Uncertainty quantification for a model of HIV-1 patient response to antiretroviral therapy interruptions

Baraldi, Robert; Cross, Karissa L.; McChesney, Christina; Poag, Laura; Thorpe, Emma; Flores, Kevin; Banks, Harvey Thomas

doi:10.1109/acc.2014.6858714

Cited by 5 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a study conducted in the USA [20], HIV-1 infection dynamic model was designed and evaluated with their data to ease the improvement in human beings. Bootstrapping is used in order to correlate the different parameters.…”

Section: Literature Reviewmentioning

confidence: 99%

Designing a Predictive Model for Antiretroviral Regimen at the Antiretroviral Therapy Center in Chiro Hospital, Ethiopia

Nemomsa¹,

Azath

2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Nowadays, the huge amount of patient’s data significantly increases with respect to the time in repositories and data mining is increasingly used as an emerging research area in medical fields for extracting useful and previously unknown insights/patterns from the repository data. These unknown patterns/hidden insights can help in discovering new knowledge hidden in these data repositories. From the observation, different ARV regimens were ordered for different patients. However, combination of these drugs causes different side effects on the patients. It has been observed that there was a lack of predictive studies and designed models available in hospitals specifically ART Centers that accurately determine or classify the patient’s ARV regimen to TDF + 3TC + EFV, TDF + 3TC + NVP, AZT + 3TC + ATV/R, AZT + 3TC + LPV/R, TDF + 3TC + LVP/R, TDF + 3TC + ATV/R, 8888, and ABC + 3TC + LPV/R. In order to solve these kinds of problems, we built an accurate classifier system or model using parameters like Patient Age, Patient Encounter Day, Patient Encounter Month, Patient Encounter Year, Patient Weight, Patient CD4 Count Adult, Patient TB Screen, Patient Following WHO Stage, Patient CD4 Percent Child, Patient Regimen Specify, Patient Regimen, and so on. The general objective of this research was predictive modeling for the patient’s ARV regimen class through data mining techniques so as to improve them. The study used the CRIPS-DM methodology to find and interpret patterns in repositories. A decision tree (J48 and Random Forest) algorithm was used for classification. Using all tested classifiers, the investigation of the study shows that the total accuracy was more than 60%. On the other hand, among different classifications, class H (ABC + 3TC + LPV/R) has shown the worst prediction. But it was revealed that the J48 classifier relatively produces higher classification accuracy for the D (AZT-3TC-NVP) regimen. Here, classification depended on the selected parameters, which revealed that prediction accuracy value differed among all classifiers and the selected attributes. Finally, the study concluded that data mining can be used as a significant technique to discover patient regimen based on salient affecting factors with 96.1% precision achieved. Ensemble learning resolves the categorizing models of greater anticipating performance with different learning algorithms. This model aligned with sentimental investigation to magnify the appearances of the dataset either from the social media or from primary data collection. The empirical investigation with different parameters shows the detailed improvement of their learning methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Designing a Predictive Model for Antiretroviral Regimen at the Antiretroviral Therapy Center in Chiro Hospital, Ethiopia

Nemomsa¹,

Azath

2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…We then used the complex step method [40] to estimate model sensitivity for each parameter. From the sensitivities, we approximated parameter covariances and standard errors [41][42][43].…”

Section: Uncertainty Quantification and Subset Selection: Which Model Parameters Can Be Estimated For Each Individual Dataset?mentioning

confidence: 99%

Predicting Inter-individual Variability During Lipid Resuscitation of Bupivacaine Cardiotoxicity in Rats: A Virtual Population Modeling Study

2021

Self Cite

View full text Add to dashboard Cite

Introduction Intravenous lipid emulsions (ILE) have been credited for successful resuscitation in drug intoxication cases where other cardiac life-support methods have failed. However, inter-individual variability can function as a confounder that challenges our ability to define the scope of efficacy for lipid interventions, particularly as relevant data are scarce. To address this challenge, we developed a quantitative systems pharmacology model to predict outcome variability and shed light on causal mechanisms in a virtual population of rats subjected to bupivacaine toxicity and ILE intervention. Materials and MethodsWe combined a physiologically based pharmacokinetic-pharmacodynamic model with data from a small study in Sprague-Dawley rats to characterize individual-specific cardiac responses to lipid infusion. We used the resulting individual parameter estimates to posit a population distribution of responses to lipid infusion. On that basis, we constructed a large virtual population of rats (N = 10,000) undergoing lipid therapy following bupivacaine cardiotoxicity. Results Using unsupervised clustering to assign resuscitation endpoints, our simulations predicted that treatment with a 30% lipid emulsion increases bupivacaine median lethal dose (LD 50 ) by 46% when compared with a simulated control fluid. Prior experimental findings indicated an LD 50 increase of 48%. Causal analysis of the population data suggested that muscle accumulation rather than liver accumulation of bupivacaine drives survival outcomes. Conclusion Our results represent a successful prediction of complex, dynamic physiological outcomes over a virtual population. Despite being informed by very limited data, our mechanistic model predicted a plausible range of treatment outcomes that accurately predicts changes in LD 50 when extrapolated to putatively toxic doses of bupivacaine. Furthermore, causal analysis of the predicted survival outcomes indicated a critical synergy between scavenging and direct cardiotonic mechanisms of ILE action.

show abstract

“…For size class 2, the adult population, however, γ = 0 is sufficiently random. We note that other works have incorporated varying γ values for certain classes of observables [14,10].…”

Section: Generalized Least Squares Parameter Estimation and Uncertainmentioning

confidence: 99%

Continuous Structured Population Models for Daphnia magna

et al. 2017

Self Cite

View full text Add to dashboard Cite

We continue our efforts in modeling Daphnia magna, a species of water flea, by proposing a continuously structured population model incorporating density-dependent and density-independent fecundity and mortality rates. We collected new individual-level data to parameterize the individual demographics relating food availability and individual daphnid growth. Our model is fit to experimental data using the generalized least-squares framework, and we use cross-validation and Akaike Information Criteria to select hyper-parameters. We present our confidence intervals on parameter estimates.

show abstract

Uncertainty quantification for a model of HIV-1 patient response to antiretroviral therapy interruptions

Cited by 5 publications

References 20 publications

Designing a Predictive Model for Antiretroviral Regimen at the Antiretroviral Therapy Center in Chiro Hospital, Ethiopia

Designing a Predictive Model for Antiretroviral Regimen at the Antiretroviral Therapy Center in Chiro Hospital, Ethiopia

Predicting Inter-individual Variability During Lipid Resuscitation of Bupivacaine Cardiotoxicity in Rats: A Virtual Population Modeling Study

Continuous Structured Population Models for Daphnia magna

Contact Info

Product

Resources

About