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.

Clinical Administration Characteristics of Subcutaneous and Intravenous Administration of Daratumumab in Patients With Multiple Myeloma at Mayo Clinic Infusion Centers.

PURPOSE: Median duration of daratumumab (DARA) administration for treatment of multiple myeloma is 3-7 hours for the intravenous formulation (DARA IV) and 3-5 minutes for the subcutaneous formulation (DARA SC). Here, we describe clinical administration characteristics of DARA using a novel method for data extraction from electronic health records. METHODS: Time-based measurements were extracted using a scheduling/pharmacy software program that tracked patient movement through appointments for patients initiating DARA in Mayo Clinic infusion centers from April 5, 2017, to October 14, 2021. Cohorts included patients who received DARA IV or DARA SC, or converted from DARA IV to DARA SC. The DARA SC cohort was further analyzed before (DARA SC initial) and after (DARA SC shortened) a reduction in the postadministration observation time mandated by the treatment plan. Events associated with administration-related reactions (ARRs) were also identified. RESULTS: Median total clinic times were 2.7-3.0 hours shorter for DARA SC versus DARA IV. Median clinic times were highest at dose 1 and decreased with subsequent doses. Median total chair times were 2.7-2.8 hours shorter for DARA SC versus DARA IV. Incidences of ARR-related events with DARA SC were low across doses. CONCLUSION: Reduced clinic times were observed with DARA SC, indicating that use of DARA SC as a treatment option results in time savings that may free clinic resources. Furthermore, novel methods of electronic health record data extraction can provide insights that may help inform clinic resource optimization.

Small-molecule-based regulation of RNA-delivered circuits in mammalian cells.

Synthetic mRNA is an attractive vehicle for gene therapies because of its transient nature and improved safety profile over DNA. However, unlike DNA, broadly applicable methods to control expression from mRNA are lacking. Here we describe a platform for small-molecule-based regulation of expression from modified RNA (modRNA) and self-replicating RNA (replicon) delivered to mammalian cells. Specifically, we engineer small-molecule-responsive RNA binding proteins to control expression of proteins from RNA-encoded genetic circuits. Coupled with specific modRNA dosages or engineered elements from a replicon, including a subgenomic promoter library, we demonstrate the capability to externally regulate the timing and level of protein expression. These control mechanisms facilitate the construction of ON, OFF, and two-output switches, with potential therapeutic applications such as inducible cancer immunotherapies. These circuits, along with other synthetic networks that can be developed using these tools, will expand the utility of synthetic mRNA as a therapeutic modality.

Model-driven engineering of gene expression from RNA replicons.

RNA replicons are an emerging platform for engineering synthetic biological systems. Replicons self-amplify, can provide persistent high-level expression of proteins even from a small initial dose, and, unlike DNA vectors, pose minimal risk of chromosomal integration. However, no quantitative model sufficient for engineering levels of protein expression from such replicon systems currently exists. Here, we aim to enable the engineering of multigene expression from more than one species of replicon by creating a computational model based on our experimental observations of the expression dynamics in single- and multireplicon systems. To this end, we studied fluorescent protein expression in baby hamster kidney (BHK-21) cells using a replicon derived from Sindbis virus (SINV). We characterized expression dynamics for this platform based on the dose-response of a single species of replicon over 50 h and on a titration of two cotransfected replicons expressing different fluorescent proteins. From this data, we derive a quantitative model of multireplicon expression and validate it by designing a variety of three-replicon systems, with profiles that match desired expression levels. We achieved a mean error of 1.7-fold on a 1000-fold range, thus demonstrating how our model can be applied to precisely control expression levels of each Sindbis replicon species in a system.