1
|
Barman H, Venkateswaran S, Santo AD, Yoo U, Silvert E, Rao K, Raghunathan B, Kottschade LA, Block MS, Chandler GS, Zalis J, Wagner TE, Mohindra R. Identification and Characterization of Immune Checkpoint Inhibitor-Induced Toxicities From Electronic Health Records Using Natural Language Processing. JCO Clin Cancer Inform 2024; 8:e2300151. [PMID: 38687915 DOI: 10.1200/cci.23.00151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Revised: 01/09/2024] [Accepted: 03/01/2024] [Indexed: 05/02/2024] Open
Abstract
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.
Collapse
|
2
|
Ghosh P, Niesen MJ, Pawlowski C, Bandi H, Yoo U, Lenehan PJ, M. PK, Nadig M, Ross J, Ardhanari S, O’Horo JC, Venkatakrishnan AJ, Rosen CJ, Telenti A, Hurt RT, Soundararajan V. Severe acute infection and chronic pulmonary disease are risk factors for developing post-COVID-19 conditions. medRxiv 2022:2022.11.30.22282831. [PMID: 36523407 PMCID: PMC9753786 DOI: 10.1101/2022.11.30.22282831] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
Post-COVID-19 conditions, also known as "long COVID", has significantly impacted the lives of many individuals, but the risk factors for this condition are poorly understood. In this study, we performed a retrospective EHR analysis of 89,843 individuals at a multi-state health system in the United States with PCR-confirmed COVID-19, including 1,086 patients diagnosed with long COVID and 1,086 matched controls not diagnosed with long COVID. For these two cohorts, we evaluated a wide range of clinical covariates, including laboratory tests, medication orders, phenotypes recorded in the clinical notes, and outcomes. We found that chronic pulmonary disease (CPD) was significantly more common as a pre-existing condition for the long COVID cohort than the control cohort (odds ratio: 1.9, 95% CI: [1.5, 2.6]). Additionally, long-COVID patients were more likely to have a history of migraine (odds ratio: 2.2, 95% CI: [1.6, 3.1]) and fibromyalgia (odds ratio: 2.3, 95% CI: [1.3, 3.8]). During the acute infection phase, the following lab measurements were abnormal in the long COVID cohort: high triglycerides (meanlongCOVID: 278.5 mg/dL vs. meancontrol: 141.4 mg/dL), low HDL cholesterol levels (meanlongCOVID: 38.4 mg/dL vs. meancontrol: 52.5 mg/dL), and high neutrophil-lymphocyte ratio (meanlongCOVID: 10.7 vs. meancontrol: 7.2). The hospitalization rate during the acute infection phase was also higher in the long COVID cohort compared to the control cohort (ratelongCOVID: 5% vs. ratecontrol: 1%). Overall, this study suggests that the severity of acute infection and a history of CPD, migraine, CFS, or fibromyalgia may be risk factors for long COVID symptoms. Our findings motivate clinical studies to evaluate whether suppressing acute disease severity proactively, especially in patients at high risk, can reduce incidence of long COVID.
Collapse
Affiliation(s)
| | | | | | - Hari Bandi
- nference, inc., Cambridge, Massachusetts 02139, USA
| | - Unice Yoo
- nference, inc., Cambridge, Massachusetts 02139, USA
| | | | | | - Mihika Nadig
- nference, inc., Cambridge, Massachusetts 02139, USA
| | - Jason Ross
- nference, inc., 18 3rd St. S.W., Rochester MN 55902, USA
| | | | | | | | - Clifford J. Rosen
- Maine Medical Center, Portland, ME 04102, USA
- NIH RECOVER Initiative, USA
| | | | | | - Venky Soundararajan
- nference Labs, Bengaluru, India
- nference, inc., Cambridge, Massachusetts 02139, USA
- nference, inc., 18 3rd St. S.W., Rochester MN 55902, USA
- nference, inc. 2424 Erwin Road, Durham, NC 27705, USA
- Anumana, inc., Cambridge, Massachusetts 02139, USA
| |
Collapse
|
3
|
Anand P, Lenehan PJ, Niesen M, Yoo U, Patwardhan D, Montorzi M, Venkatakrishnan AJ, Soundararajan V. Genetic alteration of human MYH6 is mimicked by SARS-CoV-2 polyprotein: mapping viral variants of cardiac interest. Cell Death Dis 2022; 8:124. [PMID: 35314694 PMCID: PMC8935120 DOI: 10.1038/s41420-022-00914-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Revised: 02/07/2022] [Accepted: 02/24/2022] [Indexed: 01/28/2023]
Abstract
Acute cardiac injury has been observed in a subset of COVID-19 patients, but the molecular basis for this clinical phenotype is unknown. It has been hypothesized that molecular mimicry may play a role in triggering an autoimmune inflammatory reaction in some individuals after SARS-CoV-2 infection. Here we investigate if linear peptides contained in proteins that are primarily expressed in the heart also occur in the SARS-CoV-2 proteome. Specifically, we compared the library of 136,704 8-mer peptides from 144 human proteins (including splicing variants) to 9926 8-mers from all the viral proteins in the reference SARS-CoV-2 proteome. No 8-mers were exactly identical between the reference human proteome and the reference SARS-CoV-2 proteome. However, there were 45 8-mers that differed by only one amino acid when compared to the reference SARS-CoV-2 proteome. Interestingly, analysis of protein-coding mutations from 141,456 individuals showed that one of these 8-mers from the SARS-CoV-2 Replicase polyprotein 1a/1ab (KIALKGGK) is identical to an MYH6 peptide encoded by the c.5410 C > A (Q1804K) genetic variation, which has been observed at low prevalence in Africans/African Americans (0.08%), East Asians (0.3%), South Asians (0.06%), and Latino/Admixed Americans (0.003%). Furthermore, analysis of 4.85 million SARS-CoV-2 genomes from over 200 countries shows that viral evolution has already resulted in 20 additional 8-mer peptides that are identical to human heart-enriched proteins encoded by reference sequences or genetic variants. Whether such mimicry contributes to cardiac inflammation during or after COVID-19 illness warrants further experimental evaluation. We suggest that SARS-CoV-2 variants harboring peptides identical to human cardiac proteins should be investigated as "viral variants of cardiac interest".
Collapse
Affiliation(s)
| | | | | | - Unice Yoo
- grid.510985.0nference, Cambridge, MA 02139 USA
| | | | - Marcelo Montorzi
- grid.510985.0nference, Cambridge, MA 02139 USA ,grid.492905.3Southcoast Health, Fairhaven, MA 02719 USA
| | | | - Venky Soundararajan
- nference Labs, Bengaluru, Karnataka 560017 India ,grid.510985.0nference, Cambridge, MA 02139 USA
| |
Collapse
|