Patient-tailored algorithm predicts best treatment for recurrent HCC
Click Here to Manage Email Alerts
Researchers have proposed a machine-learning algorithm for personalized treatment selection in patients with recurrent hepatocellular carcinoma, based on data published in JAMA Surgery.
“Several therapies have been investigated extensively in the literature to improve survival after recurrence (SAR); however, no clear indications are available on which treatment should be chosen according to the recurrent tumor presentation. Few guidelines provide an indication for those events, suggesting that the treatment should be selected according to the stage,” Simone Famularo, MD, of the department of biomedical sciences at Humanitas University in Milan, and colleagues wrote. “Recently, the introduction of machine-learning algorithms in medicine drastically changed the potential to develop highly accurate prediction models.
“The decision-making in oncology is the sum of the oncological knowledge and the physicians’ experience: The first is the result of several years of research, while the second is intrinsically connected to the physician’s skills, previous experiences, availability of services, but also the patient’s will.”
In a secondary analysis of data from the Hepatocarcinoma Recurrence on the Liver Study, Famularo and colleagues enrolled 701 patients (mean age, 71 years; 21.5% women) with recurrent HCC from January 2008 to December 2019. Of these patients, 41.8% underwent reoperative hepatectomy or thermoablation for recurrence, 31.4% underwent chemoembolization and 26.8% received sorafenib.
Researchers selected treatment, age, cirrhosis, number and size of recurrent nodules, bilobar presentation, extrahepatic spread, and time to recurrence as predictive variables. The area under the receiver operating curve of this model was 78.5% (95% CI, 71.7-85.3) 5 years following recurrence.
In terms of potential survival, 87.2% of patients would have benefitted from reoperative hepatectomy or thermoablation, 7.6% from chemoembolization and 5.2% from sorafenib. Further investigation showed treatment with sorafenib and chemoembolization had the highest potential to treat older patients compared with reoperative hepatectomy or thermoablation (median age, 78.5 years; 77.02 years and 71.59 years, respectively) with a lower median number of multiple recurrent nodules (1 vs. 1 vs. 2 for sorafenib, chemoembolization and hepatectomy or thermoablation, respectively).
Extrahepatic recurrence occurred in 43.2% of patients for whom sorafenib was the best potential treatment compared with 14.6% of patients for whom reoperative hepatectomy or thermoablation were the best potential treatments. In those for whom chemoembolization was the best potential treatment, 0% had extrahepatic recurrence.
“The recognition of the best potential SAR allowed the identification that up to 87% of patients who were treated with surgery for HCC and then experienced a recurrence may find an advantage from a repetitive curative strategy. However, according to our data, almost 40% received a curative approach for their recurrence,” Famularo and colleagues wrote. “Although the superiority of repeated curative therapies is not surprising, different approaches could be available in the daily practice, as a result of the availability of multidisciplinary strategies, the high tumor heterogeneity and the frequent coexistence of cirrhosis, which render clinical decisions more challenging.
“Deciding among them may be intricate: Our algorithm provides a way to simulate different strategies according to the patient’s oncological characteristics.”
Collapse
Read more about
Click Here to Manage Email Alerts