The digital transformation of hepatology: The patient is logged in

Leveraging machine learning for precision medicine: a predictive model for cognitive impairment in cholestasis patients

BACKGROUND

Cholestasis, characterized by impaired bile flow, impacts cognitive function through systemic mechanisms, including inflammation and metabolic dysregulation. Despite its significance, targeted predictive models for cognitive impairment in cholestasis remain underexplored. This study addresses this gap by developing a machine learning-based predictive model tailored to this population.

METHODS

Clinical and biochemical data from Qingyang People's Hospital (2021-2023) were used to train and validate models for predicting cognitive impairment (MoCA ≤ 17). Recursive feature elimination identified critical predictors, while LightGBM and other machine learning models were evaluated. SHAP analysis enhanced model interpretability, and clinical utility was assessed through decision curve analysis (DCA).

RESULTS

LightGBM outperformed other models with an AUC of 0.7955 on the testing dataset. Age, plasma D-dimer, and albumin were key predictors. SHAP analysis revealed non-linear interactions among features, demonstrating the model's clinical alignment. DCA confirmed its utility in improving patient stratification.

CONCLUSION

The developed LightGBM-based model effectively predicts cognitive impairment in cholestasis patients, providing actionable insights for early intervention. Integrating this tool into clinical workflows can enhance precision medicine and improve outcomes in this high-risk population.

Gut Microbiome-Liver-Brain axis in Alcohol Use Disorder. The role of gut dysbiosis and stress in alcohol-related cognitive impairment progression: possible therapeutic approaches

The Gut Microbiome-Liver-Brain Axis is a relatively novel construct with promising potential to enhance our understanding of Alcohol Use Disorder (AUD), and its therapeutic approaches. Significant alterations in the gut microbiome occur in AUD even before any other systemic signs or symptoms manifest. Prolonged and inappropriate alcohol consumption, by affecting the gut microbiota and gut mucosa permeability, is thought to contribute to the development of behavioral and cognitive impairments, leading to Alcohol-Related Liver Disorders and potentially progressing into alcoholic cirrhosis, which is often associated with severe cognitive impairment related to neurodegeneration, such as hepatic encephalopathy and alcoholic dementia. The critical role of the gut microbiota is further supported by the efficacy of FDA-approved treatments for hepatic encephalopathy in alcoholic cirrhosis (i.e., lactulose and rifaximin). To stimulate new research, we hypothesize that interactions between a maladaptive stress response and a constitutional predisposition to neurodegeneration underlie the progression of AUD to conditions of Alcohol-Related Clinical Concerns with severe cognitive impairment, which represent a significant and costly burden to society. Early identification of AUD individuals at risk for developing these conditions could help to prioritize integrated therapeutic interventions targeting different substrates of the Gut Microbiome-Liver-Brain axis. Specifically, addiction medications, microbiome modulators, stress-reducing interventions, and, possibly soon, novel agents that reduce hepatic steatosis/fibrosis will be discussed in the context of digitally supported integrated therapeutic approaches. The explicit goal of this AUD treatment performed on the early stage of the disorder would be to reduce the transition from AUD to those conditions of Alcohol-Related Common Clinical Concerns associated with severe cognitive impairment, a strategy recommended for most neurological neurodegenerative disorders.

The new digital era in decompensated cirrhosis

There is a growing global burden of liver disease with the current management for complications of liver cirrhosis being reactive as opposed to proactive, affecting outcomes. Management can often be suboptimal in overburdened health-care systems with considerable socioeconomic and geographical disparity existing, which was exacerbated by the COVID-19 pandemic, highlighting the need for sustainable care pathways to be delivered remotely. To this end, digital health care could be the key and, in this Review, we highlight the principal studies that have explored the use of digital technology in the management of cirrhosis complications. While digital health care is a somewhat new field, considerable advances have been made in various domains, particularly in the development of remote monitoring and risk modelling. We aim to provide a balanced perspective of the opportunities for and barriers to the integration of digital technology into established liver-care pathways. Lastly, we reflect on the current acceptability of digital health care and the required future directions to ensure the digital transformation of hepatology is a success.

Insights into ALD and AUD diagnosis and prognosis: Exploring AI and multimodal data streams

The rapid evolution of artificial intelligence and the widespread embrace of digital technologies have ushered in a new era of clinical research and practice in hepatology. Although its potential is far from realization, these significant strides have generated new opportunities to address existing gaps in the delivery of care for patients with liver disease. In this review, we discuss how artificial intelligence and opportunities for multimodal data integration can improve the diagnosis, prognosis, and management of alcohol-associated liver disease. An emphasis is made on how these approaches will also benefit the detection and management of alcohol use disorder. Our discussion encompasses challenges and limitations, concluding with a glimpse into the promising future of these advancements.

Artificial Intelligence, Large Language Models, and Digital Health in the Management of Alcohol-Associated Liver Disease

Artificial intelligence (AI) has the potential to aid in the diagnosis and management of alcohol-associated liver disease (ALD). Machine learning algorithms can analyze medical data, such as patient records and imaging results, to identify patterns and predict disease progression. Newer advances such as large language models (LLMs) can enhance early detection and personalized treatment strategies for individuals with chronic diseases such as ALD. However, it is essential to integrate LLMs and other AI tools responsibly, considering ethical concerns in health care applications and ensuring an evidence base for real-world applications of the existing knowledge.

Hospital-Level Care at Home for Patients with Cirrhosis

BACKGROUND

Patients with cirrhosis have a 30-day readmission rate of over 30%. Novel care delivery models are needed to reduce healthcare costs and utilization associated with cirrhosis care. One such model is Home Hospital (HH), which provides inpatient-level care at home. Limited evidence currently exists supporting HH for cirrhosis patients.

AIMS

The aims of this study were to characterize patients with cirrhosis who received hospital-level care at home in a two-site clinical trial and to describe the care they received. Secondary aims included describing their outcomes, including adverse events, readmissions and mortality.

METHODS

We identified all patients with cirrhosis who enrolled in HH as part of a two-site clinical trial between 2017 and 2022. HH services include daily clinician visits, intravenous and oral medications, continuous vital sign monitoring, and telehealth specialist consultation. We collected sociodemographic data and analyzed HH stays, including interventions, outcomes, adverse events, and follow-up.

RESULTS

22 patients with cirrhosis (45% Hispanic; 50% limited English proficiency, median MELD-Na 12) enrolled in HH during the study period. Interventions included lab chemistries (82%), intravenous medications (77%), specialist consultation (23%), and advanced diagnostics/procedures (23%). The median length of stay was 7 days (IQR 4-12); 186 bed-days were saved. Two patients (9%) experienced adverse events (AKI). No patients required escalation of care; 9% were readmitted within 30 days.

CONCLUSIONS

In this two-site study, HH was feasible for patients with cirrhosis, holding promise as a hepatology delivery model. Future randomized trials are needed to further evaluate the efficacy of HH for patients with cirrhosis.

Telehepatology Satisfaction Is Associated with Ethnicity: The Real-World Experience of a Vulnerable Population with Fatty Liver Disease

BACKGROUND

Since the coronavirus disease 2019 (COVID-19) pandemic began, telemedicine use has transformed healthcare delivery. Yet there is concern that telemedicine may widen care disparities for vulnerable populations, and patient experience data are limited.

AIMS

We aimed to assess patient satisfaction with hepatology-related telemedicine (telehepatology) for delivery of fatty liver disease (FLD) care in a safety-net healthcare system.

METHODS

Adult patients with FLD were surveyed regarding satisfaction with telehepatology. Clinical, demographic, resources, and social determinants of health (SDoH) data were collected to identify factors associated with satisfaction through multivariable modeling.

RESULTS

From June 2020 to March 2022, 220 participants were enrolled: the median age was 52 years, 37% were men, and 68% were Hispanic. One hundred nineteen (54%) had prior telehepatology experience. Overall, satisfaction was high; 70% reported being somewhat or very satisfied. On univariate analysis, Hispanic ethnicity (versus non-Hispanic, OR 0.34, 95% CI 0.1-0.9, p = 0.03) and limited access to personal cellphone/internet (OR 0.16, 95% CI 0.04-0.6, p = 0.01) were associated with lower satisfaction. On multivariable logistic regression modeling adjusted for pandemic duration, age, sex, severity of liver disease, and coexisting liver disease, Hispanic ethnicity and lack of personal cellphone/internet remained independently associated with lower telehepatology satisfaction (OR 0.24, 95% CI 0.07-0.9, p = 0.03 and OR 0.2, 95% CI 0.04-0.9, p = 0.04, respectively). The association remained statistically significant after inclusion of various SDoH in the multivariable model.

CONCLUSIONS

Satisfaction with telehepatology among FLD patients in a safety-net clinical setting was high overall. However, Hispanic ethnicity and lack of personal cellphone/internet were independently associated with lower telehepatology satisfaction. A better understanding of patients' experience with telehepatology is needed to identify reasons for dissatisfaction, and in-person visits should remain an option for patients to ensure equitable care.

Update in the Treatment of the Complications of Cirrhosis

Cirrhosis consists of 2 main stages: compensated and decompensated, the latter defined by the development/presence of ascites, variceal hemorrhage, and hepatic encephalopathy. The survival rate is entirely different, depending on the stage. Treatment with nonselective β-blockers prevents decompensation in patients with clinically significant portal hypertension, changing the previous paradigm based on the presence of varices. In patients with acute variceal hemorrhage at high risk of failure with standard treatment (defined as those with a Child-Pugh score of 10-13 or those with a Child-Pugh score of 8-9 with active bleeding at endoscopy), a pre-emptive transjugular intrahepatic portosystemic shunt (TIPS) improves the mortality rate and has become the standard of care in many centers. In patients with bleeding from gastrofundal varices, retrograde transvenous obliteration (in those with a gastrorenal shunt) and/or variceal cyanoacrylate injection have emerged as alternatives to TIPS. In patients with ascites, emerging evidence suggests that TIPS might be used earlier, before strict criteria for refractory ascites are met. Long-term albumin use is under assessment for improving the prognosis of patients with uncomplicated ascites and confirmatory studies are ongoing. Hepatorenal syndrome is the least common cause of acute kidney injury in cirrhosis, and first-line treatment is the combination of terlipressin and albumin. Hepatic encephalopathy has a profound impact on the quality of life of patients with cirrhosis. Lactulose and rifaximin are first- and second-line treatments for hepatic encephalopathy, respectively. Newer therapies such as L-ornithine L-aspartate and albumin require further assessment.

Physicians' Use of Digital Health Interventions in the Management of Nonalcoholic Fatty Liver Disease

Globally, the use of digital health interventions (DHIs) is expanding, along with growing scientific evidence of their effectiveness. Given the high and increasing prevalence of noncommunicable liver disease, we surveyed 295 physicians across Spain about their knowledge, beliefs, attitudes, practices, and access with regard to DHIs for patient care and in particular for liver diseases, including nonalcoholic fatty liver disease and nonalcoholic steatohepatitis. Physicians reported high familiarity with DHIs, although most had not recommended them in patient care. Addressing concerns, including limited available time, evidence of effectiveness, education, training, and access may contribute to an increased uptake of these technologies.

Machine learning can guide suitability of consultation and patient referral through telemedicine for hepatobiliary diseases

BACKGROUND AND AIM

Telemedicine is an evolving tool to provide health-care services. We evaluated the suitability of telemedicine to deliver effective consultation for hepatobiliary disorders.

METHODS

In this prospective study spanning over a year, we interviewed hepatologists delivering the teleconsultations through a pre-validated questionnaire. A consult was deemed suitable based on the physician's judgment in the absence of unplanned hospitalization. We evaluated factors determining the suitability through inferential statistics and machine learning models, namely, extreme gradient boosting (XGB) and decision tree (DT).

RESULTS

Of 1118 consultations, 917 (82.0%) were deemed suitable. On univariable analysis, patients with skilled occupation, higher education, out-of-pocket expenses, and diseases such as chronic hepatitis B, C, and non-alcoholic fatty liver disease (NAFLD) without cirrhosis were associated with suitability (P < 0.05). Patients with cirrhosis (compensated or decompensated), acute-on-chronic liver failure (ACLF), and biliary obstruction were likely unsuitable (P < 0.05). XGB and DT models predicted suitability with an area under the receiver operating curve of 0.808 and 0.780, respectively. DT demonstrated that compensated cirrhosis with higher education or skilled occupation with age < 55 years had 78% chance of suitability whereas hepatocellular carcinoma, decompensated cirrhosis, and ACLF patients were unsuitable with a 60-95% probability. In non-cirrhotic liver diseases, hepatitis B, C, and NAFLD were suitable, with a probability of 89.7%. Biliary obstruction and previous failure of teleconsultation were unsuitable, with a probability of 70%. Non-cirrhotic portal fibrosis, dyspepsia, and dysphagia not requiring intervention were suitable (probability: 88%).

CONCLUSION

A simple decision tree can guide the referral of unsuitable and the management of suitable patients with hepatobiliary diseases through telemedicine.

Review article: current and emerging therapies for acute alcohol-associated hepatitis

BACKGROUND

Alcohol-associated hepatitis is an acute manifestation of alcohol-associated liver disease (ALD) and is associated with 30%-40% mortality at 28 days. Abstinence and corticosteroids are the mainstays of treatment, but the latter only improves short-term mortality, so new and improved therapies remain an unmet need.

AIMS

The aim was to review the pathophysiology of alcohol-associated hepatitis and how various targets can be used by current and emerging therapies as treatment.

METHODS

A thorough literature review was conducted on acute alcohol-associated hepatitis, current therapies and therapies under investigation.

RESULTS

With the increasing prevalence of alcohol use disorder and ALD, the burden of alcohol-associated hepatitis is also expected to rise. The current understanding of alcohol-associated hepatitis pathophysiology has led to clinical trials of several therapies involving IL-1 antagonism, modification of the gut microbiome and liver regeneration.

CONCLUSIONS

Corticosteroid therapy for alcohol-associated hepatitis is restricted in its applicability and has limited efficacy. Developing multidisciplinary, patient-centred care models based on digital health technologies, in combination with continued discovery of novel therapies using multiomics data and computational biology techniques will be necessary to tackle the increasing burden of alcohol-associated hepatitis.

Therapeutic advances in alcohol-associated hepatitis

In recent years, there have been important advances in our understanding of alcohol-associated hepatitis (AH), which have occurred in parallel with a surge in clinical trial activity. Meanwhile, the broader medical field has seen a transformation in care paradigms based on emerging digital technologies. This review focuses on breakthroughs in our understanding of AH and how these breakthroughs are leading to new paradigms for biomarker discovery, clinical trial activity, and care models for patients. It portends a future in which multimodal data from genetic, radiomic, histologic, and environmental sources can be integrated and synthesised to generate personalised biomarkers and therapies for patients with AH.