1
|
Xu J, Chen T, Fang X, Xia L, Pan X. Prediction model of pressure injury occurrence in diabetic patients during ICU hospitalization--XGBoost machine learning model can be interpreted based on SHAP. Intensive Crit Care Nurs 2024; 83:103715. [PMID: 38701634 DOI: 10.1016/j.iccn.2024.103715] [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: 03/01/2024] [Revised: 04/21/2024] [Accepted: 04/26/2024] [Indexed: 05/05/2024]
Abstract
BACKGROUND The occurrence of pressure injury in patients with diabetes during ICU hospitalization can result in severe complications, including infections and non-healing wounds. AIMS The aim of this study was to predict the occurrence of pressure injury in ICU patients with diabetes using machine learning models. STUDY DESIGN In this study, LASSO regression was used for feature screening, XGBoost was employed for machine learning model construction, ROC curve analysis, calibration curve analysis, clinical decision curve analysis, sensitivity, specificity, accuracy, and F1 score were used for evaluating the model's performance. RESULTS Out of the 503 ICU patients with diabetes included in the study, pressure injury developed in 170 cases, resulting in an incidence rate of 33.8 %. The XGBoost model had a higher AUC for predicting pressure injury in patients with diabetes during ICU hospitalization (train: 0.896, 95 %CI: 0.863 to 0.929; test: 0.835, 95 % CI: 0.761-0.908). The importance of SHAP variables in the model from high to low was: 'Days in ICU', 'Mechanical Ventilation', 'Neutrophil Count', 'Consciousness', 'Glucose', and 'Warming Blanket'. CONCLUSION The XGBoost machine learning model we constructed has shown high performance in predicting the occurrence of pressure injury in ICU patients with diabetes. Additionally, the SHAP method enables the interpretation of the results provided by the machine learning model. RELEVANCE TO CLINICAL PRACTICE Improve the ability to predict the early occurrence of pressure injury in diabetic patients in the ICU. This will enable clinicians to intervene early and reduce the occurrence of complications.
Collapse
Affiliation(s)
- Jie Xu
- Department of Thoracic Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Tie Chen
- Department of Thoracic Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Xixi Fang
- Department of Thoracic Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Limin Xia
- Department of Gastrointestinal Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
| | - Xiaoyun Pan
- Department of Thoracic Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
| |
Collapse
|
2
|
Zheng C, Yue P, Cao K, Wang Y, Zhang C, Zhong J, Xu X, Lin C, Liu Q, Zou Y, Huang B. Predicting intraoperative blood loss during cesarean sections based on multi-modal information: a two-center study. Abdom Radiol (NY) 2024:10.1007/s00261-024-04419-0. [PMID: 38896245 DOI: 10.1007/s00261-024-04419-0] [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: 03/25/2024] [Revised: 05/27/2024] [Accepted: 05/29/2024] [Indexed: 06/21/2024]
Abstract
PURPOSE To develop and validate a nomogram model that combines radiomics features, clinical factors, and coagulation function indexes (CFI) to predict intraoperative blood loss (IBL) during cesarean sections, and to explore its application in optimizing perioperative management and reducing maternal morbidity. METHODS In this retrospective consecutive series study, a total of 346 patients who underwent magnetic resonance imaging (156 for training and 68 for internal test, center 1; 122 for external test, center 2) were included. IBL+ was defined as more than 1000 mL estimated blood loss during cesarean sections. The prediction models of IBL were developed based on machine-learning algorithms using CFI, radiomics features, and clinical factors. ROC analysis was performed to evaluate the performance for IBL diagnosis. RESULTS The support vector machine model incorporating all three modalities achieved an AUC of 0.873 (95% CI 0.769-0.941) and a sensitivity of 1.000 (95% CI 0.846-1.000) in the internal test set, with an AUC of 0.806 (95% CI 0.725-0.872) and a sensitivity of 0.873 (95% CI 0.799-0.922) in the external test set. It was also scored significantly higher than the CFI model (P = 0.035) on the internal test set, and both the CFI (P = 0.002) and radiomics-CFI models (P = 0.007) on the external test set. Additionally, the nomogram constructed based on three modalities achieved an internal testing set AUC of 0.960 (95% CI 0.806-0.999) and an external testing set AUC of 0.869 (95% CI 0.684-0.967) in the pregnant population without a pernicious placenta previa. It is noteworthy that the AUC of the proposed model did not show a statistically significant improvement compared to the Clinical-CFI model in both internal (P = 0.115) and external test sets (P = 0.533). CONCLUSION The proposed model demonstrated good performance in predicting intraoperative blood loss (IBL), exhibiting high sensitivity and robust generalizability, with potential applicability to other surgeries such as vaginal delivery and postpartum hysterectomy. However, the performance of the proposed model was not statistically significantly better than that of the Clinical-CFI model.
Collapse
Affiliation(s)
- Changye Zheng
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People's Hospital), Dongguan, Guangdong, China
| | - Peiyan Yue
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China
| | - Kangyang Cao
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China
| | - Ya Wang
- Dongguan Maternal and Child Health Care Hospital, Dongguan, Guangdong, China
| | - Chang Zhang
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China
| | - Jian Zhong
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China
| | - Xiaoyang Xu
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People's Hospital), Dongguan, Guangdong, China
| | - Chuxuan Lin
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China
| | - Qinghua Liu
- Dongguan Maternal and Child Health Care Hospital, Dongguan, Guangdong, China
| | - Yujian Zou
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People's Hospital), Dongguan, Guangdong, China.
| | - Bingsheng Huang
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China.
| |
Collapse
|
3
|
Mohammadyari P, Vieceli Dalla Sega F, Fortini F, Minghini G, Rizzo P, Cimaglia P, Mikus E, Tremoli E, Campo G, Calore E, Schifano SF, Zambelli C. Deep-learning survival analysis for patients with calcific aortic valve disease undergoing valve replacement. Sci Rep 2024; 14:10902. [PMID: 38740898 DOI: 10.1038/s41598-024-61685-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2023] [Accepted: 05/08/2024] [Indexed: 05/16/2024] Open
Abstract
Calcification of the aortic valve (CAVDS) is a major cause of aortic stenosis (AS) leading to loss of valve function which requires the substitution by surgical aortic valve replacement (SAVR) or transcatheter aortic valve intervention (TAVI). These procedures are associated with high post-intervention mortality, then the corresponding risk assessment is relevant from a clinical standpoint. This study compares the traditional Cox Proportional Hazard (CPH) against Machine Learning (ML) based methods, such as Deep Learning Survival (DeepSurv) and Random Survival Forest (RSF), to identify variables able to estimate the risk of death one year after the intervention, in patients undergoing either to SAVR or TAVI. We found that with all three approaches the combination of six variables, named albumin, age, BMI, glucose, hypertension, and clonal hemopoiesis of indeterminate potential (CHIP), allows for predicting mortality with a c-index of approximately 80 % . Importantly, we found that the ML models have a better prediction capability, making them as effective for statistical analysis in medicine as most state-of-the-art approaches, with the additional advantage that they may expose non-linear relationships. This study aims to improve the early identification of patients at higher risk of death, who could then benefit from a more appropriate therapeutic intervention.
Collapse
Affiliation(s)
| | | | | | - Giada Minghini
- Department of Environmental and Prevention Sciences, Università di Ferrara, Ferrara, Italy
| | - Paola Rizzo
- Maria Cecilia Hospital, GVM Care and Research, Cotignola, Italy.
- Department of Translational Medicine, Università di Ferrara, Ferrara, Italy.
- Laboratory for Technologies of Advanced Therapies (LTTA), Ferrara, Italy.
| | - Paolo Cimaglia
- Maria Cecilia Hospital, GVM Care and Research, Cotignola, Italy
| | - Elisa Mikus
- Maria Cecilia Hospital, GVM Care and Research, Cotignola, Italy
| | - Elena Tremoli
- Maria Cecilia Hospital, GVM Care and Research, Cotignola, Italy
| | - Gianluca Campo
- Department of Translational Medicine, Università di Ferrara, Ferrara, Italy
- Azienda Ospedaliero-Universitaria di Ferrara, Ferrara, Italy
| | - Enrico Calore
- Istituto Nazionale di Fisica Nucleare (INFN), Ferrara, Italy
| | - Sebastiano Fabio Schifano
- Istituto Nazionale di Fisica Nucleare (INFN), Ferrara, Italy.
- Department of Environmental and Prevention Sciences, Università di Ferrara, Ferrara, Italy.
| | | |
Collapse
|
4
|
Santagata D, Donadini MP, Ageno W. Use of artificial intelligence and radiomics for risk stratification in patients with pulmonary embolism: New tools for an old problem. Eur J Clin Invest 2024; 54:e14171. [PMID: 38265096 DOI: 10.1111/eci.14171] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 01/13/2024] [Accepted: 01/13/2024] [Indexed: 01/25/2024]
Affiliation(s)
- Davide Santagata
- Department of Medicine and Surgery, Research center on Thrombosis and Antithrombotic Therapies, University of Insubria, Varese, Italy
| | - Marco Paolo Donadini
- Department of Medicine and Surgery, Research center on Thrombosis and Antithrombotic Therapies, University of Insubria, Varese, Italy
| | - Walter Ageno
- Department of Medicine and Surgery, Research center on Thrombosis and Antithrombotic Therapies, University of Insubria, Varese, Italy
| |
Collapse
|
5
|
Parikesit AA, Hermantara R, Gregorius K, Siddharta E. Designing hybrid CRISPR-Cas12 and LAMP detection systems for treatment-resistant Plasmodium falciparum with in silico method. NARRA J 2023; 3:e301. [PMID: 38455618 PMCID: PMC10919703 DOI: 10.52225/narra.v3i3.301] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Accepted: 12/21/2023] [Indexed: 03/09/2024]
Abstract
Genes associated with drug resistance of first line drugs for Plasmodium falciparum have been identified and characterized of which three genes most commonly associated with drug resistance are P. falciparum chloroquine resistance transporter gene (PfCRT), P. falciparum multidrug drug resistance gene 1 (PfMDR1), and P. falciparum Kelch protein K13 gene (PfKelch13). Polymorphism in these genes could be used as molecular markers for identifying drug resistant strains. Nucleic acid amplification test (NAAT) along with DNA sequencing is a powerful diagnostic tool that could identify these polymorphisms. However, current NAAT and DNA sequencing technologies require specific instruments which might limit its application in rural areas. More recently, a combination of isothermal amplification and CRISPR detection system showed promising results in detecting mutations at a nucleic acid level. Moreover, the Loop-mediated isothermal amplification (LAMP)-CRISPR systems offer robust and straightforward detection, enabling it to be deployed in rural and remote areas. The aim of this study was to develop a novel diagnostic method, based on LAMP of targeted genes, that would enable the identification of drug-resistant P. falciparum strains. The methods were centered on sequence analysis of P. falciparum genome, LAMP primers design, and CRISPR target prediction. Our designed primers are satisfactory for identifying polymorphism associated with drug resistant in PfCRT, PfMDR1, and PfKelch13. Overall, the developed system is promising to be used as a detection method for P. falciparum treatment-resistant strains. However, optimization and further validation the developed CRISPR-LAMP assay are needed to ensure its accuracy, reliability, and feasibility.
Collapse
Affiliation(s)
- Arli A. Parikesit
- Department of Bioinformatics, School of Life Sciences, Indonesia International Institute for Life Sciences (I3L), Jakarta, Indonesia
| | - Rio Hermantara
- Department of Biomedicine, School of Life Sciences, Indonesia International Institute for Life Sciences (I3L), Jakarta, Indonesia
| | - Kevin Gregorius
- Department of Biomedicine, School of Life Sciences, Indonesia International Institute for Life Sciences (I3L), Jakarta, Indonesia
| | - Elizabeth Siddharta
- Department of Biomedicine, School of Life Sciences, Indonesia International Institute for Life Sciences (I3L), Jakarta, Indonesia
| |
Collapse
|