Identification and Characterization of Immune Checkpoint Inhibitor-Induced Toxicities From Electronic Health Records Using Natural Language Processing.

PURPOSE: Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet their use is associated with immune-related adverse events (irAEs). Estimating the prevalence and patient impact of these irAEs in the real-world data setting is critical for characterizing the benefit/risk profile of ICI therapies beyond the clinical trial population. Diagnosis codes, such as International Classification of Diseases codes, do not comprehensively illustrate a patient's care journey and offer no insight into drug-irAE causality. This study aims to capture the relationship between ICIs and irAEs more accurately by using augmented curation (AC), a natural language processing-based innovation, on unstructured data in electronic health records. METHODS: In a cohort of 9,290 patients treated with ICIs at Mayo Clinic from 2005 to 2021, we compared the prevalence of irAEs using diagnosis codes and AC models, which classify drug-irAE pairs in clinical notes with implied textual causality. Four illustrative irAEs with high patient impact-myocarditis, encephalitis, pneumonitis, and severe cutaneous adverse reactions, abbreviated as MEPS-were analyzed using corticosteroid administration and ICI discontinuation as proxies of severity. RESULTS: For MEPS, only 70% (n = 118) of patients found by AC were also identified by diagnosis codes. Using AC models, patients with MEPS received corticosteroids for their respective irAE 82% of the time and permanently discontinued the ICI because of the irAE 35.9% (n = 115) of the time. CONCLUSION: Overall, AC models enabled more accurate identification and assessment of patient impact of ICI-induced irAEs not found using diagnosis codes, demonstrating a novel and more efficient strategy to assess real-world clinical outcomes in patients treated with ICIs.

Whole genome sequencing across clinical trials identifies rare coding variants in GPR68 associated with chemotherapy-induced peripheral neuropathy.

BACKGROUND: Dose-limiting toxicities significantly impact the benefit/risk profile of many drugs. Whole genome sequencing (WGS) in patients receiving drugs with dose-limiting toxicities can identify therapeutic hypotheses to prevent these toxicities. Chemotherapy-induced peripheral neuropathy (CIPN) is a common dose-limiting neurological toxicity of chemotherapies with no effective approach for prevention. METHODS: We conducted a genetic study of time-to-first peripheral neuropathy event using 30× germline WGS data from whole blood samples from 4900 European-ancestry cancer patients in 14 randomized controlled trials. A substantial number of patients in these trials received taxane and platinum-based chemotherapies as part of their treatment regimen, either standard of care or in combination with the PD-L1 inhibitor atezolizumab. The trials spanned several cancers including renal cell carcinoma, triple negative breast cancer, non-small cell lung cancer, small cell lung cancer, bladder cancer, ovarian cancer, and melanoma. RESULTS: We identified a locus consisting of low-frequency variants in intron 13 of GRID2 associated with time-to-onset of first peripheral neuropathy (PN) indexed by rs17020773 (p = 2.03 × 10-8, all patients, p = 6.36 × 10-9, taxane treated). Gene-level burden analysis identified rare coding variants associated with increased PN risk in the C-terminus of GPR68 (p = 1.59 × 10-6, all patients, p = 3.47 × 10-8, taxane treated), a pH-sensitive G-protein coupled receptor (GPCR). The variants driving this signal were found to alter predicted arrestin binding motifs in the C-terminus of GPR68. Analysis of snRNA-seq from human dorsal root ganglia (DRG) indicated that expression of GPR68 was highest in mechano-thermo-sensitive nociceptors. CONCLUSIONS: Our genetic study provides insight into the impact of low-frequency and rare coding genetic variation on PN risk and suggests that further study of GPR68 in sensory neurons may yield a therapeutic hypothesis for prevention of CIPN.

Baseline risk factors associated with immune related adverse events and atezolizumab.

Background: Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of cancer patients in the last decade, but immune-related adverse events (irAEs) pose significant clinical challenges. Despite advances in the management of these unique toxicities, there remains an unmet need to further characterize the patient-level drivers of irAEs in order to optimize the benefit/risk balance in patients receiving cancer immunotherapy. Methods: An individual-patient data post-hoc meta-analysis was performed using data from 10,344 patients across 15 Roche sponsored clinical trials with atezolizumab in five different solid tumor types to assess the association between baseline risk factors and the time to onset of irAE. In this study, the overall analysis was conducted by treatment arm, indication, toxicity grade and irAE type, and the study design considered confounder adjustment to assess potential differences in risk factor profiles. Results: This analysis demonstrates that the safety profile of atezolizumab is generally consistent across indications in the 15 studies evaluated. In addition, our findings corroborate with prior reviews which suggest that reported rates of irAEs with PD-(L)1 inhibitors are nominally lower than CTLA-4 inhibitors. In our analysis, there were no remarkable differences in the distribution of toxicity grades between indications, but some indication-specific differences regarding the type of irAE were seen across treatment arms, where pneumonitis mainly occurred in lung cancer, and hypothyroidism and rash had a higher prevalence in advanced renal cell carcinoma compared to all other indications. Results showed consistency of risk factors across indications and by toxicity grade. The strongest and most consistent risk factors were mostly organ-specific such as elevated liver enzymes for hepatitis and thyroid stimulating hormone (TSH) for thyroid toxicities. Another strong but non-organ-specific risk factor was ethnicity, which was associated with rash, hepatitis and pneumonitis. Further understanding the impact of ethnicity on ICI associated irAEs is considered as an area for future research. Conclusions: Overall, this analysis demonstrated that atezolizumab safety profile is consistent across indications, is clinically distinguishable from comparator regimens without checkpoint inhibition, and in line with literature, seems to suggest a nominally lower reported rates of irAEs vs CTLA-4 inhibitors. This analysis demonstrates several risk factors for irAEs by indication, severity and location of irAE, and by patient ethnicity. Additionally, several potential irAE risk factors that have been published to date, such as demographic factors, liver enzymes, TSH and blood cell counts, are assessed in this large-scale meta-analysis, providing a more consistent picture of their relevance. However, given the small effects size, changes to clinical management of irAEs associated with the use of Anti-PDL1 therapy are not warranted.

Safety and efficacy of ozanezumab in patients with amyotrophic lateral sclerosis: a randomised, double-blind, placebo-controlled, phase 2 trial.

BACKGROUND: Neurite outgrowth inhibitor A (Nogo-A) is thought to have a role in the pathophysiology of amyotrophic lateral sclerosis (ALS). A monoclonal antibody against Nogo-A showed a positive effect in the SOD1G93A mouse model of ALS, and a humanised form of this antibody (ozanezumab) was well tolerated in a first-in-human trial. Therefore, we aimed to assess the safety and efficacy of ozanezumab in patients with ALS. METHODS: This randomised, double-blind, placebo-controlled, phase 2 trial was done in 34 centres in 11 countries. Patients aged 18-80 years with a diagnosis of familial or sporadic ALS were randomly assigned (1:1), centrally according to a computer-generated allocation schedule, to receive ozanezumab (15 mg/kg) or placebo as intravenous infusions over 1 h every 2 weeks for 46 weeks, followed by assessments at week 48 and week 60. Patients and study personnel were masked to treatment assignment. The primary outcome was a joint-rank analysis of function (ALS Functional Rating Scale-Revised) and overall survival, analysed at 48 weeks in all patients who received at least one dose of study drug. This study is registered with ClinicalTrials.gov, number NCT01753076, and with GSK-ClinicalStudyRegister.com, NOG112264, and is completed. FINDINGS: Between Dec 20, 2012, and Nov 1, 2013, we recruited 307 patients, of whom 303 were randomly assigned to receive placebo (n=151) or ozanezumab (n=152). The adjusted mean of the joint-rank score was -14·9 (SE 13·5) for the ozanezumab group and 15·0 (13·6) for the placebo group, with a least squares mean difference of -30·0 (95% CI -67·9 to 7·9; p=0·12). Overall, reported adverse events, serious adverse events, and adverse events leading to permanent discontinuation of study drug or withdrawal from study were similar between the treatment groups, except for dyspepsia (ten [7%] in the ozanezumab group vs four [3%] in the placebo group), depression (11 [7%] vs five [3%]), and diarrhoea (25 [16%] vs 12 [8%]). Respiratory failure was the most common serious adverse event (12 [8%] vs seven [5%]). At week 60, the number of deaths was higher in the ozanezumab group (20 [13%]) than in the placebo group (16 [11%]), mainly as a result of respiratory failure (ten [7%] vs five [3%]). Two deaths were considered related to the study drug (bladder transitional cell carcinoma in the ozanezumab group and cerebrovascular accident in the placebo group). INTERPRETATION: Ozanezumab did not show efficacy compared with placebo in patients with ALS. Therefore, Nogo-A does not seem to be an effective therapeutic target in ALS. FUNDING: GlaxoSmithKline.