This is an early access version
University of Jordan , Amman , Jordan
Aim: To examine the likelihood of predicting lung cancer survival versus death using Bayesian model based on demographic and laboratory data.
Methods: A predictive design using electronic health records from 2012 to 2023 was implemented. IBM SPSS Statistics version 29.0 was used for data descriptive analysis and prediction models were built using SPSS Modeler version 18.0. Among the eight generated models, the Bayesian model demonstrated the highest accuracy (71.9%) and the best area under the curve (AUC) at 80.304, showcasing its superior predictive performance for lung cancer outcome.
Results A total of 1,843 patients without missing values were used. Males constituted 64.2 % of total sample. About 70 % of the patients were aged between 46 and 99 years. The Bayesian Network identified seven key predictors for determining patient outcome (survival versus death). Among these, age was found as the most significant predictor of survival outcome.
Conclusion The Bayesian Network outperformed other models in predicting lung cancer survival versus death probability. The integration of routine laboratory testing and demographic data in the machine learning model can help in the prediction of lung cancer survival versus death.
Conceptualization, I.B.M. and M.A.; Data curation, I.B.M. and M.A.; Formal Analysis, I.B.M. and M.A.; Investigation, I.B.M. and M.A.; Methodology, I.B.M. and M.A.; Project administration, I.B.M.; Writing – original draft, I.B.M.; Writing – review & editing, M.A. All authors have read and agreed to the published version of the manuscript.
No specific funding was received for this study.
This work is licensed under a Attribution-NonCommercial-NoDerivatives 4.0 International 
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.