Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation
BackgroundChina has the largest burden of esophageal cancer (EC). Prediction models can be used to identify high-risk individuals for intensive lifestyle interventions and endoscopy screening. However, the current prediction models are limited by small sample size and a lack...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-03-01
|
| Series: | JMIR Public Health and Surveillance |
| Online Access: | https://publichealth.jmir.org/2023/1/e43725 |
| _version_ | 1797734334801641472 |
|---|---|
| author | Yuting Han Xia Zhu Yizhen Hu Canqing Yu Yu Guo Dong Hang Yuanjie Pang Pei Pei Hongxia Ma Dianjianyi Sun Ling Yang Yiping Chen Huaidong Du Min Yu Junshi Chen Zhengming Chen Dezheng Huo Guangfu Jin Jun Lv Zhibin Hu Hongbing Shen Liming Li |
| author_facet | Yuting Han Xia Zhu Yizhen Hu Canqing Yu Yu Guo Dong Hang Yuanjie Pang Pei Pei Hongxia Ma Dianjianyi Sun Ling Yang Yiping Chen Huaidong Du Min Yu Junshi Chen Zhengming Chen Dezheng Huo Guangfu Jin Jun Lv Zhibin Hu Hongbing Shen Liming Li |
| author_sort | Yuting Han |
| collection | DOAJ |
| description |
BackgroundChina has the largest burden of esophageal cancer (EC). Prediction models can be used to identify high-risk individuals for intensive lifestyle interventions and endoscopy screening. However, the current prediction models are limited by small sample size and a lack of external validation, and none of them can be embedded into the booming electronic health records (EHRs) in China.
ObjectiveThis study aims to develop and validate absolute risk prediction models for EC in the Chinese population. In particular, we assessed whether models that contain only EHR-available predictors performed well.
MethodsA prospective cohort recruiting 510,145 participants free of cancer from both high EC-risk and low EC-risk areas in China was used to develop EC models. Another prospective cohort of 18,441 participants was used for validation. A flexible parametric model was used to develop a 10-year absolute risk model by considering the competing risks (full model). The full model was then abbreviated by keeping only EHR-available predictors. We internally and externally validated the models by using the area under the receiver operating characteristic curve (AUC) and calibration plots and compared them based on classification measures.
ResultsDuring a median of 11.1 years of follow-up, we observed 2550 EC incident cases. The models consisted of age, sex, regional EC-risk level (high-risk areas: 2 study regions; low-risk areas: 8 regions), education, family history of cancer (simple model), smoking, alcohol use, BMI (intermediate model), physical activity, hot tea consumption, and fresh fruit consumption (full model). The performance was only slightly compromised after the abbreviation. The simple and intermediate models showed good calibration and excellent discriminating ability with AUCs (95% CIs) of 0.822 (0.783-0.861) and 0.830 (0.792-0.867) in the external validation and 0.871 (0.858-0.884) and 0.879 (0.867-0.892) in the internal validation, respectively.
ConclusionsThree nested 10-year EC absolute risk prediction models for Chinese adults aged 30-79 years were developed and validated, which may be particularly useful for populations in low EC-risk areas. Even the simple model with only 5 predictors available from EHRs had excellent discrimination and good calibration, indicating its potential for broader use in tailored EC prevention. The simple and intermediate models have the potential to be widely used for both primary and secondary prevention of EC. |
| first_indexed | 2024-03-12T12:42:45Z |
| format | Article |
| id | doaj.art-d59ef11d876840a8912e94ad5aee5be9 |
| institution | Directory Open Access Journal |
| issn | 2369-2960 |
| language | English |
| last_indexed | 2024-03-12T12:42:45Z |
| publishDate | 2023-03-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Public Health and Surveillance |
| spelling | doaj.art-d59ef11d876840a8912e94ad5aee5be92023-08-28T23:46:19ZengJMIR PublicationsJMIR Public Health and Surveillance2369-29602023-03-019e4372510.2196/43725Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External ValidationYuting Hanhttps://orcid.org/0000-0003-4868-3659Xia Zhuhttps://orcid.org/0000-0001-9420-4941Yizhen Huhttps://orcid.org/0000-0002-9442-1214Canqing Yuhttps://orcid.org/0000-0002-0019-0014Yu Guohttps://orcid.org/0000-0003-4254-1596Dong Hanghttps://orcid.org/0000-0001-6944-0459Yuanjie Panghttps://orcid.org/0000-0002-4826-8861Pei Peihttps://orcid.org/0000-0002-5741-6563Hongxia Mahttps://orcid.org/0000-0002-9821-6955Dianjianyi Sunhttps://orcid.org/0000-0003-3651-6693Ling Yanghttps://orcid.org/0000-0001-5750-6588Yiping Chenhttps://orcid.org/0000-0002-4973-0296Huaidong Duhttps://orcid.org/0000-0002-9814-0049Min Yuhttps://orcid.org/0000-0001-5473-0736Junshi Chenhttps://orcid.org/0000-0001-5530-1343Zhengming Chenhttps://orcid.org/0000-0001-6423-105XDezheng Huohttps://orcid.org/0000-0002-4041-1678Guangfu Jinhttps://orcid.org/0000-0003-0249-5337Jun Lvhttps://orcid.org/0000-0001-7916-3870Zhibin Huhttps://orcid.org/0000-0002-8277-5234Hongbing Shenhttps://orcid.org/0000-0002-2581-5906Liming Lihttps://orcid.org/0000-0001-5873-7089 BackgroundChina has the largest burden of esophageal cancer (EC). Prediction models can be used to identify high-risk individuals for intensive lifestyle interventions and endoscopy screening. However, the current prediction models are limited by small sample size and a lack of external validation, and none of them can be embedded into the booming electronic health records (EHRs) in China. ObjectiveThis study aims to develop and validate absolute risk prediction models for EC in the Chinese population. In particular, we assessed whether models that contain only EHR-available predictors performed well. MethodsA prospective cohort recruiting 510,145 participants free of cancer from both high EC-risk and low EC-risk areas in China was used to develop EC models. Another prospective cohort of 18,441 participants was used for validation. A flexible parametric model was used to develop a 10-year absolute risk model by considering the competing risks (full model). The full model was then abbreviated by keeping only EHR-available predictors. We internally and externally validated the models by using the area under the receiver operating characteristic curve (AUC) and calibration plots and compared them based on classification measures. ResultsDuring a median of 11.1 years of follow-up, we observed 2550 EC incident cases. The models consisted of age, sex, regional EC-risk level (high-risk areas: 2 study regions; low-risk areas: 8 regions), education, family history of cancer (simple model), smoking, alcohol use, BMI (intermediate model), physical activity, hot tea consumption, and fresh fruit consumption (full model). The performance was only slightly compromised after the abbreviation. The simple and intermediate models showed good calibration and excellent discriminating ability with AUCs (95% CIs) of 0.822 (0.783-0.861) and 0.830 (0.792-0.867) in the external validation and 0.871 (0.858-0.884) and 0.879 (0.867-0.892) in the internal validation, respectively. ConclusionsThree nested 10-year EC absolute risk prediction models for Chinese adults aged 30-79 years were developed and validated, which may be particularly useful for populations in low EC-risk areas. Even the simple model with only 5 predictors available from EHRs had excellent discrimination and good calibration, indicating its potential for broader use in tailored EC prevention. The simple and intermediate models have the potential to be widely used for both primary and secondary prevention of EC.https://publichealth.jmir.org/2023/1/e43725 |
| spellingShingle | Yuting Han Xia Zhu Yizhen Hu Canqing Yu Yu Guo Dong Hang Yuanjie Pang Pei Pei Hongxia Ma Dianjianyi Sun Ling Yang Yiping Chen Huaidong Du Min Yu Junshi Chen Zhengming Chen Dezheng Huo Guangfu Jin Jun Lv Zhibin Hu Hongbing Shen Liming Li Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation JMIR Public Health and Surveillance |
| title | Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation |
| title_full | Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation |
| title_fullStr | Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation |
| title_full_unstemmed | Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation |
| title_short | Electronic Health Record–Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation |
| title_sort | electronic health record based absolute risk prediction model for esophageal cancer in the chinese population model development and external validation |
| url | https://publichealth.jmir.org/2023/1/e43725 |
| work_keys_str_mv | AT yutinghan electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT xiazhu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT yizhenhu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT canqingyu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT yuguo electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT donghang electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT yuanjiepang electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT peipei electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT hongxiama electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT dianjianyisun electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT lingyang electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT yipingchen electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT huaidongdu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT minyu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT junshichen electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT zhengmingchen electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT dezhenghuo electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT guangfujin electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT junlv electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT zhibinhu electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT hongbingshen electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation AT limingli electronichealthrecordbasedabsoluteriskpredictionmodelforesophagealcancerinthechinesepopulationmodeldevelopmentandexternalvalidation |