Machine learning and mechanistic computational modeling of inflammation as tools for designing immunomodulatory biomaterials

An, Gary; Cockrell, Chase; Zamora, Rubén; Vodovotz, Yoram

doi:10.1016/b978-0-12-821440-4.00009-8

Cited by 2 publications

(4 citation statements)

References 126 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[53,54]. These mechanistic, equation-based models are often used in conjunction with statistically-based methods and models [57] to understand the possible dynamics associated with varying parameters sets. Parameter sampling and post-analysis of the mechanistic data obtained from the model are just two examples of processes that benefit from a statistical approach.…”

Section: Mathematical Backgroundmentioning

confidence: 99%

“…Methods such as random forest, neutral networks, and principal components analysis continue to be used in congruence with mathematical models and biological systems [62][63][64][65][66]. These methods work well to process the large amounts of data obtained from a mechanistic model and identify abstract features of the system [57]. These algorithms can also identify nonlinear interactions between factors within the model, adding crucial insight into parameters effecting the response.…”

Section: Mathematical Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Hay

Grubb

Minucci

et al. 2023

Preprint

View full text Add to dashboard Cite

A variety of pulmonary insults can result in the necessity for mechanical ventilation, which, when misused, used for prolonged periods of time, or associated with an excessive inflammatory response, can result in ventilator-induced lung injury. Older patients have been observed to have an increased risk for respiratory distress with ventilation and more recent studies suggest that this could be linked to disparities in the inflammatory response. To address this, we ventilated young (2-3 months) and old (20-25 months) mice for 2 hours using high pressure mechanical ventilation and extracted data for inflammatory cell ratios, namely macrophage phenotypes, and lung tissue integrity. A large difference in naive macrophages at baseline, alternatively-activated (M2) macrophages at baseline, and airspace enlargement after ventilation was observed in the old mice. The experimental data was used to fit a mathematical model for the inflammatory response to lung injury. Model variables include inflammatory markers and cells, namely neutrophils and macrophages, epithelial cells at varying states, and repair mediators. Parameter sampling was performed using an iterative sampling method and parameter sets were selected based on their ability to fit either the old or young macrophage phenotype percentages and epithelial variables at zero and two hours. Classification methods were performed to identify influential parameters separating the old and young parameter sets as well as user-defined health states. Parameters involved in repair and damage to epithelial cells and parameters regulating the pro-inflammatory response were shown to be important. Local sensitivity analysis preformed for the different epithelial cell variables produced similar results. A pseudo-intervention was also performed on the parameter sets. The results were most influential for the old parameter sets, specifically those with poorer lung health. These results indicate potential targets for therapeutic interventions prior to and during ventilation, particularly for old subjects.Author summaryA variety of inhaled pathogens and other pulmonary insults prompt the need for mechanical ventilation; a procedure that has become increasingly necessary following the 2019 coronavirus pandemic. A proportion of patients respond poorly to ventilation, some resulting in ventilator-induced lung injury. Observational data has shown increased instance of severe disease in older patients as well as differences in the inflammatory response to injury, although more research is needed to confirm this. We performed high-pressure ventilation on young (2-3 months) and old (20-25 months) mice and observed large disparities in inflammatory cell ratios at baseline and lung tissue integrity after ventilation. The experimental data was then used to fit a mathematical model of the inflammatory response to lung injury. We used a variety of analysis methods to identify important parameters separating the young and old parameter sets and user-defined health states of the resulting simulations. Parameters involved in damage and repair of epithelial cells in the lung as well as parameters controlling the pro-inflammatory response to injury were important in both classifying between old and young sets and determining predicted health after ventilation. These results indicate potential targets for therapeutic interventions prior to and during ventilation.

show abstract

Section: Mathematical Backgroundmentioning

confidence: 99%

Section: Mathematical Backgroundmentioning

confidence: 99%

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Hay

Grubb

Minucci

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These mechanistic, equation-based models are often used in conjunction with statistically-based methods and models [ 22 ] to understand the possible dynamics associated with varying parameter sets. Parameter sampling and post-analysis of the mechanistic data obtained from the model are just two examples of processes that benefit from a statistical approach.…”

Section: Introductionmentioning

confidence: 99%

“…Methods such as random forest, neural networks, and principal components analysis continue to be used in congruence with mathematical models and biological systems [27][28][29][30][31]. These methods work well to process the large amounts of data obtained from a mechanistic model and identify abstract features of the system [22]. These algorithms can also identify nonlinear interactions between factors within the model, adding crucial insight into parameters affecting the response.…”

Section: Introductionmentioning

confidence: 99%

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Hay,

Grubb,

Minucci

et al. 2024

PLoS Comput Biol

View full text Add to dashboard Cite

A variety of pulmonary insults can prompt the need for life-saving mechanical ventilation; however, misuse, prolonged use, or an excessive inflammatory response, can result in ventilator-induced lung injury. Past research has observed an increased instance of respiratory distress in older patients and differences in the inflammatory response. To address this, we performed high pressure ventilation on young (2-3 months) and old (20-25 months) mice for 2 hours and collected data for macrophage phenotypes and lung tissue integrity. Large differences in macrophage activation at baseline and airspace enlargement after ventilation were observed in the old mice. The experimental data was used to determine plausible trajectories for a mathematical model of the inflammatory response to lung injury which includes variables for the innate inflammatory cells and mediators, epithelial cells in varying states, and repair mediators. Classification methods were used to identify influential parameters separating the parameter sets associated with the young or old data and separating the response to ventilation, which was measured by changes in the epithelial state variables. Classification methods ranked parameters involved in repair and damage to the epithelial cells and those associated with classically activated macrophages to be influential. Sensitivity results were used to determine candidate in-silico interventions and these interventions were most impact for transients associated with the old data, specifically those with poorer lung health prior to ventilation. Model results identified dynamics involved in M1 macrophages as a focus for further research, potentially driving the age-dependent differences in all macrophage phenotypes. The model also supported the pro-inflammatory response as a potential indicator of age-dependent differences in response to ventilation. This mathematical model can serve as a baseline model for incorporating other pulmonary injuries.

show abstract

Machine learning and mechanistic computational modeling of inflammation as tools for designing immunomodulatory biomaterials

Cited by 2 publications

References 126 publications

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Age-dependent ventilator-induced lung injury: Mathematical modeling, experimental data, and statistical analysis

Contact Info

Product

Resources

About