Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment
BackgroundMachine learning is pivotal for predicting Peripherally Inserted Central Catheter-related venous thrombosis (PICC-RVT) risk, facilitating early diagnosis and proactive treatment. Existing models often assess PICC-RVT risk as static and discrete outcomes, which may limit their practical app...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2024.1445425/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556675169878016 |
|---|---|
| author | Yue Li Yue Li Shengxiao Nie Lei Wang Dongsheng Li Shengmiao Ma Ting Li Hong Sun |
| author_facet | Yue Li Yue Li Shengxiao Nie Lei Wang Dongsheng Li Shengmiao Ma Ting Li Hong Sun |
| author_sort | Yue Li |
| collection | DOAJ |
| description | BackgroundMachine learning is pivotal for predicting Peripherally Inserted Central Catheter-related venous thrombosis (PICC-RVT) risk, facilitating early diagnosis and proactive treatment. Existing models often assess PICC-RVT risk as static and discrete outcomes, which may limit their practical application.ObjectivesThis study aims to evaluate the effectiveness of seven diverse machine learning algorithms, including three deep learning and four traditional machine learning models, that incorporate time-series data to assess PICC-RVT risk. It also seeks to identify key predictive factors for PICC-RVT using these models.MethodsWe conducted a retrospective multi-center cohort study involving 5,272 patients who underwent PICC placement. After preprocessing patient data, the models were trained. Demographic, clinical pathology, and treatment data were analyzed to identify predictive factors. A variable analysis was then conducted to determine the most significant predictors of PICC-RVT. Model performance was evaluated using the Concordance Index (c-index) and the composite Brier score, and the Intraclass Correlation Coefficient (ICC) from cross-validation folds assessed model stability.ResultsDeep learning models generally outperformed traditional machine learning models in terms of predictive accuracy (mean c-index: 0.949 vs. 0.732; mean integrated Brier score: 0.046 vs. 0.093). Specifically, the DeepSurv model demonstrated exceptional precision in risk assessment (c-index: 0.95). Stability varied with the number of predictive factors, with Cox-Time showing the highest ICC (0.974) with 16 predictive factors, and DeepSurv the most stable with 26 predictive factors (ICC: 0.983). Key predictors across models included albumin levels, prefill sealant type, and activated partial thromboplastin time.ConclusionMachine learning models that incorporate time-to-event data can effectively predict PICC-RVT risk. The DeepSurv model, in particular, shows excellent discriminative and calibration capabilities. Albumin levels, type of prefill sealant, and activated partial thromboplastin time are critical indicators for identifying and managing high-risk PICC-RVT patients. |
| format | Article |
| id | doaj-art-c930524bc18840c79f8facb118bad05b |
| institution | Kabale University |
| issn | 2296-2565 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj-art-c930524bc18840c79f8facb118bad05b2025-01-07T06:50:55ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-01-011210.3389/fpubh.2024.14454251445425Integrating deep learning in public health: a novel approach to PICC-RVT risk assessmentYue Li0Yue Li1Shengxiao Nie2Lei Wang3Dongsheng Li4Shengmiao Ma5Ting Li6Hong Sun7Institute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaSchool of Electronic and Information Engineering, TianGong University, Tianjin, ChinaDepartment of Nursing, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, ChinaDepartment of Nursing, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, ChinaInstitute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaSchool of Nursing, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaInstitute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaBeijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, ChinaBackgroundMachine learning is pivotal for predicting Peripherally Inserted Central Catheter-related venous thrombosis (PICC-RVT) risk, facilitating early diagnosis and proactive treatment. Existing models often assess PICC-RVT risk as static and discrete outcomes, which may limit their practical application.ObjectivesThis study aims to evaluate the effectiveness of seven diverse machine learning algorithms, including three deep learning and four traditional machine learning models, that incorporate time-series data to assess PICC-RVT risk. It also seeks to identify key predictive factors for PICC-RVT using these models.MethodsWe conducted a retrospective multi-center cohort study involving 5,272 patients who underwent PICC placement. After preprocessing patient data, the models were trained. Demographic, clinical pathology, and treatment data were analyzed to identify predictive factors. A variable analysis was then conducted to determine the most significant predictors of PICC-RVT. Model performance was evaluated using the Concordance Index (c-index) and the composite Brier score, and the Intraclass Correlation Coefficient (ICC) from cross-validation folds assessed model stability.ResultsDeep learning models generally outperformed traditional machine learning models in terms of predictive accuracy (mean c-index: 0.949 vs. 0.732; mean integrated Brier score: 0.046 vs. 0.093). Specifically, the DeepSurv model demonstrated exceptional precision in risk assessment (c-index: 0.95). Stability varied with the number of predictive factors, with Cox-Time showing the highest ICC (0.974) with 16 predictive factors, and DeepSurv the most stable with 26 predictive factors (ICC: 0.983). Key predictors across models included albumin levels, prefill sealant type, and activated partial thromboplastin time.ConclusionMachine learning models that incorporate time-to-event data can effectively predict PICC-RVT risk. The DeepSurv model, in particular, shows excellent discriminative and calibration capabilities. Albumin levels, type of prefill sealant, and activated partial thromboplastin time are critical indicators for identifying and managing high-risk PICC-RVT patients.https://www.frontiersin.org/articles/10.3389/fpubh.2024.1445425/fullartificial intelligencemachine learningperipherally inserted central cathetertime-to-eventthrombosis |
| spellingShingle | Yue Li Yue Li Shengxiao Nie Lei Wang Dongsheng Li Shengmiao Ma Ting Li Hong Sun Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment Frontiers in Public Health artificial intelligence machine learning peripherally inserted central catheter time-to-event thrombosis |
| title | Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment |
| title_full | Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment |
| title_fullStr | Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment |
| title_full_unstemmed | Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment |
| title_short | Integrating deep learning in public health: a novel approach to PICC-RVT risk assessment |
| title_sort | integrating deep learning in public health a novel approach to picc rvt risk assessment |
| topic | artificial intelligence machine learning peripherally inserted central catheter time-to-event thrombosis |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2024.1445425/full |
| work_keys_str_mv | AT yueli integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT yueli integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT shengxiaonie integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT leiwang integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT dongshengli integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT shengmiaoma integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT tingli integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment AT hongsun integratingdeeplearninginpublichealthanovelapproachtopiccrvtriskassessment |