Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study
Abstract Background Given the rapid increase in the prevalence of prostate cancer (PCa), identifying its risk factors and developing suitable risk prediction models has important implications for public health. We used machine learning (ML) approach to screen participants with high risk of PCa and,...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-12-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-024-20852-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850253964253069312 |
|---|---|
| author | Tao Thi Tran Jeonghee Lee Junetae Kim Sun-Young Kim Hyunsoon Cho Jeongseon Kim |
| author_facet | Tao Thi Tran Jeonghee Lee Junetae Kim Sun-Young Kim Hyunsoon Cho Jeongseon Kim |
| author_sort | Tao Thi Tran |
| collection | DOAJ |
| description | Abstract Background Given the rapid increase in the prevalence of prostate cancer (PCa), identifying its risk factors and developing suitable risk prediction models has important implications for public health. We used machine learning (ML) approach to screen participants with high risk of PCa and, specifically, investigated whether participants with metabolic syndrome (MetS) exhibited an elevated PCa risk. Methods A prospective cohort study was performed with 41,837 participants in South Korea. We predicted PCa based on MetS, its components, and sociodemographic factors using Cox proportional hazards and five ML models. Integrated Brier score (IBS) and C-index were used to assess model performance. Results A total of 210 incident PCa cases were identified. We found good calibration and discrimination for all models (C-index ≥ 0.800 and IBS = 0.01). Importantly, performance increased after excluding MetS and its components from the models; the highest C-index was 0.862 for survival support vector machine. In contrast, first-degree family history of PCa, alcohol consumption, age, and income were valuable for PCa prediction. Conclusion ML models are an effective approach to develop prediction models for survival analysis. Furthermore, MetS and its components do not seem to influence PCa susceptibility, in contrast to first-degree family history of PCa, age, alcohol consumption, and income. |
| format | Article |
| id | doaj-art-3c126189ffb44896b9d734223ccf4068 |
| institution | OA Journals |
| issn | 1471-2458 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-3c126189ffb44896b9d734223ccf40682025-08-20T01:57:14ZengBMCBMC Public Health1471-24582024-12-0124111210.1186/s12889-024-20852-8Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort studyTao Thi Tran0Jeonghee Lee1Junetae Kim2Sun-Young Kim3Hyunsoon Cho4Jeongseon Kim5Department of Cancer Control and Population Health, Graduate School of Cancer Science and PolicyDepartment of Cancer Biomedical Science, Graduate School of Cancer Science and PolicyDepartment of Cancer Control and Population Health, Graduate School of Cancer Science and PolicyDepartment of Cancer Control and Population Health, Graduate School of Cancer Science and PolicyDepartment of Cancer Control and Population Health, Graduate School of Cancer Science and PolicyDepartment of Cancer Biomedical Science, Graduate School of Cancer Science and PolicyAbstract Background Given the rapid increase in the prevalence of prostate cancer (PCa), identifying its risk factors and developing suitable risk prediction models has important implications for public health. We used machine learning (ML) approach to screen participants with high risk of PCa and, specifically, investigated whether participants with metabolic syndrome (MetS) exhibited an elevated PCa risk. Methods A prospective cohort study was performed with 41,837 participants in South Korea. We predicted PCa based on MetS, its components, and sociodemographic factors using Cox proportional hazards and five ML models. Integrated Brier score (IBS) and C-index were used to assess model performance. Results A total of 210 incident PCa cases were identified. We found good calibration and discrimination for all models (C-index ≥ 0.800 and IBS = 0.01). Importantly, performance increased after excluding MetS and its components from the models; the highest C-index was 0.862 for survival support vector machine. In contrast, first-degree family history of PCa, alcohol consumption, age, and income were valuable for PCa prediction. Conclusion ML models are an effective approach to develop prediction models for survival analysis. Furthermore, MetS and its components do not seem to influence PCa susceptibility, in contrast to first-degree family history of PCa, age, alcohol consumption, and income.https://doi.org/10.1186/s12889-024-20852-8Prostate cancerMachine learningMetabolic syndromeKorea |
| spellingShingle | Tao Thi Tran Jeonghee Lee Junetae Kim Sun-Young Kim Hyunsoon Cho Jeongseon Kim Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study BMC Public Health Prostate cancer Machine learning Metabolic syndrome Korea |
| title | Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study |
| title_full | Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study |
| title_fullStr | Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study |
| title_full_unstemmed | Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study |
| title_short | Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study |
| title_sort | machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics a prospective cohort study |
| topic | Prostate cancer Machine learning Metabolic syndrome Korea |
| url | https://doi.org/10.1186/s12889-024-20852-8 |
| work_keys_str_mv | AT taothitran machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy AT jeongheelee machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy AT junetaekim machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy AT sunyoungkim machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy AT hyunsooncho machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy AT jeongseonkim machinelearningalgorithmsthatpredicttheriskofprostatecancerbasedonmetabolicsyndromeandsociodemographiccharacteristicsaprospectivecohortstudy |