SLC4A11 mediates ammonia import and promotes cancer stemness in hepatocellular carcinoma.

End stage liver disease is marked by portal hypertension, systemic elevations in ammonia, and development of hepatocellular carcinoma (HCC). While these clinical consequences of cirrhosis are well described, it remains poorly understood whether hepatic insufficiency and the accompanying elevations in ammonia contribute to HCC carcinogenesis. Using preclinical models, we discovered that ammonia entered the cell through the transporter SLC4A11 and served as a nitrogen source for amino acid and nucleotide biosynthesis. Elevated ammonia promoted cancer stem cell properties in vitro and tumor initiation in vivo. Enhancing ammonia clearance reduced HCC stemness and tumor growth. In patients, elevations in serum ammonia were associated with an increased incidence of HCC. Taken together, this study forms the foundation for clinical investigations using ammonia lowering agents as potential therapies to mitigate HCC incidence and aggressiveness.

Investigating the Obesity Paradox in Colorectal Cancer: An Analysis of Prospectively Collected Data in a Diverse Cohort.

BACKGROUND: Prior studies are inconclusive regarding the effect of obesity on mortality in persons with colorectal cancer (CRC). We sought to determine the association of pre-diagnosis body mass index (BMI) trajectories on mortality after CRC diagnosis. METHODS: Utilizing the Multiethnic Cohort, we included adults aged 18-75 between 1 January 1993 and 1 January 2019 with a diagnosis of CRC and at least three available BMIs. The primary exposure, BMI, was subjected to group-based trajectory modeling (GBTM). We evaluated all-cause and CRC-specific mortality, using Cox proportional hazard (PH) models. RESULTS: Of 924 persons, the median age was 60 years, and 54% were female. There was no statistically significant association between pre-cancer BMI trajectory and either all-cause or cancer-specific mortality. In competing risk analysis, the risk of CRC-specific mortality was higher for African Americans (HR = 1.56, 95% CI [1.00-2.43], p = 0.048) and smokers (HR = 1.59, 95% CI [1.10-2.32], p = 0.015). Risk of all-cause mortality was higher for Hawaiian persons (HR = 2.85, 95% CI [1.31-6.21], p = 0.009) and persons with diabetes (HR = 1.83, 95% CI [1.08-3.10], p = 0.026). CONCLUSIONS: Pre-diagnosis BMI trajectories were not associated with mortality after CRC diagnosis, whereas race/ethnicity, diabetes, and smoking were associated with an increased risk of death. Our findings suggest the obesity paradox alone does not account for mortality after CRC diagnosis.

Machine learning methods in automated detection of CT enterography findings in Crohn's disease: A feasibility study.

PURPOSE: Qualitative findings in Crohn's disease (CD) can be challenging to reliably report and quantify. We evaluated machine learning methodologies to both standardize the detection of common qualitative findings of ileal CD and determine finding spatial localization on CT enterography (CTE). MATERIALS AND METHODS: Subjects with ileal CD and a CTE from a single center retrospective study between 2016 and 2021 were included. 165 CTEs were reviewed by two fellowship-trained abdominal radiologists for the presence and spatial distribution of five qualitative CD findings: mural enhancement, mural stratification, stenosis, wall thickening, and mesenteric fat stranding. A Random Forest (RF) ensemble model using automatically extracted specialist-directed bowel features and an unbiased convolutional neural network (CNN) were developed to predict the presence of qualitative findings. Model performance was assessed using area under the curve (AUC), sensitivity, specificity, accuracy, and kappa agreement statistics. RESULTS: In 165 subjects with 29,895 individual qualitative finding assessments, agreement between radiologists for localization was good to very good (κ = 0.66 to 0.73), except for mesenteric fat stranding (κ = 0.47). RF prediction models had excellent performance, with an overall AUC, sensitivity, specificity of 0.91, 0.81 and 0.85, respectively. RF model and radiologist agreement for localization of CD findings approximated agreement between radiologists (κ = 0.67 to 0.76). Unbiased CNN models without benefit of disease knowledge had very similar performance to RF models which used specialist-defined imaging features. CONCLUSION: Machine learning techniques for CTE image analysis can identify the presence, location, and distribution of qualitative CD findings with similar performance to experienced radiologists.

Artificial Intelligence for Quantifying Cumulative Small Bowel Disease Severity on CT-Enterography in Crohn's Disease.

INTRODUCTION: Assessing the cumulative degree of bowel injury in ileal Crohn's disease (CD) is difficult. We aimed to develop machine learning (ML) methodologies for automated estimation of cumulative ileal injury on computed tomography-enterography (CTE) to help predict future bowel surgery. METHODS: Adults with ileal CD using biologic therapy at a tertiary care center underwent ML analysis of CTE scans. Two fellowship-trained radiologists graded bowel injury severity at granular spatial increments along the ileum (1 cm), called mini-segments. ML segmentation methods were trained on radiologist grading with predicted severity and then spatially mapped to the ileum. Cumulative injury was calculated as the sum (S-CIDSS) and mean of severity grades along the ileum. Multivariate models of future small bowel resection were compared with cumulative ileum injury metrics and traditional bowel measures, adjusting for laboratory values, medications, and prior surgery at the time of CTE. RESULTS: In 229 CTE scans, 8,424 mini-segments underwent analysis. Agreement between ML and radiologists injury grading was strong (κ = 0.80, 95% confidence interval 0.79-0.81) and similar to inter-radiologist agreement (κ = 0.87, 95% confidence interval 0.85-0.88). S-CIDSS (46.6 vs 30.4, P = 0.0007) and mean cumulative injury grade scores (1.80 vs 1.42, P < 0.0001) were greater in CD biologic users that went to future surgery. Models using cumulative spatial metrics (area under the curve = 0.76) outperformed models using conventional bowel measures, laboratory values, and medical history (area under the curve = 0.62) for predicting future surgery in biologic users. DISCUSSION: Automated cumulative ileal injury scores show promise for improving prediction of outcomes in small bowel CD. Beyond replicating expert judgment, spatial enterography analysis can augment the personalization of bowel assessment in CD.

Morphomics-informed population pharmacokinetic and physiologically-based pharmacokinetic modeling to optimize cefazolin surgical prophylaxis.

INTRODUCTION: Cefazolin is the leading antibiotic used to prevent surgical site infections worldwide. Consensus guidelines recommend adjustment of the cefazolin dose above and below 120 kg without regard to body composition. Algorithms exist to repurpose radiologic data into body composition (morphomics) and inform dosing decisions in obesity. OBJECTIVES: To compare the current standard of body weight to morphomic measurements as covariates of cefazolin pharmacokinetics and aid dose stratification of cefazolin in patients with obesity undergoing colorectal surgery. METHODS: This prospective study measured cefazolin plasma, fat, and colon tissue concentrations in colorectal surgery patients in order to develop a morphomics-informed population pharmacokinetic (PopPK) model to guide dose adjustments. A physiologically-based pharmacokinetic (PBPK) model was also constructed to inform tissue partitioning in morbidly obese patients (n = 21, body mass index ≥35 kg/m2 with one or more co-morbid conditions). RESULTS: Morphomics and pharmacokinetic data were available in 58 patients with a median [min, max] weight and age of 95.9 [68.5, 148.8] kg and 55 [25, 79] years, respectively. The plasma-to-subcutaneous fat partition coefficient was predicted to be 0.072 and 0.060 by the PopPK and PBPK models, respectively. The estimated creatinine clearance (eCLcr ) and body depth at the third lumbar vertebra (body depth_L3) were identified as covariates of cefazolin exposure. The probability of maintaining subcutaneous fat concentrations above 2 µg/mL for 100% of a 4-h surgical period was below 90% when eCLcr ≥105 mL/min and body depth_L3 ≥ 300 mm and less sensitive to the rate of infusion between 5 and 60 min. CONCLUSIONS: Kidney function and morphomics were more informative than body weight as covariates of cefazolin target site exposure. Data from more diverse populations, consensus on target cefazolin exposure, and comparative studies are needed before a change in practice can be implemented.

Using Artificial Intelligence to Predict Cirrhosis From Computed Tomography Scans.

INTRODUCTION: Undiagnosed cirrhosis remains a significant problem. In this study, we developed and tested an automated liver segmentation tool to predict the presence of cirrhosis in a population of patients with paired liver biopsy and computed tomography (CT) scans. METHODS: We used a cohort of 1,590 CT scans within the Morphomics database to train an automated liver segmentation model using 3D-U-Net and Google's DeeplLabv3+. Imaging features were then automatically calculated from an external test cohort of patients with chronic liver disease who had a paired liver biopsy and CT within 6 months of each other in January 2004-2012. Using gradient boosting decision trees, we developed multivariate models to predict the presence of histologic cirrhosis and evaluated with 5-fold cross-validated c-statistic. RESULTS: Our cohort had 351 patients; 96 patients had cirrhosis. Of the total cohort, 72 were postliver transplant. Both fibrosis (FIB)-4 and liver morphomics alone performed equally well with area under the receiving operating characteristics of 0.76 (95% confidence interval 0.70-0.81) and 0.71 (95% confidence interval 0.65-0.76), respectively ( P = 0.2). However, the combination of liver morphomics with laboratory values or liver morphomics with laboratory and demographic data resulted in significant improved performance with area under the receiving operating characteristics of 0.84 (0.80-0.89) and 0.85 (0.81-0.90), respectively, compared with FIB-4 alone ( P < 0.001). In a subgroup analysis, we also examined performance in patients without liver transplantation and saw similar augmentation of FIB-4. DISCUSSION: This proof-of-principle study demonstrates that automatically extracted features within CT scans can be combined with classic electronic medical record data to improve the prediction of cirrhosis in patients with liver disease. This tool may be used in both pretransplant and posttransplant patients and has the potential to improve our ability to detect undiagnosed cirrhosis.

Reference distributions of aortic calcification and association with Framingham risk score.

Evidence supporting aortic calcification as a leverageable cardiovascular risk factor is rapidly growing. Given aortic calcification's potential as a clinical correlate, we assessed granular vertebral-indexed calcification measurements of the abdominal aorta in a well curated reference population. We evaluated the relationship of aortic calcification measurements with Framingham risk scores. After exclusion, 4073 participants from the Reference Analytic Morphomic Population with varying vertebral levels were included. The percent of the aortic wall calcified was used to assess calcification burden at the L1-L4 levels. Descriptive statistics of participants, sex-specific vertebral indexed calcification measurements, relational plots, and relevant associations are reported. Mean aortic attenuation was higher in female than male participants. Overall, mean aortic calcium was higher with reference to inferior abdominal aortic measurements and demonstrated significant differences across all abdominal levels [L3 Area (mm[Formula: see text]): Females 6.34 (sd 16.60), Males 6.23 (sd 17.21); L3 Volume (mm[Formula: see text]): Females 178.90 (sd 474.19), Males 195.80 (sd 547.36); Wall Calcification (%): Females (L4) 6.97 (sd 16.03), Males (L3) 5.46 (13.80)]. Participants with elevated calcification had significantly higher Framingham risk scores compared to participants with normal calcification scores. Opportunistically measuring aortic calcification may inform further cardiovascular risk assessment and enhance cardiovascular event surveillance efforts.

AGA Clinical Practice Guideline on Systemic Therapy for Hepatocellular Carcinoma.

BACKGROUND & AIMS: Hepatocellular carcinoma (HCC), the most common primary liver cancer, remains a deadly cancer, with an incidence that has tripled in the United States since 1980. In recent years, new systemic therapies for HCC have been approved and a critical assessment of the existing data is necessary to balance benefits and harms and inform the development of evidence-based guidelines. METHODS: The American Gastroenterological Association formed a multidisciplinary group consisting of a Technical Review Panel and a Guideline Panel. The Technical Review Panel prioritized clinical questions and outcomes according to their importance for clinicians and patients and conducted an evidence review of systemic therapies in patients with advanced-stage HCC. The Grading of Recommendations Assessment, Development and Evaluation framework was used to assess evidence. The Guideline Panel reviewed the evidence and used the Evidence-to-Decision Framework to develop recommendations. RESULTS: The Panel reviewed the evidence, summarized in the Technical Review, for the following medications approved by the US Food and Drug Administration for HCC: first-line therapies: bevacizumab+atezolizumab, sorafenib, and lenvatinib; second-line therapies: cabozantinib, pembrolizumab, ramucirumab, and regorafenib; and other agents: bevacizumab, nivolumab, and nivolumab+ipilimumab. CONCLUSIONS: The Panel agreed on 11 recommendations focused on systemic therapy for HCC in patients who are not eligible for locoregional therapy or resection, those with metastatic disease and preserved liver function, those with poor liver function, and those on systemic therapy as adjuvant therapy.

Muscle mass affects paclitaxel systemic exposure and may inform personalized paclitaxel dosing.

AIMS: Patients with low muscle mass have increased risk of paclitaxel-induced peripheral neuropathy, which is dependent on systemic paclitaxel exposure. Dose optimization may be feasible through the secondary use of radiologic data for body composition. The objective of this study was to interrogate morphomic parameters as predictors of paclitaxel pharmacokinetics to identify alternative dosing strategies that may improve treatment outcomes. METHODS: This was a secondary analysis of female patients with breast cancer scheduled to receive 80 mg/m2 weekly paclitaxel infusions. Paclitaxel was measured at the end of initial infusion to estimate maximum concentration (Cmax ). Computed tomography (CT) scans were used to measure 29 body composition features for inclusion in pharmacokinetic modelling. Monte Carlo simulations were performed to identify infusion durations that limit the probability of exceeding Cmax > 2885 ng/mL, which was selected based on prior work linking this to an unacceptable risk of peripheral neuropathy. RESULTS: Thirty-nine patients were included in the analysis. The optimal model was a two-compartment pharmacokinetic model with T11 skeletal muscle area as a covariate of paclitaxel volume of distribution (Vd). Simulations suggest that extending infusion of the standard paclitaxel dose from 1 hour to 2 and 3 hours in patients who have skeletal muscle area 4907-7080 mm2 and <4907 mm2 , respectively, would limit risk of Cmax > 2885 ng/mL to <50%, consequently reducing neuropathy, while marginally increasing overall systemic paclitaxel exposure. CONCLUSION: Extending paclitaxel infusion duration in ~25% of patients who have low skeletal muscle area is predicted to reduce peripheral neuropathy while maintaining systemic exposure, suggesting that personalizing paclitaxel dosing based on body composition may improve treatment outcomes.

Effect of sarcopenia on survival in patients with cirrhosis: A meta-analysis.

BACKGROUND & AIMS: The association between sarcopenia and prognosis in patients with cirrhosis remains to be determined. In this study, we aimed to quantify the association between sarcopenia and the risk of mortality in patients with cirrhosis, stratified by sex, underlying liver disease etiology, and severity of hepatic dysfunction. METHODS: PubMed, Web of Science, EMBASE, and major scientific conference sessions were searched without language restriction through 13 January 2021 with an additional manual search of bibliographies of relevant articles. Cohort studies of ≥100 patients with cirrhosis and ≥12 months of follow-up that evaluated the association between sarcopenia, muscle mass and the risk of mortality were included. RESULTS: Twenty-two studies involving 6,965 patients with cirrhosis were included. The pooled prevalence of sarcopenia in patients with cirrhosis was 37.5% overall (95% CI 32.4%-42.8%), and was higher in male patients, those with alcohol-associated liver disease, those with Child-Pugh grade C cirrhosis, and when sarcopenia was defined by L3-SMI (third lumbar-skeletal muscle index). Sarcopenia was associated with an increased risk of mortality in patients with cirrhosis (adjusted hazard ratio [aHR] 2.30, 95% CI 2.01-2.63), with similar findings in a sensitivity analysis of patients with cirrhosis without hepatocellular carcinoma (aHR 2.35, 95% CI 1.95-2.83) and in subgroups stratified by sex, liver disease etiology, and severity of hepatic dysfunction. The association between quantitative muscle mass index and mortality further supports the association between sarcopenia and poor prognosis (aHR 0.95, 95% CI 0.93-0.98). There was no significant heterogeneity in any of our analyses. CONCLUSIONS: Sarcopenia was highly and independently associated with higher risk of mortality in patients with cirrhosis. LAY SUMMARY: The prevalence of sarcopenia and its association with death in patients with cirrhosis remain unclear. This meta-analysis indicated that sarcopenia affected about one-third of patients with cirrhosis and up to 50% of patients with alcohol-related liver disease or Child-Pugh class C cirrhosis. Sarcopenia was independently associated with an ∼2-fold higher risk of mortality in patients with cirrhosis. The mortality rate increased with greater severity or longer durations of sarcopenia. Increasing awareness about the importance of sarcopenia in patients with cirrhosis among stakeholders must be prioritized.

Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma.

BACKGROUND: Advances in imaging technology have the potential to transform the early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis. Computational "radiomic" techniques extract biomarker information from images which can be used to improve diagnosis and predict tumour biology. AIMS: To perform a systematic review on radiomic features in HCC diagnosis and prognosis, with a focus on reporting metrics and methodologic standardisation. METHODS: We performed a systematic review of all full-text articles published from inception through December 1, 2019. Standardised data extraction and quality assessment metrics were applied to all studies. RESULTS: A total of 54 studies were included for analysis. Radiomic features demonstrated good discriminatory performance to differentiate HCC from other solid lesions (c-statistics 0.66-0.95), and to predict microvascular invasion (c-statistic 0.76-0.92), early recurrence after hepatectomy (c-statistics 0.71-0.86), and prognosis after locoregional or systemic therapies (c-statistics 0.74-0.81). Common stratifying features for diagnostic and prognostic radiomic tools included analyses of imaging skewness, analysis of the peritumoural region, and feature extraction from the arterial imaging phase. The overall quality of the included studies was low, with common deficiencies in both internal and external validation, standardised imaging segmentation, and lack of comparison to a gold standard. CONCLUSIONS: Quantitative image analysis demonstrates promise as a non-invasive biomarker to improve HCC diagnosis and management. However, standardisation of protocols and outcome measurement, sharing of algorithms and analytic methods, and external validation are necessary prior to widespread application of radiomics to HCC diagnosis and prognosis in clinical practice.

Predicting outcomes of abdominal surgical emergencies in the elderly population using a CT muscle gauge.

BACKGROUND: Frailty has been shown to be an independent negative predictor of surgical outcomes in geriatric patients. Traditional measurements of muscle strength and mass are impractical in emergency settings, and computed tomography (CT)-measured skeletal muscle mass has been proposed as an alternative. However, the cutoff values for low muscle mass are still unknown, and their impact on abdominal emergencies in the elderly population is unclear. METHODS: A total of 462 young trauma patients aged 18-40 years were analyzed to establish sex-specific reference cutoff values for the CT-measured muscle index (MI) and muscle gauge (MG) values. The impacts of low MI and MG values were investigated in 1192 elderly patients (aged ≥ 65 years) undergoing abdominal surgery. RESULTS: The sex-specific cutoff values for MI and MG were determined by adopting European Working Group on Sarcopenia in Older People 2 guidelines. The correlation between MG and aging was significantly stronger than that between MI and ageing. With regard to the MG, the L4 psoas muscle gauge (L4 PMG) was further investigated in an elderly cohort owing to its high predictive value and ease of use in the clinical setting. A low L4 PMG value was an independent risk factor for overall complications and mortality in elderly patients with abdominal emergencies. CONCLUSION: The current study was the largest study investigating the correlations between MG values and aging in the Asian population. A low L4 PMG value may help surgeons during preoperative decision making regarding geriatric patients with abdominal emergencies.

The Use of Readily Available Longitudinal Data to Predict the Likelihood of Surgery in Crohn Disease.

BACKGROUND: Although imaging, endoscopy, and inflammatory biomarkers are associated with future Crohn disease (CD) outcomes, common laboratory studies may also provide prognostic opportunities. We evaluated machine learning models incorporating routinely collected laboratory studies to predict surgical outcomes in U.S. Veterans with CD. METHODS: Adults with CD from a Veterans Health Administration, Veterans Integrated Service Networks (VISN) 10 cohort examined between 2001 and 2015 were used for analysis. Patient demographics, medication use, and longitudinal laboratory values were used to model future surgical outcomes within 1 year. Specifically, data at the time of prediction combined with historical laboratory data characteristics, described as slope, distribution statistics, fluctuation, and linear trend of laboratory values, were considered and principal component analysis transformations were performed to reduce the dimensionality. Lasso regularized logistic regression was used to select features and construct prediction models, with performance assessed by area under the receiver operating characteristic using 10-fold cross-validation. RESULTS: We included 4950 observations from 2809 unique patients, among whom 256 had surgery, for modeling. Our optimized model achieved a mean area under the receiver operating characteristic of 0.78 (SD, 0.002). Anti-tumor necrosis factor use was associated with a lower probability of surgery within 1 year and was the most influential predictor in the model, and corticosteroid use was associated with a higher probability of surgery. Among the laboratory variables, high platelet counts, high mean cell hemoglobin concentrations, low albumin levels, and low blood urea nitrogen values were identified as having an elevated influence and association with future surgery. CONCLUSIONS: Using machine learning methods that incorporate current and historical data can predict the future risk of CD surgery.

USP11 mediates repair of DNA-protein cross-links by deubiquitinating SPRTN metalloprotease.

DNA-protein cross-links (DPCs) are toxic DNA lesions that interfere with DNA metabolic processes such as replication, transcription, and recombination. USP11 deubiquitinase participates in DNA repair, but the role of USP11 in DPC repair is not known. SPRTN is a replication-coupled DNA-dependent metalloprotease that cleaves proteins cross-linked to DNA to promote DPC repair. SPRTN function is tightly regulated by a monoubiquitin switch that controls SPRTN auto-proteolysis and chromatin accessibility during DPC repair. Previously, VCPIP1 and USP7 deubiquitinases have been shown to regulate SPRTN. Here, we identify USP11 as an SPRTN deubiquitinase. USP11 interacts with SPRTN and cleaves monoubiquitinated SPRTN in cells and in vitro. USP11 depletion impairs SPRTN deubiquitination and promotes SPRTN auto-proteolysis in response to formaldehyde-induced DPCs. Loss of USP11 causes an accumulation of unrepaired DPCs and cellular hypersensitivity to treatment with DPC-inducing agents. Our findings show that USP11 regulates SPRTN auto-proteolysis and SPRTN-mediated DPC repair to maintain genome stability.

The psoas muscle index distribution and influence of outcomes in an Asian adult trauma population: an alternative indicator for sarcopenia of acute diseases.

BACKGROUND: Sarcopenia has been shown to be an independent negative predictor in various diseases. The measurement of pre-defined criteria of skeletal muscle in patients with acute disease is usually unavailable. Therefore, we evaluate the psoas muscle area based on computed tomography (CT) imaging as an alternative for sarcopenia in an Asian trauma population. METHODS: 939 trauma patients were enrolled and had CT imaging performed primarily for trauma indications. The cross-sectional area of psoas muscle at the base of the fourth lumbar vertebral was measured on these CTs. Psoas muscle index (PMI) was calculated and analyzed to determine sex-specific cut-off values to define the "extremely low psoas muscle index" (ELPMI) group. RESULTS: Psoas muscle index was significantly higher in males (1065.09 ± 230.51 mm2/m2 in males vs 719.57 ± 147.39 mm2/m2 in females, p < 0.001) and decreased gradually with aging (p < 0.001). PMI of the subset of patients aged 18-40 (n = 462) weas analyzed to determine sex-specific cut-off values for ELPMI. PMI cut-off values for ELPMI (2 SD below mean) were 675 mm2/m2 for males and 490 mm2/m2 for females. The entire trauma cohort was further analyzed, and ELPMI was identified as an independent risk factor for a longer length of intensive unit stay (ß coefficient = 3.881, p = 0.011). CONCLUSION: Data from young trauma adults were used to establish cut-off values for ELPMI, which is a longer ICU stay predictor. These cut-off values for ELPMI may apply to other acute disease entities.

Assessment of a Deep Learning Model to Predict Hepatocellular Carcinoma in Patients With Hepatitis C Cirrhosis.

Importance: Deep learning, a family of machine learning models that use artificial neural networks, has achieved great success at predicting outcomes in nonmedical domains. Objective: To examine whether deep learning recurrent neural network (RNN) models that use raw longitudinal data extracted directly from electronic health records outperform conventional regression models in predicting the risk of developing hepatocellular carcinoma (HCC). Design, Setting, and Participants: This prognostic study included 48 151 patients with hepatitis C virus (HCV)-related cirrhosis in the national Veterans Health Administration who had at least 3 years of follow-up after the diagnosis of cirrhosis. Patients were identified by having at least 1 positive HCV RNA test between January 1, 2000, to January 1, 2016, and were followed up from the diagnosis of cirrhosis to January 1, 2019, for the development of incident HCC. A total of 3 models predicting HCC during a 3-year period were developed and compared, as follows: (1) logistic regression (LR) with cross-sectional inputs (cross-sectional LR); (2) LR with longitudinal inputs (longitudinal LR); and (3) RNN with longitudinal inputs. Data analysis was conducted from April 2018 to August 2020. Exposures: Development of HCC. Main Outcomes and Measures: Area under the receiver operating characteristic curve, area under the precision-recall curve, and Brier score. Results: During a mean (SD) follow-up of 11.6 (5.0) years, 10 741 of 48 151 patients (22.3%) developed HCC (annual incidence, 3.1%), and a total of 52 983 samples (51 948 [98.0%] from men) were collected. Patients who developed HCC within 3 years were older than patients who did not (mean [SD] age, 58.2 [6.6] years vs 56.9 [6.9] years). RNN models had superior mean (SD) area under the receiver operating characteristic curve (0.759 [0.009]) and mean (SD) Brier score (0.136 [0.003]) than cross-sectional LR (0.689 [0.009] and 0.149 [0.003], respectively) and longitudinal LR (0.682 [0.007] and 0.150 [0.003], respectively) models. Using the RNN model, the samples with the mean (SD) highest 51% (1.5%) of HCC risk, in which 80% of all HCCs occurred, or the mean (SD) highest 66% (1.2%) of HCC risk, in which 90% of all HCCs occurred, could potentially be targeted. Among samples from patients who achieved sustained virologic response, the performance of the RNN models was even better (mean [SD] area under receiver operating characteristic curve, 0.806 [0.025]; mean [SD] Brier score, 0.117 [0.007]). Conclusions and Relevance: In this study, deep learning RNN models outperformed conventional LR models, suggesting that RNN models could be used to identify patients with HCV-related cirrhosis with a high risk of developing HCC for risk-based HCC outreach and surveillance strategies.

Morphomic calcification score from clinical CT scans: A proxy for coronary artery calcium.

BACKGROUND: Screening of cardiovascular risk is essential in preventing cardiac events and quantifying asymptomatic risk. Coronary artery calcium (CAC) scores are a well-established in predicting cardiovascular risk, but require specialized computed tomography (CT) scans. Given the relationship of aortic calcification with cardiovascular risk, we sought to determine whether aortic calcification measures from incidental CT scans may approximate CAC. STUDY DESIGN: Retrospective CT scans and corresponding volumetric CAC scores were obtained from patients at the University of Michigan. Aortic calcifications were measured in 166 scans. Correlations between a novel morphomic calcium (MC) percent score and CAC score were evaluated using Kendall's correlation coefficients. Comparison of receiver operating characteristic (ROC) curves based on MC at different vertebral levels showed the highest predictive values for measures taken at L4. RESULTS: MC at L4 shows promise in predicting CAC (AUC 0.90 in non-contrast scans, 0.70 in post-contrast scans). Proposed MC threshold are (4.21% for best sensitivity, B 12.93% for balance, C = 19.26% for specificity) in scans without contrast enhancement and (D = 7.31 for sensitivity, E 8.06 for specificity) in scans with contrast enhancement. CONCLUSION: The MC score demonstrates promising potential in approximating CAC, particularly at the L4 level. The utilization of MC from incidental CT scans may be useful for assessment of cardiovascular risk. The ability to extract MC from contrast scans makes it especially valuable to patients receiving additional medical or surgical care. Recognition of high-risk patients would allow the use of indicated preventative strategies to avoid hard cardiovascular events in at risk patients.

Comparison of Body Size, Morphomics, and Kidney Function as Covariates of High-Dose Methotrexate Clearance in Obese Adults with Primary Central Nervous System Lymphoma.

BACKGROUND: High-dose methotrexate (HD-MTX) is used to treat primary central nervous system lymphoma (PCNSL), but potential differences in MTX clearance (CL) due to obesity have not been studied. We characterized the relationship between HD-MTX CL and computed tomography (CT)-generated body composition (morphomic), body size descriptors, and laboratory measurements in a cohort of obese and non-obese patients with PCNSL. METHODS: Medical records from adult patients with PCNSL treated with HD-MTX over a 10-year period were queried. Individuals with CT data within 30 days of the first cycle of treatment were included. Population pharmacokinetic analysis was performed using a 2-compartment base structural model. We specifically compared body surface area (BSA) to standard body size, morphomic, and renal function estimation methods as covariates of HD-MTX CL. RESULTS: The final data set consisted of non-obese (n=45) and obese (n=28) patients with 291 observations (3-7 samples per patient) with a mean (standard deviation) weight of 69.8 (11.6) kg and 104 (14.9) kg, respectively (p=0.0001). Vertebral body height was more informative than BSA of MTX CL. Similarly, a CL model incorporating age, albumin, and serum creatinine was more informative than kidney function equations and body size. The final model of MTX CL was based on age, albumin, serum creatinine, and vertebral body height. CONCLUSIONS: Common clinical variables coupled with vertebral body height are more predictive of first cycle MTX CL than BSA, alternate body size descriptors, and commonly used kidney function equations.

Assessing Small Bowel Stricturing and Morphology in Crohn's Disease Using Semi-automated Image Analysis.

BACKGROUND: Evaluating structural damage using imaging is essential for the evaluation of small intestinal Crohn's disease (CD), but it is limited by potential interobserver variation. We compared the agreement of enterography-based bowel damage measurements collected by experienced radiologists and a semi-automated image analysis system. METHODS: Patients with small bowel CD undergoing a CT-enterography (CTE) between 2011 and 2017 in a tertiary care setting were retrospectively reviewed. CT-enterography studies were reviewed by 2 experienced radiologists and separately underwent automated computer image analysis using bowel measurement software. Measurements included maximum bowel wall thickness (BWT-max), maximum bowel dilation (DIL-max), minimum lumen diameter (LUM-min), and the presence of a stricture. Measurement correlation coefficients and paired t tests were used to compare individual operator measurements. Multivariate regression was used to model identification of strictures using semi-automated measures. RESULTS: In 138 studies, the correlation between radiologists and semi-automated measures were similar for BWT-max (r = 0.724, 0.702), DIL-max (r = 0.812, 0.748), and LUM-min (r = 0.428, 0.381), respectively. Mean absolute measurement difference between semi-automated and radiologist measures were no different from the mean difference between paired radiologists for BWT-max (1.26 mm vs 1.12 mm, P = 0.857), DIL-max (2.78 mm vs 2.67 mm, P = 0.557), and LUM-min (0.54 mm vs 0.41 mm, P = 0.596). Finally, models of radiologist-defined intestinal strictures using automatically acquired measurements had an accuracy of 87.6%. CONCLUSION: Structural bowel damage measurements collected by semi-automated approaches are comparable to those of experienced radiologists. Radiomic measures of CD will become an important new data source powering clinical decision-making, patient-phenotyping, and assisting radiologists in reporting objective measures of disease status.

Circumscribed Choroidal Hemangioma: Visual Outcome in the Pre-Photodynamic Therapy Era versus Photodynamic Therapy Era in 458 Cases.

PURPOSE: To analyze visual outcomes after treatment of choroidal hemangioma in the pre-photodynamic therapy (PDT) era versus PDT era. DESIGN: Retrospective, comparative case series. PARTICIPANTS: A total of 458 patients with circumscribed choroidal hemangioma. METHODS: Comparison of hemangioma managed in the pre-PDT (1967-2001) era versus PDT (2002-2018) era. MAIN OUTCOME MEASURE: Visual acuity outcome. RESULTS: A total of 458 tumors were treated over this 51-year period. A comparison (pre-PDT [n = 220 cases] vs. PDT [n = 238 cases]) revealed PDT era patients were of older mean age (48.9 vs. 53.8 years, P = 0.002) and were more likely to have systemic hypertension (17.7% vs. 33.8%, P < 0.001), tumor location in the macula (57.4% vs. 67.5%, P = 0.01), subretinal fluid on OCT (33.3% vs. 70.7%, P = 0.01), and greater extent of overlying lipofuscin (P = 0.001). Findings of tumor basal diameter and thickness and fluorescein and indocyanine green angiography were no different in the 2 eras. Treatment (pre-PDT vs. PDT) included argon laser photocoagulation (42.1% vs. 0.4%), PDT (0% vs. 43.8%), transpupillary thermotherapy (0% vs. 0.4%), plaque radiotherapy (7.0% vs. 5.2%), external beam radiotherapy (1.4% vs. 1.3%), enucleation (0.9% vs. 0.4%), and observation (48.6% vs. 47.6%). After treatment, patients in the PDT era demonstrated better mean logarithm of the minimum angle of resolution visual acuity (1.28 vs. 0.51, P < 0.001) (Snellen equivalent 20/400 vs. 20/63, P < 0.001). Final visual acuity was ≥20/40 for those with entering vision of ≥20/40 (59.6% vs. 74.7%, P = 0.001) and for those with entering vision of 20/50-20/200 (25.4% vs. 47.3%, P < 0.001). CONCLUSIONS: Management of choroidal hemangioma in the PDT era has allowed for significantly better visual outcome compared with the pre-PDT era, with mean final visual acuity of 20/400 (pre-PDT era) versus 20/63 (PDT era).