Successful Desensitization with Crizotinib after Crizotinib-induced Liver Injury in ROS1-rearranged Lung Adenocarcinoma

Hepatic adverse events associated with anaplastic lymphoma kinase tyrosine kinase inhibitors: a disproportionality analysis based on FAERS database and analysis of drug-gene interaction network

BACKGROUND

Anaplastic lymphoma kinase (ALK) tyrosine kinase inhibitors (TKIs) are vital for treating ALK-positive cancers but have been associated with liver injury, necessitating further safety investigation. This study examines hepatic adverse event (AE) signals related to ALK TKIs using the U.S. FDA Adverse Event Reporting System (FAERS) and explores potential mechanisms of liver injury.

RESEARCH DESIGN AND METHODS

AE reports from FAERS (Q3 2011 to Q1 2024) related to liver injury were analyzed using the reporting odds ratio (ROR) and multi-item gamma Poisson shrinker (MGPS) methods. Pathway enrichment and drug-gene network analyses were performed to investigate underlying mechanisms.

RESULTS

This study identified 2,132 AE reports from the FAERS database linking hepatic AEs to ALK TKIs therapy. Significant signals were detected by ROR and MGPS methods, with common AEs including aminotransferase abnormalities, hyperbilirubinemia, and increased blood alkaline phosphatase, mainly occurring within the first 30 days of treatment. Gene analysis revealed key nodes in the protein-protein interaction (PPI) network, such as PIK3CA, SRC, and PTK2. Enriched KEGG pathways included the MAPK, PI3K-Akt, and Ras signaling.

CONCLUSION

This pharmacovigilance study identifies significant AE signals linking ALK TKIs to liver injury, highlighting potential mechanisms and providing insights for clinical management and patient outcomes.

Successful Retreatment with Crizotinib After Crizotinib-Induced Liver Failure in ALK-Positive Advanced Lung Adenocarcinoma: A Case Report

Patients with non-small cell lung cancer (NSCLC) harboring anaplastic lymphoma kinase (ALK) gene rearrangements are treated with crizotinib. However, treatment with crizotinib is often discontinued owing to hepatotoxicity. Herein, we report a case of crizotinib-induced liver failure that was successfully treated. A 70-year-old woman complained of a cough with blood in her sputum and presented to our hospital in September 2020. Imaging examination revealed a mass in the middle and lower lobes of the right lung invading the right pulmonary artery and metastases to the right hilar lymph nodes and pleura. A stage IVa (cT4N1M1a) lung adenocarcinoma with ALK fusion was diagnosed. The patient received crizotinib, an ALK tyrosine kinase inhibitor and achieved partial remission. However, she suffered from acute liver failure, which led to the cessation of treatment. The patient was started on a liver protection treatment, and the liver function subsequently recovered. One year later, crizotinib was readministered at a half-dose because of disease progression, and the patient achieved stable disease without hepatotoxicity for 9 months. Therefore, the patient benefited from crizotinib without hepatotoxicity one year after acute liver failure caused by crizotinib.

A Knowledge Graph Embedding Based Approach to Predict the Adverse Drug Reactions Using a Deep Neural Network

Recently Artificial Intelligence(AI) has not only been used to diagnose the disease but also to cure the disease. Researchers started using AI for drug discovery. Predicting the Adverse Drug Reactions(ADRs) caused by the drug in the manufacturing stage or in the clinical trial stage is a very important problem in drug discovery. ADRs have become a major concern resulting in injuries and also becoming fatal sometimes. Drug safety has gained much importance over the years propelling to the forefront investigation of predicting the ADRs. Although prior studies have queried diverse approaches to predict ADRs, very few were found to be effective. Also, the problem of having fewer reports makes the prediction of ADRs more difficult. To tackle this problem effectively, a novel method has been proposed in this paper. The proposed method is based on Knowledge Graph(KG) embedding. Using the KG embedding, we designed and trained a custom-made Deep Neural Network(DNN) called KGDNN(Knowledge Graph DNN) for predicting the ADRs. A KG has been constructed with 6 types of entities: drugs, ADRs, target proteins, indications, pathways, and genes. Using the Node2Vec algorithm, each node has been embedded into a feature space. Using those embeddings, the ADRs are classified by the KGDNN model. The proposed method has obtained an AUROC score of 0.917 and significantly outperformed the existing methods. Two case studies on drugs causing liver injury and COVID-19 recommended drugs have been performed to illustrate the model efficacy.

Successful Treatment with Lorlatinib after the Development of Alectinib-Induced Liver Damage in ALK-Positive Non-Small-Cell Lung Cancer: A Case Report

Alectinib is a key drug for treating anaplastic lymphoma kinase (ALK)-positive non-small-cell lung cancer (NSCLC). Alectinib-induced hepatotoxicity is less common than that through other ALK inhibitors, such as crizotinib or ceritinib. Herein, we describe a case of ALK-positive adenocarcinoma successfully treated with lorlatinib after developing alectinib-induced hepatotoxicity. A 57-year-old Japanese man received alectinib as first-line therapy for ALK-positive NSCLC. After 79 days, alectinib was discontinued because of hepatotoxicity and later restarted at 150 mg/day, inducing hepatotoxicity again after 64 days. Switching to lorlatinib treatment (continued for >4 months) caused no severe adverse effects. Hence, lorlatinib may be useful for patients experiencing alectinib-induced hepatotoxicity.

Prediction of adverse drug reactions based on knowledge graph embedding

BACKGROUND

Adverse drug reactions (ADRs) are an important concern in the medication process and can pose a substantial economic burden for patients and hospitals. Because of the limitations of clinical trials, it is difficult to identify all possible ADRs of a drug before it is marketed. We developed a new model based on data mining technology to predict potential ADRs based on available drug data.

METHOD

Based on the Word2Vec model in Nature Language Processing, we propose a new knowledge graph embedding method that embeds drugs and ADRs into their respective vectors and builds a logistic regression classification model to predict whether a given drug will have ADRs.

RESULT

First, a new knowledge graph embedding method was proposed, and comparison with similar studies showed that our model not only had high prediction accuracy but also was simpler in model structure. In our experiments, the AUC of the classification model reached a maximum of 0.87, and the mean AUC was 0.863.

CONCLUSION

In this paper, we introduce a new method to embed knowledge graph to vectorize drugs and ADRs, then use a logistic regression classification model to predict whether there is a causal relationship between them. The experiment showed that the use of knowledge graph embedding can effectively encode drugs and ADRs. And the proposed ADRs prediction system is also very effective.

Successful Treatment of Crizotinib-Induced Fulminant Liver Failure: A Case Report and Review of Literature

Crizotinib is a first-line tyrosine kinase inhibitor used for the treatment of metastatic lung cancer. Crizotinib-induced hepatotoxicity is a rare event. We report a case of a 46-year-old female with a history of metastatic lung cancer who presented with acute liver failure after being on crizotinib for two months. The medication was discontinued, and she was treated with N-acetylcysteine for seven days. Her liver function tests returned to normal limits after 26 days after admission. The precise mechanism and risk factors of crizotinib-induced hepatotoxicity remain unknown. Physicians should be aware of the potentially lethal side effect caused by crizotinib.