Anti-TNF? therapies are widely used to treat autoimmune diseases, including inflammatory bowel disease (IBD), a chronic inflammation of the digestive system which presents both an economic burden as well as prominent disability and morbidity. These therapies, however, are largely ineffective in IBD patients, with primary non- response rates varying from 10-30%, and with 23-46% of patients losing response over time. They also lead to adverse health outcomes including increased risk of infections (most notably reactivation of tuberculosis), liver problems, arthritis, and lymphoma. Due to biologic switching where multiple drugs are tried in sequence until an effect is observed, they often lead to overall increased healthcare costs. There is no clear predictive factor of response or loss of response to anti-TNF? therapies, with current research focusing on efficacious dosage and inhibitor selection. While numerous predictors of response have been identified in studies, none are robust enough to impact clinical practice. Overcoming this gap in the administration of anti-TNF? therapies will be an important next step in improving their utility and reducing overall healthcare costs, morbidity, and mortality. This project proposes a multicohort meta-analysis and machine learning approach to discover and validate a prognostic gene signature that can differentiate anti-TNF? responders from non-responders in IBD patients, allowing for improved decision-making and positive health outcomes. Despite the broad biological, clinical, and technical heterogeneity inherent in such a task, the Inflammatix analytical framework was able to identify significant differentially expressed genes that discriminate anti-TNF? responders from non-responders (mean discovery AUC of ~0.83 and mean validation AUC of ~0.81). Supported by these preliminary results, this project will (1) discover a robust, clinically translatable multi-gene prognostic signature using publicly available datasets, (2) generate independent gene expression data from retrospective cohorts of mucosal biopsy samples (n=150) to validate the signature (target AUC > ~0.8), and (3) use our proprietary Inflammatix machine learning (IML) platform to train and validate a plethora of machine learning algorithms to develop a robust, generalizable classifier (target AUC ~ 0.8 - 0.9) that is ready for clinical validation via prospective studies. Our novel prognostic signature will transform the clinical paradigm in the use and administration of anti-TNF? therapies, maximizing treatment benefit while minimizing patient exposure to potentially harmful side effects and adverse health outcomes, consequently reducing financial burden for the healthcare system and patient. Public Health Relevance Statement NARRATIVE Anti-TNF? therapies are widely used to treat autoimmune diseases, including inflammatory bowel disease (IBD), however, they are ineffective in greater than half of patients, and carry significant risks with associated healthcare costs. This project will discover and validate a prognostic, generalizable mRNA signature that can identify IBD patients who are likely to respond to anti-TNF? treatment, transforming how physicians use and administer these expensive and oftentimes risk-laden therapies to maximize patient benefit and minimize adverse health outcomes. Improved treatment decision-making will undoubtedly help address ever-increasing cases of IBD in the US and globally while reducing overall healthcare costs, morbidity, and mortality.
Project Terms: Age ; ages ; inhibitor/antagonist ; inhibitor ; Arthritis ; arthritic ; Autoimmune Diseases ; autoimmune condition ; autoimmune disorder ; Biology ; Biopsy ; Colonoscopy ; Decision Making ; gastrointestinal system ; Ailmentary System ; Alimentary System ; Digestive System ; Gastrointestinal Body System ; Gastrointestinal Organ System ; Disease ; Disorder ; Pharmaceutical Preparations ; Drugs ; Medication ; Pharmaceutic Preparations ; drug/agent ; Gene Expression ; Patient Care ; Patient Care Delivery ; Genes ; Health ; Healthcare Systems ; Health Care Systems ; Heterogeneity ; Infection ; Inflammation ; Inflammatory Bowel Diseases ; Inflammatory Bowel Disorder ; Lead ; Pb element ; heavy metal Pb ; heavy metal lead ; Liver ; hepatic body system ; hepatic organ system ; Lymphoma ; Germinoblastic Sarcoma ; Germinoblastoma ; Malignant Lymphoma ; Reticulolymphosarcoma ; Methods ; Morbidity - disease rate ; Morbidity ; mortality ; Mucous Membrane ; Mucosa ; Mucosal Tissue ; Patients ; Physicians ; Privatization ; Prospective Studies ; Quality of life ; QOL ; Research ; Risk ; Messenger RNA ; mRNA ; Signal Transduction ; Cell Communication and Signaling ; Cell Signaling ; Intracellular Communication and Signaling ; Signal Transduction Systems ; Signaling ; biological signal transduction ; Standardization ; Time ; Translating ; Tuberculosis ; M tuberculosis infection ; M. tb infection ; M. tuberculosis infection ; M.tb infection ; M.tuberculosis infection ; MTB infection ; Mycobacterium tuberculosis (MTB) infection ; Mycobacterium tuberculosis infection ; TB infection ; disseminated TB ; disseminated tuberculosis ; infection due to Mycobacterium tuberculosis ; tuberculosis infection ; tuberculous spondyloarthropathy ; cytokine ; Health Care Costs ; Health Costs ; Healthcare Costs ; Data Set ; Dataset ; base ; dosage ; Label ; improved ; Chronic ; Clinical ; Biological ; Logistic Regressions ; prognostic ; Training ; disability ; Individual ; Anti-Tumor Necrosis Factor Therapy ; anti-TNF therapy ; anti-TNF-alpha therapy ; Exposure to ; instrument ; Diagnostic ; machine learned ; Machine Learning ; Best Practice Analysis ; Benchmarking ; Robin ; Robin bird ; Performance ; Biopsy Sample ; Biopsy Specimen ; novel ; adjudicative process and procedure ; adjudication ; Predictive Factor ; (TNF)-α ; Cachectin ; Macrophage-Derived TNF ; Monocyte-Derived TNF ; TNF ; TNF A ; TNF Alpha ; TNF-α ; TNFA ; TNFα ; Tumor Necrosis Factor ; Tumor Necrosis Factor-alpha ; TNF gene ; Modeling ; Sampling ; response ; Meta-Analysis ; Address ; Data ; Economic Burden ; Validation ; Development ; developmental ; Immunomodulators ; IMiD ; Immune modulatory therapeutic ; immune modulating agents ; immune modulating drug ; immune modulating therapeutics ; immune modulators ; immune modulatory agents ; immune modulatory drugs ; immunomodulating agents ; immunomodulatory agents ; immunomodulatory drugs ; immunomodulatory therapeutics ; cost ; adjudicate ; Outcome ; Prevalence ; transcriptomics ; treatment response ; response to treatment ; therapeutic response ; genome-wide ; genome scale ; genomewide ; clinical practice ; predictive marker ; predictive biomarkers ; predictive molecular biomarker ; differential expression ; differentially expressed ; transcriptional differences ; clinically actionable ; predicting response ; prediction of response ; predictive response ; predictor of response ; response prediction ; genetic signature ; gene signatures ; response biomarker ; response markers ; responders and non-responders ; responders from non-responders ; responders or non-responders ; responders versus non-responders ; responders vs non-responders ; prognostic signature ; prognostic profile ; predictive signature ; clinically translatable ; Retrospective cohort ; clinical development ; service providers ; acute infection ; machine learning algorithm ; machine learned algorithm ; multilayer perceptron ; side effect ; infection risk ; Financial Hardship ; financial burden ; financial distress ; financial strain ; financial stress ; bioinformatics pipeline ; bio-informatics pipeline ; support vector machine ;
