Dataset Information

Validation of tacrolimus equation to predict troughs using genetic and clinical factors.

ABSTRACT:

Aim

Tacrolimus is an immunosuppressant used in transplantation. This article reports the validation of the authors' recently developed genetics-based tacrolimus equation that predicts troughs.

Methods

Validation was performed in an independent cohort of 795 kidney transplant recipients receiving tacrolimus. The performance of the equation to predict initial troughs was assessed by calculating the bias and precision of the equation. For all troughs in the first 6 months post-transplant, a comparison was made between the troughs predicted using the equation versus those predicted using a basic apparent clearance model with no covariates.

Results

For initial troughs, the equation had a low bias (0.2 ng/ml) and high precision (1.8 ng/ml). For all troughs, the equation predicted troughs significantly better than the basic apparent clearance model.

Conclusion

The tacrolimus equation had good bias and precision in predicting initial troughs and performed better than a basic apparent clearance model for all the troughs.

SUBMITTER: Passey C

PROVIDER: S-EPMC3579500 | biostudies-literature | 2012 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Validation of tacrolimus equation to predict troughs using genetic and clinical factors.

Passey Chaitali C Birnbaum Angela K AK Brundage Richard C RC Schladt David P DP Oetting William S WS Leduc Robert E RE Israni Ajay K AK Guan Weihua W Matas Arthur J AJ Jacobson Pamala A PA

Pharmacogenomics 20120701 10

<h4>Aim</h4>Tacrolimus is an immunosuppressant used in transplantation. This article reports the validation of the authors' recently developed genetics-based tacrolimus equation that predicts troughs.<h4>Methods</h4>Validation was performed in an independent cohort of 795 kidney transplant recipients receiving tacrolimus. The performance of the equation to predict initial troughs was assessed by calculating the bias and precision of the equation. For all troughs in the first 6 months post-transp ...[more]

PMID: 22909204

Similar Datasets

Project description:BackgroundEarly detection of clinical deterioration among hospitalized patients is a clinical priority for patient safety and quality of care. Current automated approaches for identifying these patients perform poorly at identifying imminent events.ObjectiveDevelop a machine learning algorithm using pager messages sent between clinical team members to predict imminent clinical deterioration.DesignWe conducted a large observational study using long short-term memory machine learning models on the content and frequency of clinical pages.ParticipantsWe included all hospitalizations between January 1, 2018 and December 31, 2020 at Vanderbilt University Medical Center that included at least one page message to physicians. Exclusion criteria included patients receiving palliative care, hospitalizations with a planned intensive care stay, and hospitalizations in the top 2% longest length of stay.Main measuresModel classification performance to identify in-hospital cardiac arrest, transfer to intensive care, or Rapid Response activation in the next 3-, 6-, and 12-hours. We compared model performance against three common early warning scores: Modified Early Warning Score, National Early Warning Score, and the Epic Deterioration Index.Key resultsThere were 87,783 patients (mean [SD] age 54.0 [18.8] years; 45,835 [52.2%] women) who experienced 136,778 hospitalizations. 6214 hospitalized patients experienced a deterioration event. The machine learning model accurately identified 62% of deterioration events within 3-hours prior to the event and 47% of events within 12-hours. Across each time horizon, the model surpassed performance of the best early warning score including area under the receiver operating characteristic curve at 6-hours (0.856 vs. 0.781), sensitivity at 6-hours (0.590 vs. 0.505), specificity at 6-hours (0.900 vs. 0.878), and F-score at 6-hours (0.291 vs. 0.220).ConclusionsMachine learning applied to the content and frequency of clinical pages improves prediction of imminent deterioration. Using clinical pages to monitor patient acuity supports improved detection of imminent deterioration without requiring changes to clinical workflow or nursing documentation.

Dataset Information

Validation of tacrolimus equation to predict troughs using genetic and clinical factors.

Aim

Methods

Results

Conclusion

Publications

Validation of tacrolimus equation to predict troughs using genetic and clinical factors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets