A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study
BackgroundDepression is associated with an increased risk of death in patients with coronary heart disease (CHD). This study aimed to explore the factors influencing depression in elderly patients with CHD and to construct a prediction model for early identification of depression in this patient pop...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.949753/full |
| _version_ | 1811341500831760384 |
|---|---|
| author | Juntao Tan Zhengguo Xu Yuxin He Lingqin Zhang Shoushu Xiang Qian Xu Qian Xu Qian Xu Xiaomei Xu Xiaomei Xu Jun Gong Chao Tan Langmin Tan |
| author_facet | Juntao Tan Zhengguo Xu Yuxin He Lingqin Zhang Shoushu Xiang Qian Xu Qian Xu Qian Xu Xiaomei Xu Xiaomei Xu Jun Gong Chao Tan Langmin Tan |
| author_sort | Juntao Tan |
| collection | DOAJ |
| description | BackgroundDepression is associated with an increased risk of death in patients with coronary heart disease (CHD). This study aimed to explore the factors influencing depression in elderly patients with CHD and to construct a prediction model for early identification of depression in this patient population.Materials and methodsWe used propensity-score matching to identify 1,065 CHD patients aged ≥65 years from four hospitals in Chongqing between January 2015 and December 2021. The patients were divided into a training set (n = 880) and an external validation set (n = 185). Univariate logistic regression, multivariate logistic regression, and least absolute shrinkage and selection operator regression were used to determine the factors influencing depression. A nomogram based on the multivariate logistic regression model was constructed using the selected influencing factors. The discrimination, calibration, and clinical utility of the nomogram were assessed by the area under the curve (AUC) of the receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA) and clinical impact curve (CIC), respectively.ResultsThe predictive factors in the multivariate model included the lymphocyte percentage and the blood urea nitrogen and low-density lipoprotein cholesterol levels. The AUC values of the nomogram in the training and external validation sets were 0.762 (95% CI = 0.722–0.803) and 0.679 (95% CI = 0.572–0.786), respectively. The calibration curves indicated that the nomogram had strong calibration. DCA and CIC indicated that the nomogram can be used as an effective tool in clinical practice. For the convenience of clinicians, we used the nomogram to develop a web-based calculator tool (https://cytjt007.shinyapps.io/dynnomapp_depression/).ConclusionReductions in the lymphocyte percentage and blood urea nitrogen and low-density lipoprotein cholesterol levels were reliable predictors of depression in elderly patients with CHD. The nomogram that we developed can help clinicians assess the risk of depression in elderly patients with CHD. |
| first_indexed | 2024-04-13T18:56:09Z |
| format | Article |
| id | doaj.art-25cbfcb6d82044f984884629635eea51 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-04-13T18:56:09Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-25cbfcb6d82044f984884629635eea512022-12-22T02:34:14ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402022-10-011310.3389/fpsyt.2022.949753949753A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched studyJuntao Tan0Zhengguo Xu1Yuxin He2Lingqin Zhang3Shoushu Xiang4Qian Xu5Qian Xu6Qian Xu7Xiaomei Xu8Xiaomei Xu9Jun Gong10Chao Tan11Langmin Tan12Operation Management Office, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Teaching and Research, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Medical Administration, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, ChinaDepartment of Biomedical Equipment, People’s Hospital of Chongqing Bishan District, Chongqing, ChinaCollege of Medical Informatics, Chongqing Medical University, Chongqing, ChinaCollege of Medical Informatics, Chongqing Medical University, Chongqing, ChinaMedical Data Science Academy, Chongqing Medical University, Chongqing, ChinaLibrary, Chongqing Medical University, Chongqing, ChinaDepartment of Gastroenterology, The Fifth People’s Hospital of Chengdu, Chengdu, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China0Department of Information Center, The University Town Hospital of Chongqing Medical University, Chongqing, China1Department of Medical Record Management, Chongqing University Cancer Hospital, Chongqing, China2Department of Neurology, Affiliated Banan Hospital of Chongqing Medical University, Chongqing, ChinaBackgroundDepression is associated with an increased risk of death in patients with coronary heart disease (CHD). This study aimed to explore the factors influencing depression in elderly patients with CHD and to construct a prediction model for early identification of depression in this patient population.Materials and methodsWe used propensity-score matching to identify 1,065 CHD patients aged ≥65 years from four hospitals in Chongqing between January 2015 and December 2021. The patients were divided into a training set (n = 880) and an external validation set (n = 185). Univariate logistic regression, multivariate logistic regression, and least absolute shrinkage and selection operator regression were used to determine the factors influencing depression. A nomogram based on the multivariate logistic regression model was constructed using the selected influencing factors. The discrimination, calibration, and clinical utility of the nomogram were assessed by the area under the curve (AUC) of the receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA) and clinical impact curve (CIC), respectively.ResultsThe predictive factors in the multivariate model included the lymphocyte percentage and the blood urea nitrogen and low-density lipoprotein cholesterol levels. The AUC values of the nomogram in the training and external validation sets were 0.762 (95% CI = 0.722–0.803) and 0.679 (95% CI = 0.572–0.786), respectively. The calibration curves indicated that the nomogram had strong calibration. DCA and CIC indicated that the nomogram can be used as an effective tool in clinical practice. For the convenience of clinicians, we used the nomogram to develop a web-based calculator tool (https://cytjt007.shinyapps.io/dynnomapp_depression/).ConclusionReductions in the lymphocyte percentage and blood urea nitrogen and low-density lipoprotein cholesterol levels were reliable predictors of depression in elderly patients with CHD. The nomogram that we developed can help clinicians assess the risk of depression in elderly patients with CHD.https://www.frontiersin.org/articles/10.3389/fpsyt.2022.949753/fullcoronary heart diseasedepressionpropensity-score matchingnomogramcalculator tool |
| spellingShingle | Juntao Tan Zhengguo Xu Yuxin He Lingqin Zhang Shoushu Xiang Qian Xu Qian Xu Qian Xu Xiaomei Xu Xiaomei Xu Jun Gong Chao Tan Langmin Tan A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study Frontiers in Psychiatry coronary heart disease depression propensity-score matching nomogram calculator tool |
| title | A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study |
| title_full | A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study |
| title_fullStr | A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study |
| title_full_unstemmed | A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study |
| title_short | A web-based novel prediction model for predicting depression in elderly patients with coronary heart disease: A multicenter retrospective, propensity-score matched study |
| title_sort | web based novel prediction model for predicting depression in elderly patients with coronary heart disease a multicenter retrospective propensity score matched study |
| topic | coronary heart disease depression propensity-score matching nomogram calculator tool |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.949753/full |
| work_keys_str_mv | AT juntaotan awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT zhengguoxu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT yuxinhe awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT lingqinzhang awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT shoushuxiang awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT xiaomeixu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT xiaomeixu awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT jungong awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT chaotan awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT langmintan awebbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT juntaotan webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT zhengguoxu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT yuxinhe webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT lingqinzhang webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT shoushuxiang webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT qianxu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT xiaomeixu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT xiaomeixu webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT jungong webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT chaotan webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy AT langmintan webbasednovelpredictionmodelforpredictingdepressioninelderlypatientswithcoronaryheartdiseaseamulticenterretrospectivepropensityscorematchedstudy |