Isolated Elevated Bilirubin

Prediction of Effectiveness and Toxicities of Immune Checkpoint Inhibitors Using Real-World Patient Data

PURPOSE

Although immune checkpoint inhibitors (ICIs) have improved outcomes in certain patients with cancer, they can also cause life-threatening immunotoxicities. Predicting immunotoxicity risks alongside response could provide a personalized risk-benefit profile, inform therapeutic decision making, and improve clinical trial cohort selection. We aimed to build a machine learning (ML) framework using routine electronic health record (EHR) data to predict hepatitis, colitis, pneumonitis, and 1-year overall survival.

METHODS

Real-world EHR data of more than 2,200 patients treated with ICI through December 31, 2018, were used to develop predictive models. Using a prediction time point of ICI initiation, a 1-year prediction time window was applied to create binary labels for the four outcomes for each patient. Feature engineering involved aggregating laboratory measurements over appropriate time windows (60-365 days). Patients were randomly partitioned into training (80%) and test (20%) sets. Random forest classifiers were developed using a rigorous model development framework.

RESULTS

The patient cohort had a median age of 63 years and was 61.8% male. Patients predominantly had melanoma (37.8%), lung cancer (27.3%), or genitourinary cancer (16.4%). They were treated with PD-1 (60.4%), PD-L1 (9.0%), and CTLA-4 (19.7%) ICIs. Our models demonstrate reasonably strong performance, with AUCs of 0.739, 0.729, 0.755, and 0.752 for the pneumonitis, hepatitis, colitis, and 1-year overall survival models, respectively. Each model relies on an outcome-specific feature set, though some features are shared among models.

CONCLUSION

To our knowledge, this is the first ML solution that assesses individual ICI risk-benefit profiles based predominantly on routine structured EHR data. As such, use of our ML solution will not require additional data collection or documentation in the clinic.

A rare case of Crigler-Najjar syndrome type 2: A case report and literature review

Key Clinical Message

Crigler-Najjar syndrome type 2 should be suspected in any young patient presenting with isolated indirect hyperbilirubinemia where all other common etiologies have been excluded. It is a relatively benign condition that responds to phenobarbitone.

Abstract

Crigler-Najjar syndrome (CNS) type 2 is an inborn cause of isolated indirect hyperbilirubinemia characterized by a partial deficiency of the enzyme uridine 5'-diphosphate-glucuronosyltransferase (UGT) responsible for bilirubin conjugation. Typically, this condition is diagnosed based on clinical manifestations, supplemented by enzyme analysis if feasible, and exhibits a significant response to phenobarbitone, known for its enzyme-inducing properties. In this case, we present a young male patient who had experienced recurrent isolated indirect hyperbilirubinemia since early childhood, with negative results in the hemolytic workup. The patient exhibited a UGT1A1 gene defect and demonstrated a highly favorable response to phenobarbitone treatment. The purpose of this report is to raise awareness among physicians about this benign condition and underscore the importance of avoiding unnecessary investigations.

Hyperbilirubinemia in a Patient With Sepsis: A Diagnostic Challenge

Cholestasis due to sepsis is commonly seen in critically ill patients; however, it is often overlooked and poses a challenge in clinical diagnosis and management. In this report, we present a 29-year-old woman who presented to the emergency department with jaundice and symptoms of a urinary tract infection. Initially suspected to be Dubin-Johnson syndrome, sepsis-induced cholestasis was eventually diagnosed after testing. Sepsis should always be considered as part of the differential diagnosis while managing a patient with jaundice. The management of sepsis-induced cholestasis involves treating the underlying infection. In most cases, liver injury improves with the resolution of the infectious process.