APASL-ACLF Research Consortium-Artificial Intelligence (AARC-AI) model precisely predicts outcomes in acute-on-chronic liver failure patients

BACKGROUND AND AIMS

We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute-on-chronic liver failure (ACLF).

METHODS

We recruited ACLF patients between 2009 and 2020 from APASL-ACLF Research Consortium (AARC). Their clinical data, investigations and organ involvement were serially noted for 90-days and utilized for AI modelling. Data were split randomly into train and validation sets. Multiple AI models, MELD and AARC-Model, were created/optimized on train set. Outcome prediction abilities were evaluated on validation sets through area under the curve (AUC), accuracy, sensitivity, specificity and class precision.

RESULTS

Among 2481 ACLF patients, 1501 in train set and 980 in validation set, the extreme gradient boost-cross-validated model (XGB-CV) demonstrated the highest AUC in train (0.999), validation (0.907) and overall sets (0.976) for predicting 30-day outcomes. The AUC and accuracy of the XGB-CV model (%Δ) were 7.0% and 6.9% higher than the standard day-7 AARC model (p < .001) and 12.8% and 10.6% higher than the day 7 MELD for 30-day predictions in validation set (p < .001). The XGB model had the highest AUC for 7- and 90-day predictions as well (p < .001). Day-7 creatinine, international normalized ratio (INR), circulatory failure, leucocyte count and day-4 sepsis were top features determining the 30-day outcomes. A simple decision tree incorporating creatinine, INR and circulatory failure was able to classify patients into high (~90%), intermediate (~60%) and low risk (~20%) of mortality. A web-based AARC-AI model was developed and validated twice with optimal performance for 30-day predictions.

CONCLUSIONS

The performance of the AARC-AI model exceeds the standard models for outcome predictions in ACLF. An AI-based decision tree can reliably undertake severity-based stratification of patients for timely interventions.

Increased survival of patients with end-stage hepatocellular carcinoma due to intake of ONCOXIN®, a dietary supplement

BACKGROUND AND AIMS

Treatment and management of patients with end-stage hepatocellular carcinoma (HCC) represents a formidable challenge to contemporary branches of medical sciences. The study presented here was conducted to assess the utility of nutrient supplement, if any, for management of patients with end-stage HCC.

MATERIALS AND METHODS

A total of 19 patients with end-stage HCC (Barcelona Clinic Liver Cancer [BCLC] staging D) were provided with ONCOXIN® for 3 months. Another 10 patients with end-stage HCC (BCLC stage D) with similar clinical conditions received conservative management, but they did not give consent for taking ONCOXIN® (non-ONCOXIN® group). All patients of both groups were followed on regular basis until their death.

STATISTICAL ANALYSIS

The results were expressed as mean and standard deviation. Comparison between groups was performed using Student's t-test or the Mann-Whitney U test. For categorical data, Chi-square or Fisher exact test was applied.

RESULTS

All patients of the control group (non-ONCOXIN® group) (10 of 10 patients) died within 2 months after study commencement. On the other hand, 10 of 19 patients receiving ONCOXIN® died within 2 months (less than 53% patients) after the start of taking ONCOXIN® (P < 0.05, compared with patients of non-ONCOXIN® group). Five more patients died within 5 months after the start of intake of ONCOXIN®. Four patients receiving ONCOXIN® survived for more than 6 months after study commencement.

CONCLUSIONS

Although this is a preliminary report, it inspires considerable optimism about safety and efficacy of a food supplement for management of patients with end-stage HCC.

Non-alcoholic Fatty Liver Disease (NAFLD)--A Review

Non-alcoholic fatty liver disease (NAFLD) is an emerging problem in Hepatology clinics. It is closely related to the increased frequency of overweight or obesity. It has recognised association with metabolic syndrome. Central obesity, diabetes mellitus, dyslipidemia are commonest risk factors. Association with hepatitis C genotype 3 is also recognised. NAFLD is an important cause of cyptogenic cirrhosis of liver. It affects all populations and all age groups. Most patients with NAFLD are asymptomatic or vague upper abdominal pain. Liver function tests are mostly normal or mild elevation of aminotranferases. Histological features almost identical to those of alcohol-induced liver damage and can range from mild steatosis to cirrhosis. Two hit hypothesis is prevailing theory for the development of NAFLD. Diagnosis is usually made by imaging tools like ultrasonogram which reveal a bright liver while liver biopsy is gold standard for diagnosis as well as differentiating simple fatty liver and non-alcoholic steatohepatitis (NASH). Prognosis is variable. Simple hepatic steatosis generally has a benign long-term prognosis. However, one to two third of NASH progress to fibrosis or cirrhosis and may have a similar prognosis as cirrhosis from other liver diseases. Treatment is mostly control of underlying disorders and dietary advice, exercise, insulin sensitizers, antioxidants, or cytoprotective agents. The prevalence of NAFLD is increasing. So it needs more research to address this problem.

Combination therapy of lamivudine and interferon-alpha in pediatric patients with chronic hepatitis B in Bangladesh: a safe and effective therapeutic approach for pediatric CHB patients in developing countries

Hepatitis B virus (HBV) is mainly transmitted during birth or perinatal period, however, treatment is not usually recommended for pediatric patients with chronic hepatitis B (CHB). Twelve pediatric patients with CHB in Bangladesh were treated with both lamivudine and interferon. Lamivudine was given at a dose of 3 mg/kg, daily for 12 months. Two months after commencement of lamivudine therapy, all patents were given interferon-alpha (3 million IU/square meter of body surface area) three times weekly, subcutaneously for 10 months. Combination therapy was safe for all pediatric CHB patients. The levels of serum HBV DNA became undetectable (less than 500 copies/ml) in 8 patients and reduced in 4 patients after the end of therapy. Anti-HBe was detected in 10 of 12 patients at this time point. The levels of serum alanine aminotransferase (ALT) were significantly reduced in these patients (p less than 0.05) due to therapy. Neither flare of HBV DNA nor elevation of serum ALT were detected during follow-up. In conclusion, combination therapy with lamivudine and interferon-alpha represents a new and novel therapeutic option for treatment of pediatric CHB patients.