Improving Adjuvant Liver-Directed Treatment Recommendations for Unresectable Hepatocellular Carcinoma: An Artificial Intelligence–Based Decision-Making Tool

Abstract

PURPOSE Liver-directed therapy after transarterial chemoembolization (TACE) can lead to improvement in survival for selected patients with unresectable hepatocellular carcinoma (HCC). However, there is uncertainty in the appropriate application and modality of therapy in current clinical practice guidelines. The aim of this study was to develop a proof-of-concept, machine learning (ML) model for treatment recommendation in patients previously treated with TACE and select patients who might benefit from additional treatment with combination stereotactic body radiotherapy (SBRT) or radiofrequency ablation (RFA). METHODS This retrospective observational study was based on data from an urban, academic hospital system selecting for patients diagnosed with stage I-III HCC from January 1, 2008, to December 31, 2018, treated with TACE, followed by adjuvant RFA, SBRT, or no additional liver-directed modality. A feedforward, ML ensemble model provided a treatment recommendation on the basis of pairwise assessments evaluating each potential treatment option and estimated benefit in survival. RESULTS Two hundred thirty-seven patients met inclusion criteria, of whom 54 (23%) and 49 (21%) received combination of TACE and SBRT or TACE and RFA, respectively. The ML model suggested a different consolidative modality in 32.7% of cases among patients who had previously received combination treatment. Patients treated in concordance with model recommendations had significant improvement in progression-free survival (hazard ratio 0.5; P = .007). The most important features for model prediction were cause of cirrhosis, stage of disease, and albumin-bilirubin grade (a measure of liver function). CONCLUSION In this proof-of-concept study, an ensemble ML model was able to provide treatment recommendations for HCC who had undergone prior TACE. Additional treatment in line with model recommendations was associated with significant improvement in progression-free survival, suggesting a potential benefit for ML-guided medical decision making.

Different applications of Artificial Intelligence in liver cancer: a scoping review – part II, from treatment planning and efficacy assessment to prognosis prediction and follow-up. (Preprint)

“…However, when multiple interventions are combined in a large period, it is hard to foresee which patient will benefit from a specific strategy and which one will not respond and should be addressed to systemic therapy or best supportive care avoiding unbeneficial invasive procedures. For 6 Thailand SPECT/CT-scan 56 CNN, automatic Segmentation for liver TARE planning (HCC) Wei, 2021 8 Germany/China US/CT-scan 52 CNN, automatic Probe plane identification for liver TA planning (HCC) De Landro, 2021 9 Italy HSI -CNN, automatic Prediction of ablation margins for LA planning (HCC) Lv, 2021 10 China CT-scan 50 ML Liver remnant volume and resection plane prediction (HCC) Takamoto, 2022 12 Japan CT-scan 144 CNN, automatic Liver and tumor segmentation and volume calculation (HCC, ICC, Met, benign lesions) Zhu, 2023 14 China MR/CT-scan radiomics, IGC 190 ML Liver functional reserve evaluation (HCC) Mo, 2022 15 USA clinical, biochemical 237 ML Treatment planning (SBRT vs. TA) after TACE (HCC) Boldanova, 2021 17 Switzerland clinical, radiological, transcriptomics 33 ML Prediction of TACE outcome (HCC) Sun, 2020 18 China MR radiomics 84 ML Prediction of TACE outcome (HCC) Hsu, 2022 19 Taiwan biochemical 82 ML Prediction of Lenvatinib response (HCC) Luo, 2022 20 China genomics/transcriptomics 450 ANN, ML Prediction of chemotherapy response (HCC)…”

The management of hepatocellular carcinoma. Current expert opinion and recommendations derived from the 24th ESMO/World Congress on Gastrointestinal Cancer, Barcelona, 2022

“…Artificial intelligence could in the future help define the optimal moment for this switch. 62 A study including 237 patients evaluated the value of adding RFA or SBRT after TACE, using an artificial intelligence system that recommended it in about half of the patients. In these patients the mean progression-free survival was 5.3 months compared to 1.8 years in untreated patients, and overall survival was also increased to 7.5 versus 5.3 years.…”