A modified risk detection approach of biomarkers by frailty effect on multiple time to event data

11/26/2020
by   Atanu Bhattacharjee, et al.
0

Multiple indications of disease progression found in a cancer patient by loco-regional relapse, distant metastasis and death. Early identification of these indications is necessary to change the treatment strategy. Biomarkers play an essential role in this aspect. The biomarkers can influence how particular cancer behaves and how it may respond to a specific treatment. The survival chance of a patient is dependent on the biomarker, and the treatment strategy also differs accordingly, e.g., the survival prediction of breast cancer patients diagnosed with HER2 positive status is different from the same with HER2 negative status. This results in a different treatment strategy. So, the heterogeneity of the biomarker statuses or levels should be taken into consideration while modelling the survival outcome. This heterogeneity factor which is often unobserved, is called frailty. When multiple indications are present simultaneously, the scenario becomes more complex as only one of them can occur, which will censor the occurrence of other events. The events indicating cancer progression are likely to be inter-related. So, the correlation should be incorporated through the frailties of different events. In our study, we considered a multiple events or risks model with a heterogeneity component. Based on the estimated variance of the frailty, the threshold levels of a biomarker are utilised as early detection tool of the disease progression or death. Additive-gamma frailty model is considered to account the correlation between different frailty components and estimation of parameters are performed using Expectation-Maximization Algorithm. With the extensive algorithm in R, we have obtained the threshold levels of activity of a biomarker in a multiple events scenario.

READ FULL TEXT
research
12/22/2022

Deep Learning of Semi-Competing Risk Data via a New Neural Expectation-Maximization Algorithm

Prognostication for lung cancer, a leading cause of mortality, remains a...
research
08/31/2022

Personalized Biopsy Schedules Using an Interval-censored Cause-specific Joint Model

Active surveillance (AS), where biopsies are conducted to detect cancer ...
research
01/21/2020

how well can sensitivity and sojourn time be estimated

Chronic disease progression models are governed by three main parameters...
research
11/22/2018

Failure of complex systems, cascading disasters, and the onset of disease

Complex systems can fail through different routes, often progressing thr...
research
07/08/2022

Stacked Autoencoder Based Multi-Omics Data Integration for Cancer Survival Prediction

Cancer survival prediction is important for developing personalized trea...
research
07/30/2019

Classification Algorithm for High Dimensional Protein Markers in Time-course Data

Identification of biomarkers is an emerging area in Oncology. In this ar...

Please sign up or login with your details

Forgot password? Click here to reset