ICG-liver test versus new biomarkers as prognostic markers for prolonged length of stay in critically ill patients - a prospective study of accuracy for prediction of length of stay in the ICU

Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a Gradient Boosting algorithm analysis

Objective

This study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework).

Methods

We analyzed a dataset of patients admitted through the ED to the "Sant"Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%).

Results

A total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6-7 day mean difference between actual and predicted LoS.

Conclusion

Our results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.

Predicting length of stay in ICU and mortality with temporal dilated separable convolution and context-aware feature fusion

In healthcare, Intensive Care Unit (ICU) bed management is a necessary task because of the limited budget and resources. Predicting the remaining Length of Stay (LoS) in ICU and mortality can assist clinicians in managing ICU beds efficiently. This study proposes a deep learning method based on several successive Temporal Dilated Separable Convolution with Context-Aware Feature Fusion (TDSC-CAFF) modules, and a multi-view and multi-scale feature fusion for predicting the remaining LoS and mortality risk for ICU patients. In each TDSC-CAFF module, temporal dilated separable convolution is used to encode each feature separately, and context-aware feature fusion is proposed to capture comprehensive and context-aware feature representations from the input time-series features, static demographics, and the output of the last TDSC-CAFF module. The CAFF outputs of each module are accumulated to achieve multi-scale representations with different receptive fields. The outputs of TDSC and CAFF are concatenated with skip connection from the output of the last module and the original time-series input. The concatenated features are processed by the proposed Point-Wise convolution-based Attention (PWAtt) that captures the inter-feature context to generate the final temporal features. Finally, the final temporal features, the accumulated multi-scale features, the encoded diagnosis, and static demographic features are fused and then processed by fully connected layers to obtain prediction results. We evaluate our proposed method on two publicly available datasets: eICU and MIMIC-IV v1.0 for LoS and mortality prediction tasks. Experimental results demonstrate that our proposed method achieves a mean squared log error of 0.07 and 0.08 for LoS prediction, and an Area Under the Receiver Operating Characteristic Curve of 0.909 and 0.926 for mortality prediction, on eICU and MIMIC-IV v1.0 datasets, respectively, which outperforms several state-of-the-art methods.

Comparison of Four Machine Learning Techniques for Prediction of Intensive Care Unit Length of Stay in Heart Transplantation Patients

Background

Post-operative heart transplantation patients often require admission to an intensive care unit (ICU). Early prediction of the ICU length of stay (ICU-LOS) of these patients is of great significance and can guide treatment while reducing the mortality rate among patients. However, conventional linear models have tended to perform worse than non-linear models.

Materials and Methods

We collected the clinical data of 365 patients from Wuhan Union Hospital who underwent heart transplantation surgery between April 2017 and August 2020. The patients were randomly divided into training data (N = 256) and test data (N = 109) groups. 84 clinical features were collected for each patient. Features were validated using the Least Absolute Shrinkage and Selection Operator (LASSO) regression’s fivefold cross-validation method. We obtained Shapley Additive explanations (SHAP) values by executing package “shap” to interpret model predictions. Four machine learning models and logistic regression algorithms were developed. The area under the receiver operating characteristic curve (AUC-ROC) was used to compare the prediction performance of different models. Finally, for the convenience of clinicians, an online web-server was established and can be freely accessed via the website https://wuhanunion.shinyapps.io/PredictICUStay/.

Results

In this study, 365 consecutive patients undergoing heart transplantation surgery for moderate (NYHA grade 3) or severe (NYHA grade 4) heart failure were collected in Wuhan Union Hospital from 2017 to 2020. The median age of the recipient patients was 47.2 years, while the median age of the donors was 35.58 years. 330 (90.4%) of the donor patients were men, and the average surgery duration was 260.06 min. Among this cohort, 47 (12.9%) had renal complications, 25 (6.8%) had hepatic complications, 11 (3%) had undergone chest re-exploration and 19 (5.2%) had undergone extracorporeal membrane oxygenation (ECMO). The following six important clinical features were selected using LASSO regression, and according to the result of SHAP, the rank of importance was (1) the use of extracorporeal membrane oxygenation (ECMO); (2) donor age; (3) the use of an intra-aortic balloon pump (IABP); (4) length of surgery; (5) high creatinine (Cr); and (6) the use of continuous renal replacement therapy (CRRT). The eXtreme Gradient Boosting (XGBoost) algorithm presented significantly better predictive performance (AUC-ROC = 0.88) than other models [Accuracy: 0.87; sensitivity: 0.98; specificity: 0.51; positive predictive value (PPV): 0.86; negative predictive value (NPV): 0.93].

Conclusion

Using the XGBoost classifier with heart transplantation patients can provide an accurate prediction of ICU-LOS, which will not only improve the accuracy of clinical decision-making but also contribute to the allocation and management of medical resources; it is also a real-world example of precision medicine in hospitals.

Predicting Prolonged Length of ICU Stay through Machine Learning

This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medical Information Mart for Intensive Care (MIMIC) III database was used for external validation. We used four different ML methods (random forest, support vector machine, deep learning, and gradient boosting decision tree (GBDT)) to develop prediction models. The prediction performance of the four models were compared with the customized simplified acute physiology score (SAPS) II. The area under the receiver operation characteristic curve (AUROC), area under the precision-recall curve (AUPRC), estimated calibration index (ECI), and Brier score were used to measure performance. In internal validation, the GBDT model achieved the best overall performance (Brier score, 0.164), discrimination (AUROC, 0.742; AUPRC, 0.537), and calibration (ECI, 8.224). In external validation, the GBDT model also achieved the best overall performance (Brier score, 0.166), discrimination (AUROC, 0.747; AUPRC, 0.536), and calibration (ECI, 8.294). External validation showed that the calibration curve of the GBDT model was an optimal fit, and four ML models outperformed the customized SAPS II model. The GBDT-based pLOS-ICU prediction model had the best prediction performance among the five models on both internal and external datasets. Furthermore, it has the potential to assist ICU physicians to identify patients with pLOS-ICU risk and provide appropriate clinical interventions to improve patient outcomes.

Leveraging electronic health record data to inform hospital resource management : A systematic data mining approach

Early identification of resource needs is instrumental in promoting efficient hospital resource management. Hospital information systems, and electronic health records (EHR) in particular, collect valuable demographic and clinical patient data from the moment patients are admitted, which can help predict expected resource needs in early stages of patient episodes. To this end, this article proposes a data mining methodology to systematically obtain predictions for relevant managerial variables by leveraging structured EHR data. Specifically, these managerial variables are: i) Diagnosis categories, ii) procedure codes, iii) diagnosis-related groups (DRGs), iv) outlier episodes and v) length of stay (LOS). The proposed methodology approaches the problem in four stages: Feature set construction, feature selection, prediction model development, and model performance evaluation. We tested this approach with an EHR dataset of 5,089 inpatient episodes and compared different classification and regression models (for categorical and continuous variables, respectively), performed temporal analysis of model performance, analyzed the impact of training set homogeneity on performance and assessed the contribution of different EHR data elements for model predictive power. Overall, our results indicate that inpatient EHR data can effectively be leveraged to inform resource management on multiple perspectives. Logistic regression (combined with minimal redundancy maximum relevance feature selection) and bagged decision trees yielded best results for predicting categorical and numerical managerial variables, respectively. Furthermore, our temporal analysis indicated that, while DRG classes are more difficult to predict, several diagnosis categories, procedure codes and LOS amongst shorter-stay patients can be predicted with higher confidence in early stages of patient stay. Lastly, value of information analysis indicated that diagnoses, medication and structured assessment forms were the most valuable EHR data elements in predicting managerial variables of interest through a data mining approach.

Predicting Prolonged Length of Hospital Stay for Peritoneal Dialysis-Treated Patients Using Stacked Generalization: Model Development and Validation Study

Background

The increasing number of patients treated with peritoneal dialysis (PD) and their consistently high rate of hospital admissions have placed a large burden on the health care system. Early clinical interventions and optimal management of patients at a high risk of prolonged length of stay (pLOS) may help improve the medical efficiency and prognosis of PD-treated patients. If timely clinical interventions are not provided, patients at a high risk of pLOS may face a poor prognosis and high medical expenses, which will also be a burden on hospitals. Therefore, physicians need an effective pLOS prediction model for PD-treated patients.

Objective

This study aimed to develop an optimal data-driven model for predicting the pLOS risk of PD-treated patients using basic admission data.

Methods

Patient data collected using the Hospital Quality Monitoring System (HQMS) in China were used to develop pLOS prediction models. A stacking model was constructed with support vector machine, random forest (RF), and K-nearest neighbor algorithms as its base models and traditional logistic regression (LR) as its meta-model. The meta-model used the outputs of all 3 base models as input and generated the output of the stacking model. Another LR-based pLOS prediction model was built as the benchmark model. The prediction performance of the stacking model was compared with that of its base models and the benchmark model. Five-fold cross-validation was employed to develop and validate the models. Performance measures included the Brier score, area under the receiver operating characteristic curve (AUROC), estimated calibration index (ECI), accuracy, sensitivity, specificity, and geometric mean (Gm). In addition, a calibration plot was employed to visually demonstrate the calibration power of each model.

Results

The final cohort extracted from the HQMS database consisted of 23,992 eligible PD-treated patients, among whom 30.3% had a pLOS (ie, longer than the average LOS, which was 16 days in our study). Among the models, the stacking model achieved the best calibration (ECI 8.691), balanced accuracy (Gm 0.690), accuracy (0.695), and specificity (0.701). Meanwhile, the stacking and RF models had the best overall performance (Brier score 0.174 for both) and discrimination (AUROC 0.757 for the stacking model and 0.756 for the RF model). Compared with the benchmark LR model, the stacking model was superior in all performance measures except sensitivity, but there was no significant difference in sensitivity between the 2 models. The 2-sided t tests revealed significant performance differences between the stacking and LR models in overall performance, discrimination, calibration, balanced accuracy, and accuracy.

Conclusions

This study is the first to develop data-driven pLOS prediction models for PD-treated patients using basic admission data from a national database. The results indicate the feasibility of utilizing a stacking-based pLOS prediction model for PD-treated patients. The pLOS prediction tools developed in this study have the potential to assist clinicians in identifying patients at a high risk of pLOS and to allocate resources optimally for PD-treated patients.

What factors predict length of stay in the intensive care unit? Systematic review and meta-analysis

PURPOSE

Studies have shown that a small percentage of ICU patients have prolonged length of stay (LoS) and account for a large proportion of resource use. Therefore, the identification of prolonged stay patients can improve unit efficiency. In this study, we performed a systematic review and meta-analysis to understand the risk factors of ICU LoS.

MATERIALS AND METHODS

We searched MEDLINE, Embase and Scopus databases from inception to November 2018. The searching process focused on papers presenting risk factors of ICU LoS. A meta-analysis was performed for studies reporting appropriate statistics.

RESULTS

From 6906 citations, 113 met the eligibility criteria and were reviewed. A meta-analysis was performed for six factors from 28 papers and concluded that patients with mechanical ventilation, hypomagnesemia, delirium, and malnutrition tend to have longer stay, and that age and gender were not significant factors.

CONCLUSIONS

This work suggested a list of risk factors that should be considered in prediction models for ICU LoS, as follows: severity scores, mechanical ventilation, hypomagnesemia, delirium, malnutrition, infection, trauma, red blood cells, and PaO2:FiO2. Our findings can be used by prediction models to improve their predictive capacity of prolonged stay patients, assisting in resource allocation, quality improvement actions, and benchmarking analysis.

ICG Clearance Test and 99mTc-GSA SPECT/CT Fusion Images

Preoperative estimation of future remnant liver function is critical for major hepatic surgery to avoid postoperative morbidity and mortality. Among several liver function tests, the indocyanine green (ICG) clearance test is still the most popular dynamic method. The usefulness of ICG clearance test parameters, such as ICGR15, KICG, or PDRICG, has been reported by many investigators. The transcutaneous non-invasive pulse dye densitometry system has made the ICG clearance test more convenient and attractive, even in Western countries. The concept of future remnant KICG (rem KICG), which combines the functional aspect and the volumetric factor of the future remnant liver, seems ideal for determining the maximum extent of major hepatic resection that will not cause postoperative liver failure. For damaged livers with functional heterogeneity among the hepatic segments, fusion images combining technetium-99m-diethylenetriaminepentaacetic acid-galactosyl human serum albumin single photon emission computed tomography (99mTc-GSA SPECT) and X-ray CT are helpful to precisely estimate the functional reserve of the future remnant liver. Another technique for image-based liver function estimation, gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid(Gd-EOB)-enhanced magnetic resonance imaging, may be an ideal candidate for the preoperative determination of future remnant liver function. Using these methods effectively, morbidity and mortality after major hepatic resection could be reduced.

Bioartificial Therapy of Sepsis: Changes of Norepinephrine-Dosage in Patients and Influence on Dynamic and Cell Based Liver Tests during Extracorporeal Treatments

Purpose. Granulocyte transfusions have been used to treat immune cell dysfunction in sepsis. A granulocyte bioreactor for the extracorporeal treatment of sepsis was tested in a prospective clinical study focusing on the dosage of norepinephrine in patients and influence on dynamic and cell based liver tests during extracorporeal therapies. Methods and Patients. Ten patients with severe sepsis were treated twice within 72 h with the system containing granulocytes from healthy donors. Survival, physiologic parameters, extended hemodynamic measurement, and the indocyanine green plasma disappearance rate (PDR) were monitored. Plasma of patients before and after extracorporeal treatments were tested with a cell based biosensor for analysis of hepatotoxicity. Results. The observed mortality rate was 50% during stay in hospital. During the treatments, the norepinephrine-dosage could be significantly reduced while mean arterial pressure was stable. In the cell based analysis of hepatotoxicity, the viability and function of sensor-cells increased significantly during extracorporeal treatment in all patients and the PDR-values increased significantly between day 1 and day 7 only in survivors. Conclusion. The extracorporeal treatment with donor granulocytes showed promising effects on dosage of norepinephrine in patients, liver cell function, and viability in a cell based biosensor. Further studies with this approach are encouraged.

Prognostic impact of ICG-PDR in patients with hypoxic hepatitis

Background

Hepatic impairment is found in up to 20 % in critically ill patients. Hypoxic/ischemic hepatitis (HH) is a diffuse hepatic damage associated with high morbidity and mortality. Indocyanine green plasma disappearance rate (ICG-PDR) is an effective tool assessing liver function in acute and chronic hepatic diseases. Aim of this study was to evaluate the prognostic impact of ICG-PDR in comparison to established parameters for risk stratification.

Methods

Patients with HH were included in this prospective observational study and compared to cirrhosis, acute liver failure (ALF) and patients without underlying liver disease. ICG-PDR, measured non-invasively by finger pulse densitometry, was assessed on admission and in patients with HH serially and results were compared between groups. Diagnostic test accuracy of ICG-PDR predicting 28-day mortality was analyzed by receiver operating characteristics (ROC).

Results

ICG-PDR on admission was significantly lower in patients with liver diseases than in patients without hepatic impairment (median 5.7 %/min, IQR 3.8–7.9 vs. 20.7 %/min, IQR 14.1–25.4 %/min; p < 0.001). ICG-PDR predicted 28-day mortality independently of SOFA score and serum lactate in patients with underlying liver disease (HR 1.27, 95 % CI 1.10–1.45, p < 0.001). In patients with HH, ICG-PDR was identified as best predictor of 28-day mortality which performed significantly better than SOFA, lactate, INR and AST over course of time (p < 0.05). Best cut-off for identification of 28-day survivors was ICG-PDR ≥9.0 %/min 48 h after admission.

Conclusions

ICG-PDR is an independent predictor of mortality in patients with liver disease. Diagnostic test accuracy of ICG-PDR was superior to standard liver function parameters and established scoring systems in patients with HH.

Current use and perspective of indocyanine green clearance in liver diseases

Indocyanine green (ICG) is a water-soluble anionic compound that binds to plasma proteins after intravenous administration. It is selectively taken up at the first pass by hepatocytes and excreted unchanged into the bile. With the development of ICG elimination measurement by spectrophotometry, the ICG retention test has become a safe, rapid, reproducible, inexpensive and noninvasive tool for the assessment of liver function. Clinical evidence suggests that the ICG retention test can enable the establishment of tailored management strategies by providing prognostic information. In particular, this method has been evaluated as a prognostic marker in patients with advanced cirrhosis or awaiting liver transplantation. In addition, it is used as a marker of portal hypertension in cirrhotic patients, as a prognostic factor in intensive care units and for the assessment of liver function in patients undergoing liver surgery. Since recent technology enables ICG-PDR to be measured noninvasively at the bedside, this parameter is an attractive addition to liver function and regional haemodynamic monitoring. However, the current state-of-the-art as concerns this technology remains at a low level of evidence and thorough assessment is required.