Outcomes of immune checkpoint inhibitor-induced liver toxicity managed by hepatologists in a multidisciplinary toxicity team.

AIM: To detect immune-related adverse events (irAEs) early and treat them appropriately, our institute established an irAE-focused multidisciplinary toxicity team in cooperation with various departments. This study aimed to evaluate a consultation system involving a team of hepatologists in terms of its utility for the management of severe immune checkpoint inhibitor (ICI)-induced liver toxicity. METHODS: To analyze the diagnosis and treatment of severe ICI-induced liver toxicity (Grade 2 requiring corticosteroid therapy and Grade 3 or higher), we examined patients' clinical courses before and after the hepatologist consultation system was established (pre-period, September 2014 to February 2019; post-period, March 2019 to March 2023). RESULTS: The median follow-up period was 392 days. Of the 1247 patients with advanced malignancies treated with ICIs, 66 developed severe ICI-induced liver toxicity (n = 22 and 44 in the pre- and post-periods, respectively). In the pre-period, hepatologist consultations were sought for 15/22 patients, whereas in the post-period, 42/44 patients were referred to and treated by hepatologists. The time from the onset of liver toxicity to the consultation was significantly shorter in the post-period than in the pre-period (mean 1.9 vs. 6.5 days, respectively; p = 0.012). The number of patients with a biopsy-confirmed diagnosis of ICI-induced liver toxicity was significantly higher in the post-period than in the pre-period (n = 22 vs. n = 3, respectively; p = 0.006). Finally, there were no cases of immune-related cholangitis in the pre-period, compared to five cases in the post-period. CONCLUSION: A hepatologist consultation system in an irAE-focused multidisciplinary toxicity team is useful for managing severe ICI-induced liver toxicity.

Predictive Models for Palliative Care Needs of Advanced Cancer Patients Receiving Chemotherapy.

CONTEXT: Early palliative care is recommended within eight-week of diagnosing advanced cancer. Although guidelines suggest routine screening to identify cancer patients who could benefit from palliative care, implementing screening can be challenging due to understaffing and time constraints. OBJECTIVES: To develop and evaluate machine learning models for predicting specialist palliative care needs in advanced cancer patients undergoing chemotherapy, and to investigate if predictive models could substitute screening tools. METHODS: We conducted a retrospective cohort study using supervised machine learning. The study included patients aged 18 or older, diagnosed with metastatic or stage IV cancer, who underwent chemotherapy and distress screening at a designated cancer hospital in Japan from April 1, 2018, to March 31, 2023. Specialist palliative care needs were assessed based on distress screening scores and expert evaluations. Data sources were hospital's cancer registry, health claims database, and nursing admission records. The predictive model was developed using XGBoost, a machine learning algorithm. RESULTS: Out of the 1878 included patients, 561 were analyzed. Among them, 114 (20.3%) exhibited needs for specialist palliative care. After under-sampling to address data imbalance, the models achieved an Area Under the Curve (AUC) of 0.89 with 95.8% sensitivity and a specificity of 71.9%. After feature selection, the model retained five variables, including the patient-reported pain score, and showcased an 0.82 AUC. CONCLUSION: Our models could forecast specialist palliative care needs for advanced cancer patients on chemotherapy. Using five variables as predictors could replace screening tools and has the potential to contribute to earlier palliative care.