1
|
Sheng Y, Gao W. Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features. Clin Nurs Res 2024; 33:460-469. [PMID: 39076023 DOI: 10.1177/10547738241260947] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/31/2024]
Abstract
This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of "input-output" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (P), recall (R), accuracy (ACC), and area under the curve (AUC). In terms of feature importance analysis, this study chooses a single feature analysis method based on the "input-output" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are P = 0.92, R = 0.95, ACC = 0.88, and AUC = 0.81. Specifically, the RF model is P = 0.95, R = 0.96, ACC = 0.92, AUC = 0.86; the ANN model is P = 0.92, R = 0.95, ACC = 0.88, AUC = 0.81; the SVC model is P = 0.88, R = 0.94, ACC = 0.85, AUC = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.
Collapse
Affiliation(s)
- Yuan Sheng
- Shandong University, Jinan, China
- Liaocheng University, Liaocheng, China
| | - Wei Gao
- Shandong University of Qilu Hospital, Jinan, China
| |
Collapse
|
2
|
Castelli B, Scagnet M, Mussa F, Genitori L, Sardi I, Stagi S. Vascular complications in craniopharyngioma-resected paediatric patients: a single-center experience. Front Endocrinol (Lausanne) 2024; 15:1292025. [PMID: 38681768 PMCID: PMC11047119 DOI: 10.3389/fendo.2024.1292025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/10/2023] [Accepted: 03/12/2024] [Indexed: 05/01/2024] Open
Abstract
Background Craniopharyngioma (CP), although slow growing and histologically benign, has high morbidity, mostly related to hypothalamus-pituitary dysfunction and electrolyte imbalance. Increased risk of vascular complications has been described. However, data are still poor, especially in the paediatric population. The aim of our study was to evaluate the occurrence, timing, and predisposing factors of deep venous thrombosis (DVT) and other vascular alterations in neurosurgical paediatric CP patients. Materials and Methods In a single-centre, retrospective study, we investigated 19 CP patients (11 males, 8 females, mean age 10.5 ± 4.3 years), who underwent neurosurgery between December 2016 and August 2022, referred to Meyer Children's Hospital IRCCS in Florence. Results Five patients (26.3%) presented vascular events, which all occurred in connection with sodium imbalances. Three DVT (two with associated pulmonary embolism, in one case leading to death) developed in the post-operative period, most frequently at 7-10 days. Elevated D-dimers, a reduced partial activated thrombin time and a prolonged C-reactive protein increase were highly related to thrombotic vascular events. One case of posterior cerebral artery pseudoaneurysm was described soon after neurosurgery, requiring vascular stenting. Superficial vein thrombophlebitis was a late complication in one patient with other predisposing factors. Conclusion CP patients undergoing neurosurgery are at risk of developing DVT and vascular alterations, thus careful follow-up is mandatory. In our study, we found that the phase of transition from central diabetes insipidus to a syndrome of inappropriate antidiuretic hormone secretion may be a period of significant risk for DVT occurrence. Careful vascular follow-up is mandatory in CP-operated patients.
Collapse
Affiliation(s)
- Barbara Castelli
- Department of Health Sciences, University of Florence, Florence, Italy
- Neuro-oncology Department, Meyer Children’s Hospital IRCCS, Florence, Italy
| | - Mirko Scagnet
- Neurosurgery Department, Meyer Children’s Hospital IRCCS, Florence, Italy
| | - Federico Mussa
- Neurosurgery Department, Meyer Children’s Hospital IRCCS, Florence, Italy
| | - Lorenzo Genitori
- Neurosurgery Department, Meyer Children’s Hospital IRCCS, Florence, Italy
| | - Iacopo Sardi
- Neuro-oncology Department, Meyer Children’s Hospital IRCCS, Florence, Italy
| | - Stefano Stagi
- Department of Health Sciences, University of Florence, Florence, Italy
- Struttura Organizzativa Complessa (SOC) Diabetology and Endocrinology, Meyer Children’s Hospital IRCCS, Florence, Italy
| |
Collapse
|
3
|
Zeng Q, Lu G, Yuan J, Ding J, Chen J, Gao X, Huang Y, Shi T, Yu H, Ni H, Li Y. Prevalence, characteristics, and risk factors of venous thromboembolism in patients with brain tumor undergoing craniotomy: a meta-analysis. Neurol Sci 2024; 45:1565-1580. [PMID: 37947983 DOI: 10.1007/s10072-023-07160-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Accepted: 10/22/2023] [Indexed: 11/12/2023]
Abstract
BACKGROUND Brain tumor patients undergoing craniotomy are significantly associated with the development of venous thromboembolism (VTE), while the contributing factors remains controversial. Our study aimed to investigate the prevalence and risk factors for VTE in postoperational brain tumor patients. METHODS We searched the PubMed, Embase, Web of Science, Medline, and Cochrane Library databases from their inception to July 2023. Article selection, data extraction, and study quality assessment were performed independently by two reviewers. Publication bias was assessed using Egger's and Begg's tests. Stata 15.0 software was used for data analysis. RESULTS A total of 25 studies were considered, with a total of 49,620 brain tumor individuals. The pooled prevalence of VTE during hospitalization in postoperational brain tumor patients was 9% [95% CI: (0.08, 0.10)]. Moreover, our results demonstrated that patients with VTE were older than those without VTE [mean difference [MD] = 8.14, 95% CI: (4.97, 11.30)]. The following variables were significantly associated with VTE: prior history of VTE [OR = 7.81, 95% CI: (3.62, 16.88)], congestive heart failure [OR = 2.33, 95% CI: (1.08-5.05)], diabetes [OR = 1.87, 95% CI: (1.12-3.10)], hypertension [OR = 1.27, 95% CI: (1.07-1.50)], steroid use [OR = 1.63, 95% CI: (1.41, 1.88)], high white blood cells counts [MD = 0.32, 95% CI: (0.01, 0.63)], and high fibrinogen levels [MD = 0.19, 95% CI: (0.08, 0.30)]. CONCLUSION This meta-analysis identified risk factors for postoperational VTE in patients with brain tumor, which can serve as a theoretical foundation for medical staff to manage and treat VTE. TRIAL REGISTRATION CRD42023357459.
Collapse
Affiliation(s)
- Qingping Zeng
- School of Nursing, Medical College of Yangzhou University, Yangzhou University, Yangzhou, China
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
| | - Guangyu Lu
- School of Public Health, Medical College of Yangzhou University, Yangzhou University, Yangzhou, China
| | - Jing Yuan
- Department of Echocardiography, Northern Jiangsu People's Hospital, Yangzhou, China
| | - Jiali Ding
- School of Nursing, Medical College of Yangzhou University, Yangzhou University, Yangzhou, China
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
| | - Juan Chen
- School of Nursing, Medical College of Yangzhou University, Yangzhou University, Yangzhou, China
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
| | - Xianru Gao
- School of Nursing, Medical College of Yangzhou University, Yangzhou University, Yangzhou, China
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
| | - Yujia Huang
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
- Neuro-Intensive Care Unit, Department of Neurosurgery, Clinical Medical College, Yangzhou University, Yangzhou, 225001, Jiangsu, China
| | - Tian Shi
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
- Neuro-Intensive Care Unit, Department of Neurosurgery, Clinical Medical College, Yangzhou University, Yangzhou, 225001, Jiangsu, China
| | - Hailong Yu
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China
- Department of Neurology, Northern Jiangsu People's Hospital, Yangzhou, China
| | - Hongbin Ni
- Department of Neurosurgery, Nanjing Drum Tower Hospital, School of Medicine, Clinical College of Nanjing Medical University, Nanjing, 210008, Jiangsu, China.
| | - Yuping Li
- Department of Neuro Intensive Care Unit, Clinical Medical College of Yangzhou University, Yangzhou, China.
- Neuro-Intensive Care Unit, Department of Neurosurgery, Clinical Medical College, Yangzhou University, Yangzhou, 225001, Jiangsu, China.
| |
Collapse
|
4
|
Chen R, Petrazzini BO, Malick W, Rosenson R, Do R. Prediction of Venous Thromboembolism in Diverse Populations Using Machine Learning and Structured Electronic Health Records. Arterioscler Thromb Vasc Biol 2024; 44:491-504. [PMID: 38095106 PMCID: PMC10872966 DOI: 10.1161/atvbaha.123.320331] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Accepted: 12/04/2023] [Indexed: 01/26/2024]
Abstract
BACKGROUND Venous thromboembolism (VTE) is a major cause of morbidity and mortality worldwide. Current risk assessment tools, such as the Caprini and Padua scores and Wells criteria, have limitations in their applicability and accuracy. This study aimed to develop machine learning models using structured electronic health record data to predict diagnosis and 1-year risk of VTE. METHODS We trained and validated models on data from 159 001 participants in the Mount Sinai Data Warehouse. We then externally tested them on 401 723 participants in the UK Biobank and 123 039 participants in All of Us. All data sets contain populations of diverse ancestries and clinical histories. We used these data sets to develop small, medium, and large models with increasing features on a range of optimizing portability to maximizing performance. We make trained models publicly available in click-and-run format at https://doi.org/10.17632/tkwzysr4y6.6. RESULTS In the holdout and external test sets, respectively, models achieved areas under the receiver operating characteristic curve of 0.80 to 0.83 and 0.72 to 0.82 for VTE diagnosis prediction and 0.76 to 0.78 and 0.64 to 0.69 for 1-year risk prediction, significantly outperforming the Padua score. Models also demonstrated robust performance across different VTE types and patient subsets, including ethnicity, age, and surgical and hospitalization status. Models identified both established and novel clinical features contributing to VTE risk, offering valuable insights into its underlying pathophysiology. CONCLUSIONS Machine learning models using structured electronic health record data can significantly improve VTE diagnosis and 1-year risk prediction in diverse populations. Model probability scores exist on a continuum, affecting mortality risk in both healthy individuals and VTE cases. Integrating these models into electronic health record systems to generate real-time predictions may enhance VTE risk assessment, early detection, and preventative measures, ultimately reducing the morbidity and mortality associated with VTE.
Collapse
Affiliation(s)
- Robert Chen
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Medical Scientist Training Program, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ben Omega Petrazzini
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Center for Genomic Data Analytics, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Waqas Malick
- The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Robert Rosenson
- The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Ron Do
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Center for Genomic Data Analytics, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| |
Collapse
|
5
|
Liu D, Song D, Ning W, Guo Y, Lei T, Qu Y, Zhang M, Gu C, Wang H, Ji J, Wang Y, Zhao Y, Qiao N, Zhang H. Development and Validation of a Clinical Prediction Model for Venous Thromboembolism Following Neurosurgery: A 6-Year, Multicenter, Retrospective and Prospective Diagnostic Cohort Study. Cancers (Basel) 2023; 15:5483. [PMID: 38001743 PMCID: PMC10670076 DOI: 10.3390/cancers15225483] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 11/02/2023] [Accepted: 11/10/2023] [Indexed: 11/26/2023] Open
Abstract
BACKGROUND Based on the literature and data on its clinical trials, the incidence of venous thromboembolism (VTE) in patients undergoing neurosurgery has been 3.0%~26%. We used advanced machine learning techniques and statistical methods to provide a clinical prediction model for VTE after neurosurgery. METHODS All patients (n = 5867) who underwent neurosurgery from the development and retrospective internal validation cohorts were obtained from May 2017 to April 2022 at the Department of Neurosurgery at the Sanbo Brain Hospital. The clinical and biomarker variables were divided into pre-, intra-, and postoperative. A univariate logistic regression (LR) was applied to explore the 67 candidate predictors with VTE. We used a multivariable logistic regression (MLR) to select all significant MLR variables of MLR to build the clinical risk prediction model. We used a random forest to calculate the importance of significant variables of MLR. In addition, we conducted prospective internal (n = 490) and external validation (n = 2301) for the model. RESULTS Eight variables were selected for inclusion in the final clinical prediction model: D-dimer before surgery, activated partial thromboplastin time before neurosurgery, age, craniopharyngioma, duration of operation, disturbance of consciousness on the second day after surgery and high dose of mannitol, and highest D-dimer within 72 h after surgery. The area under the curve (AUC) values for the development, retrospective internal validation, and prospective internal validation cohorts were 0.78, 0.77, and 0.79, respectively. The external validation set had the highest AUC value of 0.85. CONCLUSIONS This validated clinical prediction model, including eight clinical factors and biomarkers, predicted the risk of VTE following neurosurgery. Looking forward to further research exploring the standardization of clinical decision-making for primary VTE prevention based on this model.
Collapse
Affiliation(s)
- Deshan Liu
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Dixiang Song
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Weihai Ning
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Yuduo Guo
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Ting Lei
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Yanming Qu
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Mingshan Zhang
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Chunyu Gu
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Haoran Wang
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Junpeng Ji
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| | - Yongfei Wang
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical School, Fudan University, Shanghai 200030, China; (Y.W.); (Y.Z.)
| | - Yao Zhao
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical School, Fudan University, Shanghai 200030, China; (Y.W.); (Y.Z.)
| | - Nidan Qiao
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical School, Fudan University, Shanghai 200030, China; (Y.W.); (Y.Z.)
| | - Hongwei Zhang
- Department of Neurosurgery, Sanbo Brain Hospital, Capital Medical University, Beijing 100093, China; (D.L.); (D.S.); (W.N.); (Y.G.); (T.L.); (Y.Q.); (M.Z.); (C.G.); (H.W.); (J.J.)
| |
Collapse
|