Clustering using unsupervised machine learning to stratify the risk of immune‐related liver injury

Abstract

Background and Aim: Immune-related liver injury (liver-irAE) is a clinical problem with a potentially poor prognosis. Methods: We retrospectively collected clinical data from patients treated with immune checkpoint inhibitors between September 2014 and December 2021 at the Nagoya University Hospital. Using an unsupervised machine learning method, the Gaussian mixture model, to divide the cohort into clusters based on inflammatory markers, we investigated the cumulative incidence of liver-irAEs in these clusters.Results: This study included a total of 702 patients. Among them, 492 (70.1%) patients were male, and the mean age was 66.6 years. During the mean follow-up period of 423 days, severe liver-irAEs (Common Terminology Criteria for Adverse Events grade ≥ 3) occurred in 43 patients. Patients were divided into five clusters (a, b, c, d, and e). The cumulative incidence of liver-irAE was higher in cluster c than in cluster a (hazard ratio [HR]: 13.59, 95% confidence interval [CI]: 1.70-108.76, P = 0.014), and overall survival was worse in clusters c and d than in cluster a (HR: 2.83, 95% CI: 1.77-4.50, P < 0.001; HR: 2.87, 95% CI: 1.47-5.60, P = 0.002, respectively). Clusters c and d were characterized by high temperature, C-reactive protein, platelets, and low albumin. However, there were differences in the prevalence of neutrophil count, neutrophil-tolymphocyte ratio, and liver metastases between both clusters. Conclusions: The combined assessment of multiple markers and body temperature may help stratify high-risk groups for developing liver-irAE.

Risk Factors for Immune Checkpoint Inhibitor-Induced Liver Injury and the Significance of Liver Biopsy

“…Its has also been suggested to be high in PD-1 + CTLA-4 combination therapy [14,[18][19][20]. There are also reports that a high pre-administration lymphocyte or eosinophil count is related to ICI-induced LI [21,22], but a high eosinophil count is recently considered a risk factor [20]. In addition, factors including fever after the beginning of treatment [23] and a high neutrophil-lymphocyte ratio (NLR) after treatment are considered to be related to ICI-induced LI.…”

Identification of clinical phenotypes associated with poor prognosis in patients with nonalcoholic fatty liver disease via unsupervised machine learning

“…GMM is a powerful method that was also able to expose potential phenotypes within an observational cohort from a previous report. 37,38 GMM is a powerful tool for phenotyping patients into interpretable groups on a study-by-study basis with different analyses and factors.…”

“…Therefore, our study identified a possible clinical picture that aligns with the picture engaged by clinicians when treating patients. GMM is a powerful method that was also able to expose potential phenotypes within an observational cohort from a previous report 37,38 . GMM is a powerful tool for phenotyping patients into interpretable groups on a study‐by‐study basis with different analyses and factors.…”

Diagnostic guide for immune checkpoint inhibitor‐induced liver injury

“…16 Previously reported risk factors for developing ICI-induced liver injury include use of anti-CTLA-4 antibody drugs, development of irAEs in other organs, sex, fever after ICI administration, complications with autoimmune liver diseases, and type of malignant tumors, but further investigation is needed. [16][17][18][19][20] When diagnosing ICI-induced liver injury, it is important to first exclude diseases that may cause liver injury other than irAEs, as with other drug-induced liver injuries, and to evaluate the pattern and severity of the injury. A liver biopsy is useful in confirming the diagnosis, determining the presence or absence of comorbid liver disease, and evaluating the severity.…”

“…Previously reported risk factors for developing ICI‐induced liver injury include use of anti‐CTLA‐4 antibody drugs, development of irAEs in other organs, sex, fever after ICI administration, complications with autoimmune liver diseases, and type of malignant tumors, but further investigation is needed 16–20 …”