RESUMEN
BACKGROUND: There are limited prospective data among overweight and obese individuals on the prevalence of advanced fibrosis, and cirrhosis using advanced MRI-based methods in the USA. The aim of this study was to fill that gap in knowledge by prospectively determining the MRI-based prevalence of steatotic liver disease (SLD) and its subcategories, advanced fibrosis and cirrhosis among overweight and obese individuals residing in the USA. METHODS: This is a cross-sectional analysis of prospectively enrolled overweight or obese adults aged 40-75 years from primary care and community-based settings in Southern California. Participants were classified as having SLD if MRI proton density fat fraction ≥5%, and subclassified as metabolic dysfunction-associated steatotic liver disease (MASLD), metabolic dysfunction and alcohol-associated liver disease (MetALD) and alcohol-related liver disease (ALD) consistently with the new nomenclature guidance per AASLD-EASL-ALEH. Advanced fibrosis and cirrhosis were defined as magnetic resonance elastography (MRE) ≥3.63 kPa and MRE ≥4.67 kPa, respectively. RESULTS: The cohort included 539 participants with mean (±SD) age of 51.5 (±13.1) years and body mass index of 32.6 (±6.2) kg/m2, respectively. The prevalence of SLD, advanced fibrosis and cirrhosis was 75%, 10.8% and 4.5%, respectively. The prevalence of MASLD, MetALD and ALD was 67.3%, 4.8% and 2.6%, respectively. There was no difference in prevalence of advanced fibrosis and cirrhosis among subcategories. CONCLUSIONS: Using advanced MRI methods among community-dwelling overweight and obese adults, the prevalence of cirrhosis was 4.5%. Most common SLD subcategory was MASLD with 67% of individuals, whereas MetALD and ALD were less common. Systematic screening for advanced fibrosis among overweight/obese adults may be considered.
RESUMEN
While rare, cases of community-acquired Pseudomonas aeruginosa (PsA) enterocolitis have been reported and are associated with recent antibiotic use and immunocompromised hosts. Here we present a 29-year-old immunocompetent female with newly diagnosed alcoholic cirrhosis that presents with bloody diarrhea and was found to have PsA in her stool culture. This case is unique as our patient does not have a history of recent antibiotic use or prior history of immunosuppression. However, immune dysfunction in cirrhosis results in defects in both innate and acquired immunity, thus predisposing our patient to PsA-associated diarrhea. Overall, this case showcases that, while considered immunocompetent, cirrhotic patients are predisposed to rare infections such as PsA in the community due to defects in their immune system.
RESUMEN
Despite remarkable advances in immunotherapy, melanoma remains a significant cause of cancer mortality. Many factors concerning melanoma mortality are poorly understood, posing an obstacle to optimal care. We conducted a retrospective observational cohort study of 183 patients with metastatic melanoma who died following immunotherapy treatment to investigate sites of metastases at death, settings of death, and mechanisms of death. The median time from metastatic diagnosis to death was 16.1 months (range 0.3-135.1 months). Most patients experienced hospitalization within 3 months before death (80.3%), with 31.7% dying while hospitalized, 31.2% while in inpatient hospice, and 29.4% while in home hospice. The most common sites of metastases at death were distant lymph nodes (62.8%), lung (57.9%), liver (50.8%), brain (38.8%), and bone (37.7%). The most common causes of death were progressive failure to thrive (57.5%), respiratory failure (22.4%), and infection (21.8%); the vast majority (87.9%) of patients died from melanoma-specific causes. Overall, 10.9% of patients in our cohort had survival >5 years after metastatic diagnosis, and 76.2% of long-term survivors died due to melanoma. This study describes factors associated with melanoma mortality, highlighting an ongoing need for therapeutic advancements.
RESUMEN
BACKGROUND: Alcohol cessation is the only intervention that both prevents and halts the progressions of alcohol-associated liver disease. The aim of this study was to assess the relationship between a return to alcohol use and consultation with hepatology in treatment-seeking patients with alcohol use disorder (AUD). METHODS: Two hundred forty-two patients with AUD were enrolled in an inpatient treatment program, with hepatology consultation provided for 143 (59%) patients at the request of the primary team. Patients not seen by hepatology served as controls. The primary outcome was any alcohol use after discharge assessed using AUDIT-C at 26 weeks after discharge. RESULTS: For the primary endpoint, AUDIT at week 26, 61% of the hepatology group and 28% of the controls completed the questionnaire (p=0.07). For the secondary endpoint at week 52, these numbers were 22% and 11% (p = 0.6). At week 26, 39 (45%) patients in the hepatology group versus 31 (70%) controls (p = 0.006) returned to alcohol use. Patients evaluated by hepatology had decreased rates of hazardous alcohol use compared to controls, with 36 (41%) versus 29 (66%) (p = 0.008) of the patients, respectively, reporting hazardous use. There were no significant differences in baseline characteristics between groups and no difference in rates of prescribing AUD therapy. There was no difference in outcomes at 52 weeks. CONCLUSIONS: Patients evaluated by hepatology had significantly lower rates of return to alcohol use and lower rates of hazardous drinking at 26 weeks but not at 52 weeks. These findings suggest that hepatology evaluation during inpatient treatment of AUD may lead to decreased rates of early return to alcohol use.
Asunto(s)
Alcoholismo , Gastroenterología , Hepatopatías Alcohólicas , Humanos , Alcoholismo/epidemiología , Alcoholismo/terapia , Alta del Paciente , Pacientes Internos , Hepatopatías Alcohólicas/terapia , Derivación y ConsultaRESUMEN
Alcohol-related liver disease (ALD) is the leading indication for liver transplantation worldwide. Since Mathurin et al. described their experience in providing early liver transplantation for patients with ALD in 2011, other centers have followed suit with generally favorable survival outcomes. This patient population poses a unique clinical challenge given the expedited nature of the evaluation and the lack of any significant sobriety period prior to transplantation. The SALT (Sustained Alcohol Use Post-Liver Transplant) score is a standardized psychometric tool increasingly used to help stratify the risk of relapse and guide listing decisions for these challenging clinical situations. In 2018, our center introduced a protocol for early liver transplantation for acute alcohol-related hepatitis (AAH). In this article, we offer a retrospective review of 26 patients transplanted between May 2018 and May 2021, including at least 1-year follow-up, and compare outcomes to initial SALT scores; we further identify additional factors that may impact post-transplant success. As transplant committees continue to weigh the ethical dilemma of denying lifesaving treatment against the obligation to remain stewards of a limited resource, we aim to contribute to a more nuanced understanding of risk regarding early transplantation for ALD.
Asunto(s)
Hepatitis Alcohólica , Hepatopatías Alcohólicas , Trasplante de Hígado , Humanos , Trasplante de Hígado/efectos adversos , Hepatitis Alcohólica/etiología , Hepatitis Alcohólica/cirugía , Hepatopatías Alcohólicas/etiología , Hepatopatías Alcohólicas/cirugía , Consumo de Bebidas Alcohólicas , RecurrenciaRESUMEN
BACKGROUND AND AIMS: The widespread use of peroral endoscopic myotomy (POEM) has revolutionized the management of esophageal motility disorders (EMDs). The introduction of an endoluminal functional lumen imaging probe (EndoFLIP) can serve as a complimentary diagnostic tool to assess the mechanical properties (i.e., pressure, diameter, distensibility and topography) of the esophagus. During EndoFLIP measurements, different anesthesia techniques may induce variable degrees of neuromuscular blockade, potentially affecting esophageal motility and altering the results of EndoFLIP metrics. Our study aimed to compare the impact of using total intravenous anesthesia (TIVA) versus general anesthesia with inhalational anesthetics (GAIA) on diagnostic EndoFLIP measurements. METHODS: We conducted a retrospective study of all adult patients (≥18 years) undergoing EndoFlip during the POEM procedure at our institution between February 2017 and February 2022. We obtained the differences in pressure, diameter, and distensibility index using propofol-based TIVA vs sevoflurane-based GAIA with a 30ml and 60ml balloon. The differences were divided into terciles and compared between diagnoses using univariate comparisons and logistic regression models. RESULTS: 49 patients were included (39% Type 1 achalasia, 43% Type 2 or 3 achalasia, and 18% jackhammer esophagus (JE)). Compared to spastic disorders (Type 2, 3 and JE), Type 1 had lower values of pressure differences at 60 mL in univariate (3.75 vs 15.20 p=0.001) and multivariate (aOR 0.89 95%CI 0.82-0.978) analyses. Compared to Type 1, Type 2 and 3 had higher rates of pressure differences at 60 mL in univariate (9.85 vs 3.75 p=0.04); and nearly reached significance in multivariate analysis (1.09 95%CI 1-1.20). Compared to Type 1, JE demonstrated higher values in pressure differences at 60 mL (27.7 vs 3.75 p<0.001) CONCLUSION: Esophageal pressure, as measured by EndoFLIP, was significantly reduced when patients were sedated with sevoflurane-based GAIA. The use sevoflurane-based GAIA for diagnostic EndoFLIP may potentially lead to the misclassification of spastic disorders as Type I achalasia. Therefore, propofol-based TIVA should be considered over sevoflurane-based GAIA for sedation during the diagnostic test.
RESUMEN
Background: Proton beam therapy (PBT) is a non-surgical treatment that spares adjacent tissues compared to photon radiation and useful for Hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (iCCA). We present a single center experience in HCC and iCCA treated with Pencil Beam Scanning (PBS) PBT. Methods: Forty-four consecutive patients (22 patients in each group) receiving PBT were included and reviewed. PBT was delivered with hypofractionated or stereotactic body radiation therapy (SBRT) using PBS. Tumor size was approximated by clinical target volume (CTV). Outcomes were evaluated with Kaplan-Meier and liver toxicity was determined by MELD-Na and albumin-bilirubin (ALBI) grade. Results: Median follow up was 38.7 months, fourteen (35%) had multifocal disease and median CTV was 232.5cc. Four (9%) and 40 (91%) patients received SBRT and hypofractionated radiation, respectively. Two year overall survival was statistically higher for HCC (entire group: 68.9% months [95% CI: 61.3 - 76.3%]; iCCA: 49.8% [95% CI: 38.5% - 61.1%]; HCC: 89.4% [95% CI: 82.3 - 96.5%]; P <0.005). There was no statistical difference in progression-free survival or freedom from local failure. Biologically Equivalent Dose (BED) was greater than or equal to 80.5Gy in 37 (84%) patients. All iCCA patients had stable or improved ALBI grade following treatment. ALBI grade was stable in 83% of HCC patients and average MELD-Na score remained stable. Tumor size, pretreatment liver function, and total radiation dose were not associated with liver toxicity. Conclusions: PBT for unresectable HCC and iCCA is safe and effective, even for large and multifocal tumors. Liver function was preserved even in those with baseline cirrhosis in this advanced population with large tumors.
RESUMEN
Brain exposure of systemically administered biotherapeutics is highly restricted by the blood-brain barrier (BBB). Here, we report the engineering and characterization of a BBB transport vehicle targeting the CD98 heavy chain (CD98hc or SLC3A2) of heterodimeric amino acid transporters (TVCD98hc). The pharmacokinetic and biodistribution properties of a CD98hc antibody transport vehicle (ATVCD98hc) are assessed in humanized CD98hc knock-in mice and cynomolgus monkeys. Compared to most existing BBB platforms targeting the transferrin receptor, peripherally administered ATVCD98hc demonstrates differentiated brain delivery with markedly slower and more prolonged kinetic properties. Specific biodistribution profiles within the brain parenchyma can be modulated by introducing Fc mutations on ATVCD98hc that impact FcγR engagement, changing the valency of CD98hc binding, and by altering the extent of target engagement with Fabs. Our study establishes TVCD98hc as a modular brain delivery platform with favorable kinetic, biodistribution, and safety properties distinct from previously reported BBB platforms.
Asunto(s)
Barrera Hematoencefálica , Encéfalo , Animales , Ratones , Distribución Tisular , Anticuerpos , Ingeniería , Macaca fascicularisRESUMEN
OBJECTIVES: To investigate the wear resistance of conventional, CAD-milled and 3D-printed denture teeth in vitro with simulated aging. To use the collected data to train single time series sample model LSTM and provide proof of concept. METHODS: Six denture teeth materials (Three Conventional; Double-cross linked PMMA (G1), Nanohybrid composite (G2), PMMA with microfillers (G3), CAD-milled (G4), two 3D-printed teeth (G5, G6) (Total n = 60) underwent simulation for 24 and 48 months of linear reciprocating wear using a universal testing machine (UFW200, NeoPlus) under 49 N load, 1 Hz and linear stroke of 2 mm in an artificial saliva medium. Single samples were parsed through Long Short-Term Memory (LSTM) neural network model using Python. To determine minimal simulation times, multiple data splits for training were trialled (10/20/30/40%). Scanning electron microscopy (SEM) was performed for material surface evaluation. RESULTS: 3D printed tooth material (G5) had the lowest wear resistance (59 ± 35.71 µm) whereas conventional PMMA with microfillers (G3) shown the highest wear rate (303 ± 0.06 µm) after 48 months of simulation. The LSTM model successfully predicted up to 48 months wear using 30% of the collected data. Compared with the actual data, the model had a root-mean-square error range between 6.23 and 88.56 µm, mean-absolute-percentage-error 12.43-23.02% and mean-absolute-error 7.47-70.71 µm. SEM images revealed additional plastic deformations and chipping of materials, that may have introduced data artifacts. CONCLUSIONS: 3D printed denture teeth materials showed the lowest wear out of all studied for 48 months simulation. LSTM model was successfully developed to predict wear of various denture teeth. The developed LSTM model has the potential to reduce simulation duration and specimen number for wear testing of various dental materials, while potentially improving the accuracy and reliability of wear testing predictions. This work paves the way for generalized multi-sample models enhanced with empirical information.
Asunto(s)
Redes Neurales de la Computación , Polimetil Metacrilato , Ensayo de Materiales , Reproducibilidad de los Resultados , Propiedades de Superficie , DentadurasRESUMEN
INTRODUCTION: Pediatric surgery applicants are increasingly pursuing research in non-traditional fields including surgical innovation. This study aims to evaluate the relative value that pediatric surgeons involved in fellow selection place on innovation experience compared to traditional research. METHODS: A cross-sectional web-based survey of American Pediatric Surgical Association members involved in the selection of pediatric surgical fellows was conducted. Respondents reported their own innovation experience and were asked to identify valuable traits of applicants who completed an innovation fellowship. They rated the value of traditional research metrics including publications, presentations, and advanced degrees compared to patents and other innovation-related metrics. Comparisons were made between those with and without innovation experience with respect to gender, years in practice, and institutional role. RESULTS: One hundred thirty respondents were involved in pediatric surgery fellow selection. Innovation work was felt to be equal to or more valuable than basic science by 75% of respondents (84% vs. clinical/outcomes, 93% vs. other non-traditional, 72% vs. other clinical fellowships). Commonly cited concerns included "fewer publications" (21%) and "preoccupation with financial reward" (19%). The most valuable innovation-related metrics were "developing a novel surgical procedure" (67%) and "developing a novel device" (58%). When asked if the respondent would advise a junior resident to pursue an innovation fellowship, 49% would, 9% would not, and 43% were unsure. Seventeen percent expressed concern for match success. CONCLUSION: Innovation experience is generally viewed positively by pediatric surgeons involved in fellow selection. However, applicants and mentors would benefit from focusing on traditional academic outputs to ensure competitiveness. TYPE OF STUDY: Cross-sectional observational study. LEVEL OF EVIDENCE: III.
Asunto(s)
Internado y Residencia , Especialidades Quirúrgicas , Cirujanos , Niño , Humanos , Estados Unidos , Becas , Estudios Transversales , Actitud , Encuestas y CuestionariosRESUMEN
Virtual Reality (VR) allows users to interact with 3D immersive environments and has the potential to be a key technology across many domain applications, including access to a future metaverse. Yet, consumer adoption of VR technology is limited by cybersickness (CS)-a debilitating sensation accompanied by a cluster of symptoms, including nausea, oculomotor issues and dizziness. A leading problem is the lack of automated objective tools to predict or detect CS in individuals, which can then be used for resistance training, timely warning systems or clinical intervention. This paper explores the spatiotemporal brain dynamics and heart rate variability involved in cybersickness and uses this information to both predict and detect CS episodes. The present study applies deep learning of EEG in a spiking neural network (SNN) architecture to predict CS prior to using VR (85.9%, F7) and detect it (76.6%, FP1, Cz). ECG-derived sympathetic heart rate variability (HRV) parameters can be used for both prediction (74.2%) and detection (72.6%) but at a lower accuracy than EEG. Multimodal data fusion of EEG and sympathetic HRV does not change this accuracy compared to ECG alone. The study found that Cz (premotor and supplementary motor cortex) and O2 (primary visual cortex) are key hubs in functionally connected networks associated with both CS events and susceptibility to CS. F7 is also suggested as a key area involved in integrating information and implementing responses to incongruent environments that induce cybersickness. Consequently, Cz, O2 and F7 are presented here as promising targets for intervention.
RESUMEN
BACKGROUND: Laparoscopic gastrostomy is commonly performed for durable enteral access in children. T-fasteners have been used intraoperatively to achieve a secure gastropexy, traditionally using external bolsters. We compare the safety profile of a modified paired T-fastener technique to standard laparoscopic-assisted suture gastropexy. METHODS: A retrospective matched case-control study was performed of pediatric patients who underwent laparoscopic gastrostomy at a single center from 2015 to 2021. In the paired T-fastener group, pairs of T-fasteners were passed into the stomach in a square configuration, allowing the suture pairs to be tied subcutaneously. This cohort was matched in a 1:2 fashion with age, sex, and body mass index or weight-matched controls who underwent laparoscopic gastrostomy with buried transabdominal gastropexy. RESULTS: Thirty patients underwent laparoscopic gastrostomy using the paired T-fastener technique and were matched to 60 controls. There was no significant difference in median operative time or 30-day complication rates between the groups, but the paired T-fastener technique significantly reduced the number of trocars required, and it was used for patients with thicker abdominal walls. CONCLUSION: We demonstrate the modified paired T-fastener technique as a safe, efficient means of gastropexy in pediatric laparoscopic gastrostomy. The paired T-fastener approach eliminates external bolsters, reduces additional trocars, and may be advantageous for thicker abdominal walls while maintaining a similar complication profile to standard laparoscopic gastrostomy.
Asunto(s)
Gastrostomía , Laparoscopía , Humanos , Niño , Gastrostomía/métodos , Estudios Retrospectivos , Estudios de Casos y Controles , Estómago/cirugía , Laparoscopía/métodosRESUMEN
WHIM syndrome is an autosomal dominant immunodeficiency disorder caused by gain-of-function mutations in chemokine receptor CXCR4 that promote severe panleukopenia because of retention of mature leukocytes in the bone marrow (BM). We previously reported that Cxcr4-haploinsufficient (Cxcr4+/o) hematopoietic stem cells (HSCs) have a strong selective advantage for durable hematopoietic reconstitution over wild-type (Cxcr4+/+) and WHIM (Cxcr4+/w) HSCs and that a patient with WHIM was spontaneously cured by chromothriptic deletion of the disease allele in an HSC, suggesting that WHIM allele inactivation through gene editing may be a safe genetic cure strategy for the disease. We have developed a 2-step preclinical protocol of autologous hematopoietic stem and progenitor cell (HSPC) transplantation to achieve this goal. First, 1 copy of Cxcr4 in HSPCs was inactivated in vitro by CRISPR/Cas9 editing with a single guide RNA (sgRNA) that does not discriminate between Cxcr4+/w and Cxcr4+/+ alleles. Then, through in vivo natural selection, WHIM allele-inactivated cells were enriched over wild-type allele-inactivated cells. The WHIM allele-inactivated HSCs retained long-term pluripotency and selective hematopoietic reconstitution advantages. To our knowledge, this is the first example of gene therapy for an autosomal dominant gain-of-function disease using a disease allele inactivation strategy in place of the less efficient disease allele repair approach.
Asunto(s)
Síndromes de Inmunodeficiencia , Verrugas , Ratones , Animales , Alelos , Sistemas CRISPR-Cas , ARN Guía de Sistemas CRISPR-Cas , Síndromes de Inmunodeficiencia/genética , Síndromes de Inmunodeficiencia/terapia , Verrugas/genética , Verrugas/terapia , Terapia Genética , Receptores CXCR4/genéticaRESUMEN
Chronic granulomatous disease (CGD) is a rare inborn error of immunity, resulting from a defect in nicotinamide adenine dinucleotide phosphate oxidation and decreased production of phagocyte reactive oxygen species. The main clinical manifestations are recurrent infections and chronic inflammatory disorders. Current approaches to management include antimicrobial prophylaxis and control of inflammatory complications. Hematopoietic stem cell transplantation or gene therapy can provide definitive treatment. Gastrointestinal and hepatic manifestations are common in CGD and include structural changes, dysmotility, CGD-associated inflammatory bowel disease, liver abscesses, and noncirrhotic portal hypertension. The findings can be heterogeneous, and the management is complex in light of the underlying immune dysfunction. This review describes the various clinical findings and the latest studies in management of gastrointestinal and hepatic manifestations in CGD, as well as the management experience at the National Institutes of Health.
Asunto(s)
Enfermedad Granulomatosa Crónica , Trasplante de Células Madre Hematopoyéticas , Hipertensión Portal , Humanos , Enfermedad Granulomatosa Crónica/complicaciones , Enfermedad Granulomatosa Crónica/terapia , Enfermedad Granulomatosa Crónica/genética , Tracto Gastrointestinal , Trasplante de Células Madre Hematopoyéticas/efectos adversos , NADPH Oxidasas/genéticaRESUMEN
INTRODUCTION: The growing practice of living liver donation requires comprehensive understanding of the financial implications for living liver donors. While obtaining and maintaining insurance is important to financial health, little is known about the impact of liver donation on future insurability. RESEARCH QUESTIONS: The purpose of this study was to evaluate the donors' experiences with insurance following donation and identify the insurance provider-driven factors that contribute to donor insurability. DESIGN: A two center cohort of living donors with donation between January 2000 and December 2018 (N = 442) were surveyed about postdonation insurance experiences. To understand insurance provider practices towards liver donors, life (n = 11) and disability (n = 4) insurance underwriters were asked to provide policy quotes for a standardized living liver donor profile. RESULTS: Responses (N = 101) were received by August 2020 (response rate = 22.9%). Living liver donors reported owning life (58%), disability (35%), and medical (87%) insurance at rates comparable to the general population with low proportions reporting difficulty obtaining these insurance types (9%, 9%, 4%, respectively). Post-donation life insurance ownership was associated with post-donation employment (P = 0.01). Underwriter responses indicate life and disability insurability were adversely affected up to 12 months following donation. CONCLUSIONS: Living liver donors did not have difficulty maintaining insurance in the long-term but should be counseled to purchase insurance prior to surgery as short-term insurability may be affected. Perception of difficulty obtaining insurance following donation remains of significant concern among living donors. Further collaboration between the transplant community and insurance companies is warranted.
Asunto(s)
Trasplante de Hígado , Donadores Vivos , Humanos , Encuestas y Cuestionarios , Empleo , HígadoRESUMEN
This systematic review offers a world-first critical analysis of machine learning methods and systems, along with future directions for the study of cybersickness induced by virtual reality (VR). VR is becoming increasingly popular and is an important part of current advances in human training, therapies, entertainment, and access to the metaverse. Usage of this technology is limited by cybersickness, a common debilitating condition experienced upon VR immersion. Cybersickness is accompanied by a mix of symptoms including nausea, dizziness, fatigue and oculomotor disturbances. Machine learning can be used to identify cybersickness and is a step towards overcoming these physiological limitations. Practical implementation of this is possible with optimised data collection from wearable devices and appropriate algorithms that incorporate advanced machine learning approaches. The present systematic review focuses on 26 selected studies. These concern machine learning of biometric and neuro-physiological signals obtained from wearable devices for the automatic identification of cybersickness. The methods, data processing and machine learning architecture, as well as suggestions for future exploration on detection and prediction of cybersickness are explored. A wide range of immersion environments, participant activity, features and machine learning architectures were identified. Although models for cybersickness detection have been developed, literature still lacks a model for the prediction of first-instance events. Future research is pointed towards goal-oriented data selection and labelling, as well as the use of brain-inspired spiking neural network models to achieve better accuracy and understanding of complex spatio-temporal brain processes related to cybersickness.
RESUMEN
Purpose: To evaluate the performance of a deep learning (DL) model that measures the liver segmental volume ratio (LSVR) (ie, the volumes of Couinaud segments I-III/IV-VIII) and spleen volumes from CT scans to predict cirrhosis and advanced fibrosis. Materials and Methods: For this Health Insurance Portability and Accountability Act-compliant, retrospective study, two datasets were used. Dataset 1 consisted of patients with hepatitis C who underwent liver biopsy (METAVIR F0-F4, 2000-2016). Dataset 2 consisted of patients who had cirrhosis from other causes who underwent liver biopsy (Ishak 0-6, 2001-2021). Whole liver, LSVR, and spleen volumes were measured with contrast-enhanced CT by radiologists and the DL model. Areas under the receiver operating characteristic curve (AUCs) for diagnosing advanced fibrosis (≥METAVIR F2 or Ishak 3) and cirrhosis (≥METAVIR F4 or Ishak 5) were calculated. Multivariable models were built on dataset 1 and tested on datasets 1 (hold out) and 2. Results: Datasets 1 and 2 consisted of 406 patients (median age, 50 years [IQR, 44-56 years]; 297 men) and 207 patients (median age, 50 years [IQR, 41-57 years]; 147 men), respectively. In dataset 1, the prediction of cirrhosis was similar between the manual versus automated measurements for spleen volume (AUC, 0.86 [95% CI: 0.82, 0.9] vs 0.85 [95% CI: 0.81, 0.89]; significantly noninferior, P < .001) and LSVR (AUC, 0.83 [95% CI: 0.78, 0.87] vs 0.79 [95% CI: 0.74, 0.84]; P < .001). The best performing multivariable model achieved AUCs of 0.94 (95% CI: 0.89, 0.99) and 0.79 (95% CI: 0.71, 0.87) for cirrhosis and 0.8 (95% CI: 0.69, 0.91) and 0.71 (95% CI: 0.64, 0.78) for advanced fibrosis in datasets 1 and 2, respectively. Conclusion: The CT-based DL model performed similarly to radiologists. LSVR and splenic volume were predictive of advanced fibrosis and cirrhosis.Keywords: CT, Liver, Cirrhosis, Computer Applications-Detection/Diagnosis Supplemental material is available for this article. © RSNA, 2022.