Dasatinib-induced Reversible Demyelinating Peripheral Neuropathy and Successful Conversion to Nilotinib in Chronic Myelogenous Leukemia

Cross-Domain Text Mining to Predict Adverse Events from Tyrosine Kinase Inhibitors for Chronic Myeloid Leukemia

Tyrosine kinase inhibitors (TKIs) are prescribed for chronic myeloid leukemia (CML) and some other cancers. The objective was to predict and rank TKI-related adverse events (AEs), including under-reported or preclinical AEs, using novel text mining. First, k-means clustering of 2575 clinical CML TKI abstracts separated TKIs by significant (p < 0.05) AE type: gastrointestinal (bosutinib); edema (imatinib); pulmonary (dasatinib); diabetes (nilotinib); cardiovascular (ponatinib). Next, we propose a novel cross-domain text mining method utilizing a knowledge graph, link prediction, and hub node network analysis to predict new relationships. Cross-domain text mining of 30+ million articles via SemNet predicted and ranked known and novel TKI AEs. Three physiology-based tiers were formed using unsupervised rank aggregation feature importance. Tier 1 ranked in the top 1%: hematology (anemia, neutropenia, thrombocytopenia, hypocellular marrow); glucose (diabetes, insulin resistance, metabolic syndrome); iron (deficiency, overload, metabolism), cardiovascular (hypertension, heart failure, vascular dilation); thyroid (hypothyroidism, hyperthyroidism, parathyroid). Tier 2 ranked in the top 5%: inflammation (chronic inflammatory disorder, autoimmune, periodontitis); kidney (glomerulonephritis, glomerulopathy, toxic nephropathy). Tier 3 ranked in the top 10%: gastrointestinal (bowel regulation, hepatitis, pancreatitis); neuromuscular (autonomia, neuropathy, muscle pain); others (secondary cancers, vitamin deficiency, edema). Results suggest proactive TKI patient AE surveillance levels: regular surveillance for tier 1, infrequent surveillance for tier 2, and symptom-based surveillance for tier 3.

Can rheumatologists stop causing demyelinating disease?

BACKGROUND

Perhaps the most informative experiments in human disease are clinical trials and notably, responses to specific therapies can be highly-informative to help understand disease pathogenesis. There are reagents that inhibit a variety of different autoimmune conditions, such as CD20 memory B cell depleters that are active in both multiple sclerosis (MS), rheumatoid arthritis (RA) and other conditions, suggesting influences on common immune mechanisms in different diseases. However, a notable exception seemed to be the use of tumour necrosis factor (TNF) inhibitors that limits RA, yet seem to, rarely, trigger demyelination and induce MS. This was first seen with TNF-inhibiting monoclonal antibodies and TNF-receptor-immunoglobulin fusion proteins. However, this is also seen with tyrosine and Janus kinase inhibitors that inhibit RA, yet induce demyelinating disease in some individuals PURPOSE: To provide an overview, from a B cell centric perspective, that may underpin the biology that links arthritis treatments to the development of demyelinating disease.

CONCLUSIONS

It is apparent that the disease modifying anti-rheumatoid drugs that cause demyelination share a number of common features. These agents tend to inhibit TNF-receptor signalling, augment or exhibit limited inhibitor activity on class-switched memory B cells and importantly appear to be relatively excluded from the central nervous system (CNS). They will thus not target ectopic B cell follicles in the CNS, unlike that occurring in peripheral autoimmunity as seen with anti-TNF treatments in RA. Agents such as ibudilast and some Janus kinase inhibitors that inhibit TNF and clearly penetrate the CNS do not appear to induce demyelination and may even be neuroprotective. It remains to be established whether selection or development of CNS penetrant agents may avoid CNS-complications of treatments for RA. Clearly, further studies are warranted.