Drug-Induced Immune Thrombocytopenia Toxicity Prediction Based on Machine Learning

Drug-Induced Thrombocytopenia Severity and Toxicity (DITPst): binary classification of drugs by human thrombocytopenia toxicity

BACKGROUND

Drug-induced thrombocytopenia (DITP) often occurs in patients during clinical treatment. However, clinicians usually fail to distinguish which drugs can be plausible culprits accurately. We aimed to develop a large comprehensive drug benchmark database with DITP toxicity using the recommended method by FDA.

RESEARCH DESIGN AND METHODS

We collected information from six databases that involved drug labeling information, literature, safety signal mining and laboratory testing to generate the annotated drug list with DITP toxicity. Then, we descripted the DITP positive-negative distribution based on the Anatomical Therapeutic Chemical (ATC) coding system; hotspot analysis was conducted to identify therapeutic categories of drugs within each organ system that warrant attention regarding DITP.

RESULTS

The DITPst database comprised 1,765 drugs, of which 858 were DITP-positives, whereas 907 were negatives. The investigation of distribution across various therapeutic categories revealed the most frequent DITP-positive categories were immunostimulants (10/11), anti-inflammatory, and antirheumatic products (28/32), and antibacterials for systemic use (102/121). On the contrary, the least frequent DITP-positive therapeutic categories were diagnostic radiopharmaceuticals (12/12), pituitary and hypothalamic hormones and analogues (17/18), and drugs for constipation (16/17).

CONCLUSIONS

We consider the DITPst benchmark database to be an invaluable resource for the community to improve DITP safety research and drug development.

An Updated Comprehensive Pharmacovigilance Study of Drug-Induced Thrombocytopenia Based on FDA Adverse Event Reporting System Data

Drug-induced thrombocytopenia (DIT) deserves both clinical and research attention for the serious clinical consequences and high prevalence of the condition. The current study aimed to perform a comprehensive pharmacovigilance analysis of DIT reported in the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) database, with a particular focus on drugs associated with thrombocytopenia events. A disproportionality analysis of DIT was conducted using reports submitted to FARES from January 2004 to December 2022. Both the information component (IC) and reporting odds ratio (ROR) algorithms were applied to identify an association between target drugs and DIT events. A total of 15,940,383 cases were gathered in FAERS, 168,657 of which were related to DIT events. The top 50 drugs ranked by number of cases and ranked by signal strength were documented. The top 5 drugs ranked by number of cases were lenalidomide (10,601 cases), niraparib (3726 cases), ruxolitinib (3624 cases), eltrombopag (3483 cases), and heparin (3478 cases). The top 5 drugs ranked by signal strength were danaparoid (ROR 37.61, 95%CI 30.46-46.45), eptifibatide (ROR 34.75, 95%CI 30.65-39.4), inotersen (ROR 34.00, 95%CI 29.47-39.23), niraparib (ROR 30.53, 95%CI 29.42-31.69), and heparin (ROR 28.84, 95%CI 27.76-29.97). The top 3 involved drug groups were protein kinase inhibitors, antimetabolites, and monoclonal antibodies and antibody-drug conjugates. The current comprehensive pharmacovigilance study identified more drugs associated with thrombocytopenia. Although the mechanisms of DIT have been elucidated for some drugs, others still require further investigation.

Cholangiocyte organoids to study drug-induced injury

BACKGROUND

Drug induced bile duct injury is a frequently observed clinical problem leading to a wide range of pathological features. During the past decades, several agents have been identified with various postulated mechanisms of bile duct damage, however, mostly still poorly understood.

METHODS

Here, we investigated the mechanisms of chlorpromazine (CPZ) induced bile duct injury using advanced in vitro cholangiocyte cultures. Intrahepatic cholangiocyte organoids (ICOs) were driven into mature cholangiocyte like cells (CLCs), which were exposed to CPZ under cholestatic or non-cholestatic conditions through the addition of a bile acid cocktail.

RESULTS

CPZ caused loss of monolayer integrity by reducing expression levels of tight junction protein 1 (TJP1), E-cadherin 1 (CDH1) and lysyl oxidase homolog 2 (LOXL2). Loss of zonula occuludens-1 (ZO-1) and E-cadherin was confirmed by immunostaining after exposure to CPZ and rhodamine-123 leakage further confirmed disruption of the cholangiocyte barrier function. Furthermore, oxidative stress seemed to play a major role in the early damage response by CPZ. The drug also decreased expression of three main basolateral bile acid transporters, ABCC3 (ATP binding cassette subfamily C member 3), SLC51A/B (solute carrier family 51 subunit alpha/beta) and multidrug resistance transporter ABCB1 (ATP binding cassette subfamily B member 1), thereby contributing to bile acid accumulation. CPZ did not induce an inflammatory response by itself, but addition of TNFα revealed a synergistic effect.

CONCLUSION

These results show that ICOs present a model to identify toxic drugs affecting the bile ducts while providing mechanistic insights into hepatotoxicity.

Applications of Artificial Intelligence in Thrombocytopenia

Thrombocytopenia is a medical condition where blood platelet count drops very low. This drop in platelet count can be attributed to many causes including medication, sepsis, viral infections, and autoimmunity. Clinically, the presence of thrombocytopenia might be very dangerous and is associated with poor outcomes of patients due to excessive bleeding if not addressed quickly enough. Hence, early detection and evaluation of thrombocytopenia is essential for rapid and appropriate intervention for these patients. Since artificial intelligence is able to combine and evaluate many linear and nonlinear variables simultaneously, it has shown great potential in its application in the early diagnosis, assessing the prognosis and predicting the distribution of patients with thrombocytopenia. In this review, we conducted a search across four databases and identified a total of 13 original articles that looked at the use of many machine learning algorithms in the diagnosis, prognosis, and distribution of various types of thrombocytopenia. We summarized the methods and findings of each article in this review. The included studies showed that artificial intelligence can potentially enhance the clinical approaches used in the diagnosis, prognosis, and treatment of thrombocytopenia.