Background: Liver cancer is a global health concern, with overweight and obese individuals exhibiting an increased risk of its development. Understanding the interplay between obesity-related factors and liver cancer incidence is crucial for early prediction and intervention.Aim: The aim of this investigation was to construct and validate an extreme gradient boosting (XGBoost) based machine learning model for the purpose of establishing a one-year liver cancer risk prediction system specifically tailored to overweight and obese patients. In addition, this study sought to compare the predictive performance of the XGBoost model with those of a random forest model and a logistic regression model, while also identifying the most influential predictive features for liver cancer incidence.Methods: A comprehensive retrospective analysis was conducted on MIMIC III data comprising 2,354 patients. To predict the risk of liver cancer development, three machine learning models were developed: XGBoost, random forest, and logistic regression. Feature selection was executed using a stepwise regression procedure encompassing both forward selection and backward elimination.Results: The stepwise regression technique unveiled 14 predictive factors for liver cancer incidence. Among the patient cohort, 132 individuals developed liver cancer within a year of follow-up, while 2,222 did not. Notably, most liver cancer cases occurred in male patients (60%). Statistically significant differences were observed between patients with liver cancer and those without, in terms of age, gender, total bilirubin, platelet, albumin, chloride, potassium, sodium, prothrombin time (PT) and alanine aminotransferase (ALT). The XGBoost model exhibited an impressive area under the receiver operating characteristic curve (AUROC) of 99%, Random Forest (RF) of 99%, and Logistic Regression (LR) of 90%. In a multivariate analysis, total bilirubin, creatinine levels, age, gender, ALT, alkaline phosphate (ALP), PT, calcium, and chloride emerged as independent predictors for liver cancer incidence.Conclusion: The XGBoost model demonstrated superior predictive performance when compared to the RF and LR models. If corroborated through prospective studies, the XGBoost model may prove to be a valuable tool for the early prediction of liver cancer risk in overweight or obese individuals. Such predictive capabilities could, in turn, facilitate the implementation of timely preventive interventions against liver cancer.
Dear colleagues! I am satisfied with our cooperation with you. Your service is at a high level. I hope for a future relationship. Let me know if I can get a paper version of the magazine with my articles from you. I see them on the Internet.
Aksenov V.V
Thank you and your company for effective support of authors which are very much dependable on the funds gambling for science in the different countries of our huge and unpredictable world. We are doing our work and should rely on a teams like Galley Proof-HSPC. Great success to all of you for the 2019th!
Be well all the year long.
Russia
Victor V Apollonov
Your journal co-operation is very appreciable and motivational. I am really thankful to your journal and team members for the motivation and collaboration to publish my work.
Assistant Professor, UCLAS Uttaranchal University, Dehradun, India
Archna Dhasmana
Regarding to be services, we note that are work with high standards of professionalism translated into quick response, efficiency which makes communication accessible. Furthermore, I believe to be much inviting for the submission of future works for publication purposes.
Amélia João Alice Nkutxi
Thanks you and your colleague for the great help for our publication. You always provide prompt responses and high quality of service. I am so happy to have you working with me.
Thanks again!
Diana (Ding) Dai
It was a great experience publishing through JCICM. The article has reached out to several institutions. Appreciate your professional work. Hope to work with you again
Anas Wardeh
Great, We are too comfortable with the process including the peer review process and quality. But, the journal should be indexed in different databases such scopus.
Afework Edmealem
It has been a fabulous journey writing articles for your journal because of the encouragement you people provide for writers from developing nations like India. Kindly continue the same. Looking forward for a long term association.
Badareesh Lakshminarayana
"This is my first time publishing with the journal/publisher. I am impressed at the promptness of the publishing staff and the professionalism displayed. Thank you for encouraging young researchers like me!"
Ekiti State University, Nigeria
Adebukola Ajite
Your journal has accomplished its intended mission of providing very effective and efficient goals in dealing with submissions, conducting the reviewing process and in publishing accepted manuscripts in a timely manner. Keep up the great work and services that you provide.
If you are already a member of our network and need to keep track of any developments regarding a question you have already submitted, click "take me to my Query."