The prediction of in-hospital mortality in chronic kidney disease patients with coronary artery disease using machine learning models

Ye, Zixiang; An, Shuoyan; Gao, Yanxiang; Xie, Enmin; Zhao, Xianxian; Guo, Ziyu; Li, Yike; Shen, Nan; Ren, Jingyi; Zheng, Jingang

doi:10.1186/s40001-023-00995-x

Cited by 9 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, these patients have increased rates of bleeding which are thought to be driven principally by platelet dysfunction, low production of clotting factors, and anticoagulants with pharmacokinetic profile changes of the compounds that affect blood clotting mechanisms [10] . This study contributes to the existing studies on the relationship between renal failure and coagulation abnormalities and complications by investigating and highlighting PTT levels as a significant indicator of the severity and prognosis of the disease [11][12][13][14] . Regarding PT levels, there were no significant statistical differences between renal patients and control samples.…”

Section: Discussionmentioning

confidence: 99%

“…This finding is consistent with the previous findings. For instance, Ye et al (2023) highlights that since the intrinsic coagulation pathway activates factors such as VIII, IX, XI, and XII, which are principally cleared by the renal system, kidney failure prevents this clearance resulting in a hypercoagulable state that results in a low PTT level [14] . A low level means faster coagulation than normal.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

PT and PTT; Are They Significant Indicators of Poor Prognosis in Severe Renal Failure Patients?

Alshammary,

Alsowyan,

Alawain

et al. 2024

ijirms

View full text Add to dashboard Cite

The coagulation system has gained significant interest in the recent past, especially in patients diagnosed with renal failure, as they are susceptible to significant comorbidity that requires anticoagulation. Research indicates that patients diagnosed with renal failure are at an increased risk of developing complications associated with coagulation abnormalities. Renal failure patients experience excessive bleeding even on new anticoagulants due to pharmacokinetic profile changes of the compounds. However, even without anticoagulants, the coagulation systems in patients with renal failure are profoundly changed, leading to significant morbidity and mortality in such patients. The underlying reasons for such problems involve the changes in the interaction of coagulation system components such as the platelets, coagulation cascade, and the vessel wall in the metabolic conditions of renal pathology. One meaningful way of evaluating the coagulation status of patients diagnosed with renal failure is through prothrombin time (PT) and partial thromboplastin time (PTT) blood tests. The two laboratory tests are used to evaluate coagulation disorders where the PT test measures the time it takes for blood to clot in response to prothrombin, a clotting factor, activation, and the PTT test measures the time it takes for blood to clot in response to clotting factor activation. This study evaluated PT and PTT levels of renal failure patients to determine their relationship with the disease’s severity and prognosis. The study was conducted as a collaboration study between PSAU and KELANA Association. Data were collected from 20 samples, and statistical analysis was done using the SPSS software version 2.0. The research findings indicated insignificant statistical differences between PT levels of renal failure patients and controls, while PTT levels in males significantly differed between patients and the controls. The study indicates that PTT levels can be used to indicate coagulation abnormalities in male patients diagnosed with renal failure.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

PT and PTT; Are They Significant Indicators of Poor Prognosis in Severe Renal Failure Patients?

Alshammary,

Alsowyan,

Alawain

et al. 2024

ijirms

View full text Add to dashboard Cite

show abstract

“…According to a survey from 1990 to 2013, CKD is now the 13th biggest cause of mortality worldwide, with an annual rise in life loss of 90%. Kidney disorders are expected to affect 850 million individuals globally due to various factors [4].…”

Section: Introductionmentioning

confidence: 99%

Implementation of clinical diagnosis system for chronic kidney disease using deep learning algorithms

2024

IJATEE

View full text Add to dashboard Cite

Chronic kidney disease (CKD) ranks among the top 20 causes of death worldwide, affecting approximately 10% of adults. CKD impairs normal kidney function. The rising incidence of CKD underscores the need for effective prophylactic measures and early diagnosis. A novel aspect of this research is the development of a technique for diagnosing chronic renal diseases. This work aids researchers in exploring early detection methods for CKD prevention using deep learning (DL) techniques. The study involved the construction of a model for CKD diagnosis based on deep neural networks (DNN). A dataset of 400 patients with 24 features was analyzed, with mean and mode statistical analysis techniques employed to substitute missing numerical and nominal values. The effectiveness of the DNN has been demonstrated in the diagnosis results, achieving an accuracy of 98.33%. DL models employ complex algorithms to analyze large datasets containing various patient information, such as age, gender, lifestyle habits, and medical history. By automatically analyzing these factors together, the model can identify patterns indicative of potential kidney issues earlier than traditional methods. In addition to more accurate CKD prediction, DL models provide faster results, potentially leading to earlier interventions or treatments by physicians.

show abstract

“…The prediction of CKD progression is an important task for patient care in clinical management. Machine learning (ML) methods have been used to predict the risk of CKD applications in recent years [ 15 , 16 , 17 , 18 ]. In addition, several risk prediction models have been proposed for CKD applications [ 14 , 19 , 20 , 21 , 22 ].…”

Section: Introductionmentioning

confidence: 99%

Improved Survival Analyses Based on Characterized Time-Dependent Covariates to Predict Individual Chronic Kidney Disease Progression

Liao

Huang

et al. 2023

Biomedicines

View full text Add to dashboard Cite

Kidney diseases can cause severe morbidity, mortality, and health burden. Determining the risk factors associated with kidney damage and deterioration has become a priority for the prevention and treatment of kidney disease. This study followed 497 patients with stage 3–5 chronic kidney disease (CKD) who were treated at the ward of Taipei Veterans General Hospital from January 2006 to 2019 in Taiwan. The patients underwent 3-year-long follow-up sessions for clinical measurements, which occurred every 3 months. Three time-dependent survival models, namely the Cox proportional hazard model (Cox PHM), random survival forest (RSF), and an artificial neural network (ANN), were used to process patient demographics and laboratory data for predicting progression to renal failure, and important features for optimal prediction were evaluated. The individual prediction of CKD progression was validated using the Kaplan–Meier estimation method, based on patients’ true outcomes during and beyond the study period. The results showed that the average concordance indexes for the cross-validation of the Cox PHM, ANN, and RSF models were 0.71, 0.72, and 0.89, respectively. RSF had the best predictive performances for CKD patients within the 3 years of follow-up sessions, with a sensitivity of 0.79 and specificity of 0.88. Creatinine, age, estimated glomerular filtration rate, and urine protein to creatinine ratio were useful factors for predicting the progression of CKD patients in the RSF model. These results may be helpful for instantaneous risk prediction at each follow-up session for CKD patients.

show abstract

The prediction of in-hospital mortality in chronic kidney disease patients with coronary artery disease using machine learning models

Cited by 9 publications

References 34 publications

PT and PTT; Are They Significant Indicators of Poor Prognosis in Severe Renal Failure Patients?

PT and PTT; Are They Significant Indicators of Poor Prognosis in Severe Renal Failure Patients?

Implementation of clinical diagnosis system for chronic kidney disease using deep learning algorithms

Improved Survival Analyses Based on Characterized Time-Dependent Covariates to Predict Individual Chronic Kidney Disease Progression

Contact Info

Product

Resources

About