Clinical validation of circulating GDF15/MIC-1 as a marker of response to docetaxel and survival in men with metastatic castration-resistant prostate cancer.

BACKGROUND: Elevated circulating growth differentiation factor (GDF15/MIC-1), interleukin 4 (IL4), and IL6 levels were associated with resistance to docetaxel in an exploratory cohort of men with metastatic castration-resistant prostate cancer (mCRPC). This study aimed to establish level 2 evidence of cytokine biomarker utility in mCRPC. METHODS: IntVal: Plasma samples at baseline (BL) and Day 21 docetaxel (n = 120). ExtVal: Serum samples at BL and Day 42 of docetaxel (n = 430). IL4, IL6, and GDF15 levels were measured by ELISA. Monocytes and dendritic cells were treated with 10% plasma from men with high or low GDF15 or recombinant GDF15. RESULTS: IntVal: Higher GDF15 levels at BL and Day 21 were associated with shorter overall survival (OS) (BL; p = 0.03 and Day 21; p = 0.004). IL4 and IL6 were not associated with outcomes. ExtVal: Higher GDF15 levels at BL and Day 42 predicted shorter OS (BL; p < 0.0001 and Day 42; p < 0.0001). Plasma from men with high GDF15 caused an increase in CD86 expression on monocytes (p = 0.03), but was not replicated by recombinant GDF15. CONCLUSIONS: Elevated circulating GDF15 is associated with poor prognosis in men with mCRPC receiving docetaxel and may be a marker of changes in the innate immune system in response to docetaxel resistance. These findings provide a strong rationale to consider GDF15 as a biomarker to guide a therapeutic trial of drugs targeting the innate immune system in combination with docetaxel in mCRPC.

A New δ-Globin Gene Variant: Hb A2-Yulin [δ46(CD5)Gly→Arg,HBD: C.139G > A].

We report a new δ-chain hemoglobin (Hb) variant observed in a 5-year-old female living in Yulin, Guangxi, China. Capillary electrophoresis revealed splitting of the Hb A2 peak into two fractions (Hb A2 and Hb A2 variant), and the Hb A2 variant was also detected by high-performance liquid chromatography. However, it could not be detected using matrix-assisted laser desorption lonization-time of flight mass spectrometry. CD41-42 (-TCTT) heterozygosity was observed on the HBB gene by PCR and reverse dot-blot hybridization. Sanger sequencing showed a new transition (G > A) at codon 46 of the HBD gene, resulting in glycine changing to arginine. Based on the patient's place of residence, the new variant was named Hb A2-Yulin [δ46(CD5)Gly→Arg,HBD:c.139G > A].

Interrater Agreement of CT Grading of Blunt Splenic Injuries: Does the AAST Grading Need to Be Reimagined?

Introduction: The Revised Organ Injury Scale (OIS) of the American Association for Surgery of Trauma (AAST) is the most widely accepted classification of splenic trauma. The objective of this study was to evaluate inter-rater agreement for CT grading of blunt splenic injuries. Methods: CT scans in adult patients with splenic injuries at a level 1 trauma centre were independently graded by 5 fellowship trained abdominal radiologists using the AAST OIS for splenic injuries - 2018 revision. The inter-rater agreement for AAST CT injury score, as well as low-grade (IIII) versus high-grade (IV-V) splenic injury was assessed. Disagreement in two key clinical scenarios (no injury versus injury, and high versus low grade) were qualitatively reviewed to identify possible sources of disagreement. Results: A total of 610 examinations were included. The inter-rater absolute agreement was low (Fleiss kappa statistic 0.38, P < 0.001), but improved when comparing agreement between low and high grade injuries (Fleiss kappa statistic of 0.77, P < .001). There were 34 cases (5.6%) of minimum two-rater disagreement about no injury vs injury (AAST grade ≥ I). There were 46 cases (7.5%) of minimum two-rater disagreement of low grade (AAST grade I-III) versus high grade (AAST grade IV-V) injuries. Likely sources of disagreement were interpretation of clefts versus lacerations, peri-splenic fluid versus subcapsular hematoma, application of adding multiple low grade injuries to higher grade injuries, and identification of subtle vascular injuries. Conclusion: There is low absolute agreement in grading of splenic injuries using the existing AAST OIS for splenic injuries.

Machine Learning Classification of Body Part, Imaging Axis, and Intravenous Contrast Enhancement on CT Imaging.

Purpose: The development and evaluation of machine learning models that automatically identify the body part(s) imaged, axis of imaging, and the presence of intravenous contrast material of a CT series of images. Methods: This retrospective study included 6955 series from 1198 studies (501 female, 697 males, mean age 56.5 years) obtained between January 2010 and September 2021. Each series was annotated by a trained board-certified radiologist with labels consisting of 16 body parts, 3 imaging axes, and whether an intravenous contrast agent was used. The studies were randomly assigned to the training, validation and testing sets with a proportion of 70%, 20% and 10%, respectively, to develop a 3D deep neural network for each classification task. External validation was conducted with a total of 35,272 series from 7 publicly available datasets. The classification accuracy for each series was independently assessed for each task to evaluate model performance. Results: The accuracies for identifying the body parts, imaging axes, and the presence of intravenous contrast were 96.0% (95% CI: 94.6%, 97.2%), 99.2% (95% CI: 98.5%, 99.7%), and 97.5% (95% CI: 96.4%, 98.5%) respectively. The generalizability of the models was demonstrated through external validation with accuracies of 89.7 - 97.8%, 98.6 - 100%, and 87.8 - 98.6% for the same tasks. Conclusions: The developed models demonstrated high performance on both internal and external testing in identifying key aspects of a CT series.

Machine Learning Detection and Characterization of Splenic Injuries on Abdominal Computed Tomography.

BACKGROUND: Multi-detector contrast-enhanced abdominal computed tomography (CT) allows for the accurate detection and classification of traumatic splenic injuries, leading to improved patient management. Their effective use requires rapid study interpretation, which can be a challenge on busy emergency radiology services. A machine learning system has the potential to automate the process, potentially leading to a faster clinical response. This study aimed to create such a system. METHOD: Using the American Association for the Surgery of Trauma (AAST), spleen injuries were classified into 3 classes: normal, low-grade (AAST grade I-III) injuries, and high-grade (AAST grade IV and V) injuries. Employing a 2-stage machine learning strategy, spleens were initially segmented from input CT images and subsequently underwent classification via a 3D dense convolutional neural network (DenseNet). RESULTS: This single-centre retrospective study involved trauma protocol CT scans performed between January 1, 2005, and July 31, 2021, totaling 608 scans with splenic injuries and 608 without. Five board-certified fellowship-trained abdominal radiologists utilizing the AAST injury scoring scale established ground truth labels. The model achieved AUC values of 0.84, 0.69, and 0.90 for normal, low-grade injuries, and high-grade splenic injuries, respectively. CONCLUSIONS: Our findings demonstrate the feasibility of automating spleen injury detection using our method with potential applications in improving patient care through radiologist worklist prioritization and injury stratification. Future endeavours should concentrate on further enhancing and optimizing our approach and testing its use in a real-world clinical environment.

Development a novel nomogram model for predicting significant hepatic histological changes in chronic hepatitis B virus carriers.

A proportion of chronic hepatitis B virus (HBV) carriers with normal alanine transaminase (ALT) present with significant liver histological changes (SLHC). To construct a noninvasive nomogram model to identify SLHC in chronic HBV carriers with different upper limits of normal (ULNs) for ALT. The training cohort consisted of 732 chronic HBV carriers who were stratified into four sets according to different ULNs for ALT: chronic HBV carriers I, II, III, and IV. The external validation cohort comprised 277 chronic HBV carriers. Logistic regression and least absolute shrinkage and selection operator analyses were applied to develop a nomogram model to predict SLHC. A nomogram model-HBGP (based on hepatitis B surface antigen, gamma-glutamyl transpeptidase, and platelet count) demonstrated good performance in diagnosing SLHC with area under the curve (AUCs) of 0.866 (95% confidence interval [CI]: 0.839-0.892) and 0.885 (95% CI: 0.845-0.925) in the training and validation cohorts, respectively. Furthermore, HBGP displayed high diagnostic values for SLHC with AUCs of 0.866 (95% CI: 0.839-0.892), 0.868 (95% CI: 0.838-0.898), 0.865 (95% CI: 0.828-0.901), and 0.853 (95% CI: 0.798-0.908) in chronic HBV carriers I, II, III, and IV, respectively. Additionally, HBGP showed greater ability in predicting SLHC compared with the existing predictors. HBGP has shown high predictive performance for SLHC, and thus may lead to an informed decision on the initiation of antiviral treatment.

The mediating effect of psychological empowerment on the relationship between work environment and clinical decision-making among midwives: a multicentre cross-sectional study.

BACKGROUND: Clinical decision-making is considered an essential behaviour in clinical practice. However, no research has been done to examine the associations among midwives' clinical decision-making, work environment and psychological empowerment. Thus, this study aimed to determine the influence of work environment on midwives' clinical decision-making and confirm the mediating role of psychological empowerment. METHOD: This study was designed as a multicentre cross-sectional study, and included 602 registered midwives from 25 public hospitals in China. A sociodemographic questionnaire, Work Environment Scale, Psychological Empowerment Scale and Clinical decision-making Scale were applied. A structural equation model was conducted to estimate the hypothesis model of the clinical decision-making among midwives and explore the potential mediating mechanism of midwives' clinical decision-making. This model was employed maximum likelihood estimation method and bootstrapping to examine the statistical significance. RESULTS: The mean score of clinical decision-making among midwives was 143.03 ± 14.22, at an intermediate level. The data of this hypothesis model fitted well, and the results showed that work environment positively affected psychological empowerment, which in turn positively affected clinical decision-making; psychological empowerment partly mediated the relationship between work environment and clinical decision-making among midwives. CONCLUSIONS: Midwives' clinical decision-making could be promoted directly or indirectly by providing a healthy work environment and improving psychological empowerment. It is essential for hospital managers to pay attention to the assessment of the midwives' work environment and actively improve it, such as establishing a supportive, fair and just workplace, and maintaining effective communication with midwives. Furthermore, managers can also promote midwives' clinical decision-making behaviour by enhancing their psychological empowerment via enhancing job autonomy.

Combined impact of lipidomic and genetic aberrations on clinical outcomes in metastatic castration-resistant prostate cancer.

BACKGROUND: Both changes in circulating lipids represented by a validated poor prognostic 3-lipid signature (3LS) and somatic tumour genetic aberrations are individually associated with worse clinical outcomes in men with metastatic castration-resistant prostate cancer (mCRPC). A key question is how the lipid environment and the cancer genome are interrelated in order to exploit this therapeutically. We assessed the association between the poor prognostic 3-lipid signature (3LS), somatic genetic aberrations and clinical outcomes in mCRPC. METHODS: We performed plasma lipidomic analysis and cell-free DNA (cfDNA) sequencing on 106 men with mCRPC commencing docetaxel, cabazitaxel, abiraterone or enzalutamide (discovery cohort) and 94 men with mCRPC commencing docetaxel (validation cohort). Differences in lipid levels between men ± somatic genetic aberrations were assessed with t-tests. Associations between the 3LS and genetic aberrations with overall survival (OS) were examined using Kaplan-Meier methods and Cox proportional hazard models. RESULTS: The 3LS was associated with shorter OS in the discovery (hazard ratio [HR] 2.15, 95% confidence interval [CI] 1.4-3.3, p < 0.001) and validation cohorts (HR 2.32, 95% CI 1.59-3.38, p < 0.001). Elevated plasma sphingolipids were associated with AR, TP53, RB1 and PI3K aberrations (p < 0.05). Men with both the 3LS and aberrations in AR, TP53, RB1 or PI3K had shorter OS than men with neither in both cohorts (p ≤ 0.001). The presence of 3LS and/or genetic aberration was independently associated with shorter OS for men with AR, TP53, RB1 and PI3K aberrations (p < 0.02). Furthermore, aggressive-variant prostate cancer (AVPC), defined as 2 or more aberrations in TP53, RB1 and/or PTEN, was associated with elevated sphingolipids. The combination of AVPC and 3LS predicted for a median survival of ~12 months. The relatively small sample size of the cohorts limits clinical applicability and warrants future studies. CONCLUSIONS: Elevated circulating sphingolipids were associated with AR, TP53, RB1, PI3K and AVPC aberrations in mCRPC, and the combination of lipid and genetic abnormalities conferred a worse prognosis. These findings suggest that certain genotypes in mCRPC may benefit from metabolic therapies.

A nomogram for predicting rectovaginal fistula after low anterior resection for rectal cancer.

PURPOSE: Rectovaginal fistula (RVF) is a complicated and troublesome complication of low anterior resection (LAR) for rectal cancer. We aimed to investigate the risk factors for post-LAR RVF and develop a predictive nomogram. METHODS: We performed a retrospective analysis of 821 female patients with rectal cancer who underwent LAR between October 2010 and October 2018. Logistic regression was performed to identify risk factors. A nomogram was developed to predict RVF. RESULTS: The incidence of post-LAR RVF was 3.4% (28/821). A multivariate analysis showed that the preoperative serum hemoglobin level (OR 2.449, 95% CI 1.144-5.239), the distance between the tumor and anal verge (OR 4.158, 95% CI 1.392-12.418), surgical procedure (OR 2.369, 95% CI 1.117-5.027), hysterectomy (OR 2.996, 95% CI 1.106-8.833), and bilateral oophorectomy (OR 5.823, 95% CI 1.639-20.689) were significantly associated with the development of RVF. A nomogram was developed, which showed a C-index of 0.824 (95% CI 0.730-0.918) and an adjusted C-index of 0.790. CONCLUSION: This study identified the preoperative serum hemoglobin level, the distance between the tumor and the anal verge, the type of surgical procedure, hysterectomy, and bilateral oophorectomy as predictors of post-LAR RVF. A nomogram was successfully developed. It could aid in the prediction of RVF in patients undergoing LAR.

Effect of FAK inhibitor VS-6063 (defactinib) on docetaxel efficacy in prostate cancer.

BACKGROUND: Docetaxel, the standard chemotherapy for metastatic castration-resistant prostate cancer (CRPC) also enhances the survival of patients with metastatic castration-sensitive prostate cancer (CSPC) when combined with androgen-deprivation therapy. Focal Adhesion Kinase (FAK) activation is a mediator of docetaxel resistance in prostate cancer cells. The aim of this study was to investigate the effect of the second generation FAK inhibitor VS-6063 on docetaxel efficacy in pre-clinical CRPC and CSPC models. METHODS: Docetaxel-resistant CRPC cells, mice with PC3 xenografts, and ex vivo cultures of patient-derived primary prostate tumors were treated with VS-6063 and/or docetaxel, or vehicle control. Cell counting, immunoblotting, and immunohistochemistry techniques were used to evaluate the treatment effects. RESULTS: Docetaxel and VS-6063 co-treatment caused a greater decrease in the viability of docetaxel-resistant CRPC cells, and a greater inhibition in PC3 xenograft growth compared to either monotherapy. FAK expression in human primary prostate cancer was positively associated with advanced tumor stage. Patient-derived prostate tumor explants cultured with both docetaxel and VS-6063 displayed a higher percentage of apoptosis in cancer cells, than monotherapy treatment. CONCLUSIONS: Our findings suggest that co-administration of the FAK inhibitor, VS-6063, with docetaxel represents a potential therapeutic strategy to overcome docetaxel resistance in prostate cancer.

Risk Factors for Early Postoperative Small Bowel Obstruction after Elective Colon Cancer Surgery: An Observational Study of 1,244 Consecutive Patients.

BACKGROUND: Early postoperative small bowel obstruction (EPSBO) is a common complication following colon cancer surgery. EPSBO is associated with increased hospital stays, mortality rates, and healthcare costs. The purpose of this study was to identify risk factors for EPSBO following elective colon cancer surgery. STUDY DESIGN: We retrospectively reviewed the clinicopathological variables of 1,244 patients with colon cancer who underwent partial colectomy from January 2000 to December 2014. A multivariable logistic regression model was used to identify risk factors for EPSBO. RESULTS: The EPSBO rate was 3.5%. In multivariate analysis, preoperative bowel obstruction (OR 2.378; 95% CI 0.986-5.735, p = 0.054), weight loss >10% of body weight (OR 3.029; 95% CI 1.000-9.178, p = 0.05), albumin level (in g/L; OR 0.966; 95% CI 0.937-0.996, p = 0.024), and surgical duration (in min; OR 1.008; 95% CI 1.003-1.012, p = 0.003) were significant predictors of EPSBO. CONCLUSION: EPSBO is more likely to develop in the presence of poor systemic conditions (e.g., weight loss >10% of body weight, hypoalbuminemia, and preoperative bowel obstruction) and following operations of longer duration. These predictors may facilitate the stratification of patients at risk for EPSBO following surgery for elective colon cancer.

A distinct plasma lipid signature associated with poor prognosis in castration-resistant prostate cancer.

Lipids are known to influence tumour growth, inflammation and chemoresistance. However, the association of circulating lipids with the clinical outcome of metastatic castration-resistant prostate cancer (CRPC) is unknown. We investigated associations between the plasma lipidome and clinical outcome in CRPC. Lipidomic profiling by liquid chromatography-tandem mass spectrometry was performed on plasma samples from a Phase 1 discovery cohort of 96 CRPC patients. Results were validated in an independent Phase 2 cohort of 63 CRPC patients. Unsupervised analysis of lipidomic profiles (323 lipid species) classified the Phase 1 cohort into two patient subgroups with significant survival differences (HR 2.31, 95% CI 1.44-3.68, p = 0.0005). The levels of 46 lipids were individually prognostic and were predominantly sphingolipids with higher levels associated with poor prognosis. A prognostic three-lipid signature was derived (ceramide d18:1/24:1, sphingomyelin d18:2/16:0, phosphatidylcholine 16:0/16:0) and was also associated with shorter survival in the Phase 2 cohort (HR 4.8, 95% CI 2.06-11.1, p = 0.0003). The signature was an independent prognostic factor when modelled with clinicopathological factors or metabolic characteristics. The association of plasma lipids with CRPC prognosis suggests a possible role of these lipids in disease progression. Further research is required to determine if therapeutic modulation of the levels of these lipids by targeting their metabolic pathways may improve patient outcome.

Phase 2 study of circulating microRNA biomarkers in castration-resistant prostate cancer.

BACKGROUND: Biomarkers of therapeutic response and prognosis are needed to assist in the sequencing of treatments for metastatic castration-resistant prostate cancer (CRPC). Previously in a Phase 1 discovery study, we identified 14 circulating microRNAs that were associated with response to docetaxel chemotherapy or overall survival. We performed a Phase 2 validation study to verify these findings. METHODS: Using real-time PCR, the levels of the 14 microRNAs were measured in plasma collected before and after the first cycle of docetaxel from a Phase 2 cohort of 89 patients. RESULTS: The microRNAs were not associated with docetaxel response in the Phase 2 cohort. Higher baseline levels of six microRNAs, predominantly of the miR-200 family, were confirmed to be associated with shorter overall survival. A microRNA signature comprising these six microRNAs predicted high-risk patients in the Phase 2 cohort with a hazard ratio of 4.12 (95% CI 2.20-7.70, P=0.000001). The signature was an independent predictor in multivariable analysis with clinicopathological factors. CONCLUSIONS: The association of circulating microRNAs with overall survival suggests their involvement in CRPC progression.

Loss of AZGP1 as a Superior Predictor of Relapse in Margin-Positive Localized Prostate Cancer.

BACKGROUND: Positive surgical margins (PSMs) in localized prostate cancer (PC) confer a two- to three-fold increased risk of biochemical relapse (BR). Absent/weak AZGP1 expression and Gleason grade ≥4 at the margin are each independent predictors of BR in patients with PSMs. Our study aimed to determine whether the biomarkers AZGP1 expression and Gleason grade at the site of a PSM are significant independent markers of biochemical and clinical relapse (CR) when modeled together and whether one of these biomarkers may be superior in its capacity to predict outcome. METHODS: A cohort of 275 consecutive patients with margin-positive localized PC following surgery were assessed for Gleason grade and AZGP1 expression at the PSM. BR-free survival was the primary end-point, while CR-free survival and PC-specific death were secondary endpoints. Kaplan-Meier Analysis and Cox Proportional Hazards Modeling were performed. RESULTS: Absent AZGP1 expression was significantly associated with increased risk of BR (P = 0.001) and PC-specific death (P = 0.02). Gleason grade ≥4 at PSM was associated with BR (P = 0.02), CR (P = 0.003), and PC-specific death (P = 0.004). On multivariable analysis, absent AZGP1 expression remained an independent predictor of BR (HR 2.4, 95%CI 1.5-3.9, P < 0.001) when modeled with Gleason grade at margin (HR 1.3, 95%CI 0.9-1.9, P = 0.16), preoperative PSA (P = 0.002), seminal vesicle involvement (P = 0.002), extraprostatic extension (P = 0.001), Gleason score (P = 0.01), adjuvant treatment (P = 0.75), linear length of the involved margin (P = 0.001) and margin number (P = 0.09). CONCLUSION: Absent AZGP1 expression is an independent predictor of BR in margin-positive localized PC and is associated with increased PC-specific mortality in a Phase II study. Absent AZGP1 expression was superior to Gleason grade at PSM in predicting relapse and should be incorporated into subsequent clinical trials of post-operative radiotherapy in men with margin-positive PC. Prostate 76:1491-1500, 2016. © 2016 Wiley Periodicals, Inc.

Laparoscopic transabdominal approach partial intersphincteric resection for low rectal cancer: surgical feasibility and intermediate-term outcome.

BACKGROUND: Traditionally, conventional intersphincteric resection requires a combined abdominal and perineal approach and a handsewn coloanal anastomosis procedure, which is difficult to accomplish via the perineal approach. A completely abdominal approach partial intersphincteric resection (APISR) with laparoscopy can simplify the anastomosis procedure. This study evaluated the intermediate-term oncological and functional results of laparoscopic versus open APISR for low rectal cancer. METHODS: A total of 137 consecutive patients with low rectal cancer who underwent APISR from January 2006 to August 2013 were retrospectively evaluated. Patient groups were classified into as open surgery (OP, n = 48) group and laparoscopy (LAP, n = 89). The primary endpoint was 3-year disease-free survival and the Wexner score for anal function. RESULTS: The LAP group had longer operating time, less intraoperative blood loss, and shorter hospital stay after surgery compared with the OP group. Median follow-up was 32.3 months. The local recurrence rates were similar in the two groups (LAP 3.2% vs. OP 6.1%; P = 0.652). The combined 3-year disease-free survival rate was 83.2% in the LAP group and 83.8% in the OP group (P = 0.857). Wexner scores were similar in the two groups (LAP 2.9 ± 4.5 vs. OP 3.1 ± 5.0). In the LAP group, 89.7% of patients had good continence compared with 91.4% in the OP group (P = 0.311). CONCLUSIONS: Laparoscopic APISR can be performed safely and offers similar intermediate-term oncological and functional outcome compared with the open procedure. The oncological adequacy requires long-term follow-up data.

A scoring system to predict inferior mesenteric artery lymph node metastasis and prognostic value of its involvement in rectal cancer.

PURPOSE: The aim of this study is to establish a prediction scoring system for inferior mesenteric artery (IMA) lymph node metastasis and to assess the prognostic impact of dissection of positive IMA node on patients with stage III rectal cancer. METHODS: A retrospective study was performed in 264 patients with stage III rectal cancer undergoing curative surgery. Clinicopathological, survival, and recurrence data were compared between 29 patients with positive IMA nodes and 235 patients with negative IMA nodes. Clinicopathological data which were found to be significantly associated with IMA nodal status were incorporated into a scoring system. RESULTS: In the training samples, tumor differentiation and preoperative serum CEA were significant predictors of IMA node metastasis in multivariate analysis, which were incorporated into a scoring system. Using receiver operating characteristic curve analysis, we determined a cutoff value of 46.5 for scores, at which the system's sensitivity was 86 % and specificity 61 %. When applied to testing sample, the sensitivity was 80 % and specificity 60 %. Survival analysis showed that 5-year disease-free survival rate (5-DFS) and 5-year overall survival (5-OS) in the positive IMA node group (24.4 and 27.6 %, respectively) were significantly lower than in the negative IMA node group (61.8 and 71.3 %, respectively) (P < 0.001). Furthermore, multivariate analysis indicated that IMA lymph node metastasis was an unfavorable independent prognostic factor for 5-DFS and 5-OS. CONCLUSIONS: IMA lymph node metastasis is an independent poor prognostic factor for stage III rectal cancer. The prediction scoring system for IMA node metastasis would be beneficial in determining the appropriate level of IMA ligation.

Performance of the Winning Algorithms of the RSNA 2022 Cervical Spine Fracture Detection Challenge.

Purpose To evaluate and report the performance of the winning algorithms of the Radiological Society of North America Cervical Spine Fracture AI Challenge. Materials and Methods The competition was open to the public on Kaggle from July 28 to October 27, 2022. A sample of 3112 CT scans with and without cervical spine fractures (CSFx) were assembled from multiple sites (12 institutions across six continents) and prepared for the competition. The test set had 1093 scans (private test set: n = 789; mean age, 53.40 years ± 22.86 [SD]; 509 males; public test set: n = 304; mean age, 52.51 years ± 20.73; 189 males) and 847 fractures. The eight top-performing artificial intelligence (AI) algorithms were retrospectively evaluated, and the area under the receiver operating characteristic curve (AUC) value, F1 score, sensitivity, and specificity were calculated. Results A total of 1108 contestants composing 883 teams worldwide participated in the competition. The top eight AI models showed high performance, with a mean AUC value of 0.96 (95% CI: 0.95, 0.96), mean F1 score of 90% (95% CI: 90%, 91%), mean sensitivity of 88% (95% Cl: 86%, 90%), and mean specificity of 94% (95% CI: 93%, 96%). The highest values reported for previous models were an AUC of 0.85, F1 score of 81%, sensitivity of 76%, and specificity of 97%. Conclusion The competition successfully facilitated the development of AI models that could detect and localize CSFx on CT scans with high performance outcomes, which appear to exceed known values of previously reported models. Further study is needed to evaluate the generalizability of these models in a clinical environment. Keywords: Cervical Spine, Fracture Detection, Machine Learning, Artificial Intelligence Algorithms, CT, Head/Neck Supplemental material is available for this article. © RSNA, 2024.

PCPro: a clinically accessible, circulating lipid biomarker signature for poor-prognosis metastatic prostate cancer.

BACKGROUND: Using comprehensive plasma lipidomic profiling from men with metastatic castration-resistant prostate cancer (mCRPC), we have previously identified a poor-prognostic lipid profile associated with shorter overall survival (OS). In order to translate this biomarker into the clinic, these men must be identifiable via a clinically accessible, regulatory-compliant assay. METHODS: A single regulatory-compliant liquid chromatography-mass spectrometry assay of candidate lipids was developed and tested on a mCRPC Discovery cohort of 105 men. Various risk-score Cox regression prognostic models of OS were built using the Discovery cohort. The model with the highest concordance index (PCPro) was chosen for validation and tested on an independent Validation cohort of 183 men. RESULTS: PCPro, the lipid biomarker, contains Cer(d18:1/18:0), Cer(d18:1/24:0), Cer(d18:1/24:1), triglycerides and total cholesterol. Within the Discovery and Validation cohorts, men who were PCPro positive had significantly shorter OS compared to those who were PCPro negative (Discovery: median OS 12.0 months vs 24.2 months, hazard ratio (HR) 3.75 [95% confidence interval (CI) 2.29-6.15], p < 0.001, Validation: median OS 13.0 months vs 25.7 months, HR = 2.13 [95% CI 1.46-3.12], p < 0.001). CONCLUSIONS: We have developed PCPro, a lipid biomarker assay capable of prospectively identifying men with mCRPC with a poor prognosis. Prospective clinical trials are required to determine if men who are PCPro positive will benefit from therapeutic agents targeting lipid metabolism.

Plasma Lipidomic Profiling Identifies Elevated Triglycerides as Potential Risk Factor in Chemotherapy-Induced Peripheral Neuropathy.

PURPOSE: Chemotherapy-induced peripheral neuropathy (CIPN) is a dose-limiting side effect of cytotoxic cancer treatment, often necessitating dose reduction (DR) or chemotherapy discontinuation (CD). Studies on peripheral neuropathy related to chemotherapy, obesity, and diabetes have implicated lipid metabolism. This study examined the association between circulating lipids and CIPN. METHODS: Lipidomic analysis was performed on plasma samples from 137 patients receiving taxane-based treatment. CIPN was graded using Total Neuropathy Score-clinical version (TNSc) and patient-reported outcome measure European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-CIPN (EORTC-QLQ-CIPN20). RESULTS: A significant proportion of elevated baseline lipids were associated with high-grade CIPN defined by TNSc and EORTC-QLQ-CIPN20 including triacylglycerols (TGs). Multivariable Cox regression on lipid species, adjusting for BMI, age, and diabetes, showed several elevated baseline TG associated with shorter time to DR/CD. Latent class analysis identified two baseline lipid profiles with differences in risk of CIPN (hazard ratio, 2.80 [95% CI, 1.50 to 5.23]; P = .0013). The higher risk lipid profile had several elevated TG species and was independently associated with DR/CD when modeled with other clinical factors (diabetes, age, BMI, or prior numbness/tingling). CONCLUSION: Elevated baseline plasma TG is associated with an increased risk of CIPN development and warrants further validation in other cohorts. Ultimately, this may enable therapeutic intervention.

Vision Transformer-based Decision Support for Neurosurgical Intervention in Acute Traumatic Brain Injury: Automated Surgical Intervention Support Tool.

Purpose To develop an automated triage tool to predict neurosurgical intervention for patients with traumatic brain injury (TBI). Materials and Methods A provincial trauma registry was reviewed to retrospectively identify patients with TBI from 2005 to 2022 treated at a specialized Canadian trauma center. Model training, validation, and testing were performed using head CT scans with binary reference standard patient-level labels corresponding to whether the patient received neurosurgical intervention. Performance and accuracy of the model, the Automated Surgical Intervention Support Tool for TBI (ASIST-TBI), were also assessed using a held-out consecutive test set of all patients with TBI presenting to the center between March 2021 and September 2022. Results Head CT scans from 2806 patients with TBI (mean age, 57 years ± 22 [SD]; 1955 [70%] men) were acquired between 2005 and 2021 and used for training, validation, and testing. Consecutive scans from an additional 612 patients (mean age, 61 years ± 22; 443 [72%] men) were used to assess the performance of ASIST-TBI. There was accurate prediction of neurosurgical intervention with an area under the receiver operating characteristic curve (AUC) of 0.92 (95% CI: 0.88, 0.94), accuracy of 87% (491 of 562), sensitivity of 87% (196 of 225), and specificity of 88% (295 of 337) on the test dataset. Performance on the held-out test dataset remained robust with an AUC of 0.89 (95% CI: 0.85, 0.91), accuracy of 84% (517 of 612), sensitivity of 85% (199 of 235), and specificity of 84% (318 of 377). Conclusion A novel deep learning model was developed that could accurately predict the requirement for neurosurgical intervention using acute TBI CT scans. Keywords: CT, Brain/Brain Stem, Surgery, Trauma, Prognosis, Classification, Application Domain, Traumatic Brain Injury, Triage, Machine Learning, Decision Support Supplemental material is available for this article. © RSNA, 2024 See also commentary by Haller in this issue.