Machine Learning Predictive Model to Guide Treatment Allocation for Recurrent Hepatocellular Carcinoma After Surgery.

Importance: Clear indications on how to select retreatments for recurrent hepatocellular carcinoma (HCC) are still lacking. Objective: To create a machine learning predictive model of survival after HCC recurrence to allocate patients to their best potential treatment. Design, Setting, and Participants: Real-life data were obtained from an Italian registry of hepatocellular carcinoma between January 2008 and December 2019 after a median (IQR) follow-up of 27 (12-51) months. External validation was made on data derived by another Italian cohort and a Japanese cohort. Patients who experienced a recurrent HCC after a first surgical approach were included. Patients were profiled, and factors predicting survival after recurrence under different treatments that acted also as treatment effect modifiers were assessed. The model was then fitted individually to identify the best potential treatment. Analysis took place between January and April 2021. Exposures: Patients were enrolled if treated by reoperative hepatectomy or thermoablation, chemoembolization, or sorafenib. Main Outcomes and Measures: Survival after recurrence was the end point. Results: A total of 701 patients with recurrent HCC were enrolled (mean [SD] age, 71 [9] years; 151 [21.5%] female). Of those, 293 patients (41.8%) received reoperative hepatectomy or thermoablation, 188 (26.8%) received sorafenib, and 220 (31.4%) received chemoembolization. Treatment, age, cirrhosis, number, size, and lobar localization of the recurrent nodules, extrahepatic spread, and time to recurrence were all treatment effect modifiers and survival after recurrence predictors. The area under the receiver operating characteristic curve of the predictive model was 78.5% (95% CI, 71.7%-85.3%) at 5 years after recurrence. According to the model, 611 patients (87.2%) would have benefited from reoperative hepatectomy or thermoablation, 37 (5.2%) from sorafenib, and 53 (7.6%) from chemoembolization in terms of potential survival after recurrence. Compared with patients for which the best potential treatment was reoperative hepatectomy or thermoablation, sorafenib and chemoembolization would be the best potential treatment for older patients (median [IQR] age, 78.5 [75.2-83.4] years, 77.02 [73.89-80.46] years, and 71.59 [64.76-76.06] years for sorafenib, chemoembolization, and reoperative hepatectomy or thermoablation, respectively), with a lower median (IQR) number of multiple recurrent nodules (1.00 [1.00-2.00] for sorafenib, 1.00 [1.00-2.00] for chemoembolization, and 2.00 [1.00-3.00] for reoperative hepatectomy or thermoablation). Extrahepatic recurrence was observed in 43.2% (n = 16) for sorafenib as the best potential treatment vs 14.6% (n = 89) for reoperative hepatectomy or thermoablation as the best potential treatment and 0% for chemoembolization as the best potential treatment. Those profiles were used to constitute a patient-tailored algorithm for the best potential treatment allocation. Conclusions and Relevance: The herein presented algorithm should help in allocating patients with recurrent HCC to the best potential treatment according to their specific characteristics in a treatment hierarchy fashion.

Modified cisplatin/interferon α-2b/doxorubicin/5-fluorouracil (PIAF) chemotherapy in patients with no hepatitis or cirrhosis is associated with improved response rate, resectability, and survival of initially unresectable hepatocellular carcinoma.

BACKGROUND: The purpose of this study was to evaluate the factors associated with response rate, resectability, and survival after cisplatin/interferon α-2b/doxorubicin/5-fluorouracil (PIAF) combination therapy in patients with initially unresectable hepatocellular carcinoma. METHODS: The study included 2 groups of patients treated with conventional high-dose PIAF (n = 84) between 1994 and 2003 and those without hepatitis or cirrhosis treated with modified PIAF (n = 33) between 2003 and 2012. Tolerance of chemotherapy, best radiographic response, rate of conversion to curative surgery, and overall survival were analyzed and compared between the 2 groups, and multivariate and logistic regression analyses were applied to identify predictors of response and survival. RESULTS: The modified PIAF group had a higher median number of PIAF cycles (4 versus 2, P = .049), higher objective response rate (36% versus 15%, P = .013), higher rate of conversion to curative surgery (33% versus 10%, P = .004), and longer median overall survival (21.3 versus 10.6 months, P = .002). Multivariate analyses confirmed that positive hepatitis B serology (hazard ratio [HR] = 1.68; 95% confidence interval [CI] = 1.08-2.59) and Eastern Cooperative Oncology Group performance status ≥ 2 (HR = 1.75; 95% CI = 1.04-2.93) were associated with worse survival whereas curative surgical resection after PIAF treatment (HR = 0.15; 95% CI = 0.07-0.35) was associated with improved survival. CONCLUSIONS: In patients with initially unresectable hepatocellular carcinoma, the modified PIAF regimen in patients with no hepatitis or cirrhosis is associated with improved response, resectability, and survival.

Adjuvant chemotherapy with FOLFOX for primary colorectal cancer is associated with increased somatic gene mutations and inferior survival in patients undergoing hepatectomy for metachronous liver metastases.

OBJECTIVE: We hypothesized that metachronous colorectal liver metastases (CLM) have different biology after failure of oxaliplatin (FOLFOX) compared to 5-fluorouracil (5-FU) or no chemotherapy for adjuvant treatment of colorectal cancer (CRC). BACKGROUND: It is unclear whether patients treated with liver resection for metachronous CLM after adjuvant FOLFOX for CRC have worse outcomes than those who received 5-FU or no chemotherapy. METHODS: We identified 341 patients who underwent hepatectomy for metachronous CLM (disease-free interval ≥12 months, 1993-2010). Mass-spectroscopy genotyping for somatic gene mutations in CLM was performed in a subset of 129 patients. RESULTS: Adjuvant treatment for primary CRC was FOLFOX in 77 patients, 5-FU in 169 patients, and no chemotherapy in 95 patients. Node-positive primary was comparable between FOLFOX and 5-FU but lower in the no-chemotherapy group (P < 0.0001). Median metastasis size was smaller in the FOLFOX group (2.5 cm) than in the 5-FU (3.0 cm) or no-chemotherapy (3.5 cm) groups, (P = 0.008) although prehepatectomy chemotherapy utilization, metastases number, and carcinoembryonic antigen levels were similar. Disease-free survival (DFS) and overall survival (OS) rates after hepatectomy were worse in patients treated with adjuvant FOLFOX [DFS at 3 years: 14% vs 38% (5-FU) vs 45% (no-chemo), OS at 3 years: 58% vs 70% (5-FU) vs 84% (no-chemo)]. On multivariate analysis, adjuvant FOLFOX was associated with worse DFS (P < 0.0001) and OS (P < 0.0001). Mutation analysis revealed ≥1 mutations in 57% of patients (27/47) after FOLFOX, 29% (12/41) after 5-FU, and 32% (13/41) after no chemotherapy (P = 0.011). CONCLUSIONS: Adjuvant FOLFOX for primary CRC is associated with a high rate of somatic mutations in liver metastases and inferior outcomes after hepatectomy for metachronous CLM.