Browsing by Subject "survival prediction"

Now showing 1 - 2 of 2

Access status: Open Access ,
Machine learning models for predicting patients survival after liver transplantation
(Wydawnictwa AGH, 2018) Jarmulski, Wojciech; Wieczorkowska, Alicja; Trzaska, Mariusz; Ciszek, Michał; Paczek, Leszek
In our work, we have built models predicting whether a patient will lose an organ after a liver transplant within a specified time horizon. We have used the observations of bilirubin and creatinine in the whole first year after the transplantation to derive predictors, capturing not only their static value but also their variability. Our models indeed have a predictive power that proves the value of incorporating variability of biochemical measurements, and it is the first contribution of our paper. As the second contribution we have identified that full-complexity models such as random forests and gradient boosting lack sufficient interpretability despite having the best predictive power, which is important in medicine. We have found that generalized additive models (GAM) provide the desired interpretability, and their predictive power is closer to the predictions of full-complexity models than to the predictions of simple linear models.
Access status: Open Access ,
Zastosowanie sieci neuronowych do predykcji przeżycia w przypadku raka jajnika
(Wydawnictwa AGH, 2007) Grabska-Chrząstowska, Joanna; Kulpa, Jan; Rychlik, Urszula
Ovarian carcinoma is one of the most malignant carcinomas within women patients. The patients' survival is estimated at 30-50% depending on the advancement of the disease. A proper prediction of the patients' survival chances is crucial from the clinical point of view due to the possibility of introducing additional treatment after the obligatory chemotherapy. On the basis of initial research results during the primary surgery and the results received after the first step chemotherapy artificial neural network may predict a 24-month survival of particular patients with a high level of certainty.