Nomogram to predict the risk of acute kidney injury in patients with diabetic ketoacidosis: an analysis of the MIMIC-III database

Association between albumin-corrected anion gap level and the risk of acute kidney injury in intensive care unit

PURPOSE

This study was to investigate the association between albumin-corrected anion gap (AG) (ACAG) levels and the risk of acute kidney injury (AKI) in intensive care unit (ICU) patients.

METHODS

The ICU patients of this retrospective cohort study were collected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database between 2008 and 2019. ACAG = AG + {4.4 - [albumin (g/dl)]} × 2.5. The incidence of AKI was determined using the Kidney Disease: Improving Global Outcomes (KDIGO) definition. The logistic regression model was used to evaluate the association between ACAG levels and the risk of AKI. Subgroup analyses were applied based on age, gender, mechanical ventilation, vasopressors, the Charlson comorbidity index (CCI), and the Simplified Acute Physiology Score II (SAPS II).

RESULTS

Totally, 5586 patients were enrolled, of which 1929 patients (34.53%) occurred AKI. The higher levels of ACAG were associated with the risk of AKI in ICU patients, with the odds ratio (OR) value being 1.23 [95% confidence interval (CI): 1.22-1.24, P = 0.005] in ACAG level between 16.5 and 19.5, and OR value being 1.20 (95% CI 1.16-1.24, P = 0.016) in ACAG level > 19.5. A higher ACAG level was associated with a higher risk of AKI in ICU patients aged < 65 years, in ICU patients of female gender, in ICU patients who used mechanical ventilation, in ICU patients who did not use vasopressors, in patients without cardiogenic shock, and in ICU patients with CCI ≥ 2, and SAPS II > 31 (all P < 0.05).

CONCLUSION

There is an association between ACAG level and the risk of AKI in ICU patients. A higher ACAG value in ICU patients should therefore receive more attention.

Clinical nomogram prediction model to assess the risk of prolonged ICU length of stay in patients with diabetic ketoacidosis: a retrospective analysis based on the MIMIC-IV database

BACKGROUND

The duration of hospitalization, especially in the intensive care unit (ICU), for patients with diabetic ketoacidosis (DKA) is influenced by patient prognosis and treatment costs. Reducing ICU length of stay (LOS) in patients with DKA is crucial for optimising healthcare resources utilization. This study aimed to establish a nomogram prediction model to identify the risk factors influencing prolonged LOS in ICU-managed patients with DKA, which will serve as a basis for clinical treatment, healthcare safety, and quality management research.

METHODS

In this single-centre retrospective cohort study, we performed a retrospective analysis using relevant data extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Clinical data from 669 patients with DKA requiring ICU treatment were included. Variables were selected using the Least Absolute Shrinkage and Selection Operator (LASSO) binary logistic regression model. Subsequently, the selected variables were subjected to a multifactorial logistic regression analysis to determine independent risk factors for prolonged ICU LOS in patients with DKA. A nomogram prediction model was constructed based on the identified predictors. The multivariate variables included in this nomogram prediction model were the Oxford acute severity of illness score (OASIS), Glasgow coma scale (GCS), acute kidney injury (AKI) stage, vasoactive agents, and myocardial infarction.

RESULTS

The prediction model had a high predictive efficacy, with an area under the curve value of 0.870 (95% confidence interval [CI], 0.831-0.908) in the training cohort and 0.858 (95% CI, 0.799-0.916) in the validation cohort. A highly accurate predictive model was depicted in both cohorts using the Hosmer-Lemeshow (H-L) test and calibration plots.

CONCLUSION

The nomogram prediction model proposed in this study has a high clinical application value for predicting prolonged ICU LOS in patients with DKA. This model can help clinicians identify patients with DKA at risk of prolonged ICU LOS, thereby enhancing prompt intervention and improving prognosis.

Development of a nomogram to predict 30-day mortality of sepsis patients with gastrointestinal bleeding: An analysis of the MIMIC-IV database

Background

We aimed to establish and validate a prognostic nomogram model for improving the prediction of 30-day mortality of gastrointestinal bleeding (GIB) in critically ill patients with severe sepsis.

Methods

In this retrospective study, the current retrospective cohort study extracted data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, then partitioned the cohort randomly into training and validation subsets. The cohort was partitioned into training and validation subsets randomly. Our primary endpoint was 30-day all-cause mortality. To reduce data dimensionality and identify predictive variables, the least absolute shrinkage and selection operator (LASSO) regression was employed. A prediction model was constructed by multivariate logistic regression. Model performance was evaluated using the concordance index (C-index), receiver operating characteristic (ROC) curve, and decision curve analysis (DCA).

Results

The analysis included 1435 total patients, comprising 1005 in the training cohort and 430 in the validation cohort. We found that age, smoking status, glucose, (BUN), lactate, Sequential Organ Failure Assessment (SOFA) score, mechanical ventilation≥48h (MV), parenteral nutrition (PN), and chronic obstructive pulmonary disease (COPD) independently influenced mortality in sepsis patients with concomitant GIB. The C-indices were 0.746 (0.700-0.792) and 0.716 (0.663-0.769) in the training and validation sets, respectively. Based on the area under the curve (AUC) and DCA, the nomogram exhibited good discrimination for 30-day all-cause mortality in sepsis with GIB.

Conclusions

For sepsis patients complicated with GIB, we created a unique nomogram model to predict the 30-day all-cause mortality. This model could be a significant therapeutic tool for clinicians in terms of personalized treatment and prognosis prediction.

Development and validation of a nomogram for predicting in-hospital mortality of patients with cervical spine fractures without spinal cord injury

BACKGROUND

The incidence of cervical spine fractures is increasing every day, causing a huge burden on society. This study aimed to develop and verify a nomogram to predict the in-hospital mortality of patients with cervical spine fractures without spinal cord injury. This could help clinicians understand the clinical outcome of such patients at an early stage and make appropriate decisions to improve their prognosis.

METHODS

This study included 394 patients with cervical spine fractures from the Medical Information Mart for Intensive Care III database, and 40 clinical indicators of each patient on the first day of admission to the intensive care unit were collected. The independent risk factors were screened using the Least Absolute Shrinkage and Selection Operator regression analysis method, a multi-factor logistic regression model was established, nomograms were developed, and internal validation was performed. A receiver operating characteristic (ROC) curve was drawn, and the area under the ROC curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were calculated to evaluate the discrimination of the model. Moreover, the consistency between the actual probability and predicted probability was reflected using the calibration curve and Hosmer-Lemeshow (HL) test. A decision curve analysis (DCA) was performed, and the nomogram was compared with the scoring system commonly used in clinical practice to evaluate the clinical net benefit.

RESULTS

The nomogram indicators included the systolic blood pressure, oxygen saturation, respiratory rate, bicarbonate, and simplified acute physiology score (SAPS) II. The results showed that our model had satisfactory predictive ability, with an AUC of 0.907 (95% confidence interval [CI] = 0.853-0.961) and 0.856 (95% CI = 0.746-0.967) in the training set and validation set, respectively. Compared with the SAPS-II system, the NRI values of the training and validation sets of our model were 0.543 (95% CI = 0.147-0.940) and 0.784 (95% CI = 0.282-1.286), respectively. The IDI values of the training and validation sets were 0.064 (95% CI = 0.004-0.123; P = 0.037) and 0.103 (95% CI = 0.002-0.203; P = 0.046), respectively. The calibration plot and HL test results confirmed that our model prediction results showed good agreement with the actual results, where the HL test values of the training and validation sets were P = 0.8 and P = 0.95, respectively. The DCA curve revealed that our model had better clinical net benefit than the SAPS-II system.

CONCLUSION

We explored the in-hospital mortality of patients with cervical spine fractures without spinal cord injury and constructed a nomogram to predict their prognosis. This could help doctors assess the patient's status and implement interventions to improve prognosis accordingly.

Association between nutritional status scores and the 30-day mortality in patients with acute kidney injury: an analysis of MIMIC-III database

BACKGROUND

Studies have proven that the risk of acute kidney injury (AKI) increased in patients with malnutrition. Prognostic nutritional index (PNI) and geriatric nutritional risk index (GNRI) were general tools to predict the risk of mortality, but the prognostic value of them for in-hospital mortality among patients with AKI have not been validated yet. Herein, this study aims to explore the association between PNI and GNRI and 30-day mortality in patients with AKI.

METHODS

Demographic and clinical data of 863 adult patients with AKI were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database in 2001-2012 in this retrospective cohort study. Univariate and multivariate Cox proportional regression analyses were used to explore the association between PNI and GNRI and 30-day mortality. The evaluation indexes were hazard ratios (HRs) and 95% confidence intervals (CIs). Subgroup analyses of age, Sequential Organ Failure Assessment (SOFA) score and Simplified Acute Physiology (SAPS-II) score were also performed.

RESULTS

Totally, 222 (26.71%) patients died within 30 days. After adjusting for covariates, PNI ≥ 28.5 [HR = 0.71, 95%CI: (0.51-0.98)] and GNRI ≥ 83.25 [HR = 0.63, 95%CI: (0.47-0.86)] were both associated with low risk of 30-day mortality. These relationships were also found in patients who aged ≥ 65 years old. Differently, high PNI level was associated with low risk of 30-day mortality among patients with SOFA score < 6 or SAPS-II score < 43, while high GNRI was associated with low risk of 30-day mortality among those who with SOFA score ≥ 6 or SAPS-II score ≥ 43 (all P < 0.05).

CONCLUSION

PNI and GNRI may be potential predictors of 30-day mortality in patients with AKI. Whether the PNI is more recommended for patients with mild AKI, while GNRI for those with severe AKI is needed further exploration.

A nomogram for predicting sepsis-associated delirium: a retrospective study in MIMIC III

OBJECTIVE

To develop a nomogram for predicting the occurrence of sepsis-associated delirium (SAD).

MATERIALS AND METHODS

Data from a total of 642 patients were retrieved from the Medical Information Mart for Intensive Care (MIMIC III) database to build a prediction model. Multivariate logistic regression was performed to identify independent predictors and establish a nomogram to predict the occurrence of SAD. The performance of the nomogram was assessed in terms of discrimination and calibration by bootstrapping with 1000 resamples.

RESULTS

Multivariate logistic regression identified 4 independent predictors for patients with SAD, including Sepsis-related Organ Failure Assessment(SOFA) (p = 0.004; OR: 1.131; 95% CI 1.040 to 1.231), mechanical ventilation (P < 0.001; OR: 3.710; 95% CI 2.452 to 5.676), phosphate (P = 0.047; OR: 1.165; 95% CI 1.003 to 1.358), and lactate (P = 0.023; OR: 1.135; 95% CI 1.021 to 1.270) within 24 h of intensive care unit (ICU) admission. The area under the curve (AUC) of the predictive model was 0.742 in the training set and 0.713 in the validation set. The Hosmer - Lemeshow test showed that the model was a good fit (p = 0.471). The calibration curve of the predictive model was close to the ideal curve in both the training and validation sets. The DCA curve also showed that the predictive nomogram was clinically useful.

CONCLUSION

We constructed a nomogram for the personalized prediction of delirium in sepsis patients, which had satisfactory performance and clinical utility and thus could help clinicians identify patients with SAD in a timely manner, perform early intervention, and improve their neurological outcomes.

Characterization of Risk Prediction Models for Acute Kidney Injury: A Systematic Review and Meta-analysis

Importance

Despite the expansion of published prediction models for acute kidney injury (AKI), there is little evidence of uptake of these models beyond their local derivation nor data on their association with patient outcomes.

Objective

To systematically review published AKI prediction models across all clinical subsettings.

Data Sources

MEDLINE via PubMed (January 1946 to April 2021) and Embase (January 1947 to April 2021) were searched using medical subject headings and text words related to AKI and prediction models.

Study Selection

All studies that developed a prediction model for AKI, defined as a statistical model with at least 2 predictive variables to estimate future occurrence of AKI, were eligible for inclusion. There was no limitation on study populations or methodological designs.

Data Extraction and Synthesis

Two authors independently searched the literature, screened the studies, and extracted and analyzed the data following the Preferred Reporting Items for Systematic Review and Meta-analyses guideline. The data were pooled using a random-effects model, with subgroups defined by 4 clinical settings. Between-study heterogeneity was explored using multiple methods, and funnel plot analysis was used to identify publication bias.

Main Outcomes and Measures

C statistic was used to measure the discrimination of prediction models.

Results

Of the 6955 studies initially identified through literature searching, 150 studies, with 14.4 million participants, met the inclusion criteria. The study characteristics differed widely in design, population, AKI definition, and model performance assessments. The overall pooled C statistic was 0.80 (95% CI, 0.79-0.81), with pooled C statistics in different clinical subsettings ranging from 0.78 (95% CI, 0.75-0.80) to 0.82 (95% CI, 0.78-0.86). Between-study heterogeneity was high overall and in the different clinical settings (eg, contrast medium-associated AKI: I2 = 99.9%; P < .001), and multiple methods did not identify any clear sources. A high proportion of models had a high risk of bias (126 [84.4%]) according to the Prediction Model Risk Of Bias Assessment Tool.

Conclusions and Relevance

In this study, the discrimination of the published AKI prediction models was good, reflected by high C statistics; however, the wide variation in the clinical settings, populations, and predictive variables likely drives the highly heterogenous findings that limit clinical utility. Standardized procedures for development and validation of prediction models are urgently needed.

Strategies of Predictive Schemes and Clinical Diagnosis for Prognosis Using MIMIC-III: A Systematic Review

The prime purpose of the proposed study is to construct a novel predictive scheme for assisting in the prognosis of criticality using the MIMIC-III dataset. With the adoption of various analytics and advanced computing in the healthcare system, there is an increasing trend toward developing an effective prognostication mechanism. Predictive-based modeling is the best alternative to work in this direction. This paper discusses various scientific contributions using desk research methodology towards the Medical Information Mart for Intensive Care (MIMIC-III). This open-access dataset is meant to help predict patient trajectories for various purposes ranging from mortality forecasting to treatment planning. With a dominant machine learning approach in this perspective, there is a need to discover the effectiveness of existing predictive methods. The resultant outcome of this paper offers an inclusive discussion about various available predictive schemes and clinical diagnoses using MIMIC-III in order to contribute toward better information associated with its strengths and weaknesses. Therefore, the paper provides a clear visualization of existing schemes for clinical diagnosis using a systematic review approach.

A nomogram for predicting the mortality of patients with type 2 diabetes mellitus complicated with acute kidney injury in the intensive care unit

BACKGROUND

There is no predictive tool for type 2 diabetes mellitus (T2DM) patients with acute kidney injury (AKI). Our study aimed to establish an effective nomogram model for predicting mortality in T2DM patients with AKI.

METHOD

Data on T2DM patients with AKI were obtained from the Medical Information Mart for Intensive Care III. 70% and 30% of the patients were randomly selected as the training and validation cohorts, respectively. Univariate and multivariate logistic regression analyses were used to identify factors associated with death in T2DM patients with AKI. Factors significantly associated with survival outcomes were used to construct a nomogram predicting 90-day mortality. The nomogram effect was evaluated by receiver operating characteristic curve analysis, Hosmer‒Lemeshow test, calibration curve, and decision curve analysis (DCA).

RESULTS

There were 4375 patients in the training cohort and 1879 in the validation cohort. Multivariate logistic regression analysis showed that age, BMI, chronic heart failure, coronary artery disease, malignancy, stages of AKI, white blood cell count, blood urea nitrogen, arterial partial pressure of oxygen and partial thromboplastin time were independent predictors of patient survival. The results showed that the nomogram had a higher area under the curve value than the sequential organ failure assessment score and simplified acute physiology score II. The Hosmer‒Lemeshow test and calibration curve suggested that the nomogram had a good calibration effect. The DCA curve showed that the nomogram model had good clinical application value.

CONCLUSION

The nomogram model accurately predicted 90-day mortality in T2DM patients with AKI. It may provide assistance for clinical decision-making and treatment, thereby reducing the medical burden.

Predicting the risk factors of diabetic ketoacidosis-associated acute kidney injury: A machine learning approach using XGBoost

Objective

The purpose of this study was to develop and validate a predictive model based on a machine learning (ML) approach to identify patients with DKA at increased risk of AKI within 1 week of hospitalization in the intensive care unit (ICU).

Methods

Patients diagnosed with DKA from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database according to the International Classification of Diseases (ICD)-9/10 code were included. The patient's medical history is extracted, along with data on their demographics, vital signs, clinical characteristics, laboratory results, and therapeutic measures. The best-performing model is chosen by contrasting the 8 Ml models. The area under the receiver operating characteristic curve (AUC), sensitivity, accuracy, and specificity were calculated to select the best-performing ML model.

Results

The final study enrolled 1,322 patients with DKA in total, randomly split into training (1,124, 85%) and validation sets (198, 15%). 497 (37.5%) of them experienced AKI within a week of being admitted to the ICU. The eXtreme Gradient Boosting (XGBoost) model performed best of the 8 Ml models, and the AUC of the training and validation sets were 0.835 and 0.800, respectively. According to the result of feature importance, the top 5 main features contributing to the XGBoost model were blood urea nitrogen (BUN), urine output, weight, age, and platelet count (PLT).

Conclusion

An ML-based individual prediction model for DKA-associated AKI (DKA-AKI) was developed and validated. The model performs robustly, identifies high-risk patients early, can assist in clinical decision-making, and can improve the prognosis of DKA patients to some extent.

Dynamic nomogram for predicting acute kidney injury in patients with acute ischemic stroke: A retrospective study

Background

This study sought to develop and validate a dynamic nomogram chart to assess the risk of acute kidney injury (AKI) in patients with acute ischemic stroke (AIS).

Methods

These data were drawn from the Medical Information Mart for Intensive Care III (MIMIC-III) database, which collects 47 clinical indicators of patients after admission to the hospital. The primary outcome indicator was the occurrence of AKI within 48 h of intensive care unit (ICU) admission. Independent risk factors for AKI were screened from the training set using univariate and multifactorial logistic regression analyses. Multiple logistic regression models were developed, and nomograms were plotted and validated in an internal validation set. Based on the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) to estimate the performance of this nomogram.

Results

Nomogram indicators include blood urea nitrogen (BUN), creatinine, red blood cell distribution width (RDW), heart rate (HR), Oxford Acute Severity of Illness Score (OASIS), the history of congestive heart failure (CHF), the use of vancomycin, contrast agent, and mannitol. The predictive model displayed well discrimination with the area under the ROC curve values of 0.8529 and 0.8598 for the training set and the validator, respectively. Calibration curves revealed favorable concordance between the actual and predicted incidence of AKI (p > 0.05). DCA indicates the excellent net clinical benefit of nomogram in predicting AKI.

Conclusion

In summary, we explored the incidence of AKI in patients with AIS during ICU stay and developed a predictive model to help clinical decision-making.

Development and Internal Validation of a Nomogram to Predict Mortality During the ICU Stay of Thoracic Fracture Patients Without Neurological Compromise: An Analysis of the MIMIC-III Clinical Database

Background: This study aimed to develop and validate a nomogram for predicting mortality in patients with thoracic fractures without neurological compromise and hospitalized in the intensive care unit. Methods: A total of 298 patients from the Medical Information Mart for Intensive Care III (MIMIC-III) database were included in the study, and 35 clinical indicators were collected within 24 h of patient admission. Risk factors were identified using the least absolute shrinkage and selection operator (LASSO) regression. A multivariate logistic regression model was established, and a nomogram was constructed. Internal validation was performed by the 1,000 bootstrap samples; a receiver operating curve (ROC) was plotted, and the area under the curve (AUC), sensitivity, and specificity were calculated. In addition, the calibration of our model was evaluated by the calibration curve and Hosmer-Lemeshow goodness-of-fit test (HL test). A decision curve analysis (DCA) was performed, and the nomogram was compared with scoring systems commonly used during clinical practice to assess the net clinical benefit. Results: Indicators included in the nomogram were age, OASIS score, SAPS II score, respiratory rate, partial thromboplastin time (PTT), cardiac arrhythmias, and fluid-electrolyte disorders. The results showed that our model yielded satisfied diagnostic performance with an AUC value of 0.902 and 0.883 using the training set and on internal validation. The calibration curve and the Hosmer-Lemeshow goodness-of-fit (HL). The HL tests exhibited satisfactory concordance between predicted and actual outcomes (P = 0.648). The DCA showed a superior net clinical benefit of our model over previously reported scoring systems. Conclusion: In summary, we explored the incidence of mortality during the ICU stay of thoracic fracture patients without neurological compromise and developed a prediction model that facilitates clinical decision making. However, external validation will be needed in the future.

Construction and Validation of a Risk Prediction Model for Acute Kidney Injury in Patients Suffering from Septic Shock

Background. Acute kidney injury (AKI) is an important complication in critically ill patients, especially in sepsis and septic shock patients. Early prediction of AKI in septic shock can provide clinicians with sufficient information for timely intervention so that improve the patients’ survival rate and quality of life. The aim of this study was to establish a nomogram that predicts the risk of AKI in patients with septic shock in the intensive care unit (ICU). Methods. The data were collected from the Medical Information Mart for Intensive Care III (MIMIC-III) database between 2001 and 2012. The primary outcome was AKI in the 48 h following ICU admission. Univariate and multivariate logistic regression analyses were used to screen the independent risk factors of AKI. The performance of the nomogram was evaluated according to the calibration curve, receiver operating characteristic (ROC) curve, decision curve analysis, and clinical impact curve. Results. A total of 2415 patients with septic shock were included in this study. In the training and validation cohort, 1091 (64.48%) of 1690 patients and 475 (65.52%) of 725 patients developed AKI, respectively. The predictive factors for nomogram construction were gender, ethnicity, congestive heart failure, diabetes, obesity, Simplified Acute Physiology Score II (SAPS II), angiotensin-converting enzyme inhibitors (ACEI) or angiotensin receptor blockers (ARBs), bilirubin, creatinine, blood urea nitrogen (BUN), and mechanical ventilation. The model had a good discrimination with the area under the ROC curve of 0.756 and 0.760 in the training and validation cohorts, respectively. The calibration curve for probability of AKI in septic shock showed optimal agreement between prediction by nomogram and actual observation. Decision curve and clinical impact curve analysis indicated that the nomogram conferred high clinical net benefit. Conclusion. The proposed nomogram can quickly and effectively predict the risk of AKI at an early stage in patients with septic shock in ICU, which can provide information for timely and efficient intervention in patients with septic shock in the ICU setting.

Advances in artificial intelligence and deep learning systems in ICU-related acute kidney injury

PURPOSE OF REVIEW

Acute kidney injury (AKI) affects nearly 60% of all patients admitted to ICUs. Large volumes of clinical, monitoring and laboratory data produced in ICUs allow the application of artificial intelligence analytics. The purpose of this article is to assimilate and critically evaluate recently published literature regarding artificial intelligence applications for predicting, diagnosing and subphenotyping AKI among critically ill patients.

RECENT FINDINGS

Among recent studies regarding artificial intelligence implementations for predicting, diagnosing and subphenotyping AKI among critically ill patients, there are many promising models, but few had external validation, clinical interpretability and high predictive performance. Deep learning techniques leveraging multimodal clinical data show great potential to provide continuous, accurate, early predictions of AKI risk, which could be implemented clinically to optimize preventive and early therapeutic management strategies.

SUMMARY

Use of consensus criteria, standard definitions and common data models could facilitate access to machine learning-ready data sets for external validation. The lack of interpretability, explainability, fairness and transparency of artificial intelligence models hinder their entrustment and clinical implementation; compliance with standardized reporting guidelines can mitigate these challenges.