Prediction of acute kidney injury in patients with femoral neck fracture utilizing machine learning

Liu, Jun; Xu, Lingxiao; Zhu, Enzhao; Ai, Zisheng

doi:10.3389/fsurg.2022.928750

Cited by 5 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acute kidney injury (AKI) is a common complication during hospitalization for hip fractures and has an incidence rate of 24% [ 5 , 6 ]. In addition to prolonging hospital stays and increasing in-hospital mortality, AKI has been associated with elevated long-term mortality [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

Comorbidities, acute kidney injury and long-term mortality in elderly patients hospitalized because of hip fracture: a moderation analysis

Borges de Sá,

Faria,

Gonçalves

et al. 2024

Aging Clin Exp Res

View full text Add to dashboard Cite

Introduction Femoral fractures in elderly individuals present significant health challenges, often leading to increased morbidity and mortality. Acute kidney injury (AKI) during hospitalization further complicates outcomes, yet the interaction between AKI severity and comorbidities, as quantified by the Charlson Comorbidity Index (CCI), remains poorly understood in this population. This study aimed to assess the associations between AKI severity and the CCI and between AKI severity and one-year mortality postfemoral fracture in elderly patients. Methodology This study utilized data from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC-IV) database and focused on elderly patients (> 65 years) admitted with hip fractures. Patients were categorized based on AKI stage according to the KDIGO criteria and CCI scores. The primary outcome assessed was all-cause mortality one year after hospital discharge. The statistical analyses included logistic regression, Cox proportional hazards regression and moderation analysis with the Johnson–Neyman technique to evaluate associations between AKI and long-term mortality and between the CCI and long-term mortality. Results The analysis included 1,955 patients and revealed that severe AKI (stages 2 and 3) was independently associated with increased one-year mortality. Notably, the CCI moderated these associations significantly. A lower CCI score was significantly correlated with greater mortality in patients with severe AKI. The impact of severe AKI was greater for those with a CCI as low as 3, more than doubling the observed one-year mortality rate. In contrast, higher CCI scores (≥8) did not significantly impact mortality. Sensitivity analyses supported these findings, underscoring the robustness of the observed associations. Conclusion This study elucidates the complex interplay between AKI severity and comorbidities and long-term mortality in elderly hip fracture patients. These findings underscore the importance of considering both AKI severity and comorbidity burden in prognostic assessments and intervention strategies for this vulnerable population. Targeted interventions tailored to individual risk profiles may help mitigate the impact of AKI on mortality outcomes, ultimately improving patient care and outcomes. Further research is warranted to explore the underlying mechanisms involved and refine risk stratification approaches in this population.

show abstract

Section: Introductionmentioning

confidence: 99%

Comorbidities, acute kidney injury and long-term mortality in elderly patients hospitalized because of hip fracture: a moderation analysis

Borges de Sá,

Faria,

Gonçalves

et al. 2024

Aging Clin Exp Res

View full text Add to dashboard Cite

show abstract

Improving Patient Care Through the Use of a Highly Accurate CNN Model for the Detection of Cervical Spine Fractures

Tanwar,

Anand,

Chauhan

et al. 2023

2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)

View full text Add to dashboard Cite

Differentiation Between Phyllodes Tumor and Fibroadenoma of the Breast: A Radiomics Prediction Model Based on Full-Field Digital Mammography & Digital Tomosynthesis

Zeng,

Yang

et al. 2024

Technol Cancer Res Treat

View full text Add to dashboard Cite

Objective To assess the diagnostic performance of FFDM-based and DBT-based radiomics models to differentiate breast phyllodes tumors from fibroadenomas. Methods 192 patients (93 phyllodes tumors and 99 fibroadenomas) who underwent mammography were retrospectively enrolled. Radiomic features were respectively extracted from FFDM and the clearest slice of DBT images. A least absolute shrinkage and selection operator (LASSO) regression was used to select radiomics features. A combined model was constructed by radiomics and radiological signatures. Machine learning classification was done using logistic regression based on radiomics or radiological signatures (clinical model). Four radiologists were tested on phyllodes tumors and fibroadenomas with and without optimal model assistance. The area under the receiver operating characteristic (ROC) curve (AUC) was computed to assess the performance of each model or radiologist. The Delong test and McNemar's test were performed to compare the performance. Results The combined model yielded the highest performance with an AUC of 0.948 (95%CI: 0.889-1.000) in the testing set, slightly higher than the FFDM-radiomics model (AUC of 0.937, 95%CI: 0.841-0.984) and the DBT-radiomics model (AUC of 0.860, 95%CI: 0.742-0.936) and significantly superior to the clinical model (AUC of 0.719, 95%CI: 0.585-0.829). With the combined model aid, the AUCs of four radiologists were improved from 0.808 to 0.914 ( p=0.079), 0.759 to 0.888 ( p=0.015), 0.717 to 0.846 ( p=0.004), and 0.629 to 0.803 ( p=0.001). Conclusion Radiomics analysis based on FFDM and DBT shows promise in differentiating phyllodes tumors from fibroadenomas.

show abstract

Prediction of acute kidney injury in patients with femoral neck fracture utilizing machine learning

Cited by 5 publications

References 35 publications

Comorbidities, acute kidney injury and long-term mortality in elderly patients hospitalized because of hip fracture: a moderation analysis

Comorbidities, acute kidney injury and long-term mortality in elderly patients hospitalized because of hip fracture: a moderation analysis

Improving Patient Care Through the Use of a Highly Accurate CNN Model for the Detection of Cervical Spine Fractures

Differentiation Between Phyllodes Tumor and Fibroadenoma of the Breast: A Radiomics Prediction Model Based on Full-Field Digital Mammography & Digital Tomosynthesis

Contact Info

Product

Resources

About