An integrated machine learning framework for hospital readmission prediction

Attention-Based Deep Learning Model for Prediction of Major Adverse Cardiovascular Events in Peritoneal Dialysis Patients

Major adverse cardiovascular events (MACE) encompass pivotal cardiovascular outcomes such as myocardial infarction, unstable angina, and cardiovascular-related mortality. Patients undergoing peritoneal dialysis (PD) exhibit specific cardiovascular risk factors during the treatment, which can escalate the likelihood of cardiovascular events. Hence, the prediction and key factor analysis of MACE have assumed paramount significance for peritoneal dialysis patients. Current pathological methodologies for prognosis prediction are not only costly but also cumbersome in effectively processing electronic health records (EHRs) data with high dimensionality, heterogeneity, and time series. Therefore in this study, we propose the CVEformer, an attention-based neural network designed to predict MACE and analyze risk factors. CVEformer leverages the self-attention mechanism to capture temporal correlations among time series variables, allowing for weighted integration of variables and estimation of the probability of MACE. CVEformer first captures the correlations among heterogeneous variables through attention scores. Then, it analyzes the correlations within the time series data to identify key risk variables and predict the probability of MACE. When trained and evaluated on data from a large cohort of peritoneal dialysis patients across multiple centers, CVEformer outperforms existing models in terms of predictive performance.

Machine learning based readmission and mortality prediction in heart failure patients

This study intends to predict in-hospital and 6-month mortality, as well as 30-day and 90-day hospital readmission, using Machine Learning (ML) approach via conventional features. A total of 737 patients remained after applying the exclusion criteria to 1101 heart failure patients. Thirty-four conventional features were collected for each patient. First, the data were divided into train and test cohorts with a 70-30% ratio. Then train data were normalized using the Z-score method, and its mean and standard deviation were applied to the test data. Subsequently, Boruta, RFE, and MRMR feature selection methods were utilized to select more important features in the training set. In the next step, eight ML approaches were used for modeling. Next, hyperparameters were optimized using tenfold cross-validation and grid search in the train dataset. All model development steps (normalization, feature selection, and hyperparameter optimization) were performed on a train set without touching the hold-out test set. Then, bootstrapping was done 1000 times on the hold-out test data. Finally, the obtained results were evaluated using four metrics: area under the ROC curve (AUC), accuracy (ACC), specificity (SPE), and sensitivity (SEN). The RFE-LR (AUC: 0.91, ACC: 0.84, SPE: 0.84, SEN: 0.83) and Boruta-LR (AUC: 0.90, ACC: 0.85, SPE: 0.85, SEN: 0.83) models generated the best results in terms of in-hospital mortality. In terms of 30-day rehospitalization, Boruta-SVM (AUC: 0.73, ACC: 0.81, SPE: 0.85, SEN: 0.50) and MRMR-LR (AUC: 0.71, ACC: 0.68, SPE: 0.69, SEN: 0.63) models performed the best. The best model for 3-month rehospitalization was MRMR-KNN (AUC: 0.60, ACC: 0.63, SPE: 0.66, SEN: 0.53) and regarding 6-month mortality, the MRMR-LR (AUC: 0.61, ACC: 0.63, SPE: 0.44, SEN: 0.66) and MRMR-NB (AUC: 0.59, ACC: 0.61, SPE: 0.48, SEN: 0.63) models outperformed the others. Reliable models were developed in 30-day rehospitalization and in-hospital mortality using conventional features and ML techniques. Such models can effectively personalize treatment, decision-making, and wiser budget allocation. Obtained results in 3-month rehospitalization and 6-month mortality endpoints were not astonishing and further experiments with additional information are needed to fetch promising results in these endpoints.

Interpretable machine learning models for hospital readmission prediction: a two-step extracted regression tree approach

BACKGROUND

Advanced machine learning models have received wide attention in assisting medical decision making due to the greater accuracy they can achieve. However, their limited interpretability imposes barriers for practitioners to adopt them. Recent advancements in interpretable machine learning tools allow us to look inside the black box of advanced prediction methods to extract interpretable models while maintaining similar prediction accuracy, but few studies have investigated the specific hospital readmission prediction problem with this spirit.

METHODS

Our goal is to develop a machine-learning (ML) algorithm that can predict 30- and 90- day hospital readmissions as accurately as black box algorithms while providing medically interpretable insights into readmission risk factors. Leveraging a state-of-art interpretable ML model, we use a two-step Extracted Regression Tree approach to achieve this goal. In the first step, we train a black box prediction algorithm. In the second step, we extract a regression tree from the output of the black box algorithm that allows direct interpretation of medically relevant risk factors. We use data from a large teaching hospital in Asia to learn the ML model and verify our two-step approach.

RESULTS

The two-step method can obtain similar prediction performance as the best black box model, such as Neural Networks, measured by three metrics: accuracy, the Area Under the Curve (AUC) and the Area Under the Precision-Recall Curve (AUPRC), while maintaining interpretability. Further, to examine whether the prediction results match the known medical insights (i.e., the model is truly interpretable and produces reasonable results), we show that key readmission risk factors extracted by the two-step approach are consistent with those found in the medical literature.

CONCLUSIONS

The proposed two-step approach yields meaningful prediction results that are both accurate and interpretable. This study suggests a viable means to improve the trust of machine learning based models in clinical practice for predicting readmissions through the two-step approach.

Predicting 30-day all-cause hospital readmission using multimodal spatiotemporal graph neural networks

Reduction in 30-day readmission rate is an important quality factor for hospitals as it can reduce the overall cost of care and improve patient post-discharge outcomes. While deep-learning-based studies have shown promising empirical results, several limitations exist in prior models for hospital readmission prediction, such as: (a) only patients with certain conditions are considered, (b) do not leverage data temporality, (c) individual admissions are assumed independent of each other, which ignores patient similarity, (d) limited to single modality or single center data. In this study, we propose a multimodal, spatiotemporal graph neural network (MM-STGNN) for prediction of 30-day all-cause hospital readmission, which fuses in-patient multimodal, longitudinal data and models patient similarity using a graph. Using longitudinal chest radiographs and electronic health records from two independent centers, we show that MM-STGNN achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 on both datasets. Furthermore, MM-STGNN significantly outperformed the current clinical reference standard, LACE+ (AUROC=0.61), on the internal dataset. For subset populations of patients with heart disease, our model significantly outperformed baselines, such as gradient-boosting and Long Short-Term Memory models (e.g., AUROC improved by 3.7 points in patients with heart disease). Qualitative interpretability analysis indicated that while patients' primary diagnoses were not explicitly used to train the model, features crucial for model prediction may reflect patients' diagnoses. Our model could be utilized as an additional clinical decision aid during discharge disposition and triaging high-risk patients for closer post-discharge follow-up for potential preventive measures.

Effective hospital readmission prediction models using machine-learned features

BACKGROUND

Hospital readmissions are one of the costliest challenges facing healthcare systems, but conventional models fail to predict readmissions well. Many existing models use exclusively manually-engineered features, which are labor intensive and dataset-specific. Our objective was to develop and evaluate models to predict hospital readmissions using derived features that are automatically generated from longitudinal data using machine learning techniques.

METHODS

We studied patients discharged from acute care facilities in 2015 and 2016 in Alberta, Canada, excluding those who were hospitalized to give birth or for a psychiatric condition. We used population-level linked administrative hospital data from 2011 to 2017 to train prediction models using both manually derived features and features generated automatically from observational data. The target value of interest was 30-day all-cause hospital readmissions, with the success of prediction measured using the area under the curve (AUC) statistic.

RESULTS

Data from 428,669 patients (62% female, 38% male, 27% 65 years or older) were used for training and evaluating models: 24,974 (5.83%) were readmitted within 30 days of discharge for any reason. Patients were more likely to be readmitted if they utilized hospital care more, had more physician office visits, had more prescriptions, had a chronic condition, or were 65 years old or older. The LACE readmission prediction model had an AUC of 0.66 ± 0.0064 while the machine learning model's test set AUC was 0.83 ± 0.0045, based on learning a gradient boosting machine on a combination of machine-learned and manually-derived features.

CONCLUSION

Applying a machine learning model to the computer-generated and manual features improved prediction accuracy over the LACE model and a model that used only manually-derived features. Our model can be used to identify high-risk patients, for whom targeted interventions may potentially prevent readmissions.

Predictive Modeling of Hospital Readmission: Challenges and Solutions

Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, e.g. 30 or 90 days, after the discharge. The motivation is to help health providers deliver better treatment and post-discharge strategies, lower the hospital readmission rate, and eventually reduce the medical costs. Due to inherent complexity of diseases and healthcare ecosystems, modeling hospital readmission is facing many challenges. By now, a variety of methods have been developed, but existing literature fails to deliver a complete picture to answer some fundamental questions, such as what are the main challenges and solutions in modeling hospital readmission; what are typical features/models used for readmission prediction; how to achieve meaningful and transparent predictions for decision making; and what are possible conflicts when deploying predictive approaches for real-world usages. In this paper, we systematically review computational models for hospital readmission prediction, and propose a taxonomy of challenges featuring four main categories: (1) data variety and complexity; (2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation. The review summarizes methods in each category, and highlights technical solutions proposed to address the challenges. In addition, a review of datasets and resources available for hospital readmission modeling also provides firsthand materials to support researchers and practitioners to design new approaches for effective and efficient hospital readmission prediction.

Leveraging Advanced Data Analytics to Predict the Risk of All-Cause Seven-Day Emergency Readmissions

Introduction

Emergency readmissions have been a long-time, multifaceted, unsolved problem. Developing a predictive model calibrated with hospital-specific Electronic Health Record (EHR) data could give higher prediction accuracy and insights into high-risk patients for readmission. Thus, we need to proactively introduce the necessary interventions. This study aims to investigate the relationship between features that consider significant predictors of at-risk patients for seven-day readmission through logistic regression in addition to developing several machine learning models to test the predictability of those attributes using EHR data in a Saudi Arabia-specific ED context.

Methods

Univariate and multivariate logistic regression has been used to identify the most statistically significant features that contributed to classifying readmitted and not readmitted patients. Seven different machine learning models were trained and tested, and a comparison between the best-performing model was conducted in terms of five performance metrics. To construct the prediction model and internally validate it, the processed dataset was split into two sets: 70% for the training set and 30% for the test set or validation set.

Results

XGBoost achieved the highest accuracy (64%) in predicting early seven-day readmissions. Catboost was the second-best predictive model at 61%. XGBoost achieved the highest specificity at 70%, and all the models had a sensitivity of 57% except for XGBoost and Catboost at 32% and 38%, respectively. All predictive attributes, patient age, length of stay (LOS) in minutes, visit time (AM), marital status (married), number of medications, and number of abnormal lab results were significant predictors of early seven-day readmissions while marital status and number of vital-sign instabilities at discharge were not statistically significant predictors of seven-day readmission.

Conclusion

Although XGBoost and Catboost showed good accuracy, none of the models achieved good discriminative ability in terms of sensitivity and specificity. Thus, none can be clinically used for predicting early seven-day readmission. More predictive variables need to be fed into the model, specifically predictors approximate to the day of discharge, in order to optimize the model’s performance.

A Prospective Observational Study Assessing the Impacts of Health Literacy and Psychosocial Determinants of Health on 30-day Readmission Risk

Our objective was to assess the utility of an assessment battery capturing health literacy (HL) and biopsychosocial determinants of health in predicting 30-day readmission in comparison to a currently well-adopted readmission risk calculator. We also sought to capture the distribution of inpatient HL, with emphasis on inadequate and marginal HL (an intermediate HL level). A prospective observational study was conducted to obtain HL and biopsychosocial data on general medicine inpatients admitted to the UCLA health system. Five hundred thirty-seven subjects were tracked prospectively for 30-day readmission after index hospitalization. HL was significantly better at predicting readmission compared to LACE + (Length, admission acuity, comorbidities, emergency room visits) alone (P = .013). A multivariate model including education, insurance, and language comfort was a strong predictor of adequate HL (P < .001). In conclusion, HL offered significant improvement in risk stratification in comparison to LACE + alone. Patients with marginal HL were high-risk, albeit difficult to characterize. Incorporating robust HL and biopsychosocial determinant assessments may allow hospital systems to allocate educational resources towards at-risk patients, thereby mitigating readmission risk.

AI Models for Predicting Readmission of Pneumonia Patients within 30 Days after Discharge

A model with capability for precisely predicting readmission is a target being pursued worldwide. The objective of this study is to design predictive models using artificial intelligence methods and data retrieved from the National Health Insurance Research Database of Taiwan for identifying high-risk pneumonia patients with 30-day all-cause readmissions. An integrated genetic algorithm (GA) and support vector machine (SVM), namely IGS, were used to design predictive models optimized with three objective functions. In IGS, GA was used for selecting salient features and optimal SVM parameters, while SVM was used for constructing the models. For comparison, logistic regression (LR) and deep neural network (DNN) were also applied for model construction. The IGS model with AUC used as the objective function achieved an accuracy, sensitivity, specificity, and area under ROC curve (AUC) of 70.11%, 73.46%, 69.26%, and 0.7758, respectively, outperforming the models designed with LR (65.77%, 78.44%, 62.54%, and 0.7689, respectively) and DNN (61.50%, 79.34%, 56.95%, and 0.7547, respectively), as well as previously reported models constructed using thedata of electronic health records with an AUC of 0.71–0.74. It can be used for automatically detecting pneumonia patients with a risk of all-cause readmissions within 30 days after discharge so as to administer suitable interventions to reduce readmission and healthcare costs.

Time-Aware Multi-Type Data Fusion Representation Learning Framework for Risk Prediction of Cardiovascular Diseases

Predicting the future risk of cardiovascular diseases from the historical Electronic Health Records (EHRs) is a significant research task in personalized healthcare fields. In recent years, many deep neural network-based methods have emerged, which model patient disease progression by capturing the temporal patterns in sequential visit data. However, existing methods usually cannot effectively integrate the features of heterogeneous clinical data, and do not fully consider the impact of patients age and irregular time interval between consecutive medical records on the patients disease development. To address these challenges, we propose a Time-Aware Multi-type Data fUsion Representation learning framework (TAMDUR) for CVDs risk prediction. In this framework, we design a time-aware decay function, which is based on the patients age and the elapsed time between visits, to model the disease progression pattern. A parallel combination of Bi LSTM and CNN is constructed to respectively learn the temporal and non-temporal features from various types of clinical data. Finally, a multi-type data fusion representation layer based on self-attention is utilized to integrate various features and their correlations to obtain the final patient representation. We evaluate our model on a real medical dataset, and the experimental results demonstrate that TAMDUR outperforms the state-of-the-art approaches.

Development of Prediction Models for Unplanned Hospital Readmission within 30 Days Based on Common Data Model: A Feasibility Study

Background  Unplanned hospital readmission after discharge reflects low satisfaction and reliability in care and the possibility of potential medical accidents, and is thus indicative of the quality of patient care and the appropriateness of discharge plans.

Objectives  The purpose of this study was to develop and validate prediction models for all-cause unplanned hospital readmissions within 30 days of discharge, based on a common data model (CDM), which can be applied to multiple institutions for efficient readmission management.

Methods  Retrospective patient-level prediction models were developed based on clinical data of two tertiary general university hospitals converted into a CDM developed by Observational Medical Outcomes Partnership. Machine learning classification models based on the LASSO logistic regression model, decision tree, AdaBoost, random forest, and gradient boosting machine (GBM) were developed and tested by manipulating a set of CDM variables. An internal 10-fold cross-validation was performed on the target data of the model. To examine its transportability, the model was externally validated. Verification indicators helped evaluate the model performance based on the values of area under the curve (AUC).

Results  Based on the time interval for outcome prediction, it was confirmed that the prediction model targeting the variables obtained within 30 days of discharge was the most efficient (AUC of 82.75). The external validation showed that the model is transferable, with the combination of various clinical covariates. Above all, the prediction model based on the GBM showed the highest AUC performance of 84.14 ± 0.015 for the Seoul National University Hospital cohort, yielding in 78.33 in external validation.

Conclusions  This study showed that readmission prediction models developed using machine-learning techniques and CDM can be a useful tool to compare two hospitals in terms of patient-data features.

Predictive modelling of hospital readmission: Evaluation of different preprocessing techniques on machine learning classifiers

Hospital readmission is a major cost for healthcare systems worldwide. If patients with a higher potential of readmission could be identified at the start, existing resources could be used more efficiently, and appropriate plans could be implemented to reduce the risk of readmission. Therefore, it is important to predict the right target patients. Medical data is usually noisy, incomplete, and inconsistent. Hence, before developing a prediction model, it is crucial to efficiently set up the predictive model so that improved predictive performance is achieved. The current study aims to analyse the impact of different preprocessing methods on the performance of different machine learning classifiers. The preprocessing applied by previous hospital readmission studies were compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling. The hyperparameters were selected using Bayesian optimisation. The different preprocessing pipelines were assessed using various performance metrics and computational costs. The results indicated that the preprocessing approaches helped improve the model’s prediction of hospital readmission.

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.

High-Risk Prediction of Cardiovascular Diseases via Attention-Based Deep Neural Networks

High-risk prediction of cardiovascular disease is of great significance and impendency in medical fields with the increasing phenomenon of sub-health these years. Most existing pathological methods for the prognosis prediction are either costly or prone to misjudgement. Therefore, plenty of automated models based on machine learning have been proposed to predict the onset of cardiovascular disease with the premorbid information of patients extracted from their historical Electronic Health Records (EHRs). However, it is a tough job to select proper features from longitudinal and heterogeneous EHRs, and also a great challenge to obtain accurate and robust representations for patients. In this paper, we propose an entirely end-to-end model called DeepRisk based on attention mechanism and deep neural networks, which can not only learn high-quality features automatically from EHRs, but also efficiently integrate heterogeneous and time-ordered medical data, and finally predict patients' risk of cardiovascular diseases. Experiments are carried out on a real medical dataset and results show that DeepRisk can significantly improve the high-risk prediction accuracy for cardiovascular disease compared with state-of-the-art approaches.