A patient-specific in silico model of inflammation and healing tested in acute vocal fold injury

Abstract

The development of personalized medicine is a primary objective of the medical community and increasingly also of funding and registration agencies. Modeling is generally perceived as a key enabling tool to target this goal. Agent-Based Models (ABMs) have previously been used to simulate inflammation at various scales up to the whole-organism level. We extended this approach to the case of a novel, patient-specific ABM that we generated for vocal fold inflammation, with the ultimate goal of identifying individually optimized treatments. ABM simulations reproduced trajectories of inflammatory mediators in laryngeal secretions of individuals subjected to experimental phonotrauma up to 4 hrs post-injury, and predicted the levels of inflammatory mediators 24 hrs post-injury. Subject-specific simulations also predicted different outcomes from behavioral treatment regimens to which subjects had not been exposed. We propose that this translational application of computational modeling could be used to design patient-specific therapies for the larynx, and will serve as a paradigm for future extension to other clinical domains.

Figure 1. Empirical and model-predicted inflammatory and wound healing responses to acute phonotrauma in a single human subject (Subject 3) following spontaneous speech (Panels A–C), voice rest (Panels D–F) and resonant voice treatment conditions (Panels G–I).

Panels A, D and G display empirical and predicted trajectories of IL-1β. Panels B, E and H show empirical and predicted trajectories of TNF-α. Panels C, F and I show empirical and predicted trajectories of IL-10. Inflammatory marker concentrations are in pg/ml. The grey bars represent the mean of the simulated data, and the error bars represent standard deviations in the simulated data. The dark circles represent the input data for the first three time-points (baseline, post-loading, 4-hr post treatment onset), obtained from human laryngeal secretion data. The empty circles represent the validation data at the 24-hr time point from the human laryngeal secretion data. B: baseline; PL: post vocal loading; 4hrPRx: following a 4-hr treatment. Note that human validation data for Days 2–5 have not yet been generated.

Figure 2. Empirical and model-predicted inflammatory and wound healing responses to acute phonotrauma in three subjects following spontaneous speech (Subject 3; Panels A–C), voice rest (Subject 1; Panels D–F) and resonant voice treatment conditions (Subject 2; Panels G–I).

Panels A, D and G display empirical and predicted trajectories of IL-1β. Panels B, E and H show empirical and predicted trajectories of TNF-α. Panels C, F and I show empirical and predicted trajectories of IL-10. Inflammatory marker concentrations are in pg/ml. The grey bars represent the means from the simulated data, and the error bars represent the standard deviation from the simulated data. The dark circles represent the input data for the first three time-points (baseline, post-loading, 4-hr post treatment onset) from the human laryngeal secretion data. The empty circles represent the validation data at the 24-hr time point from the human laryngeal secretion data. B: baseline; PL: post vocal loading; 4hrPRx: following a 4-hr treatment. Note that human validation data for Days 2–5 have not yet been generated.

Figure 3. An overall flowchart of the model.

The model assumes that biomechanical stress during phonation causes mucosal damage and activates platelets, neutrophils and macrophages. Platelets produce TGF-β1, which chemoattracts both neutrophils and macrophages. Activated neutrophils and macrophages secrete pro-inflammatory mediators, which in turn induce anti-inflammatory mediator release. Pro-inflammatory mediators also induce neutrophils and macrophages to produce free radicals that damage tissue. In our model, the activity of free radicals was subsumed in the actions of TNF-α. Anti-inflammatory mediators contribute to fibroblast activation. Activated fibroblasts secrete collagen that mediates tissue repair. In the model, collagen accumulation is considered as the surrogate for healing outcome following phonotrauma. Collagen is an important ECM protein involving both structural and biomechanical functions in the vocal folds (Gray & Titze, 1988; Gray et al., 2000).