Dataset Information

A novel learning algorithm to predict individual survival after liver transplantation for primary sclerosing cholangitis.

ABSTRACT: Deciding who should receive a liver transplant (LT) depends on both urgency and utility. Most survival scores are validated through discriminative tests, which compare predicted outcomes between patients. Assessing post-transplant survival utility is not discriminate, but should be "calibrated" to be effective. There are currently no such calibrated models. We developed and validated a novel calibrated model to predict individual survival after LT for Primary Sclerosing Cholangitis (PSC). We applied a software tool, PSSP, to adult patients in the Scientific Registry of Transplant Recipients (n = 2769) who received a LT for PSC between 2002 and 2013; this produced a model for predicting individual survival distributions for novel patients. We also developed an appropriate evaluation measure, D-calibration, to validate this model. The learned PSSP model showed an excellent D-calibration (p = 1.0), and passed the single-time calibration test (Hosmer-Lemeshow p-value of over 0.05) at 0.25, 1, 5 and 10 years. In contrast, the model based on traditional Cox regression showed worse calibration on long-term survival and failed at 10 years (Hosmer-Lemeshow p value = 0.027). The calculator and visualizer are available at: http://pssp.srv.ualberta.ca/calculator/liver_transplant_2002. In conclusion we present a new tool that accurately estimates individual post liver transplantation survival.

SUBMITTER: Andres A

PROVIDER: S-EPMC5854273 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A novel learning algorithm to predict individual survival after liver transplantation for primary sclerosing cholangitis.

Andres Axel A Montano-Loza Aldo A Greiner Russell R Uhlich Max M Jin Ping P Hoehn Bret B Bigam David D Shapiro James Andrew Mark JAM Kneteman Norman Mark NM

PloS one 20180315 3

Deciding who should receive a liver transplant (LT) depends on both urgency and utility. Most survival scores are validated through discriminative tests, which compare predicted outcomes between patients. Assessing post-transplant survival utility is not discriminate, but should be "calibrated" to be effective. There are currently no such calibrated models. We developed and validated a novel calibrated model to predict individual survival after LT for Primary Sclerosing Cholangitis (PSC). We app ...[more]

PMID: 29543895

Similar Datasets

Project description:Background & aimsAlthough worsening liver-related symptoms during pregnancy can occur in primary sclerosing cholangitis (PSC), there are insufficient data to effectively counsel patients on their pre-conception risk and no clear recommendations on monitoring and management during pregnancy. We aimed to describe maternal liver-related symptoms in pregnancy, both before and after PSC diagnosis, and explore factors associated with worsening symptoms and liver-related outcomes.MethodsWe conducted a multicentre retrospective observational study of females with PSC and known pregnancy with live birth, via the International PSC Study Group. We included 450 patients from 12 European centres. Data included clinical variables, liver-related symptoms (pruritus and/or cholangitis) during pregnancy, and liver biochemistry. A composite primary endpoint of transplant-free survival from time of PSC diagnosis was used.ResultsThere were 266 pregnancies in 178 patients following PSC diagnosis. Worsening liver-related symptoms were reported in 66/228 (28.9%) pregnancies; they had a reduced transplant-free survival (p = 0.03), which retained significance on multivariate analysis (hazard ratio 3.02, 95% CI 1.24-7.35; p = 0.02).Abnormal biochemistry and/or liver-related symptoms (pruritus and/or cholangitis) were noted during pregnancy before PSC diagnosis in 21/167 (12.6%) patients. They had a reduced transplant-free survival from pregnancy (p = 0.01), which did not retain significance in a multivariable model (hazard ratio 1.10, 95% CI 0.43-2.85; p = 0.84).ConclusionsLiver-related symptoms are frequently encountered during pregnancies before the diagnosis of PSC, and pregnancy may expose the pre-clinical phase of PSC in some patients. Worsening liver-related symptoms were seen in a third of our cohort with known PSC during pregnancy; and this subgroup had a poorer prognosis, which may be related to more advanced liver disease at time of pregnancy and/or a more severe disease phenotype.Impact and implicationsPatients with PSC can develop worsening of their liver-related symptoms during pregnancy; however, risk factors for this and the long-term implications are not known. We identified that there is a significant risk of these symptoms in pregnancy, both before and after PSC has been diagnosed, particularly in patients with elevated alkaline phosphatase. Furthermore, our findings suggest that worsening symptoms during pregnancy may be associated with adverse long-term clinical outcomes of liver transplantation and death in patients with known PSC. This may be related to the presence of more advanced liver disease at time of pregnancy. This information can be used to counsel patients with PSC before conception and identify patients who need close follow-up after delivery.

Dataset Information

A novel learning algorithm to predict individual survival after liver transplantation for primary sclerosing cholangitis.

Publications

A novel learning algorithm to predict individual survival after liver transplantation for primary sclerosing cholangitis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets