Prediction of Chronic Disease-Related Inpatient Prolonged Length of Stay Using Machine Learning Algorithms

Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence

Introduction

Bipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.

Aim

To develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.

Methods

The study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.

Results

The admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.

Conclusion

ML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

Machine learning for predicting hepatitis B or C virus infection in diabetic patients

Highly prevalent hepatitis B and hepatitis C virus (HBV and HCV) infections have been reported among individuals with diabetes. Given the frequently asymptomatic nature of hepatitis and the challenges associated with screening in some vulnerable populations such as diabetes patients, we conducted an investigation into the performance of various machine learning models for the identification of hepatitis in diabetic patients while also evaluating the significance of features. Analyzing NHANES data from 2013 to 2018, machine learning models were evaluated; random forest (RF), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and least absolute shrinkage and selection operator (LASSO) along with stacked ensemble model. We performed hyperparameter tuning to improve the performance of the model, and selected important predictors using the best performance model. LASSO showed the highest predictive performance (AUC-ROC = 0.810) rather than other models. Illicit drug use, poverty, and race were highly ranked as predictive factors for developing hepatitis in diabetes patients. Our study demonstrated that a machine-learning-based model performed optimally in the detection of hepatitis among diabetes patients, achieving high performance. Furthermore, models and predictors evaluated from the current study, we expect, could be supportive information for developing screening or treatment methods for hepatitis care in diabetes patients.

Personalized prediction for multiple chronic diseases by developing the multi-task Cox learning model

Personalized prediction of chronic diseases is crucial for reducing the disease burden. However, previous studies on chronic diseases have not adequately considered the relationship between chronic diseases. To explore the patient-wise risk of multiple chronic diseases, we developed a multitask learning Cox (MTL-Cox) model for personalized prediction of nine typical chronic diseases on the UK Biobank dataset. MTL-Cox employs a multitask learning framework to train semiparametric multivariable Cox models. To comprehensively estimate the performance of the MTL-Cox model, we measured it via five commonly used survival analysis metrics: concordance index, area under the curve (AUC), specificity, sensitivity, and Youden index. In addition, we verified the validity of the MTL-Cox model framework in the Weihai physical examination dataset, from Shandong province, China. The MTL-Cox model achieved a statistically significant (p<0.05) improvement in results compared with competing methods in the evaluation metrics of the concordance index, AUC, sensitivity, and Youden index using the paired-sample Wilcoxon signed-rank test. In particular, the MTL-Cox model improved prediction accuracy by up to 12% compared to other models. We also applied the MTL-Cox model to rank the absolute risk of nine chronic diseases in patients on the UK Biobank dataset. This was the first known study to use the multitask learning-based Cox model to predict the personalized risk of the nine chronic diseases. The study can contribute to early screening, personalized risk ranking, and diagnosing of chronic diseases.

Hospital length of stay prediction tools for all hospital admissions and general medicine populations: systematic review and meta-analysis

Background

Unwarranted extended length of stay (LOS) increases the risk of hospital-acquired complications, morbidity, and all-cause mortality and needs to be recognized and addressed proactively.

Objective

This systematic review aimed to identify validated prediction variables and methods used in tools that predict the risk of prolonged LOS in all hospital admissions and specifically General Medicine (GenMed) admissions.

Method

LOS prediction tools published since 2010 were identified in five major research databases. The main outcomes were model performance metrics, prediction variables, and level of validation. Meta-analysis was completed for validated models. The risk of bias was assessed using the PROBAST checklist.

Results

Overall, 25 all admission studies and 14 GenMed studies were identified. Statistical and machine learning methods were used almost equally in both groups. Calibration metrics were reported infrequently, with only 2 of 39 studies performing external validation. Meta-analysis of all admissions validation studies revealed a 95% prediction interval for theta of 0.596 to 0.798 for the area under the curve. Important predictor categories were co-morbidity diagnoses and illness severity risk scores, demographics, and admission characteristics. Overall study quality was deemed low due to poor data processing and analysis reporting.

Conclusion

To the best of our knowledge, this is the first systematic review assessing the quality of risk prediction models for hospital LOS in GenMed and all admissions groups. Notably, both machine learning and statistical modeling demonstrated good predictive performance, but models were infrequently externally validated and had poor overall study quality. Moving forward, a focus on quality methods by the adoption of existing guidelines and external validation is needed before clinical application.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42021272198.

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.

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.

Predictability of Mortality in Patients With Myocardial Injury After Noncardiac Surgery Based on Perioperative Factors via Machine Learning: Retrospective Study

Background

Myocardial injury after noncardiac surgery (MINS) is associated with increased postoperative mortality, but the relevant perioperative factors that contribute to the mortality of patients with MINS have not been fully evaluated.

Objective

To establish a comprehensive body of knowledge relating to patients with MINS, we researched the best performing predictive model based on machine learning algorithms.

Methods

Using clinical data from 7629 patients with MINS from the clinical data warehouse, we evaluated 8 machine learning algorithms for accuracy, precision, recall, F1 score, area under the receiver operating characteristic (AUROC) curve, and area under the precision-recall curve to investigate the best model for predicting mortality. Feature importance and Shapley Additive Explanations values were analyzed to explain the role of each clinical factor in patients with MINS.

Results

Extreme gradient boosting outperformed the other models. The model showed an AUROC of 0.923 (95% CI 0.916-0.930). The AUROC of the model did not decrease in the test data set (0.894, 95% CI 0.86-0.922; P=.06). Antiplatelet drugs prescription, elevated C-reactive protein level, and beta blocker prescription were associated with reduced 30-day mortality.

Conclusions

Predicting the mortality of patients with MINS was shown to be feasible using machine learning. By analyzing the impact of predictors, markers that should be cautiously monitored by clinicians may be identified.

Identifying Children at Readmission Risk: At-Admission versus Traditional At-Discharge Readmission Prediction Model

The timing of 30-day pediatric readmissions is skewed with approximately 40% of the incidents occurring within the first week of hospital discharges. The skewed readmission time distribution coupled with delay in health information exchange among healthcare providers might offer a limited time to devise a comprehensive intervention plan. However, pediatric readmission studies are thus far limited to the development of the prediction model after hospital discharges. In this study, we proposed a novel pediatric readmission prediction model at the time of hospital admission which can improve the high-risk patient selection process. We also compared proposed models with the standard at-discharge readmission prediction model. Using the Hospital Cost and Utilization Project database, this prognostic study included pediatric hospital discharges in Florida from January 2016 through September 2017. Four machine learning algorithms—logistic regression with backward stepwise selection, decision tree, Support Vector machines (SVM) with the polynomial kernel, and Gradient Boosting—were developed for at-admission and at-discharge models using a recursive feature elimination technique with a repeated cross-validation process. The performance of the at-admission and at-discharge model was measured by the area under the curve. The performance of the at-admission model was comparable with the at-discharge model for all four algorithms. SVM with Polynomial Kernel algorithms outperformed all other algorithms for at-admission and at-discharge models. Important features associated with increased readmission risk varied widely across the type of prediction model and were mostly related to patients’ demographics, social determinates, clinical factors, and hospital characteristics. Proposed at-admission readmission risk decision support model could help hospitals and providers with additional time for intervention planning, particularly for those targeting social determinants of children’s overall health.

Health information technology to improve care for people with multiple chronic conditions

OBJECTIVE

To review evidence regarding the use of Health Information Technology (health IT) interventions aimed at improving care for people living with multiple chronic conditions (PLWMCC) in order to identify critical knowledge gaps.

DATA SOURCES

We searched MEDLINE, CINAHL, PsycINFO, EMBASE, Compendex, and IEEE Xplore databases for studies published in English between 2010 and 2020.

STUDY DESIGN

We identified studies of health IT interventions for PLWMCC across three domains as follows: self-management support, care coordination, and algorithms to support clinical decision making.

DATA COLLECTION/EXTRACTION METHODS

Structured search queries were created and validated. Abstracts were reviewed iteratively to refine inclusion and exclusion criteria. The search was supplemented by manually searching the bibliographic sections of the included studies. The search included a forward citation search of studies nested within a clinical trial to identify the clinical trial protocol and published clinical trial results. Data were extracted independently by two reviewers.

PRINCIPAL FINDINGS

The search yielded 1907 articles; 44 were included. Nine randomized controlled trials (RCTs) and 35 other studies including quasi-experimental, usability, feasibility, qualitative studies, or development/validation studies of analytic models were included. Five RCTs had positive results, and the remaining four RCTs showed that the interventions had no effect. The studies address individual patient engagement and assess patient-centered outcomes such as quality of life. Few RCTs assess outcomes such as disability and none assess mortality.

CONCLUSIONS

Despite a growing body of literature on health IT interventions or multicomponent interventions including a health IT component for chronic disease management, current evidence for applying health IT solutions to improve care for PLWMCC is limited. The body of literature included in this review provides critical information on the state of the science as well as the many gaps that need to be filled for digital health to fulfill its promise in supporting care delivery that meets the needs of PLWMCC.