A new analytical framework for missing data imputation and classification with uncertainty: Missing data imputation and heart failure readmission prediction

Application of machine learning techniques in population pharmacokinetics/pharmacodynamics modeling

Population pharmacokinetics/pharmacodynamics (pop-PK/PD) consolidates pharmacokinetic and pharmacodynamic data from many subjects to understand inter- and intra-individual variability due to patient backgrounds, including disease state and genetics. The typical workflow in pop-PK/PD analysis involves the determination of the structure model, selection of the error model, analysis based on the base model, covariate modeling, and validation of the final model. Machine learning is gaining considerable attention in the medical and various fields because, in contrast to traditional modeling, which often assumes linear or predefined relationships, machine learning modeling learns directly from data and accommodates complex patterns. Machine learning has demonstrated excellent capabilities for prescreening covariates and developing predictive models. This review introduces various applications of machine learning techniques in pop-PK/PD research.

Data-Fusion-Based Quality Enhancement for HR Measurements Collected by Wearable Sensors

The advancements of Internet of Things (IoT) technologies have enabled the implementation of smart and wearable sensors, which can be employed to provide older adults with affordable and accessible continuous biophysiological status monitoring. The quality of such monitoring data, however, is unsatisfactory due to excessive noise induced by various disturbances, such as motion artifacts. Existing methods take advantage of summary statistics, such as mean or median values, for denoising, without taking into account the biophysiological patterns embedded in data. In this research, a functional data analysis modeling method was proposed to enhance the data quality by learning individual subjects' diurnal heart rate (HR) patterns from historical data, which were further improved by fusing newly collected data. This proposed data-fusion approach was developed based on a Bayesian inference framework. Its effectiveness was demonstrated in an HR analysis from a prospective study involving older adults residing in assisted living or home settings. The results indicate that it is imperative to conduct personalized healthcare by estimating individualized HR patterns. Furthermore, the proposed calibration method provides a more accurate (smaller mean errors) and more precise (smaller error standard deviations) HR estimation than raw HR and conventional methods, such as the mean.

Missing data matter: an empirical evaluation of the impacts of missing EHR data in comparative effectiveness research

OBJECTIVES

The impacts of missing data in comparative effectiveness research (CER) using electronic health records (EHRs) may vary depending on the type and pattern of missing data. In this study, we aimed to quantify these impacts and compare the performance of different imputation methods.

MATERIALS AND METHODS

We conducted an empirical (simulation) study to quantify the bias and power loss in estimating treatment effects in CER using EHR data. We considered various missing scenarios and used the propensity scores to control for confounding. We compared the performance of the multiple imputation and spline smoothing methods to handle missing data.

RESULTS

When missing data depended on the stochastic progression of disease and medical practice patterns, the spline smoothing method produced results that were close to those obtained when there were no missing data. Compared to multiple imputation, the spline smoothing generally performed similarly or better, with smaller estimation bias and less power loss. The multiple imputation can still reduce study bias and power loss in some restrictive scenarios, eg, when missing data did not depend on the stochastic process of disease progression.

DISCUSSION AND CONCLUSION

Missing data in EHRs could lead to biased estimates of treatment effects and false negative findings in CER even after missing data were imputed. It is important to leverage the temporal information of disease trajectory to impute missing values when using EHRs as a data resource for CER and to consider the missing rate and the effect size when choosing an imputation method.

A classification framework using filter–wrapper based feature selection approach for the diagnosis of congenital heart failure

Premature mortality from cardiovascular disease can be reduced with early detection of heart failure by analysing the patients’ risk factors and assuring accurate diagnosis. This work proposes a clinical decision support system for the diagnosis of congenital heart failure by utilizing a data pre-processing approach for dealing missing values and a filter-wrapper based method for selecting the most relevant features. Missing values are imputed using a missForest method in four out of eight heart disease datasets collected from the Machine Learning Repository maintained by University of California, Irvine. The Fast Correlation Based Filter is used as the filter approach, while the union of the Atom Search Optimization Algorithm and the Henry Gas Solubility Optimization represent the wrapper-based algorithms, with the fitness function as the combination of accuracy, G-mean, and Matthew’s correlation coefficient measured by the Support Vector Machine. A total of four boosted classifiers namely, XGBoost, AdaBoost, CatBoost, and LightGBM are trained using the selected features. The proposed work achieves an accuracy of 89%, 84%, 83%, 80% for Heart Failure Clinical Records, 81%, 80%, 83%, 82% for Single Proton Emission Computed Tomography, 90%, 82%, 93%, 80% for Single Proton Emission Computed Tomography F, 80%, 80%, 81%, 80% for Statlog Heart Disease, 80%, 85%, 83%, 86% for Cleveland Heart Disease, 82%, 85%, 85%, 82% for Hungarian Heart Disease, 80%, 81%, 79%, 82% for VA Long Beach, 97%, 89%, 98%, 97%, for Switzerland Heart Disease for four classifiers respectively. The suggested technique outperformed the other classifiers when evaluated against Random Forest, Classification and Regression Trees, Support Vector Machine, and K-Nearest Neighbor.

Applying an Improved Stacking Ensemble Model to Predict the Mortality of ICU Patients with Heart Failure

Cardiovascular diseases have been identified as one of the top three causes of death worldwide, with onset and deaths mostly due to heart failure (HF). In ICU, where patients with HF are at increased risk of death and consume significant medical resources, early and accurate prediction of the time of death for patients at high risk of death would enable them to receive appropriate and timely medical care. The data for this study were obtained from the MIMIC-III database, where we collected vital signs and tests for 6699 HF patient during the first 24 h of their first ICU admission. In order to predict the mortality of HF patients in ICUs more precisely, an integrated stacking model is proposed and applied in this paper. In the first stage of dataset classification, the datasets were subjected to first-level classifiers using RF, SVC, KNN, LGBM, Bagging, and Adaboost. Then, the fusion of these six classifier decisions was used to construct and optimize the stacked set of second-level classifiers. The results indicate that our model obtained an accuracy of 95.25% and AUROC of 82.55% in predicting the mortality rate of HF patients, which demonstrates the outstanding capability and efficiency of our method. In addition, the results of this study also revealed that platelets, glucose, and blood urea nitrogen were the clinical features that had the greatest impact on model prediction. The results of this analysis not only improve the understanding of patients' conditions by healthcare professionals but allow for a more optimal use of healthcare resources.

Predicting the Mortality of ICU Patients by Topic Model with Machine-Learning Techniques

Predicting clinical patients’ vital signs is a leading critical issue in intensive care units (ICUs) related studies. Early prediction of the mortality of ICU patients can reduce the overall mortality and cost of complication treatment. Some studies have predicted mortality based on electronic health record (EHR) data by using machine learning models. However, the semi-structured data (i.e., patients’ diagnosis data and inspection reports) is rarely used in these models. This study utilized data from the Medical Information Mart for Intensive Care III. We used a Latent Dirichlet Allocation (LDA) model to classify text in the semi-structured data of some particular topics and established and compared the classification and regression trees (CART), logistic regression (LR), multivariate adaptive regression splines (MARS), random forest (RF), and gradient boosting (GB). A total of 46,520 ICU Patients were included, with 11.5% mortality in the Medical Information Mart for Intensive Care III group. Our results revealed that the semi-structured data (diagnosis data and inspection reports) of ICU patients contain useful information that can assist clinical doctors in making critical clinical decisions. In addition, in our comparison of five machine learning models (CART, LR, MARS, RF, and GB), the GB model showed the best performance with the highest area under the receiver operating characteristic curve (AUROC) (0.9280), specificity (93.16%), and sensitivity (83.25%). The RF, LR, and MARS models showed better performance (AUROC are 0.9096, 0.8987, and 0.8935, respectively) than the CART (0.8511). The GB model showed better performance than other machine learning models (CART, LR, MARS, and RF) in predicting the mortality of patients in the intensive care unit. The analysis results could be used to develop a clinically useful decision support system.

Prediction of unplanned 30-day readmission for ICU patients with heart failure

BACKGROUND

Intensive Care Unit (ICU) readmissions in patients with heart failure (HF) result in a significant risk of death and financial burden for patients and healthcare systems. Prediction of at-risk patients for readmission allows for targeted interventions that reduce morbidity and mortality.

METHODS AND RESULTS

We presented a process mining/deep learning approach for the prediction of unplanned 30-day readmission of ICU patients with HF. A patient's health records can be understood as a sequence of observations called event logs; used to discover a process model. Time information was extracted using the DREAM (Decay Replay Mining) algorithm. Demographic information and severity scores upon admission were then combined with the time information and fed to a neural network (NN) model to further enhance the prediction efficiency. Additionally, several machine learning (ML) algorithms were developed to be used as the baseline models for the comparison of the results.

RESULTS

By using the Medical Information Mart for Intensive Care III (MIMIC-III) dataset of 3411 ICU patients with HF, our proposed model yielded an area under the receiver operating characteristics (AUROC) of 0.930, 95% confidence interval of [0.898-0.960], the precision of 0.886, sensitivity of 0.805, accuracy of 0.841, and F-score of 0.800 which were far better than the results of the best baseline model and the existing literature.

CONCLUSIONS

The proposed approach was capable of modeling the time-related variables and incorporating the medical history of patients from prior hospital visits for prediction. Thus, our approach significantly improved the outcome prediction compared to that of other ML-based models and health calculators.

What can machines learn about heart failure? A systematic literature review

This paper presents a systematic literature review with respect to application of data science and machine learning (ML) to heart failure (HF) datasets with the intention of generating both a synthesis of relevant findings and a critical evaluation of approaches, applicability and accuracy in order to inform future work within this field. This paper has a particular intention to consider ways in which the low uptake of ML techniques within clinical practice could be resolved. Literature searches were performed on Scopus (2014-2021), ProQuest and Ovid MEDLINE databases (2014-2021). Search terms included ‘heart failure’ or ‘cardiomyopathy’ and ‘machine learning’, ‘data analytics’, ‘data mining’ or ‘data science’. 81 out of 1688 articles were included in the review. The majority of studies were retrospective cohort studies. The median size of the patient cohort across all studies was 1944 (min 46, max 93260). The largest patient samples were used in readmission prediction models with the median sample size of 5676 (min. 380, max. 93260). Machine learning methods focused on common HF problems: detection of HF from available dataset, prediction of hospital readmission following index hospitalization, mortality prediction, classification and clustering of HF cohorts into subgroups with distinctive features and response to HF treatment. The most common ML methods used were logistic regression, decision trees, random forest and support vector machines. Information on validation of models was scarce. Based on the authors’ affiliations, there was a median 3:1 ratio between IT specialists and clinicians. Over half of studies were co-authored by a collaboration of medical and IT specialists. Approximately 25% of papers were authored solely by IT specialists who did not seek clinical input in data interpretation. The application of ML to datasets, in particular clustering methods, enabled the development of classification models assisting in testing the outcomes of patients with HF. There is, however, a tendency to over-claim the potential usefulness of ML models for clinical practice. The next body of work that is required for this research discipline is the design of randomised controlled trials (RCTs) with the use of ML in an intervention arm in order to prospectively validate these algorithms for real-world clinical utility.

Assessing the Value of Unsupervised Clustering in Predicting Persistent High Health Care Utilizers: Retrospective Analysis of Insurance Claims Data

BACKGROUND

A high proportion of health care services are persistently utilized by a small subpopulation of patients. To improve clinical outcomes while reducing costs and utilization, population health management programs often provide targeted interventions to patients who may become persistent high users/utilizers (PHUs). Enhanced prediction and management of PHUs can improve health care system efficiencies and improve the overall quality of patient care.

OBJECTIVE

The aim of this study was to detect key classes of diseases and medications among the study population and to assess the predictive value of these classes in identifying PHUs.

METHODS

This study was a retrospective analysis of insurance claims data of patients from the Johns Hopkins Health Care system. We defined a PHU as a patient incurring health care costs in the top 20% of all patients' costs for 4 consecutive 6-month periods. We used 2013 claims data to predict PHU status in 2014-2015. We applied latent class analysis (LCA), an unsupervised clustering approach, to identify patient subgroups with similar diagnostic and medication patterns to differentiate variations in health care utilization across PHUs. Logistic regression models were then built to predict PHUs in the full population and in select subpopulations. Predictors included LCA membership probabilities, demographic covariates, and health utilization covariates. Predictive powers of the regression models were assessed and compared using standard metrics.

RESULTS

We identified 164,221 patients with continuous enrollment between 2013 and 2015. The mean study population age was 19.7 years, 55.9% were women, 3.3% had ≥1 hospitalization, and 19.1% had 10+ outpatient visits in 2013. A total of 8359 (5.09%) patients were identified as PHUs in both 2014 and 2015. The LCA performed optimally when assigning patients to four probability disease/medication classes. Given the feedback provided by clinical experts, we further divided the population into four diagnostic groups for sensitivity analysis: acute upper respiratory infection (URI) (n=53,232; 4.6% PHUs), mental health (n=34,456; 12.8% PHUs), otitis media (n=24,992; 4.5% PHUs), and musculoskeletal (n=24,799; 15.5% PHUs). For the regression models predicting PHUs in the full population, the F1-score classification metric was lower using a parsimonious model that included LCA categories (F1=38.62%) compared to that of a complex risk stratification model with a full set of predictors (F1=48.20%). However, the LCA-enabled simple models were comparable to the complex model when predicting PHUs in the mental health and musculoskeletal subpopulations (F1-scores of 48.69% and 48.15%, respectively). F1-scores were lower than that of the complex model when the LCA-enabled models were limited to the otitis media and acute URI subpopulations (45.77% and 43.05%, respectively).

CONCLUSIONS

Our study illustrates the value of LCA in identifying subgroups of patients with similar patterns of diagnoses and medications. Our results show that LCA-derived classes can simplify predictive models of PHUs without compromising predictive accuracy. Future studies should investigate the value of LCA-derived classes for predicting PHUs in other health care settings.

Current Trends in Readmission Prediction: An Overview of Approaches

Hospital readmission shortly after discharge threatens the quality of patient care and leads to increased medical care costs. In the United States, hospitals with high readmission rates are subject to federal financial penalties. This concern calls for incentives for healthcare facilities to reduce their readmission rates by predicting patients who are at high risk of readmission. Conventional practices involve the use of rule-based assessment scores and traditional statistical methods, such as logistic regression, in developing risk prediction models. The recent advancements in machine learning driven by improved computing power and sophisticated algorithms have the potential to produce highly accurate predictions. However, the value of such models could be overrated. Meanwhile, the use of other flexible models that leverage simple algorithms offer great transparency in terms of feature interpretation, which is beneficial in clinical settings. This work presents an overview of the current trends in risk prediction models developed in the field of readmission. The various techniques adopted by researchers in recent years are described, and the topic of whether complex models outperform simple ones in readmission risk stratification is investigated.