Risk evaluation of carbapenem-induced liver injury based on machine learning analysis

Drug Induced Liver Injury: Highlights and Controversies in the 2023 Literature

Drug-induced liver injury (DILI) remains an active field of clinical research and investigation with more than 4700 publications appearing in 2023 relating to hepatotoxicity of all causes and injury patterns. As in years past, we have attempted to identify and summarize highlights and controversies from the past year's literature. Several new and novel therapeutic agents were approved by the US Food and Drug Administration (FDA) in 2023, a number of which were associated with significant hepatotoxicity. Updates in the diagnosis and management of DILI using causality scores as well as newer artificial intelligence-based methods were published. Details of newly established hepatotoxins as well as updated information on previously documented hepatotoxic drugs is presented. Significant updates in treatment of DILI were also included as well as reports related to global DILI registries.

Potential of Albumin-Bilirubin Score for Estimating the Voriconazole-Induced Hepatotoxicity Undergoing Therapeutic Drug Monitoring: A Single-Center Retrospective Cohort Study

PURPOSE

Despite implementation of therapeutic drug monitoring (TDM) for voriconazole, the incidence of hepatotoxicity remains high. The albumin-bilirubin (ALBI) score may be useful for estimating voriconazole-induced hepatotoxicity. This pilot study aimed to investigate whether the ALBI score could estimate voriconazole-induced hepatotoxicity during TDM implementation.

METHODS

This single-center, retrospective cohort study included 134 patients. The primary outcome was voriconazole-induced hepatotoxicity. The cutoff value of the ALBI score was determined using a receiver operating characteristic curve. The cumulative risk of hepatotoxicity was evaluated using Kaplan-Meier curve analysis with a log-rank test for the cutoff value and ALBI grade. Moreover, the group of patients with the trough concentration of voriconazole 1-4 μg/mL was also investigated.

FINDINGS

The incidence of hepatotoxicity was 13.4% (18/134). The cutoff value of the ALBI score was -1.91 (sensitivity, 0.611; specificity, 0.655; area under the curve, 0.615). The cumulative risk of hepatotoxicity was significantly higher in the ALBI score ≥-1.91 group than in the ALBI score <-1.91 group (P = 0.024) and patients with higher ALBI grades tended to be at higher risk (P = 0.080). The cumulative risk tended to be higher with ALBI ≥-1.91 in the trough concentration 1-4 μg/mL group; however, no significant difference was found (P = 0.134).

IMPLICATIONS

The pilot study indicated that the ALBI score ≥-1.91 may be an indicator for voriconazole-induced hepatotoxicity even when TDM is conducted. Because this study was a single-center and small cohort design, further studies should be conducted using a large datasets and translational research.

Decreased Hepatic Functional Reserve Increases the Risk of Piperacillin/Tazobactam-Induced Abnormal Liver Enzyme Levels: A Retrospective Case-Control Study

BACKGROUND

Piperacillin/tazobactam (PIPC/TAZ), which is a combination of a beta-lactam/beta-lactamase inhibitor, often causes liver enzyme abnormalities. The albumin-bilirubin (ALBI) score is a simple index that uses the serum albumin and total bilirubin levels for estimating hepatic functional reserve. Although patients with low hepatic reserve may be at high risk for drug-induced liver enzyme abnormalities, the relationship between PIPC/TAZ-induced abnormal liver enzymes levels and the ALBI score remains unknown.

OBJECTIVE

This study aimed to elucidate the relationship between PIPC/TAZ-induced abnormal liver enzyme levels and the ALBI score.

METHODS

This single-center retrospective case-control study included 335 patients. The primary outcome was PIPC/TAZ-induced abnormal liver enzyme levels. We performed COX regression analysis with male gender, age (≥75 years), alanine aminotransferase level (≥20 IU/L), and ALBI score (≥-2.00) as explanatory factors. To investigate the influence of the ALBI score on the development of abnormal liver enzyme levels, 1:1 propensity score matching between the ≤-2.00 and ≥-2.00 ALBI score groups was performed using the risk factors for drug-induced abnormal liver enzyme levels.

RESULTS

The incidence of abnormal liver enzyme levels was 14.0% (47/335). COX regression analysis revealed that an ALBI score ≥-2.00 was an independent risk factor for PIPC/TAZ-induced abnormal liver enzyme levels (adjusted hazard ratio: 3.08, 95% coefficient interval: 1.207-7.835, P = 0.019). After 1:1 propensity score matching, the Kaplan-Meier curve revealed that the cumulative risk for PIPC/TAZ-induced abnormal liver enzyme levels was significantly higher in the ALBI score ≥-2.00 group (n = 76) than in the <-2.00 group (n = 76) (P = 0.033).

CONCLUSION AND RELEVANCE

An ALBI score ≥-2.00 may predict the development of PIPC/TAZ-induced abnormal liver enzyme levels. Therefore, frequent monitoring of liver enzymes should be conducted to minimize the risk of severe PIPC/TAZ-induced abnormal liver enzyme levels in patients with low hepatic functional reserve.

Risk Prediction of Liver Injury in Pediatric Tuberculosis Treatment: Development of an Automated Machine Learning Model

Purpose

Drug-induced liver injury (DILI) is one of the most common and serious adverse drug reactions related to first-line anti-tuberculosis drugs in pediatric tuberculosis patients. This study aims to develop an automatic machine learning (AutoML) model for predicting the risk of anti-tuberculosis drug-induced liver injury (ATB-DILI) in children.

Methods

A retrospective study was performed on the clinical data and therapeutic drug monitoring (TDM) results of children initially treated for tuberculosis at the affiliated Changsha Central Hospital of University of South China. After the features were screened by univariate risk factor analysis, AutoML technology was used to establish predictive models. The area under the receiver operating characteristic curve (AUC) was used to evaluate model's performance, and then the TreeShap algorithm was employed to interpret the variable contributions.

Results

A total of 184 children were enrolled in this study, of whom 19 (10.33%) developed ATB-DILI. Univariate analysis showed that seven variables were risk factors for ATB-DILI, including the plasma peak concentration (Cmax) of rifampicin, body mass index (BMI), alanine aminotransferase, total bilirubin, total bile acids, aspartate aminotransferase and creatinine. Among the numerous predictive models constructed by the "H2O" AutoML platform, the gradient boost machine (GBM) model exhibited the superior performance with AUCs of 0.838 and 0.784 on the training and testing sets, respectively. The TreeShap algorithm showed that Cmax of rifampicin and BMI were important features that affect the AutoML model's performance.

Conclusion

The GBM model established by AutoML technology shows high predictive accuracy and interpretability for ATB-DILI in children. The prediction model can assist clinicians to implement timely interventions and mitigation strategies, and formulate personalized medication regimens, thereby minimizing potential harm to high-risk children of ATB-DILI.

Predicting adverse drug event using machine learning based on electronic health records: a systematic review and meta-analysis

Introduction

Adverse drug events (ADEs) pose a significant challenge in current clinical practice. Machine learning (ML) has been increasingly used to predict specific ADEs using electronic health record (EHR) data. This systematic review provides a comprehensive overview of the application of ML in predicting specific ADEs based on EHR data.

Methods

A systematic search of PubMed, Web of Science, Embase, and IEEE Xplore was conducted to identify relevant articles published from the inception to 20 May 2024. Studies that developed ML models for predicting specific ADEs or ADEs associated with particular drugs were included using EHR data.

Results

A total of 59 studies met the inclusion criteria, covering 15 drugs and 15 ADEs. In total, 38 machine learning algorithms were reported, with random forest (RF) being the most frequently used, followed by support vector machine (SVM), eXtreme gradient boosting (XGBoost), decision tree (DT), and light gradient boosting machine (LightGBM). The performance of the ML models was generally strong, with an average area under the curve (AUC) of 76.68% ± 10.73, accuracy of 76.00% ± 11.26, precision of 60.13% ± 24.81, sensitivity of 62.35% ± 20.19, specificity of 75.13% ± 16.60, and an F1 score of 52.60% ± 21.10. The combined sensitivity, specificity, diagnostic odds ratio (DOR), and AUC from the summary receiver operating characteristic (SROC) curve using a random effects model were 0.65 (95% CI: 0.65-0.66), 0.89 (95% CI: 0.89-0.90), 12.11 (95% CI: 8.17-17.95), and 0.8069, respectively. The risk factors associated with different drugs and ADEs varied.

Discussion

Future research should focus on improving standardization, conducting multicenter studies that incorporate diverse data types, and evaluating the impact of artificial intelligence predictive models in real-world clinical settings.

Systematic Review Registration

https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42024565842, identifier CRD42024565842.

A decision tree approach for investigating the background of research activity of community and hospital pharmacists in Mie Prefecture: a retrospective questionnaire-based survey

BACKGROUND

The support system for research activities has not been sufficiently established in clinical settings. A survey should be conducted to identify the causes of low research activity among pharmacists and the characteristics of pharmacists who could serve as mentors to build a support system at the regional level.

METHODS

A retrospective cross-sectional survey was conducted with 156 pharmacists, including hospital and community pharmacists, who attended a webinar on research ethics held once a year in Mie Prefecture. Decision tree (DT) analysis was performed to extract the low research activities and pharmacists who could serve as mentors in research activities using independent factors identified by multivariate logistic regression analysis.

RESULTS

The questionnaire response rate was 72.4% (113/156), and most respondents were community pharmacists (81.4%). In the DT model, pharmacists who did not belong to academic societies (78%, 46/59) or those who belonged to one or two academic societies but had no certifications (100%, 5/5) had low research activities. Pharmacists who read papers more than once a month and had a nearby mentor (73%, 11/15) were more likely to become mentors in research activities.

CONCLUSIONS

The combination of the number of academic societies and the presence of certifications determines the efforts in research activities. In addition to reading at least one paper monthly, the presence of a mentor for writing research papers may also be a crucial factor in becoming a mentor. The proposed DT model may be helpful in building a support system for research activities at the regional level.

Interpretable multitemporal liver function indicator model for prediction and risk factor analysis of drug induced liver injury

The occurrence of liver injury during cancer treatment is extremely harmful. The risk factors for drug.induced liver injury (DILI) in the pancreatic cancer population have not been investigated. This study aims to develop and validate an interpretable decision tree (DT) model for the early prediction of DILI in pancreatic cancer patients using multitemporal clinical data and screening for related risk factors. A retrospective collection of data was conducted on 307 patients, the training set (n = 215) was used to develop the model, and the test set (n = 92) was used to evaluate the model. The classification and regression trees algorithm was employed to establish the DT model. The Shapley Additive explanations (SHAP) method was used to facilitate clinical interpretation. Model performance was assessed using AUC and the Hosmer‒Lemeshow test. The DT model exhibited superior diagnostic efficacy, the AUC values were 0.995 and 0.994 in the training and test sets, respectively. Four risk factors associated with DILI occurrence were identified: delta.albumin, delta.ALT, and post (AST: ALT), and post.GGT. The multiperiod liver function indicator.based interpretable DT model predicted DILI occurrence in the pancreatic cancer population and contributes to personalized clinical management of pancreatic cancer patients.

Future Perspectives on Radiomics in Acute Liver Injury and Liver Trauma

Background: Acute liver injury occurs most frequently due to trauma, but it can also occur because of sepsis or drug-induced injury. This review aims to analyze artificial intelligence (AI)'s ability to detect and quantify liver injured areas in adults and pediatric patients. Methods: A literature analysis was performed on the PubMed Dataset. We selected original articles published from 2018 to 2023 and cohorts with ≥10 adults or pediatric patients. Results: Six studies counting 564 patients were collected, including 170 (30%) children and 394 adults. Four (66%) articles reported AI application after liver trauma, one (17%) after sepsis, and one (17%) due to chemotherapy. In five (83%) studies, Computed Tomography was performed, while in one (17%), FAST-UltraSound was performed. The studies reported a high diagnostic performance; in particular, three studies reported a specificity rate > 80%. Conclusions: Radiomics models seem reliable and applicable to clinical practice in patients affected by acute liver injury. Further studies are required to achieve larger validation cohorts.

Effect of Ceftriaxone Dosage and Albumin-Bilirubin Score on the Risk of Ceftriaxone-Induced Liver Injury

The albumin-bilirubin (ALBI) score is an index of hepatic functional reserve and is calculated from serum albumin and total bilirubin levels. However, the relationship between ceftriaxone (CTRX)-induced liver injury and ALBI score remains unknown. Therefore, we aimed to elucidate the risk of CTRX-induced liver injury based on the ALBI scores and CTRX dosage. This was a single-center, retrospective, case-control study of 490 patients and the primary outcome was CTRX-induced liver injury. We performed a COX regression analysis using age ≥75 years, male sex, alanine aminotransferase levels, ALBI score, and CTRX dosage regimen (4 ≥2 or 1 g/d) as explanatory factors. We also performed 1 : 1 propensity score matching between non-liver injury and liver injury groups. The incidence of liver injury was 10.0% (49/490). In COX regression analysis, CTRX 4 g/d was an independent risk factor for liver injury (95% coefficient interval: 1.05-6.96, p = 0.04). Meanwhile, ALBI score ≥-1.61 was an independent factor for liver injury (95% coefficient interval: 1.03-3.22, p = 0.04) with the explanatory factor of ≥2 and 1 g/d. The Kaplan-Meier curve indicated that the cumulative risk for CTRX-induced liver injury was significantly higher in the ALBI score ≥-1.61 group than in the ALBI score <-1.61 group before propensity score matching (p = 0.032); however, no significant differences were observed after propensity score matching (p = 0.791). These findings suggest that in patients treated with CTRX with ALBI score ≥-1.61, frequent liver function monitoring should be considered.