Comparative assessment of manual chart review and ICD claims data in evaluating immunotherapy-related adverse events

Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records

We assessed the generalizability of machine learning methods using natural language processing (NLP) techniques to detect adverse drug events (ADEs) from clinical narratives in electronic medical records (EMRs). We constructed a new corpus correlating drugs with adverse drug events using 1,394 clinical notes of 47 randomly selected patients who received immune checkpoint inhibitors (ICIs) from 2011 to 2018 at The Ohio State University James Cancer Hospital, annotating 189 drug-ADE relations in single sentences within the medical records. We also used data from Harvard's publicly available 2018 National Clinical Challenge (n2c2), which includes 505 discharge summaries with annotations of 1,355 single-sentence drug-ADE relations. We applied classical machine learning (support vector machine (SVM)), deep learning (convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM)), and state-of-the-art transformer-based (bidirectional encoder representations from transformers (BERT) and ClinicalBERT) methods trained and tested in the two different corpora and compared performance among them to detect drug-ADE relationships. ClinicalBERT detected drug-ADE relationships better than the other methods when trained using our dataset and tested in n2c2 (ClinicalBERT F-score, 0.78; other methods, F-scores, 0.61-0.73) and when trained using the n2c2 dataset and tested in ours (ClinicalBERT F-score, 0.74; other methods, F-scores, 0.55-0.72). Comparison among several machine learning methods demonstrated the superior performance and, therefore, the greatest generalizability of findings of ClinicalBERT for the detection of drug-ADE relations from clinical narratives in electronic medical records.

Risk Factors for Immune Checkpoint Inhibitor Immunotherapy Toxicity Among Older Adults with Cancer

OBJECTIVES

Immune checkpoint inhibitor immunotherapy (IO) is revolutionizing cancer care but can lead to significant toxicity. This study seeks to describe potential risk factors for immune-related adverse events (irAEs) specifically among older adults.

MATERIALS AND METHODS

This was a retrospective study at a single academic comprehensive cancer center based on chart review data abstracted by physicians. For patients aged ≥70 years, frequency, type, and grade of irAEs and their association with baseline patient demographics, comorbidities, mobility, and functional status were characterized using bivariate analysis. Based on those results, multivariable logistic regressions were constructed to model the association between these characteristics with any grade and grade 3 or higher irAEs.

RESULTS

Data were analyzed for 238 patients aged ≥70 years who received IO for mostly (≥90%) advanced cancer between 2011 and 2018. Thirty-nine percent of older adults experienced an irAE and 13% experienced one that was grade 3 or higher. In the multivariable analysis, depression was associated with an increased incidence of any grade irAE, while decreased life-space mobility was associated with an increased incidence of grade ≥3 irAEs.

CONCLUSION

Most characteristics of special interest among older adults, include fall risk, weight loss, cognitive limitations, and hearing loss, were not associated with irAEs in our study. However, decreased life-space mobility and depression are potential risk factors for IO toxicity among older adults with advanced cancer. Interventions designed to evaluate and mitigate modifiable risk factors for treatment-related toxicity are needed, and the results of this study may be useful for guiding those efforts.

Drug-related causes attributed to acute kidney injury and their documentation in intensive care patients

PURPOSE

To investigate drug-related causes attributed to acute kidney injury (DAKI) and their documentation in patients admitted to the Intensive Care Unit (ICU).

METHODS

This study was conducted in an academic hospital in the Netherlands by reusing electronic health record (EHR) data of adult ICU admissions between November 2015 to January 2020. First, ICU admissions with acute kidney injury (AKI) stage 2 or 3 were identified. Subsequently, three modes of DAKI documentation in EHR were examined: diagnosis codes (structured data), allergy module (semi-structured data), and clinical notes (unstructured data).

RESULTS

n total 8124 ICU admissions were included, with 542 (6.7%) ICU admissions experiencing AKI stage 2 or 3. The ICU physicians deemed 102 of these AKI cases (18.8%) to be drug-related. These DAKI cases were all documented in the clinical notes (100%), one in allergy module (1%) and none via diagnosis codes. The clinical notes required the highest time investment to analyze.

CONCLUSIONS

Drug-related causes comprise a substantial part of AKI in the ICU patients. However, current unstructured DAKI documentation practice via clinical notes hampers our ability to gain better insights about DAKI occurrence. Therefore, both automating DAKI identification from the clinical notes and increasing structured DAKI documentation should be encouraged.

Risk factors and predictors of immune-related adverse events: implications for patients with non-small cell lung cancer

INTRODUCTION

Immune checkpoint inhibitors (ICI) are now utilized as a standard of care treatment for multiple cancers, including in both the metastatic setting as well as in earlier stages of disease. The identification of unique immune-related adverse events (irAE) that occur during ICI treatment has led to intense research to identify potential risk factors and biomarkers that may assist in clinical decision making. Although initial studies in ICI were primarily in advanced stage disease, the use of ICI in earlier stages of disease as adjuvant therapies requires a better understanding of patient risk stratification to mitigate or prevent serious irAE.

AREAS COVERED

In this review, we set out to describe the current state of research regarding potential risk factors for irAE in patients with non-small cell lung cancer, as well as explore the barriers to understanding irAE. We review data from irAE that occur in large phase 3 trials and prospective studies focusing on irAE, as well as the many retrospective studies that currently form the bulk of our understanding of irAE.

Moderate Colitis Not Requiring IV Steroids Is Associated with Improved Survival in Stage IV Melanoma after Anti-CTLA4 Monotherapy, But Not Combination Therapy

Background

For patients with melanoma, gastrointestinal immune-related adverse events are common after receipt of anti-CTLA4 therapy. These present difficult decision points regarding whether to discontinue therapy. Detailing the situations in which colitis might predict for improved survival and how this is affected by discontinuation or resumption of therapy can help guide clinical decision-making.

Materials and Methods

Patients with stage IV melanoma receiving anti-CTLA4 therapy from 2008 to 2019 were analyzed. Immune-related colitis treated with ≥50 mg prednisone or equivalent daily or secondary immunosuppression was included. Moderate colitis was defined as receipt of oral glucocorticoids only; severe colitis was defined as requiring intravenous glucocorticoids or secondary immunosuppression. The primary outcome was overall survival (OS).

Results

In total, 171 patients received monotherapy, and 91 received dual checkpoint therapy. In the monotherapy group, 25 patients developed colitis and a nonsignificant trend toward improved OS was observed in this group. Notably, when colitis was categorized as none, moderate or severe, OS was significantly improved for moderate colitis only. This survival difference was not present after dual checkpoint therapy. There were no differences in known prognostic variables between groups, and on multivariable analysis neither completion of all ipilimumab cycles nor resumption of immunotherapy correlated with OS, while the development of moderate colitis did significantly affect OS.

Conclusion

This single-institution retrospective series suggests moderate colitis correlates with improved OS for patients with stage IV melanoma treated with single-agent anti-CTLA4, but not dual agent, and that this is true regardless of whether the immune-checkpoint blockade is permanently discontinued.