Background and Objectives: Posthepatectomy liver failure (PHLF) remains a major cause of morbidity and mortality for patients undergoing major liver resections. Recent research highlights the expanding role of machine learning (ML), a crucial subfield of artificial intelligence (AI), in optimizing risk stratification. The aim of the current study was to review, elaborate on and critically analyze the available literature regarding the use of ML-driven risk prediction models for posthepatectomy liver failure. Materials and Methods: A systematic search was conducted in the PubMed/MEDLINE, Scopus and Web of Science databases. Fifteen studies that trained and validated ML models for prediction of PHLF were further included and analyzed. Results: The available literature supports the value of ML-derived models for PHLF prediction. Perioperative clinical, laboratory and imaging features have been combined in a variety of different algorithms to provided interpretable and accurate models for identifying patients at risk of PHLF. The ML-based algorithms have consistently demonstrated high area under the curve and sensitivity values, surpassing traditionally used risk scores in predictive performance. Limitations include the small sample sizes, heterogeneity in populations included, lack of external validation and a reported poor ability to distinguish between true positive and false positive cases in several studies. Conclusions: Despite the constraints, ML-driven tools, in combination with traditional scoring systems and clinical insight, may enable early and accurate PHLF risk detection, personalized surgical planning and optimization of postoperative outcomes in liver surgery.

Background: The introduction of tyrosine kinase inhibitors has revolutionised the treatment of gastrointestinal stromal tumours (GISTs), yet the role of cytoreductive surgery (CRS) plus hyperthermic intraperitoneal chemotherapy (HIPEC) in peritoneal GISTosis remains controversial. Methods: A retrospective analysis was conducted on patients with peritoneal GISTosis who underwent CRS plus HIPEC in an 18-year period. We analysed the clinicopathological characteristics and evaluated the perioperative and long-term outcomes based on the extent of disease (peritoneal cancer index, PCI), the resection (completeness of cytoreduction score) and the IM-administration. The survival factors were also analysed and the Kaplan–Meier estimator to model and estimate overall (OS) and progression-free survival (PFS). The median follow-up period was 72 months (range, 12–146). Results: A total of 25 patients (M:F = 15:10) with a median age of 57 years (range, 32–69) underwent CRS with HIPEC for peritoneal GIST metastases, detected either synchronously (n = 11) or metachronously (n = 14). The media PCI score was 9 (range, 4–20) and complete cytoreduction was achieved in 80%. Grade III complications were observed in two patients, whereas there was no postoperative mortality. Neoadjuvant imatinib-mesylate (IM) therapy was administered in 60% of patients who detected with metachronous metastases (n = 8/14), whereas adjuvant IM therapy was administered in 19 of 25 patients. Median OS was 62 months (95% CI = 22.8–101.2). Median OS and DFS for patients with PCI scores ≤ 10 were significantly longer compared to those with PCI scores > 10 (p = 0.009 and p = 0.024, respectively). Patients with CC scores of 0–1 had a significantly longer OS compared to those with CC scores of 2 (p = 0.005) and 3 (p = 0.002) and longer PFS compared to those with CC scores of 3 (p = 0.005). The need for imatinib did not significantly impact OS (p = 0.240) or PFS (p = 0.243). Conclusions: CRS combined with HIPEC shows promising results in peritoneal GISTosis, especially in patients with lower PCI and CC scores. Until larger studies validate its safety and efficacy, it should be primarily performed in expert hands in specialised peritoneal surface oncology centres.

Malignant peritoneal mesothelioma (MPM) is a rare and aggressive tumour with poor prognosis, often diagnosed late due to nonspecific symptoms. Current standard treatment involves systemic chemotherapy and cytoreductive surgery combined with hyperthermic intraperitoneal chemotherapy (CRS/HIPEC), but this approach is limited to selected patients. Pressurized Intraperitoneal Aerosol Chemotherapy (PIPAC) has emerged as a novel technique improving drug delivery and penetration in the peritoneal cavity. This narrative review evaluates the role of PIPAC in the treatment of MPM, analysing data from clinical studies on its feasibility, safety, and efficacy. Evidence suggests that PIPAC is a well-tolerated procedure, with a manageable safety profile and potential to improve survival and tumour response in patients with unresectable or recurrent disease. Limitations in current studies include small cohorts and heterogeneous patient populations, underscoring the need for further research. PIPAC represents a promising therapeutic option, offering enhanced intraperitoneal chemotherapy (IPC) delivery with minimal systemic toxicity. Future investigations should focus on optimizing treatment protocols and evaluating long-term benefits to better define PIPAC’s role in clinical practice.