Development and validation of a real-time mortality risk calculator before, during and after hepatectomy: an analysis of the ACS NSQIP database

Dynamic ALBI score and FIB-4 index trends to predict complications after resection of hepatocellular carcinoma: A K-means clustering approach

BACKGROUND

Severe postoperative complications still occur following hepatectomy among patients with hepatocellular carcinoma (HCC). There is a need to identify high-risk patients for severe complications to enhance patient safety. We sought to evaluate the combined impact of pre- and postoperative albumin-bilirubin (ALBI) score and Fibrosis-4 (FIB-4) index trends to predict severe complications after HCC resection.

METHOD

Patients with HCC undergoing curative-intent hepatectomy (2000-2023) were identified from an international, multi-institutional database. The cohort was divided into training (n = 439) and testing (n = 651) sets. ALBI score and FIB-4 index trends from preoperative to postoperative days 1, 3, and 5 were used for K-means clustering (K = 3). A logistic regression model was developed using the training set, and its performance was evaluated using the area under the receiver operating characteristic curve (AUC) in both cohorts.

RESULTS

Severe complications (Clavien-Dindo Grade ≥ IIIa) occurred in 118 patients (10.8 %); 43 (9.8 %) in training and 75 (11.5 %) in testing set (p = 0.42). K-means clustering identified three groups: Cluster1 (low), Cluster2 (intermediate), and Cluster3 (high), which was associated with a progressively increasing risk of complications (p < 0.01). On multivariable logistic regression, patients in ALBI Cluster1 had 76 % decreased odds (odds ratio[OR] 0.24, 95 % CI 0.07-0.83, p = 0.02) of postoperative complications relative to Cluster3 patients. Individuals categorized into FIB-4 Cluster1 had 85 % decreased odds (OR 0.15, 95 % CI 0.02-1.24, p = 0.07) versus patients in FIB-4 Cluster3. A new prediction model incorporating ALBI and FIB-4 index clusters achieved an AUC of 0.71, outperforming models based on preoperative data. A tool was made available at https://nm49jf-miho-akabane.shinyapps.io/HCC_ALBI/.

CONCLUSION

A dynamic ALBI score and FIB-4 index trend tool improved risk stratification of patients undergoing resection of HCC relative to severe complications.

Extent of resection and underlying liver disease influence the accuracy of the preoperative risk assessment with the American College of Surgeons Risk Calculator

BACKGROUND

Liver surgery is associated with a significant risk of postoperative complications, depending on the extent of liver resection and the underlying liver disease. Therefore, adequate patient selection is crucial. This study aimed to assess the accuracy of the American College of Surgeons Risk Calculator (ACS-RC) by considering liver parenchyma quality and the type of liver resection.

METHODS

Patients who underwent open or minimally invasive liver resection for benign or malignant indications between January 2019 and March 2023 at the University Hospital Basel were included. Brier score and feature importance analysis were performed to investigate the accuracy of the ACS-RC.

RESULTS

A total of 376 patients were included in the study, 214 (57%) who underwent partial hepatectomy, 89 (24%) who underwent hemihepatectomy, and 73 (19%) who underwent trisegmentectomy. Most patients had underlying liver diseases, with 143 (38%) patients having fibrosis, 75 patients (20%) having steatosis, and 61 patients (16%) having cirrhosis. The ACS-RC adequately predicted surgical site infection (Brier score of 0.035), urinary tract infection (Brier score of 0.038), and death (Brier score of 0.046), and moderate accuracy was achieved for serious complications (Brier score of 0.216) and overall complications (Brier score of 0.180). Compared with the overall cohort, the prediction was limited in patients with cirrhosis, fibrosis, and steatosis and in those who underwent hemihepatectomy and trisegmentectomy. The inclusion of liver parenchyma quality improved the prediction accuracy.

CONCLUSION

The ACS-RC is a reliable tool for estimating 30-day postoperative morbidity, particularly for patients with healthy liver parenchyma undergoing partial liver resection. However, accurate perioperative risk prediction should be adjusted for underlying liver disease and extended liver resections.

Machine learning models including preoperative and postoperative albumin-bilirubin score: short-term outcomes among patients with hepatocellular carcinoma

BACKGROUND

We sought to assess the impact of various perioperative factors on the risk of severe complications and post-surgical mortality using a novel maching learning technique.

METHODS

Data on patients undergoing resection for HCC were obtained from an international, multi-institutional database between 2000 and 2020. Gradient boosted trees were utilized to construct predictive models.

RESULTS

Among 962 patients who underwent HCC resection, the incidence of severe postoperative complications was 12.7% (n = 122); in-hospital mortality was 2.9% (n = 28). Models that exclusively used preoperative data achieved AUC values of 0.89 (95%CI 0.85 to 0.92) and 0.90 (95%CI 0.84 to 0.96) to predict severe complications and mortality, respectively. Models that combined preoperative and postoperative data achieved AUC values of 0.93 (95%CI 0.91 to 0.96) and 0.92 (95%CI 0.86 to 0.97) for severe morbidity and mortality, respectively. The SHAP algorithm demonstrated that the factor most strongly predictive of severe morbidity and mortality was postoperative day 1 and 3 albumin-bilirubin (ALBI) scores.

CONCLUSION

Incorporation of perioperative data including ALBI scores using ML techniques can help risk-stratify patients undergoing resection of HCC.

Perioperative outcomes after hepatectomy for hepatocellular carcinoma among patients with cirrhosis, fatty liver disease, and clinically normal livers

INTRODUCTION

Despite superior outcomes with liver transplantation, cirrhotic patients with HCC may turn to other forms of definitive treatment. To understand perioperative outcomes, we examined perioperative mortality and major morbidity after hepatectomy for HCC among cirrhotic and non-cirrhotic patients.

METHOD

ology: The American College of Surgeons National Surgical Quality Improvement Project (ACS-NSQIP) database was queried for liver resection for HCC. Multivariable logistic regression was performed to determine the association between liver texture and risk of major non-infectious morbidity, post-hepatectomy liver failure (PHLF) and 30-day mortality.

RESULTS

From 2014 to 2018, 2203 patients underwent hepatectomy: 58.6 % cirrhotic, 12.8 % fatty and 28.6 % normal texture. Overall 30 day-mortality was 2.1 % (n = 46), although higher among fatty liver (2.8 %) and cirrhotic (2.6 %; p = 0.025) patients. The incidence of PHLF was 6.9 %, with hepatectomy type, cirrhosis, and platelet count as major risk factors. Age, resection type, and platelet count were associated with major complications. Trisegmentectomy and right hepatectomy (OR = 3.60, OR = 3.46, respectively) conferred a greater risk of major noninfectious morbidity compared to partial hepatectomy. Among cirrhotics alone, hepatectomy type, platelet count, preoperative sepsis and ASA class were associated with major morbidity.

DISCUSSION

Hepatic parenchymal disease/texture and function, presence of portal hypertension, and the extent of the liver resection are critical determinants of perioperative risk among HCC patients.

A novel preoperative predictive model of 90-day mortality after liver resection for huge hepatocellular carcinoma

Background

Hepatectomy for huge hepatocellular carcinoma (HCC) (diameter ≥10 cm) is characterized by high mortality. This study aimed to establish a preoperative model to evaluate the risk of postoperative 90-day mortality for huge HCC patients.

Methods

We retrospectively enrolled 1,127 consecutive patients and prospectively enrolled 93 patients with huge HCC who underwent hepatectomy (training cohort, n=798; validation cohort, n=329; prospective cohort, n=93) in our institute. Based on independent preoperative predictors of 90-day mortality, we established a logistic regression model and visualized the model by nomogram.

Results

The 90-day mortality rates were 9.6%, 9.2%, and 10.9% in the training, validation, and prospective cohort. The α-fetoprotein (AFP) level, the prealbumin levels, and the presence of portal vein tumor thrombosis (PVTT) were preoperative independent predictors of 90-day mortality. A logistic regression model, AFP-prealbumin-PVTT score (APP score), was subsequently established and showed good performance in predicting 90-day mortality (training cohort, AUC =0.87; validation cohort, AUC =0.91; prospective cohort, AUC =0.93). Using a cut-off of −1.96, the model could stratify patients into low risk (≤−1.96) and high risk (>−1.96) with different 90-day mortality rates (~30% vs. ~2%). Furthermore, the predictive performance for 90-day mortality and overall survival was significantly superior to the Child-Pugh score, the model of end-stage liver disease (MELD) score, and the albumin-bilirubin (ALBI) score.

Conclusions

The APP score can precisely predict postoperative 90-day mortality as well as long-term survival for patients with huge HCC, assisting physician selection of suitable candidates for liver resection and improving the safety and efficacy of surgical treatment.

A Novel Machine-Learning Approach to Predict Recurrence After Resection of Colorectal Liver Metastases

BACKGROUND

Surgical resection of hepatic metastases remains the only potentially curative treatment option for patients with colorectal liver metastases (CRLM). Widely adopted prognostic tools may oversimplify the impact of model parameters relative to long-term outcomes.

METHODS

Patients with CRLM who underwent a hepatectomy between 2001 and 2018 were identified in an international, multi-institutional database. Bootstrap resampling methodology used in tandem with multivariable mixed-effects logistic regression analysis was applied to construct a prediction model that was validated and compared with scores proposed by Fong and Vauthey.

RESULTS

Among 1406 patients who underwent hepatic resection of CRLM, 842 (59.9%) had recurrence. The full model (based on age, sex, primary tumor location, T stage, receipt of chemotherapy before hepatectomy, lymph node metastases, number of metastatic lesions in the liver, size of the largest hepatic metastases, carcinoembryonic antigen [CEA] level and KRAS status) had good discriminative ability to predict 1-year (area under the receiver operating curve [AUC], 0.693; 95% confidence interval [CI], 0.684-0.704), 3-year (AUC, 0.669; 95% CI, 0.661-0.677), and 5-year (AUC, 0.669; 95% CI, 0.661-0.679) risk of recurrence. Studies analyzing validation cohorts demonstrated similar model performance, with excellent model accuracy. In contrast, the AUCs for the Fong and Vauthey scores to predict 1-year recurrence were only 0.527 (95% CI, 0.514-0.538) and 0.525 (95% CI, 0.514-0.533), respectively. Similar trends were noted for 3- and 5-year recurrence.

CONCLUSION

The proposed clinical score, derived via machine learning, which included clinical characteristics and morphologic data, as well as information on KRAS status, accurately predicted recurrence after CRLM resection with good discrimination and prognostic ability.