Survival prediction for bladder cancer using machine learning: development of BlaCaSurv online survival prediction application

Abstract

BackgroundBladder cancer is the most common cancer of the urinary system among the American population and it is the fourth most common cause of cancer morbidity and the eight most common cause of cancer mortality among men. Using machine learning algorithms, we predict the five-year survival among bladder cancer patients and deploy the best performing algorithm as a web application for survival prediction.MethodsMicroscopically confirmed adult bladder cancer patients were included from the Surveillance Epidemiology and End Results (SEER) database (2000-2017) and randomly split into training and test datasets (70/30 ratio). Five machine learning algorithms (logistic regression, support vector machine, gradient boosting, random forest, and K nearest neighbor) were trained on features to predict five-year survival. The algorithms were compared with performance metrics and the best performing algorithm was deployed as a web application.ResultsA total of 52,529 patients were included in our study. The gradient boosting algorithm was the best performer in terms of predictive ability and discrimination. It was deployed as the survival prediction web application named BlaCaSurv (https://blacasurv.herokuapp.com/).ConclusionsWe tested several machine learning algorithms and developed a web application for predicting five-year survival for bladder cancer patients. This application can be used as a supplementary prognostic tool to clinical decision making.

Comparing of Data Mining Techniques for Predicting In-Hospital Mortality Among Patients with COVID-19

“…The selected features are used as inputs for developing ML-based models for predicting severity, deterioration and mortality of COVID-19 patients. The ten top clinical variables predicting mortalities in reviewing studies, including age (high) (5, (4,5,14,41,(45)(46)(47), body temperature (high) (5,14,36,40,41,44,48), oxygen saturation (decreased) (20,21,41,43,48,49), lymphocyte/neutrophil count (raised) (21, 41-43, 46, 49), C reactive protein (raised) (21,43,44,47) , D dimer (increased) (20,40,42,47), ALT and/or AST (raised) (42,43,46,48,49), LDH (elevated) (36,42,46,50), hypertension/ cardiovascular diseases (41)(42)(43)(44)(45)47). On the other hand diarrhea (5,21,44,48,<...…”

Modeling and analyzing predictive monthly survival in females diagnosed with gynecological cancers

“…New therapeutics can possibly be better targeted or transported by different mechanisms based on some of this data, but may still fail to lower the mortality rates of many cancer types. The best method to develop new therapeutics and identify better therapeutics and delivery targets is by using a genetic profile analysis and even expanding to a proteomics based understanding of how certain cancers are activated and respond to treatment by comprehensively characterizing the condition of patients at different cancer stages [11]- [13]. Additionally, novel therapeutic targets can be identified in order to develop cell-specific therapeutics and better develop patient specific medicine [9], [14]- [16].…”