Predictors of in-hospital length of stay among cardiac patients: A machine learning approach

The importance of SNOMED CT concept specificity in healthcare analytics

BACKGROUND

Healthcare data frequently lack the specificity level needed to achieve clinical and operational objectives such as optimising bed management. Pneumonia is a disease of importance as it accounts for more bed days than any other lung disease and has a varied aetiology. The condition has a range of SNOMED CT concepts with different levels of specificity.

OBJECTIVE

This study aimed to quantify the importance of the specificity of an SNOMED CT concept, against well-established predictors, for forecasting length of stay for pneumonia patients.

METHOD

A retrospective data analysis was conducted of pneumonia admissions to a tertiary hospital between 2011 and 2021. For inclusion, the primary diagnosis was a subtype of bacterial or viral pneumonia, as identified by SNOMED CT concepts. Three linear mixed models were constructed. Model One included known predictors of length of stay. Model Two included the predictors in Model One and SNOMED CT concepts of lower specificity. Model Three included the Model Two predictors and the concepts with higher specificity. Model performances were compared.

RESULTS

Sex, ethnicity, deprivation rank and Charlson Comorbidity Index scores (age-adjusted) were meaningful predictors of length of stay in all models. Inclusion of lower specificity SNOMED CT concepts did not significantly improve performance (ΔR2 = 0.41%, p = .058). SNOMED CT concepts with higher specificity explained more variance than each of the individual predictors (ΔR2 = 4.31%, p < .001).

CONCLUSION

SNOMED CT concepts with higher specificity explained more variance in length of stay than a range of well-studied predictors.

IMPLICATIONS

Accurate and specific clinical documentation using SNOMED CT can improve predictive modelling and the generation of actionable insights. Resources should be dedicated to optimising and assuring clinical documentation quality at the point of recording.

Predicting hospital length of stay using machine learning on a large open health dataset

BACKGROUND

Governments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient's length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper.

METHODS

We investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns.

RESULTS

The study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns.

CONCLUSION

Our study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery.

The classification algorithms to support the management of the patient with femur fracture

Effectiveness in health care is a specific characteristic of each intervention and outcome evaluated. Especially with regard to surgical interventions, organization, structure and processes play a key role in determining this parameter. In addition, health care services by definition operate in a context of limited resources, so rationalization of service organization becomes the primary goal for health care management. This aspect becomes even more relevant for those surgical services for which there are high volumes. Therefore, in order to support and optimize the management of patients undergoing surgical procedures, the data analysis could play a significant role. To this end, in this study used different classification algorithms for characterizing the process of patients undergoing surgery for a femoral neck fracture. The models showed significant accuracy with values of 81%, and parameters such as Anaemia and Gender proved to be determined risk factors for the patient's length of stay. The predictive power of the implemented model is assessed and discussed in view of its capability to support the management and optimisation of the hospitalisation process for femoral neck fracture, and is compared with different model in order to identify the most promising algorithms. In the end, the support of artificial intelligence algorithms laying the basis for building more accurate decision-support tools for healthcare practitioners.

Translational artificial intelligence-led optimization and realization of estimated discharge with a supportive weekend interprofessional flow team (TAILORED-SWIFT)

Weekend discharges occur less frequently than discharges on weekdays, contributing to hospital congestion. Artificial intelligence algorithms have previously been derived to predict which patients are nearing discharge based upon ward round notes. In this implementation study, such an artificial intelligence algorithm was coupled with a multidisciplinary discharge facilitation team on weekend shifts. This approach was implemented in a tertiary hospital, and then compared to a historical cohort from the same time the previous year. There were 3990 patients included in the study. There was a significant increase in the proportion of inpatients who received weekend discharges in the intervention group compared to the control group (median 18%, IQR 18-20%, vs median 14%, IQR 12% to 17%, P = 0.031). There was a corresponding higher absolute number of weekend discharges during the intervention period compared to the control period (P = 0.025). The studied intervention was associated with an increase in weekend discharges and economic analyses support this approach as being cost-effective. Further studies are required to examine the generalizability of this approach to other centers.

Beyond the Bedside: Machine Learning-Guided Length of Stay (LOS) Prediction for Cardiac Patients in Tertiary Care

Efficient management of hospital resources is essential for providing high-quality healthcare while ensuring sustainability. Length of stay (LOS), measuring the duration from admission to discharge, directly impacts patient outcomes and resource utilization. Accurate LOS prediction offers numerous benefits, including reducing re-admissions, ensuring appropriate staffing, and facilitating informed discharge planning. While conventional methods rely on statistical models and clinical expertise, recent advances in machine learning (ML) present promising avenues for enhancing LOS prediction. This research focuses on developing an ML-based LOS prediction model trained on a comprehensive real-world dataset and discussing the important factors towards practical deployment of trained ML models in clinical settings. This research involves the development of a comprehensive adult cardiac patient dataset (SaudiCardioStay (SCS)) from the King Faisal Specialist Hospital & Research Centre (KFSH&RC) hospital in Saudi Arabia, comprising 4930 patient encounters for 3611 unique patients collected from 2019 to 2022 (excluding 2020). A diverse range of classical ML models (i.e., Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), artificial neural networks (ANNs), Average Voting Regression (AvgVotReg)) are implemented for the SCS dataset to explore the potential of existing ML models in LOS prediction. In addition, this study introduces a novel approach for LOS prediction by incorporating a dedicated LOS classifier within a sophisticated ensemble methodology (i.e., Two-Level Sequential Cascade Generalization (2LSCG), Three-Level Sequential Cascade Generalization (3LSCG), Parallel Cascade Generalization (PCG)), aiming to enhance prediction accuracy and capture nuanced patterns in healthcare data. The experimental results indicate the best mean absolute error (MAE) of 0.1700 for the 3LSCG model. Relatively comparable performance was observed for the AvgVotReg model, with a MAE of 0.1703. In the end, a detailed analysis of the practical implications, limitations, and recommendations concerning the deployment of ML approaches in actual clinical settings is presented.

Predictors of in-ICU length of stay among congenital heart defect patients using artificial intelligence model: A pilot study

Objective

This study aims to develop a predictive model using artificial intelligence to estimate the ICU length of stay (LOS) for Congenital Heart Defects (CHD) patients after surgery, improving care planning and resource management.

Design

We analyze clinical data from 2240 CHD surgery patients to create and validate the predictive model. Twenty AI models are developed and evaluated for accuracy and reliability.

Setting

The study is conducted in a Brazilian hospital's Cardiovascular Surgery Department, focusing on transplants and cardiopulmonary surgeries.

Participants

Retrospective analysis is conducted on data from 2240 consecutive CHD patients undergoing surgery.

Interventions

Ninety-three pre and intraoperative variables are used as ICU LOS predictors.

Measurements and main results

Utilizing regression and clustering methodologies for ICU LOS (ICU Length of Stay) estimation, the Light Gradient Boosting Machine, using regression, achieved a Mean Squared Error (MSE) of 15.4, 11.8, and 15.2 days for training, testing, and unseen data. Key predictors included metrics such as "Mechanical Ventilation Duration", "Weight on Surgery Date", and "Vasoactive-Inotropic Score". Meanwhile, the clustering model, Cat Boost Classifier, attained an accuracy of 0.6917 and AUC of 0.8559 with similar key predictors.

Conclusions

Patients with higher ventilation times, vasoactive-inotropic scores, anoxia time, cardiopulmonary bypass time, and lower weight, height, BMI, age, hematocrit, and presurgical oxygen saturation have longer ICU stays, aligning with existing literature.

Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study

Background

Recently, crowding in emergency departments (EDs) has become a recognised critical factor impacting global public healthcare, resulting from both the rising supply/demand mismatch in medical services and the paucity of hospital beds available in inpatients units and EDs. The length of stay in the ED (ED-LOS) has been found to be a significant indicator of ED bottlenecks. The time a patient spends in the ED is quantified by measuring the ED-LOS, which can be influenced by inefficient care processes and results in increased mortality and health expenditure. Therefore, it is critical to understand the major factors influencing the ED-LOS through forecasting tools enabling early improvements.

Methods

The purpose of this work is to use a limited set of features impacting ED-LOS, both related to patient characteristics and to ED workflow, to predict it. Different factors were chosen (age, gender, triage level, time of admission, arrival mode) and analysed. Then, machine learning (ML) algorithms were employed to foresee ED-LOS. ML procedures were implemented taking into consideration a dataset of patients obtained from the ED database of the "San Giovanni di Dio e Ruggi d'Aragona" University Hospital (Salerno, Italy) from the period 2014-2019.

Results

For the years considered, 496,172 admissions were evaluated and 143,641 of them (28.9%) revealed a prolonged ED-LOS. Considering the complete data (48.1% female vs. 51.9% male), 51.7% patients with prolonged ED-LOS were male and 47.3% were female. Regarding the age groups, the patients that were most affected by prolonged ED-LOS were over 64 years. The evaluation metrics of Random Forest algorithm proved to be the best; indeed, it achieved the highest accuracy (74.8%), precision (72.8%), and recall (74.8%) in predicting ED-LOS.

Conclusions

Different variables, referring to patients' personal and clinical attributes and to the ED process, have a direct impact on the value of ED-LOS. The suggested prediction model has encouraging results; thus, it may be applied to anticipate and manage ED-LOS, preventing crowding and optimising effectiveness and efficiency of the ED.

Health system and patient-level factors associated with multidisciplinary care and patient education among hospitalized, older cancer survivors

Objective

The purpose of this study was to examine system- and patient-level factors associated with the number of healthcare disciplines involved in delivery of patient education among hospitalized older cancer survivors.

Methods

We used electronic health record (EHR) data from a single institution documenting patient education among hospitalized older patients (≥65 years) with a history of cancer between 9/1/2018 and 10/1/2019. We used parametric ordinal logistic regression to assess the number of healthcare disciplines involved in documented education activities.

Results

The sample (n = 446) was predominantly male, White, and on average 74 years old. Adjusting for patient and system-level variables, men and larger department units had higher odds of receiving education from fewer healthcare disciplines. Patients with a history of breast or prostate cancer and longer lenths of stay had lower odds of receiving patient education from fewer healthcare disciplines.

Conclusion

Hospital size, severity of illness, and cancer type are associated with delivery of multidisciplinary education in this sample.

Innovation

EHR provides an opportunity to identify patterns in patient education among cancer survivors. Future research should investigate provider perspectives of the findings to inform provider- and system-level strategies to improve patient education.

Association of Length of Stay With the Clinical Trajectory of Hospitalized Patients With Atrial Fibrillation: Staying Less Is More?

Data predicting the length of stay (LOS) in patients with concurrent atrial fibrillation (AF) are scarce. This study aimed to investigate the potential predictors for prolonged LOS and its prognostic value. In this observational post hoc analysis of the MISOAC-AF (Motivational Interviewing to Support Oral AntiCoagulation adherence in patients with non-valvular Atrial Fibrillation) randomized trial logistic regression analyses were conducted to identify the parameters associated with prolonged LOS (defined as >7 days according to diagnostic accuracy analyses). Kaplan-Meier and Cox regression analyses were performed to generate survival curves and adjusted hazard ratios (aHRs) with 95% confidence intervals (CIs) for the primary end point of all-cause mortality and for the secondary end points during a median 3.7-year follow-up. Of the 1,057 patients studied, 462 (43.7%) were hospitalized for ≥7 days. Heart failure with reduced ejection fracture (aHR 1.75, 95% CI 1.17 to 2.63), permanent AF (aHR 1.72, 95% CI 1.29 to 2.31), history of coronary artery disease (aHR 2.32, 95% CI 1.59 to 3.39), and advanced or end-stage chronic kidney disease (aHR 1.54, 95% CI 1.15 to 2.06) were independently associated with prolonged hospitalization. Prolonged LOS was independently linked with increased all-cause mortality rates (aHR 1.68, 95% CI 1.25 to 2.26), cardiovascular mortality (aHR 1.92, 95% CI 1.36 to 2.72), major bleeding (aHR 3.07, 95% CI 1.07 to 8.78), and the composite outcome of cardiovascular death or rehospitalization (aHR 1.31, 95% CI 1.04 to 1.66). Each extra day of LOS was an independent predictor of all-cause mortality (aHR 1.03, 95% CI 1.02 to 1.04). Hospitalized patients with concurrent AF carry a substantial morbidity burden being prone to extended LOS. A jointed approach seems reasonable to reduce the LOS in patients with AF.

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.

The Length of Hospital Stay of Patients with Venous Thromboembolism: A Cross-Sectional Study from Jordan

Background and Objectives: Venous thromboembolism is one of the leading causes of mortality and disability worldwide. Treatment with anticoagulation therapy is essential and requires a delicate approach to select the most appropriate option to improve patient outcomes, including the length of hospital stay (LOS). The aim of this study was to determine the LOS among patients with acute onset of VTE in several public hospitals in Jordan. Materials and Methods: In this study, we recruited hospitalized patients with a confirmed diagnosis of VTE. We reviewed the electronic medical records and charts of VTE admitted patients in addition to a detailed survey to collect the patients' self-reported data. Hospital LOS was categorized into three levels: 1-3 days, 4-6 days, and ≥7 days. An ordered logistic regression model was used to study the significant predictors of LOS. Results: A total of 317 VTE patients were recruited, with 52.4% of them were male and 35.3% aged between 50 and 69 years. Most patients had a deep vein thrombosis (DVT) diagnosis (84.2%), and most of the VTE cases were admitted for the first-time (64.6%). The majority of the patients were smokers (57.2%), overweight/obese (66.3%), and hypertensive (59%). Most of the VTE patients received Warfarin overlapped with low molecular weight heparins as their treatment regimen (>70%). Almost half of the admitted VTE patients (45%) were hospitalized for at least 7 days. Longer LOS was significantly associated with hypertension. Conclusions: We recommend using therapies that have been proven to reduce hospital LOS, such as non-vitamin K antagonist oral anticoagulants or direct oral anticoagulants, to treat VTE patients in Jordan. Additionally, preventing and controlling comorbidities such as hypertension is essential.

A study on predicting the length of hospital stay for Chinese patients with ischemic stroke based on the XGBoost algorithm

BACKGROUND

The incidence of stroke is a challenge in China, as stroke imposes a heavy burden on families, national health services, social services, and the economy. The length of hospital stay (LOS) is an essential indicator of utilization of medical services and is usually used to assess the efficiency of hospital management and patient quality of care. This study established a prediction model based on a machine learning algorithm to predict ischemic stroke patients' LOS.

METHODS

A total of 18,195 ischemic stroke patients' electronic medical records and 28 attributes were extracted from electronic medical records in a large comprehensive hospital in China. The prediction of LOS was regarded as a multi classification problem, and LOS was divided into three categories: 1-7 days, 8-14 days and more than 14 days. After preprocessing the data and feature selection, the XGBoost algorithm was used to build a machine learning model. Ten fold cross-validation was used for model validation. The accuracy (ACC), recall rate (RE) and F1 measure were used to evaluate the performance of the prediction model of LOS of ischemic stroke patients. Finally, the XGBoost algorithm was used to identify and remove irrelevant features by ranking all attributes based on feature importance.

RESULTS

Compared with the naive Bayesian algorithm, logistic region algorithm, decision tree classifier algorithm and ADaBoost classifier algorithm, the XGBoot algorithm has higher ACC, RE and F1 measure. The average ACC, RE and F1 measure were 0.89, 0.89 and 0.89 under the 10-fold cross-validation. According to the analysis of the importance of features, the LOS of ischemic stroke patients was affected by demographic characteristics, past medical history, admission examination features, and operation characteristics. Finally, the features in terms of hemiplegia aphasia, MRS, NIHSS, TIA, Operation or not, coma index etc. were found to be the top features in importance in predicting the LOS of ischemic stroke patients.

CONCLUSIONS

The XGBoost algorithm was an appropriate machine learning method for predicting the LOS of patients with ischemic stroke. Based on the prediction model, an intelligent medical management prediction system could be developed to predict the LOS based on ischemic stroke patients' electronic medical records.

Predicting length of stay ranges by using novel deep neural networks

Background and aims

Accurately predicting length of stay (LOS) is considered a challenging task for health care systems globally. In previous studies on LOS range prediction, researchers commonly pre-classified the LOS ranges, which were the same for all patients in the same classification, and then utilized a classifier for prediction. In this study, we innovatively aimed to predict the specific LOS range for each patient (the LOS range was different for each patient).

Methods

In the modified deep neural network (DNN), the overall sample error (root mean square error (RMSE) method), the estimated sample error (ERR_pred method), the probability distribution with different loss functions (Dis_pred_Loss1, Dis_pred_Loss2, and Dis_pred_Loss3 method), and the generative adversarial networks (WGAN-GP for LOS method) are used for LOS range prediction. The Medical Information Mart for Intensive Care III (MIMIC-III) database is used to validate these methods.

Results

The RMSE method is convenient for LOS range prediction, but the predicted ranges are all consistent in the same batch of samples. The ERR_pred method can achieve better prediction results in samples with low errors. However, the prediction effect is worse in samples with larger errors. The Dis_pred_Loss1 method encounters a training instability problem. The Dis_pred_Loss2 and Dis_pred_Loss3 methods perform well in making predictions. Although WGAN-GP for LOS method does not show a substantial advantage over other methods, this method might have the potential to improve the predictive performance.

Conclusion

The results show that it is possible to achieve an acceptable accurate LOS range prediction through a reasonable model design, which may help physicians in the clinic.

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm

The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

Comparing artificial neural network training algorithms to predict length of stay in hospitalized patients with COVID-19

BACKGROUND

The exponential spread of coronavirus disease 2019 (COVID-19) causes unexpected economic burdens to worldwide health systems with severe shortages in hospital resources (beds, staff, equipment). Managing patients' length of stay (LOS) to optimize clinical care and utilization of hospital resources is very challenging. Projecting the future demand requires reliable prediction of patients' LOS, which can be beneficial for taking appropriate actions. Therefore, the purpose of this research is to develop and validate models using a multilayer perceptron-artificial neural network (MLP-ANN) algorithm based on the best training algorithm for predicting COVID-19 patients' hospital LOS.

METHODS

Using a single-center registry, the records of 1225 laboratory-confirmed COVID-19 hospitalized cases from February 9, 2020 to December 20, 2020 were analyzed. In this study, first, the correlation coefficient technique was developed to determine the most significant variables as the input of the ANN models. Only variables with a correlation coefficient at a P-value < 0.2 were used in model construction. Then, the prediction models were developed based on 12 training algorithms according to full and selected feature datasets (90% of the training, with 10% used for model validation). Afterward, the root mean square error (RMSE) was used to assess the models' performance in order to select the best ANN training algorithm. Finally, a total of 343 patients were used for the external validation of the models.

RESULTS

After implementing feature selection, a total of 20 variables were determined as the contributing factors to COVID-19 patients' LOS in order to build the models. The conducted experiments indicated that the best performance belongs to a neural network with 20 and 10 neurons in the hidden layer of the Bayesian regularization (BR) training algorithm for whole and selected features with an RMSE of 1.6213 and 2.2332, respectively.

CONCLUSIONS

MLP-ANN-based models can reliably predict LOS in hospitalized patients with COVID-19 using readily available data at the time of admission. In this regard, the models developed in our study can help health systems to optimally allocate limited hospital resources and make informed evidence-based decisions.

Temporal convolutional networks and data rebalancing for clinical length of stay and mortality prediction

It is critical for hospitals to accurately predict patient length of stay (LOS) and mortality in real-time. We evaluate temporal convolutional networks (TCNs) and data rebalancing methods to predict LOS and mortality. This is a retrospective cohort study utilizing the MIMIC-III database. The MIMIC-Extract pipeline processes 24 hour time-series clinical objective data for 23,944 unique patient records. TCN performance is compared to both baseline and state-of-the-art machine learning models including logistic regression, random forest, gated recurrent unit with decay (GRU-D). Models are evaluated for binary classification tasks (LOS > 3 days, LOS > 7 days, mortality in-hospital, and mortality in-ICU) with and without data rebalancing and analyzed for clinical runtime feasibility. Data is split temporally, and evaluations utilize tenfold cross-validation (stratified splits) followed by simulated prospective hold-out validation. In mortality tasks, TCN outperforms baselines in 6 of 8 metrics (area under receiver operating characteristic, area under precision-recall curve (AUPRC), and F-1 measure for in-hospital mortality; AUPRC, accuracy, and F-1 for in-ICU mortality). In LOS tasks, TCN performs competitively to the GRU-D (best in 6 of 8) and the random forest model (best in 2 of 8). Rebalancing improves predictive power across multiple methods and outcome ratios. The TCN offers strong performance in mortality classification and offers improved computational efficiency on GPU-enabled systems over popular RNN architectures. Dataset rebalancing can improve model predictive power in imbalanced learning. We conclude that temporal convolutional networks should be included in model searches for critical care outcome prediction systems.

Length of Hospitalization-Related Differences and Associated Long-Term Prognosis of Patients with Cardiac Resynchronization Therapy: A Propensity Score-Matched Cohort

Previous studies indicated that prolonged lengths of hospitalization (LOH) during cardiac resynchronization therapy (CRT) implantation are associated with poorer physical status and higher in-hospital mortality. However, evidence on the impact of LOH on the long-term prognosis of CRT patients is limited. The purpose of this study was to assess LOH-related prognostic differences in CRT patients. In the propensity score-matched cohort, patients with standard LOH (≤7 days, n = 172) were compared with those with prolonged LOH (>7 days, n = 172) for cardiac function and study outcomes during follow-up. The study outcomes were all-cause death and heart failure (HF) hospitalization. In addition, cardiac function and changes in cardiac function at the follow-up period were used for comparison. At a mean follow-up of 3.36 years, patients with prolonged LOH, as compared with those with standard LOH, were associated with a significantly higher risk of all-cause death (hazard ratio [HR] 1.87, 95% confidence interval [CI] 1.18−2.96, p = 0.007), and a higher risk of HF hospitalization (HR 1.68, 95% CI 1.08−2.63, p = 0.023). Moreover, patients with standard LOH had a more significant improvement in cardiac function and a pronounced reduction in QRS duration during follow-up than those with prolonged LOH. LOH-associated differences were found in the long-term prognosis of CRT patients. Patients with prolonged LOH had a worse prognosis than those with standard LOH.

Implementation of Predictive Algorithms for the Study of the Endarterectomy LOS

Background: In recent years, the length of hospital stay (LOS) following endarterectomy has decreased significantly from 4 days to 1 day. LOS is influenced by several common complications and factors that can adversely affect the patient’s health and may vary from one healthcare facility to another. The aim of this work is to develop a forecasting model of the LOS value to investigate the main factors affecting LOS in order to save healthcare cost and improve management. Methods: We used different regression and machine learning models to predict the LOS value based on the clinical and organizational data of patients undergoing endarterectomy. Data were obtained from the discharge forms of the “San Giovanni di Dio e Ruggi d’Aragona” University Hospital (Salerno, Italy). R² goodness of fit and the results in terms of accuracy, precision, recall and F1-score were used to compare the performance of various algorithms. Results: Before implementing the models, the preliminary correlation study showed that LOS was more dependent on the type of endarterectomy performed. Among the regression algorithms, the best was the multiple linear regression model with an R² value of 0.854, while among the classification algorithms for LOS divided into classes, the best was decision tree, with an accuracy of 80%. The best performance was obtained in the third class, which identifies patients with prolonged LOS, with a precision of 95%. Among the independent variables, the most influential on LOS was type of endarterectomy, followed by diabetes and kidney disorders. Conclusion: The resulting forecast model demonstrates its effectiveness in predicting the value of LOS that could be used to improve the endarterectomy surgery planning.

Parsimonious machine learning models to predict resource use in cardiac surgery across a statewide collaborative

Objective

Methods

Results

Conclusions

Length of Stay Prediction Model of Indoor Patients Based on Light Gradient Boosting Machine

The influx of hospital patients has become common in recent years. Hospital management departments need to redeploy healthcare resources to meet the massive medical needs of patients. In this process, the hospital length of stay (LOS) of different patients is a crucial reference to the management department. Therefore, building a model to predict LOS is of great significance. Five machine learning (ML) algorithms named Lasso regression (LR), ridge regression (RR), random forest regression (RFR), light gradient boosting machine (LightGBM), and extreme gradient boosting regression (XGBR) and six feature encoding methods named label encoding, count encoding, one-hot encoding, target encoding, leave-one-out encoding, and the proposed encoding method are used to construct the regression prediction model. The Scikit-Learn toolbox on the Python platform builds the prediction model. The input is the dataset named Hospital Inpatient Discharges (SPARCS De-Identified) 2017 with 2343569 instances provided by the New York State Department of Health verify the model after removing 2.2% of the missing data, and the model ultimately uses mean squared error (MSE) and coefficient of determination (R2) as the performance measurement. The results show that the model with the LightGBM algorithm and the proposed encoding method has the best R2 (96.0%) and MSE score (2.231).

Predicting Abnormalities in Laboratory Values of Patients in the Intensive Care Unit Using Different Deep Learning Models: Comparative Study

Background

In recent years, the volume of medical knowledge and health data has increased rapidly. For example, the increased availability of electronic health records (EHRs) provides accurate, up-to-date, and complete information about patients at the point of care and enables medical staff to have quick access to patient records for more coordinated and efficient care. With this increase in knowledge, the complexity of accurate, evidence-based medicine tends to grow all the time. Health care workers must deal with an increasing amount of data and documentation. Meanwhile, relevant patient data are frequently overshadowed by a layer of less relevant data, causing medical staff to often miss important values or abnormal trends and their importance to the progression of the patient’s case.

Objective

The goal of this work is to analyze the current laboratory results for patients in the intensive care unit (ICU) and classify which of these lab values could be abnormal the next time the test is done. Detecting near-future abnormalities can be useful to support clinicians in their decision-making process in the ICU by drawing their attention to the important values and focus on future lab testing, saving them both time and money. Additionally, it will give doctors more time to spend with patients, rather than skimming through a long list of lab values.

Methods

We used Structured Query Language to extract 25 lab values for mechanically ventilated patients in the ICU from the MIMIC-III and eICU data sets. Additionally, we applied time-windowed sampling and holding, and a support vector machine to fill in the missing values in the sparse time series, as well as the Tukey range to detect and delete anomalies. Then, we used the data to train 4 deep learning models for time series classification, as well as a gradient boosting–based algorithm and compared their performance on both data sets.

Results

The models tested in this work (deep neural networks and gradient boosting), combined with the preprocessing pipeline, achieved an accuracy of at least 80% on the multilabel classification task. Moreover, the model based on the multiple convolutional neural network outperformed the other algorithms on both data sets, with the accuracy exceeding 89%.

Conclusions

In this work, we show that using machine learning and deep neural networks to predict near-future abnormalities in lab values can achieve satisfactory results. Our system was trained, validated, and tested on 2 well-known data sets to ensure that our system bridged the reality gap as much as possible. Finally, the model can be used in combination with our preprocessing pipeline on real-life EHRs to improve patients’ diagnosis and treatment.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

The Association between Nutritional Status and Length of Hospital Stay among Patients with Hypertension

Background: Nutritional status is related to the prognosis and length of hospital stay (LOS) of patients with hypertension (HT). This study aimed to assess how nutritional status and body mass index (BMI) affect LOS for patients with hypertension. Method: We performed a retrospective analysis of 586 medical records of patients who had been admitted to the Institute of Heart Diseases of the University Clinical Hospital in Wroclaw, Poland. Results: A total of 586 individuals were included in the analysis. Individuals who were at a nutritional risk represented less than 2% of the study population, but more than 60% were overweight or obese. The mean BMI was 28.4 kg/m² (SD: 5.16). LOS averaged 3.53 days (SD = 2.78). In the case of obese individuals, hospitalisation lasted for 3.4 ± 2.43 days, which was significantly longer than for patients of normal weight. For underweight patients, hospitalisation lasted for 5.14 ± 2.27 days, which was also significantly longer than for those in other BMI categories (p = 0.017). The independent predictors of shorter hospitalisations involved higher LDL concentration (parameter of regression: −0.015) and HDL concentration (parameter of regression: −0.04). Conclusions: The study revealed that with regard to the nutritional status of hypertensive patients, being either underweight or obese was associated with longer LOS. Additional factors that related to prolonged LOS were lower LDL and HDL levels and higher CRP concentrations.

Machine Learning-based Prediction of Prolonged Intensive Care Unit Stay for Critical Patients with Spinal Cord Injury

STUDY DESIGN

A retrospective cohort study.

OBJECTIVE

The objective of the study was to develop machine-learning (ML) classifiers for predicting prolonged intensive care unit (ICU)-stay and prolonged hospital-stay for critical patients with spinal cord injury (SCI).

SUMMARY OF BACKGROUND DATA

Critical patients with SCI in ICU need more attention. SCI patients with prolonged stay in ICU usually occupy vast medical resources and hinder the rehabilitation deployment.

METHODS

A total of 1599 critical patients with SCI were included in the study and labeled with prolonged stay or normal stay. All data were extracted from the eICU Collaborative Research Database and the Medical Information Mart for Intensive Care III-IV Database. The extracted data were randomly divided into training, validation and testing (6:2:2) subdatasets. A total of 91 initial ML classifiers were developed, and the top three initial classifiers with the best performance were further stacked into an ensemble classifier with logistic regressor. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicting outcome was prolonged ICU-stay, while the secondary predicting outcome was prolonged hospital-stay.

RESULTS

In predicting prolonged ICU-stay, the AUC of the ensemble classifier was 0.864 ± 0.021 in the three-time five-fold cross-validation and 0.802 in the independent testing. In predicting prolonged hospital-stay, the AUC of the ensemble classifier was 0.815 ± 0.037 in the three-time five-fold cross-validation and 0.799 in the independent testing. Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top three initial classifiers varied a lot in either predicting prolonged ICU-stay or discriminating prolonged hospital-stay.

CONCLUSION

The ensemble classifiers successfully predict the prolonged ICU-stay and the prolonged hospital-stay, which showed a high potential of assisting physicians in managing SCI patients in ICU and make full use of medical resources.Level of Evidence: 3.

Network analytics and machine learning for predicting length of stay in elderly patients with chronic diseases at point of admission

Background

An aging population with a burden of chronic diseases puts increasing pressure on health care systems. Early prediction of the hospital length of stay (LOS) can be useful in optimizing the allocation of medical resources, and improving healthcare quality. However, the data available at the point of admission (PoA) are limited, making it difficult to forecast the LOS accurately.

Methods

In this study, we proposed a novel approach combining network analytics and machine learning to predict the LOS in elderly patients with chronic diseases at the PoA. Two networks, including multimorbidity network (MN) and patient similarity network (PSN), were constructed and novel network features were created. Five machine learning models (eXtreme Gradient Boosting, Gradient Boosting Decision Tree, Random Forest, Linear Support Vector Machine, and Deep Neural Network) with different input feature sets were developed to compare their performance.

Results

The experimental results indicated that the network features can bring significant improvements to the performances of the prediction models, suggesting that the MN and PSN are useful for LOS predictions.

Conclusion

Our predictive framework which integrates network science with data mining can forecast the LOS effectively at the PoA and provide decision support for hospital managers, which highlights the potential value of network-based machine learning in healthcare field.

Towards accurate prediction of patient length of stay at emergency department: a GAN-driven deep learning framework

Recently, the hospital systems face a high influx of patients generated by several events, such as seasonal flows or health crises related to epidemics (e.g., COVID'19). Despite the extent of the care demands, hospital establishments, particularly emergency departments (EDs), must admit patients for medical treatments. However, the high patient influx often increases patients' length of stay (LOS) and leads to overcrowding problems within the EDs. To mitigate this issue, hospital managers need to predict the patient's LOS, which is an essential indicator for assessing ED overcrowding and the use of the medical resources (allocation, planning, utilization rates). Thus, accurately predicting LOS is necessary to improve ED management. This paper proposes a deep learning-driven approach for predicting the patient LOS in ED using a generative adversarial network (GAN) model. The GAN-driven approach flexibly learns relevant information from linear and nonlinear processes without prior assumptions on data distribution and significantly enhances the prediction accuracy. Furthermore, we classified the predicted patients' LOS according to time spent at the pediatric emergency department (PED) to further help decision-making and prevent overcrowding. The experiments were conducted on actual data obtained from the PED in Lille regional hospital center, France. The GAN model results were compared with other deep learning models, including deep belief networks, convolutional neural network, stacked auto-encoder, and four machine learning models, namely support vector regression, random forests, adaboost, and decision tree. Results testify that deep learning models are suitable for predicting patient LOS and highlight GAN's superior performance than the other models.

Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

BACKGROUND

Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD).

OBJECTIVE

Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period.

METHODS

The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method.

RESULTS

The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R² from 0.3 to 0.6.

CONCLUSIONS

By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.

Machine learning using preoperative patient factors can predict duration of surgery and length of stay for total knee arthroplasty

BACKGROUND

Total knee arthroplasty (TKA) is one of the most resource-intensive, high-volume surgical procedures. Two drivers of the cost of TKAs are duration of surgery (DOS) and postoperative inpatient length of stay (LOS). The ability to predict TKA DOS and LOS has substantial implications for hospital finances, scheduling, and resource allocation. The goal of this study was to predict DOS and LOS for elective unilateral TKAs using machine learning models (MLMs) based on preoperative factors.

METHODS

The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for unilateral TKAs from 2014 to 2019. The dataset was split into training, validation, and testing based on year. Models (linear, tree-based, and multilayer perceptron (MLP)) were fitted to the training set in scikit-learn and PyTorch, with hyperparameters tuned on the validation set. The models were trained to minimize the mean squared error (MSE). Models with the best performance on the validation set were evaluated on the testing set according to 1) MSE, 2) buffer accuracy, and 3) classification accuracy, with results compared to a mean regressor.

RESULTS

A total of 302,300 patients were included in this study. During validation, the PyTorch MLPs had the best MSEs for DOS (0.918) and LOS (0.715). During testing, the PyTorch MLPs similarly performed best based on MSEs for DOS (0.896) and LOS (0.690). While the scikit-learn MLP yielded the best 30-minute buffer accuracy for DOS (78.8%), the PyTorch MLP provided the best 1-day buffer accuracy for LOS (75.2%). Nearly all the ML models were more accurate than the mean regressors for both DOS and LOS.

CONCLUSION

Conventional and deep learning models performed better than mean regressors for predicting DOS and LOS of unilateral elective TKA patients based on preoperative factors. Future work should include operational factors to improve overall predictions.

Improving patient flow during infectious disease outbreaks using machine learning for real-time prediction of patient readiness for discharge

BACKGROUND

Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis.

METHODS AND PERFORMANCE

Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients' real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models' inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within the following 24 hours. The 20% of patients with the highest ranking are considered as candidates for discharge and would therefore expect to have a further screening by a clinician to confirm whether they are ready for discharge or not. Performance was evaluated in terms of positive predictive value (PPV), i.e., the proportion of these patients who would have been correctly deemed as 'ready for discharge' after having the second screening by a clinician. Performance was high for patients on their first day of admission (PPV = 0.96/0.94 for planned/emergency patients respectively) but dropped for patients further into a longer admission (PPV = 0.66/0.71 for planned/emergency patients still in hospital after 7 days).

CONCLUSION

We demonstrate the efficacy of machine learning methods at making operationally focused, next-day discharge readiness predictions for all individual patients in hospital at any given moment and propose a strategy for their use within a decision-support tool during crisis periods.

Quantifying the impact of addressing data challenges in prediction of length of stay

BACKGROUND

Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower.

METHODS

In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender.

RESULTS

The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values.

CONCLUSION

We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.

Predicting in-hospital length of stay for very-low-birth-weight preterm infants using machine learning techniques

BACKGROUND/PURPOSE

The in-hospital length of stay (LOS) among very-low-birth-weight (VLBW, BW < 1500 g) infants is an index for care quality and affects medical resource allocation. We aimed to analyze the LOS among VLBW infants in Taiwan, and to develop and compare the performance of different LOS prediction models using machine learning (ML) techniques.

METHODS

This retrospective study illustrated LOS data from VLBW infants born between 2016 and 2018 registered in the Taiwan Neonatal Network. Among infants discharged alive, continuous variables (LOS or postmenstrual age, PMA) and categorical variables (late and non-late discharge group) were used as outcome variables to build prediction models. We used 21 early neonatal variables and six algorithms. The performance was compared using the coefficient of determination (R²) for continuous variables and area under the curve (AUC) for categorical variables.

RESULTS

A total of 3519 VLBW infants were included to illustrate the profile of LOS. We found 59% of mortalities occurred within the first 7 days after birth. The median of LOS among surviving and deceased infants was 62 days and 5 days. For the ML prediction models, 2940 infants were enrolled. Prediction of LOS or PMA had R² values less than 0.6. Among the prediction models for prolonged LOS, the logistic regression (ROC: 0.724) and random forest (ROC: 0.712) approach had better performance.

CONCLUSION

We provide a benchmark of LOS among VLBW infants in each gestational age group in Taiwan. ML technique can improve the accuracy of the prediction model of prolonged LOS of VLBW.

Hospital Length of Stay Prediction Methods: A Systematic Review

OBJECTIVE

This systematic review sought to establish a picture of length of stay (LOS) prediction methods based on available hospital data and study protocols designed to measure their performance.

MATERIALS AND METHODS

An English literature search was done relative to hospital LOS prediction from 1972 to September 2019 according to the PRISMA guidelines. Articles were retrieved from PubMed, ScienceDirect, and arXiv databases. Information were extracted from the included papers according to a standardized assessment of population setting and study sample, data sources and input variables, LOS prediction methods, validation study design, and performance evaluation metrics.

RESULTS

Among 74 selected articles, 98.6% (73/74) used patients' data to predict LOS; 27.0% (20/74) used temporal data; and 21.6% (16/74) used the data about hospitals. Overall, regressions were the most popular prediction methods (64.9%, 48/74), followed by machine learning (20.3%, 15/74) and deep learning (17.6%, 13/74). Regarding validation design, 35.1% (26/74) did not use a test set, whereas 47.3% (35/74) used a separate test set, and 17.6% (13/74) used cross-validation. The most used performance metrics were R2 (47.3%, 35/74), mean squared (or absolute) error (24.4%, 18/74), and the accuracy (14.9%, 11/74). Over the last decade, machine learning and deep learning methods became more popular (P=0.016), and test sets and cross-validation got more and more used (P=0.014).

CONCLUSIONS

Methods to predict LOS are more and more elaborate and the assessment of their validity is increasingly rigorous. Reducing heterogeneity in how these methods are used and reported is key to transparency on their performance.

Opening the black box: the promise and limitations of explainable machine learning in cardiology

Many clinicians remain wary of machine learning due to long-standing concerns about "black box" models. "Black box" is shorthand for models that are sufficiently complex that they are not straightforwardly interpretable to humans. Lack of interpretability in predictive models can undermine trust in those models, especially in health care where so many decisions are literally life and death. There has recently been an explosion of research in the field of explainable machine learning aimed at addressing these concerns. The promise of explainable machine learning is considerable, but it is important for cardiologists who may encounter these techniques in clinical decision support tools or novel research papers to have a critical understanding of both their strengths and their limitations. This paper reviews key concepts and techniques in the field of explainable machine learning as they apply to cardiology. Key concepts reviewed include interpretability versus explainability and global versus local explanations. Techniques demonstrated include permutation importance, surrogate decision trees, local interpretable model-agnostic explanations, and partial dependence plots. We discuss several limitations with explainability techniques, focusing on the how the nature of explanations as approximations may omit important information about how black box models work and why they make certain predictions. We conclude by proposing a rule of thumb about when it is appropriate to use black box models with explanations, rather than interpretable models.

Determinants of Prolonged Length of Hospital Stay of Patients with Atrial Fibrillation

Background and Aim: The increasing prevalence and high hospitalization rates make atrial fibrillation (AF) a significant healthcare strain. However, there are limited data regarding the length of hospital stay (LOS) of AF patients. Our purpose was to determine the main drivers of extended LOS of AF patients. Methods: All AF patients, hospitalized consecutively in a tertiary cardiology center, from January 2018 to February 2020 were included in this retrospective cohort study. Readmissions were excluded. Prolonged LOS was defined as more than seven days (the upper limit of the third quartile). Results: Our study included 949 AF patients, 52.9% females. The mean age was 72.5 ± 10.3 years. The median LOS was 4 days. A total of 28.7% had an extended LOS. Further, 82.9% patients had heart failure (HF). In multivariable analysis, the independent predictors of extended LOS were: acute coronary syndromes (ACS) (HR 4.60, 95% CI 1.66–12.69), infections (HR 2.61, 95% CI 1.44–3.23), NT-proBNP > 1986 ng/mL (HR 1.96, 95% CI 1.37–2.82), acute decompensated HF (ADHF) (HR 1.76, 95% CI 1.23–2.51), HF with reduced ejection fraction (HFrEF) (HR 1.69, 95% CI 1.15–2.47) and the HAS-BLED score (HR 1.42, 95% CI 1.14–1.78). Conclusion: ACS, ADHF, HFrEF, increased NT-proBNP levels, infections and elevated HAS-BLED were independent predictors of extended LOS, while specific clinical or therapeutical AF characteristics were not.

Machine learning in medicine: It has arrived, let's embrace it

Machine learning and artificial intelligence (AI) have arrived in medicine and the healthcare community is experiencing significant growth in their adoption across numerous patient care settings. There are countless applications for machine learning and AI in medicine ranging from patient outcome prediction, to clinical decision support, to predicting future patient therapeutic setpoints. This commentary discusses a recent application leveraging machine learning to predict one-year patient survival following orthotopic heart transplantation. This modeling approach has significant implications in terms of improving clinical decision-making, patient counseling, and ultimately organ allocation and has been shown to significantly outperform pre-existing algorithms. This commentary also discusses how adoption and advancement of this modeling approach in the future can provide increased personalization of patient care. The continued expansion of information systems and growth of electronic patient data sources in health care will continue to pave the way for increased use and adoption of data science in medicine. Personalized medicine has been a long-standing goal of the healthcare community and with machine learning and AI now being continually incorporated into clinical settings and practice, this technology is well on the pathway to make a considerable impact to greatly improve patient care in the near future.

Prolonged hospital length of stay in pediatric trauma: a model for targeted interventions

BACKGROUND

In this study, trauma-specific risk factors of prolonged length of stay (LOS) in pediatric trauma were examined. Statistical and machine learning models were used to proffer ways to improve the quality of care of patients at risk of prolonged length of stay and reduce cost.

METHODS

Data from 27 hospitals were retrieved on 81,929 hospitalizations of pediatric patients with a primary diagnosis of trauma, and for which the LOS was >24 h. Nested mixed effects model was used for simplified statistical inference, while a stochastic gradient boosting model, considering high-order statistical interactions, was built for prediction.

RESULTS

Over 18.7% of the encounters had LOS >1 week. Burns and corrosion and suspected and confirmed child abuse are the strongest drivers of prolonged LOS. Several other trauma-specific and general pediatric clinical variables were also predictors of prolonged LOS. The stochastic gradient model obtained an area under the receiver operator characteristic curve of 0.912 (0.907, 0.917).

CONCLUSIONS

The high performance of the machine learning model coupled with statistical inference from the mixed effects model provide an opportunity for targeted interventions to improve quality of care of trauma patients likely to require long length of stay.

IMPACT

Targeted interventions on high-risk patients would improve the quality of care of pediatric trauma patients and reduce the length of stay. This comprehensive study includes data from multiple hospitals analyzed with advanced statistical and machine learning models. The statistical and machine learning models provide opportunities for targeted interventions and reduction in prolonged length of stay reducing the burden of hospitalization on families.

Missing value imputation with linear methods in the database of cardiological patients in prediction of mortality

This study examines missing value imputation in the Russian Acute Coronary Syndrome Registry (RusACSR) and assessment of the probability of predicting mortality. Linear methods with the most probable or average value were used for imputation. The prediction problem was solved using the k-nearest neighbors method. This work reveals that the imputation method, despite their simplicity, increases the probability of prediction of mortality by 6%.

Prediction of arrhythmia after intervention in children with atrial septal defect based on random forest

BACKGROUND

Using random forest to predict arrhythmia after intervention in children with atrial septal defect.

METHODS

We constructed a prediction model of complications after interventional closure for children with atrial septal defect. The model was based on random forest, and it solved the need for postoperative arrhythmia risk prediction and assisted clinicians and patients' families to make preoperative decisions.

RESULTS

Available risk prediction models provided patients with specific risk factor assessments, we used Synthetic Minority Oversampling Technique algorithm and random forest machine learning to propose a prediction model, and got a prediction accuracy of 94.65 % and an Area Under Curve value of 0.8956.

CONCLUSIONS

Our study was based on the model constructed by random forest, which can effectively predict the complications of arrhythmia after interventional closure in children with atrial septal defect.

Predicting need for hospital-specific interventional care after surgery using electronic health record data

BACKGROUND

A significant proportion of surgical inpatients is often admitted longer than necessary. Early identification of patients who do not need care that is strictly provided within hospitals would allow timely discharge of patients to a postoperative nursing home for further recovery. We aimed to develop a model to predict whether a patient needs hospital-specific interventional care beyond the second postoperative day.

METHODS

This study included all adult patients discharged from surgical care in the surgical oncology department from June 2017 to February 2020. The primary outcome was to predict whether a patient still needs hospital-specific interventional care beyond the second postoperative day. Hospital-specific care was defined as unplanned reoperations, radiological interventions, and intravenous antibiotics administration. Different analytical methods were compared with respect to the area under the receiver-operating characteristics curve, sensitivity, specificity, positive predictive value, and negative predictive value.

RESULTS

Each model was trained on 1,174 episodes. In total, 847 (50.5%) patients required an intervention during postoperative admission. A random forest model performed best with an area under the receiver-operating characteristics curve of 0.88 (95% confidence interval 0.83-0.93), sensitivity of 79.1% (95% confidence interval 0.67-0.92), specificity of 80.0% (0.73-0.87), positive predictive value of 57.6% (0.45-0.70) and negative predictive value of 91.7% (0.87-0.97).

CONCLUSION

This proof-of-concept study found that a random forest model could successfully predict whether a patient could be safely discharged to a nursing home and does not need hospital care anymore. Such a model could aid hospitals in addressing capacity challenges and improve patient flow, allowing for timely surgical care.

Machine learning in patient flow: a review

This work is a review of the ways in which machine learning has been used in order to plan, improve or aid the problem of moving patients through healthcare services. We decompose the patient flow problem into four subcategories: prediction of demand on a healthcare institution, prediction of the demand and resource required to transfer patients from the emergency department to the hospital, prediction of potential resource required for the treatment and movement of inpatients and prediction of length-of-stay and discharge timing. We argue that there are benefits to both approaches of considering the healthcare institution as a whole as well as the patient by patient case and that ideally a combination of these would be best for improving patient flow through hospitals. We also argue that it is essential for there to be a shared dataset that will allow researchers to benchmark their algorithms on and thereby allow future researchers to build on that which has already been done. We conclude that machine learning for the improvement of patient flow is still a young field with very few papers tailor-making machine learning methods for the problem being considered. Future works should consider the need to transfer algorithms trained on a dataset to multiple hospitals and allowing for dynamic algorithms which will allow real-time decision-making to help clinical staff on the shop floor.

Health informatics publication trends in Saudi Arabia: a bibliometric analysis over the last twenty-four years

OBJECTIVE

Understanding health informatics (HI) publication trends in Saudi Arabia may serve as a framework for future research efforts and contribute toward meeting national "e-Health" goals. The authors' intention was to understand the state of the HI field in Saudi Arabia by exploring publication trends and their alignment with national goals.

METHODS

A scoping review was performed to identify HI publications from Saudi Arabia in PubMed, Embase, and Web of Science. We analyzed publication trends based on topics, keywords, and how they align with the Ministry of Health's (MOH's) "digital health journey" framework.

RESULTS

The total number of publications included was 242. We found 1 (0.4%) publication in 1995-1999, 11 (4.5%) publications in 2000-2009, and 230 (95.0%) publications in 2010-2019. We categorized publications into 3 main HI fields and 4 subfields: 73.1% (n=177) of publications were in clinical informatics (85.1%, n=151 medical informatics; 5.6%, n=10 pharmacy informatics; 6.8%, n=12 nursing informatics; 2.3%, n=4 dental informatics); 22.3% (n=54) were in consumer health informatics; and 4.5% (n=11) were in public health informatics. The most common keyword was "medical informatics" (21.5%, n=52). MOH framework-based analysis showed that most publications were categorized as "digitally enabled care" and "digital health foundations."

CONCLUSIONS

The years of 2000-2009 may be seen as an infancy stage of the HI field in Saudi Arabia. Exploring how the Saudi Arabian MOH's e-Health initiatives may influence research is valuable for advancing the field. Data exchange and interoperability, artificial intelligence, and intelligent health enterprises might be future research directions in Saudi Arabia.

Predicting Length of Stay of Coronary Artery Bypass Grafting Patients Using Machine Learning

BACKGROUND

There is a growing need to identify which bits of information are most valuable for healthcare providers. The aim of this study was to search for the highest impact variables in predicting postsurgery length of stay (LOS) for patients who undergo coronary artery bypass grafting (CABG).

MATERIALS AND METHODS

Using a single institution's Society of Thoracic Surgeons (STS) Registry data, 2121 patients with elective or urgent, isolated CABG were analyzed across 116 variables. Two machine learning techniques of random forest and artificial neural networks (ANNs) were used to search for the highest impact variables in predicting LOS, and results were compared against multiple linear regression. Out-of-sample validation of the models was performed on 105 patients.

RESULTS

Of the 10 highest impact variables identified in predicting LOS, four of the most impactful variables were duration intubated, last preoperative creatinine, age, and number of intraoperative packed red blood cell transfusions. The best performing model was an ANN using the ten highest impact variables (testing sample mean absolute error (MAE) = 1.685 d, R² = 0.232), which performed consistently in the out-of-sample validation (MAE = 1.612 d, R² = 0.150).

CONCLUSION

Using machine learning, this study identified several novel predictors of postsurgery LOS and reinforced certain known risk factors. Out of the entire STS database, only a few variables carry most of the predictive value for LOS in this population. With this knowledge, a simpler linear regression model has been shared and could be used elsewhere after further validation.

Machine Learning Can Predict Total Death After Radiofrequency Ablation in Liver Cancer Patients

Objective:

Over 1 million new cases of hepatocellular carcinoma (HCC) are diagnosed worldwide every year. Its prognosis remains poor, and the 5-year survival rate in all disease stages is estimated to be between 10% and 20%. Radiofrequency ablation (RFA) has become an important local treatment for liver cancer, and machine learning (ML) can provide many shortcuts for liver cancer medical research. Therefore, we explore the role of ML in predicting the total mortality of liver cancer patients undergoing RFA.

Methods:

This study is a secondary analysis of public database data from 578 liver cancer patients. We used Python for ML to establish the prognosis model.

Results:

The results showed that the 5 most important factors were platelet count (PLT), Alpha-fetoprotein (AFP), age, tumor size, and total bilirubin, respectively. Results of the total death model for liver cancer patients in test group: among the 5 algorithm models, the highest accuracy rate was that of gbm (0.681), followed by the Logistic algorithm (0.672); among the 5 algorithms, area under the curve (AUC) values, from high to low, were Logistic (0.738), DecisionTree (0.723), gbm (0.717), GradientBoosting (0.714), and Forest (0.693); Among the 5 algorithms, gbm had the highest precision rate (0.721), followed by the Logistic algorithm (0.714). Among the 5 algorithms, DecisionTree had the highest recall rate (0.642), followed by the GradientBoosting algorithm (0.571).

Conclusion:

Machine learning can predict total death after RFA in liver cancer patients. Therefore, ML research has great potential for both personalized treatment and prognosis of liver cancer.

Key Experimental Factors of Machine Learning-Based Identification of Surgery Cancellations

This study aimed to provide effective methods for the identification of surgeries with high cancellation risk based on machine learning models and analyze the key factors that affect the identification performance. The data covered the period from January 1, 2013, to December 31, 2014, at West China Hospital in China, which focus on elective urologic surgeries. All surgeries were scheduled one day in advance, and all cancellations were of institutional resource- and capacity-related types. Feature selection strategies, machine learning models, and sampling methods are the most discussed topic in general machine learning researches and have a direct impact on the performance of machine learning models. Hence, they were considered to systematically generate complete schemes in machine learning-based identification of surgery cancellations. The results proved the feasibility and robustness of identifying surgeries with high cancellation risk, with the considerable maximum of area under the curve (AUC) (0.7199) for random forest model with original sampling using backward selection strategy. In addition, one-side Delong test and sum of square error analysis were conducted to measure the effects of feature selection strategy, machine learning model, and sampling method on the identification of surgeries with high cancellation risk, and the selection of machine learning model was identified as the key factors that affect the identification of surgeries with high cancellation risk. This study offers methodology and insights for identifying the key experimental factors for identifying surgery cancellations, and it is helpful to further research on machine learning-based identification of surgeries with high cancellation risk.