 0.2-2.2), and 87% had a positive net benefit. Compared with participants at lower risk of AEs from BP lowering, those at higher risk had a greater net benefit from intensive BP lowering despite experiencing more AEs (P<0.001 in both simulations). Most SPRINT participants had a predicted net benefit that favored intensive BP lowering, but the degree of net benefit varied considerably. Tailoring BP targets using each patient's risks and preferences may provide more refined BP target recommendations.

Ensemble Algorithm for Risk Prediction of Clinical Failure After Anterior Cruciate Ligament Reconstruction.

Patient-specific risk profiles of clinical failure after anterior cruciate ligament reconstruction (ACLR) are meaningful for preoperative surgical planning and postoperative rehabilitation guidance. To create an ensemble algorithm machine learning (ML) model and ML-based web-based tool that can predict the patient-specific risk of clinical failure after ACLR. Cohort study; Level of evidence, 3. Included were 432 patients (mean age, 26.8 ± 8.4 years; 74.1% male) who underwent anatomic double-bundle ACLR with hamstring tendon autograft between January 2010 and February 2019. The primary outcome was the probability of clinical failure at a minimum 2-year follow-up. The authors included 24 independent variables for feature selection and model development. The data set was split randomly into training sets (75%) and test sets (25%). Models were built using 4 ML algorithms: extreme gradient boosting, random forest, light gradient boosting machine, and adaptive boosting. In addition, a weighted-average voting (WAV) ensemble model was constructed using the ensemble-voting technique to predict clinical failure after ACLR. Concordance (area under the receiver operating characteristic curve [AUC]), calibration, and decision curve analysis were used to evaluate predictive performances of the 5 models. Clinical failure occurred in 73 of the 432 patients (16.9%). The 8 most important predictors for clinical failure were follow-up period, high-grade preoperative knee laxity, time from injury to ACLR, participation in competitive sports, posterior tibial slope, graft diameter, age at surgery, and medial meniscus resection. The WAV ensemble algorithm achieved the best predictive performance based on concordance (AUC, 0.9139), calibration (calibration intercept, -0.1806; calibration slope, 1.2794; Brier score, 0.0888), and decision curve analysis (greatest net benefits) and was used to develop an web-based application to predict a patient's clinical failure risk of ACLR. The WAV ensemble algorithm was able to accurately predict patient-specific risk of clinical failure after ACLR. Clinicians and patients can use the web-based application during preoperative consultation to understand individual prediction outcomes.

External Validation of Serologic Scores for the Detection of Liver Steatosis Among People With HIV.

Fatty liver index (FLI) and hepatic steatosis index (HSI) are serologic scores used to detect liver steatosis. However, their diagnostic performance in people with HIV (PWH) remains unclear. We performed an external validation of FLI and HSI in the Swiss HIV Cohort Study. We systematically performed vibration-controlled transient elastography (VCTE) among Swiss HIV Cohort Study participants at Bern University Hospital between November 2019 and August 2021. Individuals with viral hepatitis and pregnant women were excluded. We defined liver steatosis as controlled attenuation parameter ≥248 dB/m using VCTE. Model discrimination was assessed with the C-index and model calibration with calibration plots. A decision curve analysis was performed to compare the clinical usefulness of both scores. Of 321 participants, 91 (28.4%) were female, the median age was 51.4 years (IQR, 42-59), 230 (71.7%) were Caucasian, and 164 (51.1%) had a body mass index >25 kg/m2. VCTE-confirmed liver steatosis was present in 158 (49.2%). Overall, 125 (38.9%) had an FLI ≥60, and 128 (39.9%) had an HSI ≥36. At these cutoffs, the C-index to diagnose liver steatosis was 0.85 for FLI (95% CI, .80-.89) and 0.78 for HSI (95% CI, .73-.83). Whereas FLI was well calibrated, HSI overestimated the risk for steatosis. Both models showed a positive net benefit, with FLI having a greater net benefit when compared with HSI. FLI and HSI are valid tools to detect liver steatosis in PWH. FLI should be the preferred score, given its better performance and greater clinical usefulness.

Radiomic analysis based on magnetic resonance imaging for the prediction of VEGF expression in hepatocellular carcinoma patients

ObjectiveThe purpose of this study was to investigate the ability of radiomic characteristics of magnetic resonance images to predict vascular endothelial growth factor (VEGF) expression in hepatocellular carcinoma (HCC) patients.MethodsOne hundred and twenty-four patients with HCC who underwent fat-suppressed T2-weighted imaging (FS-T2WI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) one week before surgical resection were enrolled in this retrospective study. Immunohistochemical analysis was used to evaluate the expression level of VEGF. Radiomic features were extracted from the axial FS-T2WI, DCE-MRI (arterial phase and portal venous phase) images of axial MRI. Least absolute shrinkage and selection operator (LASSO) and stepwise regression analyses were performed to select the best radiomic features. Multivariate logistic regression models were constructed and validated using tenfold cross-validation. Receiver operating characteristic (ROC) curve analysis, calibration curve analysis and decision curve analysis (DCA) were employed to evaluate these models.ResultsOur results show that there were 94 patients with high VEGF expression and 30 patients with low VEGF expression among the 124 HCC patients. The FS-T2WI, DCE-MRI and combined MRI radiomics models had AUCs of 0.8713, 0.7819, and 0.9191, respectively. There was no significant difference in the AUC between the FS-T2WI radiomics model and the DCE-MRI radiomics model (p > 0.05), but the AUC for the combined model was significantly greater than the AUCs for the other two models (p < 0.05) according to the DeLong test. The combined model had the greatest net benefit according to the DCA results.ConclusionThe radiomic model based on multisequence MR images has the potential to predict VEGF expression in HCC patients. The combined model showed the best performance.Graphical

Diffusion-/perfusion-weighted imaging fusion to automatically identify stroke within 4.5 h

ObjectivesWe aimed to develop machine learning (ML) models based on diffusion- and perfusion-weighted imaging fusion (DP fusion) for identifying stroke within 4.5 h, to compare them with DWI- and/or PWI-based ML models, and to construct an automatic segmentation-classification model and compare with manual labeling methods.MethodsML models were developed from multimodal MRI datasets of acute stroke patients within 24 h of clear symptom onset from two centers. The processes included manual segmentation, registration, DP fusion, feature extraction, and model establishment (logistic regression (LR) and support vector machine (SVM)). A segmentation-classification model (X-Net) was proposed for automatically identifying stroke within 4.5 h. The area under the receiver operating characteristic curve (AUC), sensitivity, Dice coefficients, decision curve analysis, and calibration curves were used to evaluate model performance.ResultsA total of 418 patients (≤ 4.5 h: 214; > 4.5 h: 204) were evaluated. The DP fusion model achieved the highest AUC in identifying the onset time in the training (LR: 0.95; SVM: 0.92) and test sets (LR: 0.91; SVM: 0.90). The DP fusion-LR model displayed consistent positive and greater net benefits than other models across a broad range of risk thresholds. The calibration curve demonstrated the good calibration of the DP fusion-LR model (average absolute error: 0.049). The X-Net model obtained the highest Dice coefficients (DWI: 0.81; Tmax: 0.83) and achieved similar performance to manual labeling (AUC: 0.84).ConclusionsThe automatic segmentation-classification models based on DWI and PWI fusion images had high performance in identifying stroke within 4.5 h.Clinical relevance statementPerfusion-weighted imaging (PWI) fusion images had high performance in identifying stroke within 4.5 h. The automatic segmentation-classification models based on DWI and PWI fusion images could provide clinicians with decision-making guidance for acute stroke patients with unknown onset time.Key Points• The diffusion/perfusion-weighted imaging fusion model had the best performance in identifying stroke within 4.5 h.• The X-Net model had the highest Dice and achieved performance close to manual labeling in segmenting lesions of acute stroke.• The automatic segmentation-classification model based on DP fusion images performed well in identifying stroke within 4.5 h.

Differentiation of testicular seminomas from nonseminomas based on multiphase CT radiomics combined with machine learning: A multicenter study

BackgroundDifferentiating seminomas from nonseminomas is crucial for formulating optimal treatment strategies for testicular germ cell tumors (TGCTs). Therefore, our study aimed to develop and validate a clinical-radiomics model for this purpose. MethodsIn this study, 221 patients with TGCTs confirmed by pathology from four hospitals were enrolled and classified into training (n = 126), internal validation (n = 55) and external test (n = 40) cohorts. Radiomics features were extracted from the CT images. After feature selection, we constructed a clinical model, radiomics models and clinical-radiomics model with different machine learning algorithms. The top-performing model was chosen utilizing receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was also conducted to assess its practical utility. ResultsCompared with those of the clinical and radiomics models, the clinical-radiomics model demonstrated the highest discriminatory ability, with AUCs of 0.918 (95 % CI: 0.870 – 0.966), 0.909 (95 % CI: 0.829 – 0.988) and 0.839 (95 % CI: 0.709 – 0.968) in the training, validation and test cohorts, respectively. Moreover, DCA confirmed that the combined model had a greater net benefit in predicting seminomas and nonseminomas. ConclusionThe clinical-radiomics model serves as a potential tool for noninvasive differentiation between testicular seminomas and nonseminomas, offering valuable guidance for clinical treatment.

Harms and benefits of mammographic screening for breast cancer in Brazil.

In the absence of evidence on the effect of mammographic screening on overall mortality, comparing the number of deaths avoided with the number of deaths caused by screening would be ideal, but the only existing models of this type adopt a very narrow definition of harms. The objective of the present study was to estimate the number of deaths prevented and induced by various mammography screening protocols in Brazil. A simulation study of cohorts of Brazilian women screened, considering various age groups and screening interval protocols, was performed based on life tables. The number of deaths avoided and caused by screening was estimated, as was the absolute risk reduction, the number needed to invite for screening-NNS, the net benefit of screening, and the ratio of "lives saved" to "lives lost". Nine possible combinations of balances between benefits and harms were performed for each protocol, in addition to other sensitivity analyses. The most efficient protocol was biennial screening from 60 to 69 years of age, with almost three times more deaths avoided than biennial screening from 50 to 59 years of age, with a similar number of deaths avoided by biennial screening from 50 to 69 years of age and with the greatest net benefit. Compared with the best scenario of annual screening from 40 to 49 years of age, the NNS of the protocol with biennial screening from 60 to 69 years of age was three-fold lower. Even in its best scenario, the addition of annual screening from 40 to 49 years of age to biennial screening from 50 to 69 years of age results in a decreased net benefit. However, even in the 50-69 year age group, the estimated reduction in breast cancer mortality for Brazil was half that estimated for the United Kingdom.

A Metric Shedding Light on the Relationship Between White Coat Hypertension and Anxiety: The Hospital Anxiety and Depression Scale-Anxiety.

To investigate the relationship between anxiety and white coat hypertension (WCH) using the hospital anxiety and depression scale-anxiety (HADS-A) score. Participants lacking a pre-existing diagnosis of hypertension but displaying increased office blood pressure were included in this study. Subsequently, they were classified as either newly diagnosed sustained hypertension (SustHT) or white coat hypertension (WCH) patients, as determined by 24-hour ambulatory blood pressure monitoring measurements. The assessment of their anxiety levels was conducted using the HADS-A questionnaire. We performed regression, comparative, and sensitivity analyses to elucidate the association between anxiety and WCH. In this cohort of 303 consecutive individuals (mean age 54 years, 46% female), 81 (26.7%) patients were diagnosed with WCH. Those with WCH were younger (49 vs. 56 years, P < .001), had higher heart rate (85 vs. 76 bpm, P < .001) and exhibited a female predominance (56% vs. 43%, P = .049) compared to individuals with SustHT. The HADS-A was higher in WCH than in SustHT (9.0 ± 2.9 vs. 6.6 ± 2.6, P < .001). Furthermore, HADS-A showed positive correlation with systolic and diastolic pressures measured in the out-patient clinic (r = 0.523 and r = 0.387, respectively; P < .001 for both). The full model with HADS-A had better discriminatory power (Harrell's c-index 0.82 vs. 0.77, P = .0025), increased calibration, and a greater net benefit than the base model without. The ROC curve analysis, using a cut-off of >6 for HADS-A, demonstrated a sensitivity of 76.5% and specificity of 53.6% in detecting WCH (Area Under the Curve = 0.72, P < .001). Our study revealed that individuals with WCH, in comparison to those with SustHT, exhibit a higher level of anxiety as indicated by HADS-A.

Contrast-enhanced CT radiomics combined with multiple machine learning algorithms for preoperative identification of lymph node metastasis in pancreatic ductal adenocarcinoma.

This research aimed to assess the value of radiomics combined with multiple machine learning algorithms in the diagnosis of pancreatic ductal adenocarcinoma (PDAC) lymph node (LN) metastasis, which is expected to provide clinical treatment strategies. A total of 128 patients with pathologically confirmed PDAC and who underwent surgical resection were randomized into training (n=93) and validation (n=35) groups. This study incorporated a total of 13 distinct machine learning algorithms and explored 85 unique combinations of these algorithms. The area under the curve (AUC) of each model was computed. The model with the highest mean AUC was selected as the best model which was selected to determine the radiomics score (Radscore). The clinical factors were examined by the univariate and multivariate analysis, which allowed for the identification of factors suitable for clinical modeling. The multivariate logistic regression was used to create a combined model using Radscore and clinical variables. The diagnostic performance was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). Among the 233 models constructed using arterial phase (AP), venous phase (VP), and AP+VP radiomics features, the model built by applying AP+VP radiomics features and a combination of Lasso+Logistic algorithm had the highest mean AUC. A clinical model was eventually constructed using CA199 and tumor size. The combined model consisted of AP+VP-Radscore and two clinical factors that showed the best diagnostic efficiency in the training (AUC = 0.920) and validation (AUC = 0.866) cohorts. Regarding preoperative diagnosis of LN metastasis, the calibration curve and DCA demonstrated that the combined model had a good consistency and greatest net benefit. Combining radiomics and machine learning algorithms demonstrated the potential for identifying the LN metastasis of PDAC. As a non-invasive and efficient preoperative prediction tool, it can be beneficial for decision-making in clinical practice.

Elevated splenic 18F-fluorodeoxyglucose positron emission tomography/computed tomography activity is associated with 5-year risk of recurrence in non-metastatic invasive ductal carcinoma of the breast.

To construct prediction models including baseline 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) metabolic parameters of tumoural lesions and non-tumour lymphoid tissue for recurrence-free survival within 5 years (5y-RFS) after imaging examination in patients with invasive ductal carcinomas (IDCs) of the breast. The study included 101 consecutive female patients. Univariable and multivariable Cox regression were used to identify clinicopathological and metabolic parameters associated with risk of recurrence. Four prediction models based on the results of multivariable analysis were constructed and visualized as nomograms. Performance of each nomogram was evaluated using the concordance index (C-index), integrated discrimination improvement, decision curve analysis (DCA), and calibration curve. N3 status, total metabolic tumour volume, the maximum standardized uptake value of spleen, and spleen-to-liver ratio were significant predictors of 5y-RFS. The nomogram including all significant predictors demonstrated superior predictive performance for 5y-RFS, with a C-index of 0.907 (95% CI, 0.833-0.981), greatest net benefit on DCA, good accuracy on calibration curves, and excellent risk stratification on Kaplan-Meier curves. The model that included metabolic parameters of the spleen had the best performance for predicting 5y-RFS in patients with IDCs of the breast. This model may guide personalized treatment decisions and inform patients and clinicians about prognosis. This research identifies 18F-FDG PET/CT metabolic parameters of non-tumour lymphoid tissue as predictors of recurrence in breast cancer.

Development and validation of a nomogram for preoperative prediction of immature teratoma in children with teratoma: a retrospective, multicenter, diagnostic study.

Teratomas are the most common germ cell tumors in children, and histologically classified as mature teratomas (MTs) and immature teratomas (ITs). Preoperative IT identification can affect the surgical approach, the type of procedure, and future possible reproductive health. However, there is no complete diagnostic criterion for ITs nowadays. We aimed to establish and validate a nomogram based on clinical and computed tomography (CT) features for preoperative prediction of ITs in children. We retrospectively reviewed 519 teratoma patients from hospital I for training (n=364) and validation (n=155), and 113 patients from hospital II for external validation. Univariate and multivariate logistic regression analyses were performed on the training set to screen risk factors, including alpha-fetoprotein (AFP), age, gender, tumor site, size, tumor composition, calcification and fat. Then, a nomogram was established based on identified risk factors and validated on the validation set. The performance of the nomogram was evaluated in terms of discrimination, calibration and the clinical usefulness. Multivariate logistic regression showed that tumor composition, AFP, age, calcification and fat were independent risk factors for preoperative prediction of IT. The area under the receiver operating characteristic (ROC) curves (AUCs) for the nomogram on the training set, internal and external validation set were 0.92 (0.88-0.96), 0.91 (0.84-0.97) and 0.92 (0.86-0.97), respectively. The model demonstrated sensitivity of 80%, specificity of 90% at the cut-off value of 0.262. Whatever the set, the calibration curve indicated good calibration. Decision curve analysis (DCA) curves demonstrated that the nomogram had greater net benefits than either the treat-all tactics or the treat-none tactics within a large scope of threshold. The nomogram established based on clinical and CT findings had the favorable accuracy for the preoperative prediction of IT, and may help in clinical decision-making and risk stratification.

MRI radiomics-based evaluation of tuberculous and brucella spondylitis.

We analyzed magnetic resonance imaging (MRI) and radiomics labels from tuberculous spondylitis (TBS) and brucella spondylitis (BS) to build machine learning models that differentiate TBS from BS and culture-positive TBS (TBS(+)) from culture-negative TBS (TBS(-). This retrospective study included 56 patients with BS, 63 patients with TBS(+) and 71 patients with TBS(-). Radiomics labels were extracted from T2-weighted fat-suppression images. MRI labels were analyzed via logistic regression (LR); radiomics labels were analyzed by t-tests, SelectKBest, and least absolute shrinkage and selection operator (LASSO). Random forest (RF) and support vector machine (SVM) models were established using radiomics or joint (radiomics+MRI) labels. Models were evaluated by receiver operating characteristic curves, areas under the curve (AUCs), decision curve analysis (DCA), and Hosmer-Lemeshow tests. When joint-label models were used to compare BS vs TBS(+) and BS vs TBS(-) groups, SVM AUCs were 0.904 and 0.944, respectively, whereas RF AUCs were 0.950 and 0.947, respectively; these were higher than the AUCs of the MRI label-based LR model. DCA showed that radiomics-based machine learning models had a greater net benefit; Hosmer-Lemeshow tests demonstrated good prediction consistency for all models. Radiomics can help distinguish TBS from BS and TBS(+) from TBS(-).

Defining the role of host biomarkers in the diagnosis and prognosis of the severity of childhood pneumonia: a prospective cohort study

Reliable tools to inform outpatient management of childhood pneumonia in resource-limited settings are needed. We investigated the value added by biomarkers of the host infection response to the performance of the Liverpool quick Sequential Organ Failure Assessment score (LqSOFA), for triage of children presenting with pneumonia to a primary care clinic in a refugee camp on the Thailand-Myanmar border. 900 consecutive presentations of children aged ≤ 24 months meeting WHO pneumonia criteria were included. The primary outcome was receipt of supplemental oxygen. We compared discrimination of a clinical risk score (LqSOFA) to markers of endothelial injury (Ang-1, Ang-2, sFlt-1), immune activation (CHI3L1, IP-10, IL-1ra, IL-6, IL-8, IL-10, sTNFR-1, sTREM-1), and inflammation (CRP, PCT), and quantified the net benefit of including biomarkers alongside LqSOFA. We evaluated the differential contribution of LqSOFA and host biomarkers to the diagnosis and prognosis of pneumonia severity. 49/900 (5.4%) presentations met the primary outcome. Discrimination of LqSOFA and Ang-2, the best performing biomarker, were comparable (AUC 0.82 [95% CI 0.76–0.88] and 0.81 [95% CI 0.74–0.87] respectively). Combining Ang-2 with LqSOFA improved discrimination (AUC 0.91; 95% CI 0.87–0.94; p < 0.001), and resulted in greater net benefit, with 10–30% fewer children who required oxygen supplementation incorrectly identified as safe for community-based management. Ang-2 had greater prognostic utility than LqSOFA to identify children requiring supplemental oxygen later in their illness course. Combining Ang-2 and LqSOFA could guide referrals of childhood pneumonia from resource-limited community settings. Further work on test development and integration into patient triage is required.

The Efficacy of Selected Insecticides Against Wheat Aphids on Irrigated Wheat in North Western Amhara, Ethiopia

Aphid infestations cause significant losses in wheat production. The experiment was conducted at the Koga irrigation site during 2021 to evaluate the efficacy of commercial insecticides for the management of wheat aphids. Seven types of insecticides with unsprayed control were laid in a completely randomized block design with three replications. The result showed a reduced aphid infestation with maximum grain yield were from dimethoate, imidacloprid, lambda-cyhalotrin, profenfos + lambda-cyhalothrin, imidacloprid + lambda-cyhalothrin, and profenofos-sprayed plots. However, the greater net benefit and marginal rate of return were provided by the applications of imidacloprid and dimethoate insecticides. The economically feasible insecticide application can be considered as an effective aphid management practice in wheat production.

Multivariable stratification of PI-RADS version 2.1 categories for the risk of false-positive target biopsy: Impact on prostate biopsy decisions

PurposeTo identify clinical and multiparametric magnetic resonance imaging (mpMRI) factors predicting false positive target biopsy (FP-TB) of prostate imaging reporting and data system version 2.1 (PI-RADSv2.1) ≥ 3 findings. MethodWe retrospectively included 221 men with and without previous negative prostate biopsy who underwent 3.0 T/1.5 T mpMRI for suspicious clinically significant prostate cancer (csPCa) between April 2019-July 2021. A study coordinator revised mpMRI reports provided by one of two radiologists (experience of > 1500/>500 mpMRI examinations, respectively) and matched them with the results of transperineal systematic biopsy plus fusion target biopsy (TB) of PI-RADSv2.1 ≥ 3 lesions or PI-RADSv2.1 ≤ 2 men with higher clinical risk. A multivariable model was built to identify features predicting FP-TB of index lesions, defined as the absence of csPCa (International Society of Urogenital Pathology [ISUP] ≥ 2). The model was internally validated with the bootstrap technique, receiving operating characteristics (ROC) analysis, and decision analysis. ResultsFeatures significantly associated with FP-TB were age < 65 years (odds ratio [OR] 2.77), prostate-specific antigen density (PSAD) < 0.15 ng/mL/mL (OR 2.45), PI-RADS 4/5 category vs. category 3 (OR 0.15/0.07), and multifocality (OR 0.46), with a 0.815 area under the curve (AUC) in assessing FP-TB. When adjusting PI-RADSv2.1 categorization for the model, mpMRI showed 87.5% sensitivity and 79.9% specificity for csPCa, with a greater net benefit in triggering biopsy compared to unadjusted categorization or adjustment for PSAD only at decision analysis, from threshold probability ≥ 15%. ConclusionAdjusting PI-RADSv2.1 categories for a multivariable risk of FP-TB is potentially more effective in triggering TB of index lesions than unadjusted PI-RADS categorization or adjustment for PSAD alone.

Comparison of machine learning techniques in prediction of mortality following cardiac surgery: analysis of over 220000 patients from a large national database.

To perform a systematic comparison of in-hospital mortality risk prediction post-cardiac surgery, between the predominant scoring system-European System for Cardiac Operative Risk Evaluation (EuroSCORE) II, logistic regression (LR) retrained on the same variables and alternative machine learning techniques (ML)-random forest (RF), neural networks (NN), XGBoost and weighted support vector machine. Retrospective analyses of prospectively routinely collected data on adult patients undergoing cardiac surgery in the UK from January 2012 to March 2019. Data were temporally split 70:30 into training and validation subsets. Mortality prediction models were created using the 18 variables of EuroSCORE II. Comparisons of discrimination, calibration and clinical utility were then conducted. Changes in model performance, variable-importance over time and hospital/operation-based model performance were also reviewed. Of the 227087 adults who underwent cardiac surgery during the study period, there were 6258 deaths (2.76%). In the testing cohort, there was an improvement in discrimination [XGBoost (95% confidence interval (CI) area under the receiver operator curve (AUC), 0.834-0.834, F1 score, 0.276-0.280) and RF (95% CI AUC, 0.833-0.834, F1, 0.277-0.281)] compared with EuroSCORE II (95% CI AUC, 0.817-0.818, F1, 0.243-0.245). There was no significant improvement in calibration with ML and retrained-LR compared to EuroSCORE II. However, EuroSCORE II overestimated risk across all deciles of risk and over time. The calibration drift was lowest in NN, XGBoost and RF compared with EuroSCORE II. Decision curve analysis showed XGBoost and RF to have greater net benefit than EuroSCORE II. ML techniques showed some statistical improvements over retrained-LR and EuroSCORE II. The clinical impact of this improvement is modest at present. However the incorporation of additional risk factors in future studies may improve upon these findings and warrants further study.