Machine Learning-Based Approaches for Prediction of Patients’ Functional Outcome and Mortality after Spontaneous Intracerebral Hemorrhage

Spontaneous intracerebral hemorrhage (SICH) has been common in China with high morbidity and mortality rates. This study aims to develop a machine learning (ML)-based predictive model for the 90-day evaluation after SICH. We retrospectively reviewed 751 patients with SICH diagnosis and analyzed clinical, radiographic, and laboratory data. A modified Rankin scale (mRS) of 0–2 was defined as a favorable functional outcome, while an mRS of 3–6 was defined as an unfavorable functional outcome. We evaluated 90-day functional outcome and mortality to develop six ML-based predictive models and compared their efficacy with a traditional risk stratification scale, the intracerebral hemorrhage (ICH) score. The predictive performance was evaluated by the areas under the receiver operating characteristic curves (AUC). A total of 553 patients (73.6%) reached the functional outcome at the 3rd month, with the 90-day mortality rate of 10.2%. Logistic regression (LR) and logistic regression CV (LRCV) showed the best predictive performance for functional outcome (AUC = 0.890 and 0.887, respectively), and category boosting presented the best predictive performance for the mortality (AUC = 0.841). Therefore, ML might be of potential assistance in the prediction of the prognosis of SICH.

Characteristics and nomogram for primary lung lepidic adenocarcinoma

Background: Lepidic adenocarcinoma (LPA) is an infrequent subtype of invasive pulmonary adenocarcinoma (ADC). However, the clinicopathological features and prognostic factors of LPA have not been elucidated.Methods: Data from the Surveillance, Epidemiology, and End Results (SEER) database of 4087 LPA patients were retrospectively analyzed and compared with non-LPA pulmonary ADC to explore the clinicopathological and prognosis features of LPA. Univariate and multivariate Cox proportional hazard models were performed to identify independent survival predictors for further nomogram development. The nomograms were validated by using the concordance index, receiver operating characteristic curves, and calibration plots, as well as decision curve analysis, in both the training and validation cohorts.Results: Compared with non-LPA pulmonary ADC patients, those with LPA exhibited unique clinicopathological features, including more elderly and female patients, smaller tumor size, less pleural invasion, and lower histological grade and stage. Multivariate analyses showed that age, sex, marital status, primary tumor size, pleural invasion, histological grade, stage, primary tumor surgery, and chemotherapy were independently associated with overall survival (OS) and cancer-specific survival (CSS) in patients with LPA, while race was the only independent prognostic factor for OS, not for CSS. The nomograms showed good accuracy compared with the actual observed results and demonstrated improved prognostic capacity compared with TNM stage.Conclusions: Patients with LPA are more likely to be older and female. Smaller tumor size, lower histological grade and stage are the clinicopathological features of LPA, which may indicate a good prognosis. The constructed nomograms accurately predict the long-term survival of LPA patients.

Comparison of diagnostic accuracy of 2D and 3D measurements to determine opportunistic screening of osteoporosis using the proximal femur on abdomen-pelvic CT

Objectives To compare the osteoporosis-predicting ability of computed tomography (CT) indexes in abdomen-pelvic CT using the proximal femur and the reliability of measurements in two- and three-dimensional analyses. Methods Four hundred thirty female patients (age range, 50–96 years) who underwent dual-energy X-ray absorptiometry and abdominal-pelvic CT within 1 month were retrospectively selected. The volumes of interest (VOIs) from the femoral head to the lesser trochanter and the femoral neck were expressed as 3DFemur. Round regions of interest (ROIs) of image plane drawn over the femoral neck touching the outer cortex were determined as 2Dcoronal. In HU histogram analysis (HUHA), the percentages of HU histogram ranges related to the ROI or VOI were classified as HUHAFat (<0 HU) and HUHABone (126 HU≤). Diagnostic performance, correlation analysis and measurement reliability were analyzed by receiver operating characteristic curves, correlation coefficient and interobserver correlation coefficient (ICC), respectively. Results AUCs of each HUHA and mean-HU measurement on 2D-ROI and 3D-VOI were 0.94 or higher (P < 0.001). Both 3DFemur-Mean-HU and 3DFemur-HUHABone showed the highest AUC (0.96). The cut-off value of 3DFemur-Mean-HU was 231HU or less, (sensitivity: 94.8%; specificity: 85.0%; correlation coefficient: −0.65; P <0.001) for diagnosis of osteoporosis. There was no superiority between AUCs in 2D-ROI and 3D-VOI measurements (P > 0.05). Reliability of the 3D-VOI measurement showed perfect agreement (ICC ≥ 0.94), and 2D-ROI showed moderate to good agreement (ICC range: 0.63~0.84). Conclusions CT indexes on 3D-VOI for predicting femoral osteoporosis showed similar diagnostic accuracy with better reproducibility of measurement, compared with 2D-ROI.

Prospective comparison of AMB, GAP AND START scores and triage nurse clinical judgement for predicting admission from an ED: a single-centre prospective study

BackgroundIt is postulated that early determination of the need for admission can improve flow through EDs. There are several scoring systems which have been developed for predicting patient admission at triage, although they have not been directly compared. In addition, it is not known if these scoring systems perform better than clinical judgement. Therefore, the aim of this study was to validate existing tools in predicting hospital admission during triage and then compare them with the clinical judgement of triage nurses.MethodsTo conduct this prospective, single-centre observational study, we enrolled consecutive adult patients who presented between 30 September 2019 and 25 October 2019 at the ED of a large teaching hospital in Milan, Italy. For each patient, triage nurses recorded all of the variables needed to perform Ambulatory (AMB), Glasgow Admission Prediction (GAP) and Sydney Triage to Admission Risk Tool (START) scoring. The probability of admission was estimated by the triage nurses using clinical judgement and expressed as a percentage from 0 to 100 with intervals of 5. Nurse estimates were dichotomised for analysis, with ≥50% likelihood being a prediction of admission. Receiver operating characteristic curves were generated for accuracy of the predictions. Area under the curve (AUC) with 95% CI for each of the scores and for the nursing judgements was also calculated.ResultsA total of 1710 patients (844 men; median age, 54 years (IQR: 34–75)) and 35 nurses (15 men; median age, 37 years (IQR: 33–48)) were included in this study. Among these patients, 310 (18%) were admitted to hospital from the ED. AUC values for AMB, GAP and START scores were 0.77 (95% CI: 0.74 to 0.79), 0.72 (95% CI: 0.69 to 0.75) and 0.61 (95% CI: 0.58 to 0.64), respectively. The AUC for nurse clinical judgement was 0.86 (95% CI: 0.84 to 0.89).ConclusionAMB, GAP and START scores provided moderate accuracy in predicting patient admission. However, all of the scores were significantly worse than the clinical judgement of the triage nurses.

Characteristics and Nomogram for Primary Lung Lepidic Adenocarcinoma

Background: Lepidic adenocarcinoma (LPA) is an infrequent subtype of invasive pulmonary adenocarcinoma (ADC). However, the clinicopathological features and prognostic factors of LPA have not been elucidated.Methods: Data from the Surveillance, Epidemiology, and End Results (SEER) database of 4087 LPA patients were retrospectively analyzed and compared with non-LPA pulmonary ADC to explore the clinicopathological and prognosis features of LPA. Univariate and multivariate Cox proportional hazard models were performed to identify independent survival predictors for further nomogram development. The nomograms were validated by using the concordance index, receiver operating characteristic curves, and calibration plots, as well as decision curve analysis, in both the training and validation cohorts.Results: Compared with non-LPA pulmonary ADC patients, those with LPA exhibited unique clinicopathological features, including more elderly and female patients, smaller tumor size, less pleural invasion, and lower histological grade and stage. Multivariate analyses showed that age, sex, marital status, primary tumor size, pleural invasion, histological grade, stage, primary tumor surgery, and chemotherapy were independently associated with overall survival (OS) and cancer-specific survival (CSS) in patients with LPA, while race was the only independent prognostic factor for OS, not for CSS. The nomograms showed good accuracy compared with the actual observed results and demonstrated improved prognostic capacity compared with TNM stage.Conclusions: Patients with LPA are more likely to be older and female. Smaller tumor size, lower histological grade and stage are the clinicopathological features of LPA, which may indicate a good prognosis. The constructed nomograms accurately predict the long-term survival of LPA patients.

Transcranial photoacoustic characterization of neurovascular physiology during early-stage photothrombotic stroke in neonatal piglets in vivo

Perinatal ischemic stroke is estimated to occur in 1/2300–1/5000 live births, but early differential diagnosis from global hypoxia-ischemia is often difficult. In this study, we tested the ability of a hand-held transcranial photoacoustic (PA) imaging probe to non-invasively detect a focal photothrombotic stroke (PTS) within 2 hours of stroke onset in a gyrencephalic piglet brain. 17 stroke lesions of approximately 1-cm2 area were introduced randomly in anterior or posterior cortex via the light/dye PTS technique in anesthetized neonatal piglets (n = 11). The contralateral non-ischemic region served as control tissue for discrimination contrast for the PA hemoglobin metrics: oxygen saturation, total hemoglobin (tHb), and individual quantities of oxygenated and deoxygenated hemoglobin (HbO2 and HbR). The PA-derived tissue oxygen saturation at 2 hours yielded a significant separation between control and affected regions-of-interest (p < 0.0001), which were well matched with 24-hr post-stroke cerebral infarction confirmed in the triphenyltetrazolium chloride-stained image. The quantity of HbO2 also displayed a significant contrast (p = 0.021), whereas tHb and HbR did not. The analysis on receiver operating characteristic curves and multivariate data analysis also agreed with the results above. This study shows that a hand-held transcranial PA neuroimaging device can detect a regional thrombotic stroke in the cerebral cortex of a neonatal piglet. In particular, we conclude that the oxygen saturation metric can be used alone to identify regional stroke lesions. The lack of change in tHb may be related to arbitrary hand-held imaging configuration and/or entrapment of red blood cells within the thrombotic stroke.

Score for the Overall Survival Probability Scores of Fibrosarcoma Patients after Surgery: A Novel Nomogram-Based Risk Assessment System

Background. The primary purpose of this study was to determine the risk factors affecting overall survival (OS) in patients with fibrosarcoma after surgery and to develop a prognostic nomogram in these patients. Methods. Data were collected from the Surveillance, Epidemiology, and End Results database on 439 postoperative patients with fibrosarcoma who underwent surgical resection from 2004 to 2015. Independent risk factors were identified by performing Cox regression analysis on the training set, and based on this, a prognostic nomogram was created. The accuracy of the prognostic model in terms of survival was demonstrated by the area under the curve (AUC) of the receiver operating characteristic curves. In addition, the prediction consistency and clinical value of the nomogram were validated by calibration curves and decision curve analysis. Results. All included patients were divided into a training set (n = 308) and a validation set (n = 131). Based on univariate and multivariate analyses, we determined that age, race, grade, and historic stage were independent risk factors for overall survival after surgery in patients with fibrosarcoma. The AUC of the receiver operating characteristic curves demonstrated the high predictive accuracy of the prognostic nomogram, while the decision curve analysis revealed the high clinical application of the model. The calibration curves showed good agreement between predicted and observed survival rates. Conclusion. We developed a new nomogram to estimate 1-year, 3-year, and 5-year OS based on the independent risk factors. The model has good discriminatory performance and calibration ability for predicting the prognosis of patients with fibrosarcoma after surgery.

Convolutional Neural Network-Based Diagnostic Model for a Solid, Indeterminate Solitary Pulmonary Nodule or Mass on Computed Tomography

PurposeTo establish a non-invasive diagnostic model based on convolutional neural networks (CNNs) to distinguish benign from malignant lesions manifesting as a solid, indeterminate solitary pulmonary nodule (SPN) or mass (SPM) on computed tomography (CT).MethodA total of 459 patients with solid indeterminate SPNs/SPMs on CT were ultimately included in this retrospective study and assigned to the train (n=366), validation (n=46), and test (n=47) sets. Histopathologic analysis was available for each patient. An end-to-end CNN model was proposed to predict the natural history of solid indeterminate SPN/SPMs on CT. Receiver operating characteristic curves were plotted to evaluate the predictive performance of the proposed CNN model. The accuracy, sensitivity, and specificity of diagnoses by radiologists alone were compared with those of diagnoses by radiologists by using the CNN model to assess its clinical utility.ResultsFor the CNN model, the AUC was 91% (95% confidence interval [CI]: 0.83–0.99) in the test set. The diagnostic accuracy of radiologists with the CNN model was significantly higher than that without the model (89 vs. 66%, P&lt;0.01; 87 vs. 61%, P&lt;0.01; 85 vs. 66%, P=0.03, in the train, validation, and test sets, respectively). In addition, while there was a slight increase in sensitivity, the specificity improved significantly by an average of 42% (the corresponding improvements in the three sets ranged from 43, 33, and 42% to 82, 78, and 84%, respectively; P&lt;0.01 for all).ConclusionThe CNN model could be a valuable tool in non-invasively differentiating benign from malignant lesions manifesting as solid, indeterminate SPNs/SPMs on CT.

Considerations on the region of interest in the ROC space

Receiver Operating Characteristic curves have been widely used to represent the performance of diagnostic tests. The corresponding area under the curve, widely used to evaluate their performance quantitatively, has been criticized in several respects. Several proposals have been introduced to improve area under the curve by taking into account only specific regions of the Receiver Operating Characteristic space, that is, the plane to which Receiver Operating Characteristic curves belong. For instance, a region of interest can be delimited by setting specific thresholds for the true positive rate or the false positive rate. Different ways of setting the borders of the region of interest may result in completely different, even opposing, evaluations. In this paper, we present a method to define a region of interest in a rigorous and objective way, and compute a partial area under the curve that can be used to evaluate the performance of diagnostic tests. The method was originally conceived in the Software Engineering domain to evaluate the performance of methods that estimate the defectiveness of software modules. We compare this method with previous proposals. Our method allows the definition of regions of interest by setting acceptability thresholds on any kind of performance metric, and not just false positive rate and true positive rate: for instance, the region of interest can be determined by imposing that [Formula: see text] (also known as the Matthews Correlation Coefficient) is above a given threshold. We also show how to delimit the region of interest corresponding to acceptable costs, whenever the individual cost of false positives and false negatives is known. Finally, we demonstrate the effectiveness of the method by applying it to the Wisconsin Breast Cancer Data. We provide Python and R packages supporting the presented method.

Role of the CBX Molecular Family in Lung Adenocarcinoma Tumorigenesis and Immune Infiltration

Background: The members of the Chromobox (CBX) family are important epigenetic regulatory molecules with critical biological roles in many tumors. However, no study has analyzed or verified their role in lung adenocarcinoma (LUAD).Methods: UALCAN and Oncomine databases were used to analyze CBX expression in LUAD, and the cBioPortal database was used to analyze CBX genetic variations. The Kaplan-Meier plotter and UALCAN databases were used to identify molecules with prognostic value. Gene Ontology pathway, receiver operating characteristic curves, and tumor-infiltrating immune cell analyses were used to clarify the biological function of the CBX hub molecules. Paired tumor samples and lung adenocarcinoma cell lines were collected for molecular functional assays to validate the results of the bioinformatics analysis.Results: CBX3/5 may have a cancer-promoting effect and its expression is associated with a poor patient prognosis, while CBX7 shows an opposite trend. CBX3/5/7 can regulate signaling pathways, regulate tumor immune cell infiltration, and has diagnostic value. Molecular biology experiments show that CBX3/5 is highly expressed in LUAD patients; in vitro it promotes the proliferation and migration of the LUAD cell line and can regulate the expression of the corresponding cytokines. CBX7 has opposite effects.Conclusion: Our bioinformatics analysis and subsequent experimental verification confirmed the CBX family members acted as hub signaling molecules in LUAD. The results provide new potential targets for the diagnosis and treatment of this cancer.