Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning.

BACKGROUND: Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective. PURPOSE: To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI). METHODS: This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index. RESULTS: A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts). CONCLUSIONS: Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice. CLINICAL RELEVANCE STATEMENT: Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards. KEY POINTS: • Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.

Community-Level Factors Associated with Hepatocellular Carcinoma Incidence and Mortality: An Observational Registry Study.

BACKGROUND: Hepatocellular carcinoma (HCC) incidence and outcomes vary across populations in the United States, but few studies evaluate local drivers of observed disparities. We measured HCC incidence at the community level and assessed community-level HCC risk factors with the goal of informing resource allocation to improve early case detection, which is associated with improved outcomes. METHODS: Clinical and demographic data including census tract of residence for all adults diagnosed with HCC in the Connecticut Tumor Registry between 2008 and 2019 were combined with publicly available U.S. Census and Centers for Disease Control and Prevention (CDC) data at the ZIP Code tabulation area (ZCTA) level. The average annual incidence of HCC was calculated for each ZCTA and associations between community-level characteristics, HCC incidence, stage at diagnosis, and survival were evaluated. RESULTS: Average annual HCC incidence during the study period was 8.9/100,000 adults and varied from 0 to 97.7 per 100,000 adults by ZCTA. At the community level, lower rates of high school graduation, higher rates of poverty, and rural community type were associated with higher HCC incidence. Persons with HCC living in the highest incidence ZCTAs were diagnosed at a younger age and were less likely to be alive at 1, 2, and 5 years after diagnosis. CONCLUSIONS: Community-level socioeconomic factors are strongly associated with HCC incidence and survival in Connecticut. IMPACT: This reproducible geo-localization approach using cancer registry, Census, and CDC data can be used to identify communities most likely to benefit from health system investments to reduce disparities in HCC.

European Society for Organ Transplantation (ESOT) Consensus Statement on Outcome Measures in Liver Transplantation According to Value-Based Health Care.

Liver transplantation is a highly complex, life-saving, treatment for many patients with advanced liver disease. Liver transplantation requires multidisciplinary teams, system-wide adaptations and significant investment, as well as being an expensive treatment. Several metrics have been proposed to monitor processes and outcomes, however these lack patient focus and do not capture all aspects of the process. Most of the reported outcomes do not capture those outcomes that matter to the patients. Adopting the principles of Value-Based Health Care (VBHC), may provide an opportunity to develop those metrics that matter to patients. In this article, we present a Consensus Statement on Outcome Measures in Liver Transplantation following the principles of VBHC, developed by a dedicated panel of experts under the auspices of the European Society of Organ Transplantation (ESOT) Guidelines' Taskforce. The overarching goal is to provide a framework to facilitate the development of outcome measures as an initial step to apply the VMC paradigm to liver transplantation.

Value-based medicine, a compass to guide healthcare decisions in the COVID-19 aftermath.

The ongoing COVID-19 pandemics has claimed hundreds of thousands of lives among the elderly, the patients with chronic conditions and among underserved communities and people in social distress. In addition, the measures that succeeded in containing the epidemic created a profound economic crisis, which real dimension is still unclear. It is clear, however, that most healthcare systems were unprepared. Years of cost containments had eroded the ability of the healthcare sector to cope with the surge in cases. This editorial contends that rebuilding the healthcare systems will require forward thinking, a data-driven approach and avoidance of reactive decision making. The editorial proposes the Value Based Medicine approach as a way to avoid the errors of the past and to align decision making in healthcare with patient health and quality of life (Value). This is an approach that is gaining traction in several systems. It needs a built-in capability to collect and analyse outcome and costing data. Today the necessary informatic and computational capabilities are widely available.

Clinical outcome indicators in chronic hepatitis B and C: A primer for value-based medicine in hepatology.

BACKGROUND & AIMS: Chronic liver diseases (CLDs) are major health problems that require complex and costly treatments. Liver-specific clinical outcome indicators (COIs) able to assist both clinicians and administrators in improving the value of care are presently lacking. The Value-Based Medicine in Hepatology (VBMH) study aims to fill this gap, devising and testing a set of COIs for CLD, that could be easily collected during clinical practice. Here we report the COIs generated and recorded for patients with HBV or HCV infection at different stages of the disease. METHODS/RESULTS: In the first phase of VBMH study, COIs were identified, based on current international guidelines and literature, using a modified Delphi method and a RAND 9-point appropriateness scale. In the second phase, COIs were tested in an observational, longitudinal, prospective, multicentre study based in Lombardy, Italy. Eighteen COIs were identified for HBV and HCV patients. Patients with CLD secondary to HBV (547) or HCV (1391) were enrolled over an 18-month period and followed for a median of 4 years. The estimation of the proposed COIs was feasible in the real-word clinical practice and COI values compared well with literature data. Further, the COIs were able to capture the impact of new effective treatments like direct-acting antivirals (DAAs) in the clinical practice. CONCLUSIONS: The COIs efficiently measured clinical outcomes at different stages of CLDs. While specific clinical practice settings and related healthcare systems may modify their implementation, these indicators will represent an important component of the tools for a value-based approach in hepatology and will positively affect care delivery.

Modeling of implementation of the new Organ Procurement and Transplantation Network/United Network for Organ Sharing policy for patients with hepatocellular carcinoma.

Aim: To simulate effects of the new Organ Procurement and Transplantation Network/United Network for Organ Sharing policy on the patients' characteristics and post orthotopic liver transplantation (OLT) outcome. Materials & methods: The United Network for Organ Sharing database was used to identify patients with hepatocellular carcinoma who were listed for OLT 2002-2014. All patients (actual group) versus simulated group with new 6-month delay in assigning Model for End-Stage Liver Disease score exception and Model for End-Stage Liver Disease exception cap of 34 were compared. Results & conclusion: With the new policy, 7,745 (30.4%) of the transplanted patients would have received a delayed transplantation or not be transplanted. The simulated group also showed significantly higher mean overall survival after OLT (p < 0.002) and received more locoreginal treatments (p < 0.001).

Diagnostic Value of Quantitative Perfusion Computed Tomography Technique in the Assessment of Tumor Response to Sorafenib in Patients With Advanced Hepatocellular Carcinoma.

AIM: The aim of this study was to assess the role of dynamic contrast-enhanced perfusion computed tomography (pCT) imaging in the early detection of blood flow changes related to antiangiogenic treatment with sorafenib, in patients with advanced hepatocellular carcinoma (HCC), being the modified Response Evaluation Criteria in Solid Tumors (mRECIST) criteria the standard of reference. METHODS: Between 2012 and 2016, 43 cirrhotic patients (male, n = 39; female, n = 4) with biopsy-proven multifocal HCC underwent multi-detector-row computed tomography, and pCT examinations were performed before and every 2 months after sorafenib administration. Perfusion CT technique is based on the acquisition of 16 dynamic slices/scan per 40 scans, performed on a 256-slice multi-detector-row computed tomography scanner, after intravenous bolus injection of 50 mL of iodinated contrast agent (350 mg I/mL) at a flow rate of 5 mL/s. According to mRECIST, patients were stratified into complete (CR) or partial response (PR) and stable (SD) or progressive disease (PD). The following pCT parameters were calculated: hepatic perfusion (mL/s per 100 g), time to peak (seconds), arterial perfusion (mL/s), and hepatic perfusion index (%). Perfusion CT values at baseline and first follow-up were reported for all mRECIST groups and then compared between the nonprogressor (CR, PR, SD) and progressor groups (PD). RESULTS: Most pCT values were significantly higher (P < 0.01) between baseline and follow-up in the CR and PR groups, whereas nonsignificant differences were found among SD patients, and a nonsignificant trend (P > 0.05) toward increase was observed among PD patients. Moreover, pCT values were significantly higher (P = 0.05) at baseline in the nonprogressor group compared with the progressor. CONCLUSION: Preliminary results suggest that pCT adds quantitative data of vascularization, thus demonstrating its usefulness in the assessment of therapeutic response to sorafenib in advanced HCC, in line with mRECIST criteria, offering 1-step information on tissue cellularity and vascularization.

Forecasting Hepatitis C liver disease burden on real-life data. Does the hidden iceberg matter to reach the elimination goals?

BACKGROUND & AIMS: Advances in direct-acting antiviral treatment of HCV have reinvigorated public health initiatives aimed at identifying affected individuals. We evaluated the possible impact of only diagnosed and linked-to-care individuals on overall HCV burden estimates and identified a possible strategy to achieve the WHO targets by 2030. METHODS: Using a modelling approach grounded in Italian real-life data of diagnosed and treated patients, different linkage-to-care scenarios were built to evaluate potential strategies in achieving the HCV elimination goals. RESULTS: Under the 40% linked-to-care scenario, viraemic burden would decline (60%); however, eligible patients to treat will be depleted by 2025. Increased case finding through a targeted screening strategy in 1948-1978 birth cohorts could supplement the pool of diagnosed patients by finding 75% of F0-F3 cases. Under the 60% linked-to-care scenario, viraemic infections would decline by 70% by 2030 but the patients eligible for treatment will run out by 2028. If treatment is to be maintained, a screening strategy focusing on 1958-1978 birth cohorts could capture 55% of F0-F3 individuals. Under the 80% linked-to-care scenario, screening limited in 1968-1978 birth cohorts could sustain treatment at levels required to achieve the HCV elimination goals. CONCLUSION: In Italy, which is an HCV endemic country, the eligible pool of patients to treat will run out between 2025 and 2028. To maintain the treatment rate and achieve the HCV elimination goals, increased case finding in targeted, high prevalence groups is required.

Diagnostic value of dynamic contrast-enhanced CT with perfusion imaging in the quantitative assessment of tumor response to sorafenib in patients with advanced hepatocellular carcinoma: A feasibility study.

PURPOSE: To investigate the feasibility of perfusion-CT (p-CT) measurements in quantitative assessment of hemodynamic changes related to sorafenib in patients with advanced hepatocellular carcinoma (HCC). MATERIALS AND METHODS: Twenty-two patients with advanced HCC underwent p-CT study (256-MDCT scanner) before and 2 months after sorafenib administration. Dedicated perfusion software generated a quantitative map of arterial and portal perfusion and calculated the following perfusion parameters in target liver lesion: hepatic perfusion (HP), time-to-peak (TTP), blood volume (BV), arterial perfusion (AP), and hepatic perfusion index (HPI). After the follow-up scan, patients were categorized as responders and non-responders, according to mRECIST. Perfusion values were analyzed and compared in HCC lesions and in the cirrhotic parenchyma (n=22), such as between baseline and follow-up in progressors and non-progressors. RESULTS: Before treatment, all mean perfusion values were significantly higher in HCC lesions than in the cirrhotic parenchyma (HP 47.8±17.2 vs 13.3±6.3mL/s per 100g; AP 47.9±18.1 vs 12.9±10.7mL/s; p<0.001). The group that responded to sorafenib (n=17) showed a significant reduction of values in HCC target lesions after therapy (HP 29.2±23.3 vs 48.1±15.1; AP 29.4±24.6 vs 49.2±17.4; p<0.01), in comparison with the non-responder group (n=5) that demonstrated no significant variation before and after treatment of HP (46.9±25.1 vs 46.7±24.1) and AP (43.4±21.7 vs 43.5±24.6). Among the responder group, HP percentage variation (Δ) in target lesions, during treatment, showed a significantly different (p=0.04) ΔHP in the group with complete response (79%) compared to the group with partial response or stable disease (16%). CONCLUSIONS: p-CT technique can be used for HCC quantitative assessment of changes related to anti-angiogenic therapy. Identification of response predictors might help clinicians in selection of patients who may benefit from targeted-therapy allowing for optimization of individualized treatment.

Value-based care in hepatology.

The migration from legacy fee-for-service reimbursement to payments linked to high-value health care is accelerating in the United States because of new legislation and redesign of payments from the Centers for Medicare and Medicaid Services. Because patients with chronic diseases account for substantial use of health care resources, payers and health systems are focusing on maximizing the value of care for these patients. Because chronic liver diseases impose a major health burden worldwide affecting the health and lives of many individuals and families as well as substantial costs for individuals and payers, hepatologists must understand how they can improve their practices. Hepatologists practice a high-intensity cognitive subspecialty, using complex and costly procedures and medications. High-value patient care requires multidisciplinary coordination, labor-intensive support for critically ill patients, and effective chronic disease management. Under current fee-for-service reimbursement, patient values, medical success, and financial success can all be misaligned. Many current attempts to link health outcomes to reimbursement are based on compliance with process measures, with less emphasis on outcomes that matter most to patients, thus slowing transformation to higher-value team-based care. Outcome measures that reflect the entire cycle of care are needed to assist both clinicians and administrators in improving the quality and value of care. A comprehensive set of outcome measures for liver diseases is not currently available. Numerous researchers now are attempting to fill this gap by devising and testing outcome indicators and patient-reported outcomes for the major liver conditions. These indicators will provide tools to implement a value-based approach for patients with chronic liver diseases to compare results and value of care between referral centers, to perform health technology assessment, and to guide decision-making processes for health authorities. This review sets the groundwork for implementing a value-based, patient-centered approach to chronic liver diseases within a health system. (Hepatology 2017;65:1749-1755).

Direct-acting antivirals combination for elderly patients with chronic hepatitis C: A cost-effectiveness analysis.

BACKGROUND: Chronic hepatitis C (CHC) has been undertreated among elderly patients. Interferon-free treatment represents an opportunity for these patients. The aim of this study was to assess the cost-effectiveness of directly acting antivirals (DAAs) in CHC elderly patients. METHODS: A Markov model of CHC natural history was built. This study focuses on CHC patients older than 65 years, stratified according to genotype (1/4, 2 and 3), liver fibrosis (METAVIR F1 to F4), age and frailty phenotype (robust, pre-frail and frail). DAAs combination vs no treatment was simulated for each theoretical population, assessing life years, quality-adjusted life years (QALYs), costs, incremental cost-effectiveness ratios (ICERs) in a lifetime time horizon and by the Healthcare System perspective. RESULTS: Incremental cost-effectiveness ratio increased with age and frailty status in all fibrosis stages. For robust F3 and F4 patients ICERs remained below the willingness-to-pay threshold (WTP) of 40 000€/QALY up to age 75 and 86 years, respectively, depending on drug price and sustained virological response probability (sensitivity analysis). Notably, in F4 and frail subjects older than 75 years, ICER was more sensitive to non-liver-related mortality rate. In elderly F1 and F2 patients, ICERs were below WTP only up to 77 years old, with wide variability among frailty phenotypes. CONCLUSIONS: Cost-effectiveness of DAAs treatment of elderly CHC patients is solid in those with advanced fibrosis, but it depends strongly on frailty status and age, particularly in patients with milder fibrosis stages. Accurate assessment of clinical variables, including frailty, is necessary to allocate limited resources to this special population.

Effective but costly: How to tackle difficult trade-offs in evaluating health improving technologies in liver diseases.

UNLABELLED: In the current context of rising health care costs and decreasing sustainability, it is becoming increasingly common to resort to decision analytical modeling and health economics evaluations. Decision analytic models are analytical tools that help decision makers to select the best choice between alternative health care interventions, taking into consideration the complexity of the disease, the socioeconomic context, and the relevant differences in outcomes. We present a brief overview of the use of decision analytical models in health economic evaluations and their applications in the area of liver diseases. The aim is to provide the reader with the basic elements to evaluate health economic analysis reports and to discuss some limitations of the current approaches, as highlighted by the case of the therapy of chronic hepatitis C. To serve its purpose, health economics evaluations must be able to do justice to medical innovation and the market while protecting patients and society and promoting fair access to treatment and its economic sustainability. CONCLUSION: New approaches and methods able to include variables such as prevalence of the disease, budget impact, and sustainability into the cost-effectiveness analysis are needed to reach this goal. (Hepatology 2016;64:1331-1342).

Incidence and management of colorectal cancer in liver transplant recipients.

Liver transplant recipients are at an increased risk of developing de novo malignancies because of the prolonged immunosuppression necessary to avoid acute and chronic rejections. Skin cancers and lymphoproliferative diseases are the most common malignancies, but the overall incidence of colon cancer in this patient population does differ from that of the general population. Therefore, colorectal cancer (CRC) is a major health concern in liver transplant recipients. Furthermore, there are unique subsets of liver transplant recipients, such as those with primary sclerosing cholangitis and inflammatory bowel disease, who are at an increased risk for developing CRC after liver transplantation and might require special screening/surveillance strategies. The similar principles for management of colon cancer can be applied to transplant recipients if the adjustment to maintain the need for the long-term immunosuppression is made. Colectomy can be performed safely during the posttransplantation period. Prophylactic colectomy at the time of liver transplantation has been performed in some patients at high risk or with known premalignant conditions. Chemotherapy with 5- fluorouracil and oxaliplatin has been used in transplant recipients for the treatment of metastatic CRC; however, further research is required to examine the safety, tolerability, and efficacy of combination chemotherapy and biologic agents in this patient population. This review summarizes the incidence, risk factors, diagnosis, and management of de novo CRC in liver transplant recipients.