Development of a radiomics model to diagnose pheochromocytoma preoperatively: a multicenter study with prospective validation

Background Preoperative diagnosis of pheochromocytoma (PHEO) accurately impacts preoperative preparation and surgical outcome in PHEO patients. Highly reliable model to diagnose PHEO is lacking. We aimed to develop a magnetic resonance imaging (MRI)-based radiomic-clinical model to distinguish PHEO from adrenal lesions. Methods In total, 305 patients with 309 adrenal lesions were included and divided into different sets. The least absolute shrinkage and selection operator (LASSO) regression model was used for data dimension reduction, feature selection, and radiomics signature building. In addition, a nomogram incorporating the obtained radiomics signature and selected clinical predictors was developed by using multivariable logistic regression analysis. The performance of the radiomic-clinical model was assessed with respect to its discrimination, calibration, and clinical usefulness. Results Seven radiomics features were selected among the 1301 features obtained as they could differentiate PHEOs from other adrenal lesions in the training (area under the curve [AUC], 0.887), internal validation (AUC, 0.880), and external validation cohorts (AUC, 0.807). Predictors contained in the individualized prediction nomogram included the radiomics signature and symptom number (symptoms include headache, palpitation, and diaphoresis). The training set yielded an AUC of 0.893 for the nomogram, which was confirmed in the internal and external validation sets with AUCs of 0.906 and 0.844, respectively. Decision curve analyses indicated the nomogram was clinically useful. In addition, 25 patients with 25 lesions were recruited for prospective validation, which yielded an AUC of 0.917 for the nomogram. Conclusion We propose a radiomic-based nomogram incorporating clinically useful signatures as an easy-to-use, predictive and individualized tool for PHEO diagnosis.

Development of Clinical Prediction Rules for One-Year Postoperative Functional Outcome in Patients with Intertrochanteric Fractures: The Intertrochanteric Fracture Ambulatory Prediction (IT-AP) Tool

Individualized prediction of postoperative ambulatory status for patients with intertrochanteric fractures is clinically relevant, during both preoperative and intraoperative periods. This study intended to develop clinical prediction rules (CPR) to predict one-year postoperative functional outcomes in patients with intertrochanteric fractures. CPR development was based on a secondary analysis of a retrospective cohort of patients with intertrochanteric fractures aged ≥50 years who underwent a surgical fixation. Good ambulatory status was defined as a New Mobility Score ≥5. Two CPR for preoperative and intraoperative predictions were derived using clinical profiles and surgical-related parameters using logistic regression with the multivariable fractional polynomial procedure. In this study, 221 patients with intertrochanteric fractures were included. Of these, 160 (72.4%) had good functional status at one year. The preoperative model showed an acceptable AuROC of 0.77 (95%CI 0.70 to 0.85). After surgical-related parameters were incorporated into the preoperative model, the model discriminative ability was significantly improved to an AuROC of 0.83 (95%CI 0.77 to 0.88) (p = 0.021). The newly-derived CPR enable physicians to provide patients with intertrochanteric fractures with their individualized predictions of functional outcome one year after surgery, which could be used for risk communication, surgical optimization and tailoring postoperative care that fits patients’ expectations.

A nomogram model for predicting prognosis of obstructive colorectal cancer

Background The prognosis of obstructive colorectal cancer (oCRC) is worse than that of nonobstructive colorectal cancer. However, no previous study has established an individualized prediction model for the prognosis of patients with oCRC. We aimed to screen the factors that affect the prognosis of oCRC and to use these findings to establish a nomogram model that predicts the individual prognosis of patients with oCRC. Methods This retrospective study collected data of 181 patients with oCRC from three medical hospitals between February 2012 and December 2017. Among them, 129 patients from one hospital were used as the training cohort. Univariate and multivariate analyses were used in this training cohort to select independent risk factors that affect the prognosis of oCRC, and a nomogram model was established. The other 52 patients from two additional hospitals were used as the validation cohort to verify the model. Results Multivariate analysis showed that carcinoembryonic antigen level (p = 0.037, hazard ratio [HR] = 2.872 [1.065–7.740]), N stage (N1 vs. N0, p = 0.028, HR = 3.187 [1.137–8.938]; N2 vs. N0, p = 0.010, HR = 4.098 [1.393–12.051]), and surgical procedures (p = 0.002, HR = 0.299 [0.139–0.643]) were independent prognostic factors of overall survival in patients with oCRC. These factors were used to construct the nomogram model, which showed good concordance and accuracy. Conclusion Carcinoembryonic antigen, N stage, and surgical method are independent prognostic factors for overall survival in patients with oCRC, and the nomogram model can visually display these results.

N-Terminal Pro-brain Natriuretic Peptide Is Associated With Hemorrhagic Transformation and Poor Outcomes in Patients With Stroke Treated With Intravenous Thrombolysis

Background: N-terminal pro-brain natriuretic peptide (NT-proBNP) levels are a promising biomarker for predicting stroke outcomes; however, their prognostic validity is not well-understood in patients who have undergone intravenous thrombolysis. This study was designed to evaluate the prognostic value of NT-proBNP levels in patients with acute ischemic stroke treated with intravenous thrombolysis.Methods: Patients with ischemic stroke who underwent intravenous thrombolysis between April 2015 and December 2020 were analyzed. Demographic information, information related to intravenous thrombolysis, medical history, and laboratory test results were collected. Outcomes, such as hemorrhagic transformation, early neurologic deterioration, poor 3-month functional outcomes, and 3-month mortality were recorded. Correlations between NT-proBNP levels and the above outcomes were analyzed, an individualized prediction model based on NT-proBNP levels for functional outcomes was developed, and a nomogram was drafted.Results: A total of 404 patients were included in the study. Elevated NT-proBNP levels were independently associated with hemorrhagic transformation, poor 3-month functional outcomes, and 3-month mortality, while early neurological deterioration was not. An association between NT-proBNP levels and hemorrhagic transformation was noted. An individualized prediction model for poor functional outcomes was established, which was composed of ln(NT-proBNP), National Institutes of Health Stroke Scale (NIHSS), and baseline glucose, with good discrimination [area under the curve (AUC) 0.764] and calibration (P > 0.05).Conclusion: To the best of our knowledge, this is the first report on the association between NT-proBNP levels and hemorrhagic transformation in patients who have undergone intravenous thrombolysis. The 3-month functional outcomes and mortality were found to be associated with NT-proBNP levels. An individualized prediction model based on NT-proBNP levels to predict the 3-month functional outcomes was established. Our results suggest that NT-proBNP levels could be used as a prognostic biomarker in patients with acute ischemic stroke treated with intravenous thrombolysis.

A Portrait of Intratumoral Genomic and Transcriptomic Heterogeneity at Single-Cell Level in Colorectal Cancer

In the study of cancer, omics technologies are supporting the transition from traditional clinical approaches to precision medicine. Intra-tumoral heterogeneity (ITH) is detectable within a single tumor in which cancer cell subpopulations with different genome features coexist in a patient in different tumor areas or may evolve/differ over time. Colorectal carcinoma (CRC) is characterized by heterogeneous features involving genomic, epigenomic, and transcriptomic alterations. The study of ITH is a promising new frontier to lay the foundation towards successful CRC diagnosis and treatment. Genome and transcriptome sequencing together with editing technologies are revolutionizing biomedical research, representing the most promising tools for overcoming unmet clinical and research challenges. Rapid advances in both bulk and single-cell next-generation sequencing (NGS) are identifying primary and metastatic intratumoral genomic and transcriptional heterogeneity. They provide critical insight in the origin and spatiotemporal evolution of genomic clones responsible for early and late therapeutic resistance and relapse. Single-cell technologies can be used to define subpopulations within a known cell type by searching for differential gene expression within the cell population of interest and/or effectively isolating signal from rare cell populations that would not be detectable by other methods. Each single-cell sequencing analysis is driven by clustering of cells based on their differentially expressed genes. Genes that drive clustering can be used as unique markers for a specific cell population. In this review we analyzed, starting from published data, the possible achievement of a transition from clinical CRC research to precision medicine with an emphasis on new single-cell based techniques; at the same time, we focused on all approaches and issues related to this promising technology. This transition might enable noninvasive screening for early diagnosis, individualized prediction of therapeutic response, and discovery of additional novel drug targets.

Mechanical Learning for Prediction of Sepsis-Associated Encephalopathy

Objective: The study aims to develop a mechanical learning model as a predictive model for predicting the appearance of sepsis-associated encephalopathy (SAE).Materials and Methods: The prediction model was developed in a primary cohort of 2,028 sepsis patients from June 2001 to October 2012, retrieved from the Medical Information Mart for Intensive Care (MIMIC III) database. Least absolute shrinkage and selection operator (LASSO) regression model was used for data dimension reduction and feature selection. The model was developed using multivariable logistic regression analysis. The performance of the nomogram has been evaluated in terms of calibration, discrimination, and clinical utility.Results: There were nine particular features in septic patients that were significantly associated with SAE. Predictors of individualized prediction nomograms included age, rapid sequential evaluation of organ failure (qSOFA), and drugs including carbapenem antibiotics, quinolone antibiotics, steroids, midazolam, H2-antagonist, diphenhydramine hydrochloride, and heparin sodium injection. The area under the curve (AUC) was 0.743, indicating good discrimination. The prediction model showed calibration curves with minor deviations from the ideal predictions. Decision curve analysis (DCA) suggested that the nomogram was clinically useful.Conclusion: We propose a nomogram for the individualized prediction of SAE with satisfactory performance and clinical utility, which could aid the clinician in the early detection and management of SAE.