The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors

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.

Predicting the Length of Stay of Cardiac Patients Based on Pre-Operative Variables-Bayesian Models vs. Machine Learning Models

Length of stay (LoS) prediction is deemed important for a medical institution's operational and logistical efficiency. Sound estimates of a patient's stay increase clinical preparedness and reduce aberrations. Various statistical methods and techniques are used to quantify and predict the LoS of a patient based on pre-operative clinical features. This study evaluates and compares the results of Bayesian (simple Bayesian regression and hierarchical Bayesian regression) models and machine learning (ML) regression models against multiple evaluation metrics for the problem of LoS prediction of cardiac patients admitted to Tabba Heart Institute, Karachi, Pakistan (THI) between 2015 and 2020. In addition, the study also presents the use of hierarchical Bayesian regression to account for data variability and skewness without homogenizing the data (by removing outliers). LoS estimates from the hierarchical Bayesian regression model resulted in a root mean squared error (RMSE) and mean absolute error (MAE) of 1.49 and 1.16, respectively. Simple Bayesian regression (without hierarchy) achieved an RMSE and MAE of 3.36 and 2.05, respectively. The average RMSE and MAE of ML models remained at 3.36 and 1.98, respectively.

Causal determinants of postoperative length of stay in cardiac surgery using causal graphical learning

OBJECTIVE

We aimed to learn the causal determinants of postoperative length of stay in cardiac surgery patients undergoing isolated coronary artery bypass grafting or aortic valve replacement surgery.

METHODS

For patients undergoing isolated coronary artery bypass grafting or isolated aortic valve replacement surgeries between 2011 and 2016, we used causal graphical modeling on electronic health record data. The Fast Causal Inference (FCI) algorithm from the Tetrad software was used on data to estimate a Partial Ancestral Graph (PAG) depicting direct and indirect causes of postoperative length of stay, given background clinical knowledge. Then, we used the latent variable intervention-calculus when the directed acyclic graph is absent (LV-IDA) algorithm to estimate strengths of causal effects of interest. Finally, we ran a linear regression for postoperative length of stay to contrast statistical associations with what was learned by our causal analysis.

RESULTS

In our cohort of 2610 patients, the mean postoperative length of stay was 219 hours compared with the Society of Thoracic Surgeons 2016 national mean postoperative length of stay of approximately 168 hours. Most variables that clinicians believe to be predictors of postoperative length of stay were found to be causes, but some were direct (eg, age, diabetes, hematocrit, total operating time, and postoperative complications), and others were indirect (including gender, race, and operating surgeon). The strongest average causal effects on postoperative length of stay were exhibited by preoperative dialysis (209 hours); neuro-, pulmonary-, and infection-related postoperative complications (315 hours, 89 hours, and 131 hours, respectively); reintubation (61 hours); extubation in operating room (-47 hours); and total operating room duration (48 hours). Linear regression coefficients diverged from causal effects in magnitude (eg, dialysis) and direction (eg, crossclamp time).

CONCLUSIONS

By using retrospective electronic health record data and background clinical knowledge, causal graphical modeling retrieved direct and indirect causes of postoperative length of stay and their relative strengths. These insights will be useful in designing clinical protocols and targeting improvements in patient management.

Adoption of machine learning algorithm for predicting the length of stay of patients (construction workers) during COVID pandemic

The construction sector in a rapidly developing country like India is a very unorganized sector. A large number of workers were affected and hospitalized during the pandemic. This situation is costing the sector heavily in several respects. This research study was conducted as part of using machine learning algorithms to improve construction company health and safety policies. LOS (length of stay) is used to predict how long a patient will stay in a hospital. Predicting LOS is very useful not only for hospitals, but also for construction companies to measure resources and reduce costs. Predicting LOS has become an important step in most hospitals before admitting patients. In this post, we used the Medical Information Mart for Intensive Care(MIMIC III) dataset and applied four different machine learning algorithms: decision tree classifier, random forest, Artificial Neural Network (ANN), and logistic regression. First, I performed data pre-processing to clean up the dataset. In the next step, we performed function selection using the Select Best algorithm with an evaluation function of chi2 to perform hot coding. We then performed a split between training and testing and applied a machine learning algorithm. The metric used for comparison was accuracy. After implementing the algorithms, the accuracy was compared. Random forest was found to perform best at 89%. Afterwards, we performed hyperparameter tuning using a grid search algorithm on a random forest to obtain higher accuracy. The final accuracy is 90%. This kind of research can help improve health security policies by introducing modern computational techniques, and can also help optimize resources.

Machine learning using institution-specific multi-modal electronic health records improves mortality risk prediction for cardiac surgery patients

Background

The Society of Thoracic Surgeons risk scores are widely used to assess risk of morbidity and mortality in specific cardiac surgeries but may not perform optimally in all patients. In a cohort of patients undergoing cardiac surgery, we developed a data-driven, institution-specific machine learning-based model inferred from multi-modal electronic health records and compared the performance with the Society of Thoracic Surgeons models.

Methods

All adult patients undergoing cardiac surgery between 2011 and 2016 were included. Routine electronic health record administrative, demographic, clinical, hemodynamic, laboratory, pharmacological, and procedural data features were extracted. The outcome was postoperative mortality. The database was randomly split into training (development) and test (evaluation) cohorts. Models developed using 4 classification algorithms were compared using 6 evaluation metrics. The performance of the final model was compared with the Society of Thoracic Surgeons models for 7 index surgical procedures.

Results

A total of 6392 patients were included and described by 4016 features. Overall mortality was 3.0% (n = 193). The XGBoost algorithm using only features with no missing data (336 features) yielded the best-performing predictor. When applied to the test set, the predictor performed well (F-measure = 0.775; precision = 0.756; recall = 0.795; accuracy = 0.986; area under the receiver operating characteristic curve = 0.978; area under the precision-recall curve = 0.804). eXtreme Gradient Boosting consistently demonstrated improved performance over the Society of Thoracic Surgeons models when evaluated on index procedures within the test set.

Conclusions

Machine learning models using institution-specific multi-modal electronic health records may improve performance in predicting mortality for individual patients undergoing cardiac surgery compared with the standard-of-care, population-derived Society of Thoracic Surgeons models. Institution-specific models may provide insights complementary to population-derived risk predictions to aid patient-level decision making.

Improving Hospital Outpatient Clinics Appointment Schedules by Prediction Models

Patient no-shows and suboptimal patient appointment length scheduling reduce clinical efficiency and impair the clinic's quality of service. The main objective of this study is to improve appointment scheduling in hospital outpatient clinics. We developed generic supervised machine learning models to predict patient no-shows and patient's length of appointment (LOA). We performed a retrospective study using more than 100,000 records of patient appointments in a hospital outpatient clinic. Several machine learning algorithms were used for the development of our prediction models. We trained our models on a dataset that contained patients', physicians', and appointments' characteristics. Our feature set combines both unstudied features and features adopted from previous studies. In addition, we identified the influential features for predicting LOA and no-show. Our LOA model's performance was 6.92 in terms of MAE, and our no-show model's performance was 92.1% in terms of F-score. We compared our models' performance to the performance of previous research models by applying their methods to our dataset; our models demonstrated better performance. We show that the major effector of such differences is the use of our novel features. To evaluate the effect of our prediction results on the quality of schedules produced by appointment systems (AS), we developed an interface layer between our prediction models and the AS, where prediction results comprise the AS input. Using our prediction models, there was an 80% improvement in the daily cumulative patient waiting time and a 33% reduction in the daily cumulative physician idle time.

Stratification of Length of Stay Prediction following Surgical Cytoreduction in Advanced High-Grade Serous Ovarian Cancer Patients Using Artificial Intelligence; the Leeds L-AI-OS Score

(1) Background: Length of stay (LOS) has been suggested as a marker of the effectiveness of short-term care. Artificial Intelligence (AI) technologies could help monitor hospital stays. We developed an AI-based novel predictive LOS score for advanced-stage high-grade serous ovarian cancer (HGSOC) patients following cytoreductive surgery and refined factors significantly affecting LOS. (2) Methods: Machine learning and deep learning methods using artificial neural networks (ANN) were used together with conventional logistic regression to predict continuous and binary LOS outcomes for HGSOC patients. The models were evaluated in a post-hoc internal validation set and a Graphical User Interface (GUI) was developed to demonstrate the clinical feasibility of sophisticated LOS predictions. (3) Results: For binary LOS predictions at differential time points, the accuracy ranged between 70-98%. Feature selection identified surgical complexity, pre-surgery albumin, blood loss, operative time, bowel resection with stoma formation, and severe postoperative complications (CD3-5) as independent LOS predictors. For the GUI numerical LOS score, the ANN model was a good estimator for the standard deviation of the LOS distribution by ± two days. (4) Conclusions: We demonstrated the development and application of both quantitative and qualitative AI models to predict LOS in advanced-stage EOC patients following their cytoreduction. Accurate identification of potentially modifiable factors delaying hospital discharge can further inform services performing root cause analysis of LOS.

Time-to-event modeling for hospital length of stay prediction for COVID-19 patients

Providing timely patient care while maintaining optimal resource utilization is one of the central operational challenges hospitals have been facing throughout the pandemic. Hospital length of stay (LOS) is an important indicator of hospital efficiency, quality of patient care, and operational resilience. Numerous researchers have developed regression or classification models to predict LOS. However, conventional models suffer from the lack of capability to make use of typically censored clinical data. We propose to use time-to-event modeling techniques, also known as survival analysis, to predict the LOS for patients based on individualized information collected from multiple sources. The performance of six proposed survival models is evaluated and compared based on clinical data from COVID-19 patients.

A systematic review of the prediction of hospital length of stay: Towards a unified framework

Hospital length of stay of patients is a crucial factor for the effective planning and management of hospital resources. There is considerable interest in predicting the LoS of patients in order to improve patient care, control hospital costs and increase service efficiency. This paper presents an extensive review of the literature, examining the approaches employed for the prediction of LoS in terms of their merits and shortcomings. In order to address some of these problems, a unified framework is proposed to better generalise the approaches that are being used to predict length of stay. This includes the investigation of the types of routinely collected data used in the problem as well as recommendations to ensure robust and meaningful knowledge modelling. This unified common framework enables the direct comparison of results between length of stay prediction approaches and will ensure that such approaches can be used across several hospital environments. A literature search was conducted in PubMed, Google Scholar and Web of Science from 1970 until 2019 to identify LoS surveys which review the literature. 32 Surveys were identified, from these 32 surveys, 220 papers were manually identified to be relevant to LoS prediction. After removing duplicates, and exploring the reference list of studies included for review, 93 studies remained. Despite the continuing efforts to predict and reduce the LoS of patients, current research in this domain remains ad-hoc; as such, the model tuning and data preprocessing steps are too specific and result in a large proportion of the current prediction mechanisms being restricted to the hospital that they were employed in. Adopting a unified framework for the prediction of LoS could yield a more reliable estimate of the LoS as a unified framework enables the direct comparison of length of stay methods. Additional research is also required to explore novel methods such as fuzzy systems which could build upon the success of current models as well as further exploration of black-box approaches and model interpretability.

Machine learning methods for perioperative anesthetic management in cardiac surgery patients: a scoping review

Background

Machine learning (ML) is developing fast with promising prospects within medicine and already has several applications in perioperative care. We conducted a scoping review to examine the extent and potential limitations of ML implementation in perioperative anesthetic care, specifically in cardiac surgery patients.

Methods

We mapped the current literature by searching three databases: MEDLINE (Ovid), EMBASE (Ovid), and Cochrane Library. Articles were eligible if they reported on perioperative ML use in the field of cardiac surgery with relevance to anesthetic practices. Data on the applicability of ML and comparability to conventional statistical methods were extracted.

Results

Forty-six articles on ML relevant to the work of the anesthesiologist in cardiac surgery were identified. Three main categories emerged: (I) event and risk prediction, (II) hemodynamic monitoring, and (III) automation of echocardiography. Prediction models based on ML tend to behave similarly to conventional statistical methods. Using dynamic hemodynamic or ultrasound data in ML models, however, shifts the potential to promising results.

Conclusions

ML in cardiac surgery is increasingly used in perioperative anesthetic management. The majority is used for prediction purposes similar to conventional clinical scores. Remarkable ML model performances are achieved when using real-time dynamic parameters. However, beneficial clinical outcomes of ML integration have yet to be determined. Nonetheless, the first steps introducing ML in perioperative anesthetic care for cardiac surgery have been taken.

Machine Learning-Based Risk Prediction of Critical Care Unit Admission for Advanced Stage High Grade Serous Ovarian Cancer Patients Undergoing Cytoreductive Surgery: The Leeds-Natal Score

Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful in monitoring CCU admissions to improve standards of care. We aimed to improve the accuracy of predicting CCU admission in HGSOC patients by ML algorithms and developed an ML-based predictive score. A cohort of 291 advanced stage HGSOC patients with fully curated data was selected. Several linear and non-linear distances, and quadratic discriminant ML methods, were employed to derive prediction information for CCU admission. When all the variables were included in the model, the prediction accuracies were higher for linear discriminant (0.90) and quadratic discriminant (0.93) methods compared with conventional logistic regression (0.84). Feature selection identified pre-treatment albumin, surgical complexity score, estimated blood loss, operative time, and bowel resection with stoma as the most significant prediction features. The real-time prediction accuracy of the Graphical User Interface CCU calculator reached 95%. Limited, potentially modifiable, mostly intra-operative factors contributing to CCU admission were identified and suggest areas for targeted interventions. The accurate quantification of CCU admission patterns is critical information when counseling patients about peri-operative risks related to their cytoreductive surgery.

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

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

The Use of Artificial Neural Networks to Determine In-Hospital Mortality After Coronary Artery Bypass Surgery

OBJECTIVES

The aim of this study was to present an artificial neural network (ANN) model for the accurate estimation of in-hospital mortality and to demonstrate the validity of the model with real data and a comparison with conventional multiple linear regression models.

DESIGN

Retrospective clinical study.

SETTING

University hospital.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Data were collected from the medical records of 88 patients who had undergone coronary artery bypass graft surgery with an extracorporeal cardiopulmonary pump between January 2018 and March 2020. An ANN approach was used to assess the association between in-hospital mortality and variables from preoperative, intraoperative, and postoperative data garnered retrospectively from patient files. The study examined the data of 88 patients with a mean age of 62.4 ± ten years, 60 (68.1%) of whom were men and 28 (31.8%) of whom were women. An examination of the average success of the training algorithms in the training, validation, and test sets revealed that the quick propagation algorithm ranked first with 97.397%. The algorithm that best matched the present study's dataset was the batch back propagation algorithm, with an average of 99.622 (in other words, this training set accurately estimated 99.622% of every 100 items of data). Furthermore, the rates continuously were greater than 90% when the probability of estimating the estimated output was examined.

CONCLUSION

The ANN model tended to outperform multiple linear regression models in predicting in-hospital mortality among patients who have undergone coronary artery bypass graft surgery. Physicians can make use of this information as an aid in performing treatments and ensuring that more accurate quality of surgical care is achieved.

Length of hospital stay prediction with an integrated approach of statistical-based fuzzy cognitive maps and artificial neural networks

Chronic obstructive pulmonary disease (COPD) is a global burden, which is estimated to be the third leading cause of death worldwide by 2030. The economic burden of COPD grows continuously because it is not a curable disease. These conditions make COPD an important research field of artificial intelligence (AI) techniques in medicine. In this study, an integrated approach of the statistical-based fuzzy cognitive maps (SBFCM) and artificial neural networks (ANN) is proposed for predicting length of hospital stay of patients with COPD, who admitted to the hospital with an acute exacerbation. The SBFCM method is developed to determine the input variables of the ANN model. The SBFCM conducts statistical analysis to prepare preliminary information for the experts and then collects expert opinions accordingly, to define a conceptual map of the system. The integration of SBFCM and ANN methods provides both statistical data and expert opinion in the prediction model. In the numerical application, the proposed approach outperformed the conventional approach and other machine learning algorithms with 79.95% accuracy, revealing the power of expert opinion involvement in medical decisions. A medical decision support framework is constructed for better prediction of length of hospital stay and more effective hospital management.

The likelihood of requiring a diagnostic test: Classifying emergency department patients with logistic regression

BACKGROUND

Emergency departments (EDs) play an important role in health systems since they are the front line for patients with emergency medical conditions who frequently require diagnostic tests and timely treatment.

OBJECTIVE

To improve decision-making and accelerate processes in EDs, this study proposes predictive models for classifying patients according to whether or not they are likely to require a diagnostic test based on referral diagnosis, age, gender, triage category and type of arrival.

METHOD

Retrospective data were categorised into four output patient groups: not requiring any diagnostic test (group A); requiring a radiology test (group B); requiring a laboratory test (group C); requiring both tests (group D). Multivariable logistic regression models were used, with the outcome classifications represented as a series of binary variables: test (1) or no test (0); in the case of group A, no test (1) or test (0).

RESULTS

For all models, age, triage category, type of arrival and referral diagnosis were significant predictors whereas gender was not. The main referral diagnosis with high model coefficients varied by designed output groups (groups A, B, C and D). The overall accuracies of the logistic regression models for groups A, B, C and D were, respectively, 74.11%, 73.07%, 82.47% and 85.79%. Specificity metrics were higher than the sensitivities for groups B, C and D, meaning that these models were better able to predict negative outcomes.

IMPLICATIONS

These results provide guidance for ED triage staff, researchers and practitioners in making rapid decisions regarding patients' diagnostic test requirements based on specified variables in the predictive models. This is critical in ED operations planning as it potentially decreases waiting times, while increasing patient satisfaction and operational performance.

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

Objectives

The study aimed to develop and compare predictive models based on supervised machine learning algorithms for predicting the prolonged length of stay (LOS) of hospitalized patients diagnosed with five different chronic conditions.

Methods

An administrative claim dataset (2008-2012) of a regional network of nine hospitals in the Tampa Bay area, Florida, USA, was used to develop the prediction models. Features were extracted from the dataset using the International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM) codes. Five learning algorithms, namely, decision tree C5.0, linear support vector machine (LSVM), k-nearest neighbors, random forest, and multi-layered artificial neural networks, were used to build the model with semi-supervised anomaly detection and two feature selection methods. Issues with the unbalanced nature of the dataset were resolved using the Synthetic Minority Over-sampling Technique (SMOTE).

Results

LSVM with wrapper feature selection performed moderately well for all patient cohorts. Using SMOTE to counter data imbalances triggered a tradeoff between the model's sensitivity and specificity, which can be masked under a similar area under the curve. The proposed aggregate rank selection approach resulted in a balanced performing model compared to other criteria. Finally, factors such as comorbidity conditions, source of admission, and payer types were associated with the increased risk of a prolonged LOS.

Conclusions

Prolonged LOS is mostly associated with pre-intraoperative clinical and patient socioeconomic factors. Accurate patient identification with the risk of prolonged LOS using the selected model can provide hospitals a better tool for planning early discharge and resource allocation, thus reducing avoidable hospitalization costs.

Use of machine learning to analyse routinely collected intensive care unit data: a systematic review

BACKGROUND

Intensive care units (ICUs) face financial, bed management, and staffing constraints. Detailed data covering all aspects of patients' journeys into and through intensive care are now collected and stored in electronic health records: machine learning has been used to analyse such data in order to provide decision support to clinicians.

METHODS

Systematic review of the applications of machine learning to routinely collected ICU data. Web of Science and MEDLINE databases were searched to identify candidate articles: those on image processing were excluded. The study aim, the type of machine learning used, the size of dataset analysed, whether and how the model was validated, and measures of predictive accuracy were extracted.

RESULTS

Of 2450 papers identified, 258 fulfilled eligibility criteria. The most common study aims were predicting complications (77 papers [29.8% of studies]), predicting mortality (70 [27.1%]), improving prognostic models (43 [16.7%]), and classifying sub-populations (29 [11.2%]). Median sample size was 488 (IQR 108-4099): 41 studies analysed data on > 10,000 patients. Analyses focused on 169 (65.5%) papers that used machine learning to predict complications, mortality, length of stay, or improvement of health. Predictions were validated in 161 (95.2%) of these studies: the area under the ROC curve (AUC) was reported by 97 (60.2%) but only 10 (6.2%) validated predictions using independent data. The median AUC was 0.83 in studies of 1000-10,000 patients, rising to 0.94 in studies of > 100,000 patients. The most common machine learning methods were neural networks (72 studies [42.6%]), support vector machines (40 [23.7%]), and classification/decision trees (34 [20.1%]). Since 2015 (125 studies [48.4%]), the most common methods were support vector machines (37 studies [29.6%]) and random forests (29 [23.2%]).

CONCLUSIONS

The rate of publication of studies using machine learning to analyse routinely collected ICU data is increasing rapidly. The sample sizes used in many published studies are too small to exploit the potential of these methods. Methodological and reporting guidelines are needed, particularly with regard to the choice of method and validation of predictions, to increase confidence in reported findings and aid in translating findings towards routine use in clinical practice.

Predicting Intracerebral Hemorrhage Patients' Length-of-Stay Probability Distribution Based on Demographic, Clinical, Admission Diagnosis, and Surgery Information

The vast majority of patients with intracerebral hemorrhage (ICH) suffer from long and uncertain length of stay (LOS). The aim of our study was to provide decision support for discharge and admission plans by predicting ICH patients' LOS probability distribution. The demographics, clinical predictors, admission diagnosis, and surgery information from 3,600 ICH patients were used in this study. We used univariable Cox analysis, multivariable Cox analysis, Cox-variable of importance (Cox-VIMP) analysis, and an intersection analysis to select predictors and used random survival forests (RSF)—a method in survival analysis—to predict LOS probability distribution. The Cox-VIMP method constructed by us effectively selected significant correlation predictors. The Cox-VIMP RSF model can improve prediction performance and is significantly different from the other models. The Cox-VIMP can contribute to the screening of predictors, and the RSF model can be established through those predictors to predict the probability distribution of LOS in each patient.

Length of Hospital Stay Prediction at the Admission Stage for Cardiology Patients Using Artificial Neural Network

For hospitals' admission management, the ability to predict length of stay (LOS) as early as in the preadmission stage might be helpful to monitor the quality of inpatient care. This study is to develop artificial neural network (ANN) models to predict LOS for inpatients with one of the three primary diagnoses: coronary atherosclerosis (CAS), heart failure (HF), and acute myocardial infarction (AMI) in a cardiovascular unit in a Christian hospital in Taipei, Taiwan. A total of 2,377 cardiology patients discharged between October 1, 2010, and December 31, 2011, were analyzed. Using ANN or linear regression model was able to predict correctly for 88.07% to 89.95% CAS patients at the predischarge stage and for 88.31% to 91.53% at the preadmission stage. For AMI or HF patients, the accuracy ranged from 64.12% to 66.78% at the predischarge stage and 63.69% to 67.47% at the preadmission stage when a tolerance of 2 days was allowed.

Hierarchical Genetic Algorithm and Fuzzy Radial Basis Function Networks for Factors Influencing Hospital Length of Stay Outliers

Objectives

Controlling hospital high length of stay outliers can provide significant benefits to hospital management resources and lead to cost reduction. The strongest predictive factors influencing high length of stay outliers should be identified to build a high-performance prediction model for hospital outliers.

Methods

We highlight the application of the hierarchical genetic algorithm to provide the main predictive factors and to define the optimal structure of the prediction model fuzzy radial basis function neural network. To establish the prediction model, we used a data set of 26,897 admissions from five different intensive care units with discharges between 2001 and 2012. We selected and analyzed the high length of stay outliers using the trimming method geometric mean plus two standard deviations. A total of 28 predictive factors were extracted from the collected data set and investigated.

Results

High length of stay outliers comprised 5.07% of the collected data set. The results indicate that the prediction model can provide effective forecasting. We found 10 common predictive factors within the studied intensive care units. The obtained main predictive factors include patient demographic characteristics, hospital characteristics, medical events, and comorbidities.

Conclusions

The main initial predictive factors available at the time of admission are useful in evaluating high length of stay outliers. The proposed approach can provide a practical tool for healthcare providers, and its application can be extended to other hospital predictions, such as readmissions and cost.

Extract critical factors affecting the length of hospital stay of pneumonia patient by data mining (case study: an Iranian hospital)

MOTIVATION

Pneumonia is a prevalent infection of lower respiratory tract caused by infected lungs. Length of stay (LOS) in hospital is one of the simplest and most important indicators in hospital activity that is used for different purposes. The aim of this study is to explore the important factors affecting the LOS of patients with pneumonia in hospitals.

METHODS

The clinical data set for the study were collected from 387 patients in a specialized hospital in Iran between 2009 and 2015. Patients discharge summary includes their demographic details, reasons for admission, prescribed medications for the patient, the result of laboratory tests, and length of treatment.

RESULTS AND CONCLUSIONS

The proposed model in the study demonstrates the way various scenarios of data processing impact on the scale efficiency model, which points to the significance of the pre-processing in data mining. In this article, some methods were utilized; it is noteworthy that Bayesian boosting method led to better results in identifying the factors affecting LOS (accuracy 95.17%). In addition, it was found that 58% of patients younger than 15 years old and 74% of the elderly within the age range of 74-88 were more vulnerable to pneumonia disease. Also, it was found that the Meropenem is a relatively more effective medicine compared to other antibiotics which are used to treat pneumonia in the majority of age groups. Regardless of the impact of various laboratory findings (including CRP, ESR, WBC, NA, K), the patients LOS decreased as a result of Meropenem.

Patient length of stay and mortality prediction: A survey

Over the past few years, there has been increased interest in data mining and machine learning methods to improve hospital performance, in particular hospitals want to improve their intensive care unit statistics by reducing the number of patients dying inside the intensive care unit. Research has focused on prediction of measurable outcomes, including risk of complications, mortality and length of hospital stay. The length of stay is an important metric both for healthcare providers and patients, influenced by numerous factors. In particular, the length of stay in critical care is of great significance, both to patient experience and the cost of care, and is influenced by factors specific to the highly complex environment of the intensive care unit. The length of stay is often used as a surrogate for other outcomes, where those outcomes cannot be measured; for example as a surrogate for hospital or intensive care unit mortality. The length of stay is also a parameter, which has been used to identify the severity of illnesses and healthcare resource utilisation. This paper examines a range of length of stay and mortality prediction applications in acute medicine and the critical care unit. It also focuses on the methods of analysing length of stay and mortality prediction. Moreover, the paper provides a classification and evaluation for the analytical methods of the length of stay and mortality prediction associated with a grouping of relevant research papers published in the years 1984 to 2016 related to the domain of survival analysis. In addition, the paper highlights some of the gaps and challenges of the domain.

Preprocessing structured clinical data for predictive modeling and decision support. A roadmap to tackle the challenges

BACKGROUND

EHR systems have high potential to improve healthcare delivery and management. Although structured EHR data generates information in machine-readable formats, their use for decision support still poses technical challenges for researchers due to the need to preprocess and convert data into a matrix format. During our research, we observed that clinical informatics literature does not provide guidance for researchers on how to build this matrix while avoiding potential pitfalls.

OBJECTIVES

This article aims to provide researchers a roadmap of the main technical challenges of preprocessing structured EHR data and possible strategies to overcome them.

METHODS

Along standard data processing stages - extracting database entries, defining features, processing data, assessing feature values and integrating data elements, within an EDPAI framework -, we identified the main challenges faced by researchers and reflect on how to address those challenges based on lessons learned from our research experience and on best practices from related literature. We highlight the main potential sources of error, present strategies to approach those challenges and discuss implications of these strategies.

RESULTS

Following the EDPAI framework, researchers face five key challenges: (1) gathering and integrating data, (2) identifying and handling different feature types, (3) combining features to handle redundancy and granularity, (4) addressing data missingness, and (5) handling multiple feature values. Strategies to address these challenges include: cross-checking identifiers for robust data retrieval and integration; applying clinical knowledge in identifying feature types, in addressing redundancy and granularity, and in accommodating multiple feature values; and investigating missing patterns adequately.

CONCLUSIONS

This article contributes to literature by providing a roadmap to inform structured EHR data preprocessing. It may advise researchers on potential pitfalls and implications of methodological decisions in handling structured data, so as to avoid biases and help realize the benefits of the secondary use of EHR data.

Random Survival Forests for Predicting the Bed Occupancy in the Intensive Care Unit

Predicting the bed occupancy of an intensive care unit (ICU) is a daunting task. The uncertainty associated with the prognosis of critically ill patients and the random arrival of new patients can lead to capacity problems and the need for reactive measures. In this paper, we work towards a predictive model based on Random Survival Forests which can assist physicians in estimating the bed occupancy. As input data, we make use of the Sequential Organ Failure Assessment (SOFA) score collected and calculated from 4098 patients at two ICU units of Ghent University Hospital over a time period of four years. We compare the performance of our system with a baseline performance and a standard Random Forest regression approach. Our results indicate that Random Survival Forests can effectively be used to assist in the occupancy prediction problem. Furthermore, we show that a group based approach, such as Random Survival Forests, performs better compared to a setting in which the length of stay of a patient is individually assessed.

Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables

Background

Advanced predictive analytical techniques are being increasingly applied to clinical risk assessment. This study compared a neural network model to several other models in predicting the length of stay (LOS) in the cardiac surgical intensive care unit (ICU) based on pre-incision patient characteristics.

Methods

Thirty six variables collected from 185 cardiac surgical patients were analyzed for contribution to ICU LOS. The Automatic Linear Modeling (ALM) module of IBM-SPSS software identified 8 factors with statistically significant associations with ICU LOS; these factors were also analyzed with the Artificial Neural Network (ANN) module of the same software. The weighted contributions of each factor (“trained” data) were then applied to data for a “new” patient to predict ICU LOS for that individual.

Results

Factors identified in the ALM model were: use of an intra-aortic balloon pump; O₂ delivery index; age; use of positive cardiac inotropic agents; hematocrit; serum creatinine ≥ 1.3 mg/deciliter; gender; arterial pCO₂. The r² value for ALM prediction of ICU LOS in the initial (training) model was 0.356, p <0.0001. Cross validation in prediction of a “new” patient yielded r² = 0.200, p <0.0001. The same 8 factors analyzed with ANN yielded a training prediction r² of 0.535 (p <0.0001) and a cross validation prediction r² of 0.410, p <0.0001. Two additional predictive algorithms were studied, but they had lower prediction accuracies. Our validated neural network model identified the upper quartile of ICU LOS with an odds ratio of 9.8(p <0.0001).

Conclusions

ANN demonstrated a 2-fold greater accuracy than ALM in prediction of observed ICU LOS. This greater accuracy would be presumed to result from the capacity of ANN to capture nonlinear effects and higher order interactions. Predictive modeling may be of value in early anticipation of risks of post-operative morbidity and utilization of ICU facilities.

Exploiting expert systems in cardiology: a comparative study

An improved Adaptive Neuro-Fuzzy Inference System (ANFIS) in the field of critical cardiovascular diseases is presented. The system stems from an earlier application based only on a Sugeno-type Fuzzy Expert System (FES) with the addition of an Artificial Neural Network (ANN) computational structure. Thus, inherent characteristics of ANNs, along with the human-like knowledge representation of fuzzy systems are integrated. The ANFIS has been utilized into building five different sub-systems, distinctly covering Coronary Disease, Hypertension, Atrial Fibrillation, Heart Failure, and Diabetes, hence aiding doctors of medicine (MDs), guide trainees, and encourage medical experts in their diagnoses centering a wide range of Cardiology. The Fuzzy Rules have been trimmed down and the ANNs have been optimized in order to focus into each particular disease and produce results ready-to-be applied to real-world patients.

Use of data mining techniques to determine and predict length of stay of cardiac patients

Objectives

Predicting the length of stay (LOS) of patients in a hospital is important in providing them with better services and higher satisfaction, as well as helping the hospital management plan and managing hospital resources as meticulously as possible. We propose applying data mining techniques to extract useful knowledge and draw an accurate model to predict the LOS of heart patients.

Methods

Data were collected from patients with coronary artery disease (CAD). The patient records of 4,948 patients who had suffered CAD were included in the analysis. The techniques used are classification with three algorithms, namely, decision tree, support vector machines (SVM), and artificial neural network (ANN). LOS is the target variable, and 36 input variables are used for prediction. A confusion matrix was obtained to calculate sensitivity, specificity, and accuracy.

Results

The overall accuracy of SVM was 96.4% in the training set. Most single patients (64.3%) had an LOS ≤5 days, whereas 41.2% of married patients had an LOS >10 days. Moreover, the study showed that comorbidity states, such as lung disorders and hemorrhage with drug consumption have an impact on long LOS. The presence of comorbidities, an ejection fraction <2, being a current smoker, and having social security type insurance in coronary artery patients led to longer LOS than other subjects.

Conclusions

All three algorithms are able to predict LOS with various degrees of accuracy. The findings demonstrated that the SVM was the best fit. There was a significant tendency for LOS to be longer in patients with lung or respiratory disorders and high blood pressure.

CardioSmart365: Artificial Intelligence in the Service of Cardiologic Patients

Artificial intelligence has significantly contributed in the evolution of medical informatics and biomedicine, providing a variety of tools available to be exploited, from rule-based expert systems and fuzzy logic to neural networks and genetic algorithms. Moreover, familiarizing people with smartphones and the constantly growing use of medical-related mobile applications enables complete and systematic monitoring of a series of chronic diseases both by health professionals and patients. In this work, we propose an integrated system for monitoring and early notification for patients suffering from heart diseases. CardioSmart365 consists of web applications, smartphone native applications, decision support systems, and web services that allow interaction and communication among end users: cardiologists, patients, and general doctors. The key features of the proposed solution are (a) recording and management of patients' measurements of vital signs performed at home on regular basis (blood pressure, blood glucose, oxygen saturation, weight, and height), (b) management of patients' EMRs, (c) cardiologic patient modules for the most common heart diseases, (d) decision support systems based on fuzzy logic, (e) integrated message management module for optimal communication between end users and instant notifications, and (f) interconnection to Microsoft HealthVault platform. CardioSmart365 contributes to the effort for optimal patient monitoring at home and early response in cases of emergency.

Integrating stress-related ventricular functional and angiographic data in preventive cardiology: a unified approach implementing a Bayesian network

BACKGROUND

Identification of key factors associated with the risk of adverse cardiovascular events and quantification of this risk using multivariable prediction algorithms are among the major advances made in preventive cardiology and cardiovascular epidemiology.

METHODS

In the present paper, we examined clinical predictors of adverse cardiovascular events among 228 individuals with symptoms suggestive of coronary artery disease (CAD) undergoing functional (stress echocardiography) and anatomical (coronary angiography) assessment of CAD. Particularly, we evaluate the possibility to integrate simple measures that have known prognostic value and more recently discovered predictors of risk, such as stress-related ventricular function data and angiographic data, in a unique model implementing a Bayesian network (BN). Moreover, we compared the performance of BN and the covariates hierarchy with those obtained from logistic regression model and from a set of alternative tools becoming popular in various clinical settings, including random forest classification tree analysis, artificial neural networks and support vector machine.

RESULTS

Network graph and results coming from sensitivity analysis, where variables are ranked according to the gain they provided in variance reduction, seem have an easily intuitive lecture: variables that are measure of ventricular disfunction or of the extent of CAD show a greater impact in predicting event. On the other hand, anamnestic data such as diabetes, dyslipidaemia, hypertension, smoke habits, which are related to the outcome throughout a process of intermediate variables, per se have a small role in outcome prediction. BNs are able to explain a relevant part of variance (70%) and have discrimination ability superior or comparable with those to random forest classification tree analysis, artificial neural networks and support vector machine.

DISCUSSION

Despite the complexity of interactions, model obtained implementing a BN seems to be able to adequately describe the relationships existing among the analysed variables. BN, being able to predict scenarios in which new variables can be incorporated as health process evolves, can measure individual's risks for adverse cardiovascular events, providing a permanent second opinion to the medical practitioner and assisting diagnostic and therapeutic process.

Using VLAD scores to have a look insight ICU performance: towards a modelling of the errors

RATIONALE, AIMS AND OBJECTIVES

Mortality prediction models using logistic regression analysis play a pivotal role in intensive care quality evaluation, allowing a hospital's performance to be compared with a standard. However, when a difference between predicted and observed mortality exists, that is, the numerator of the Variable Life Adjusted Display (VLAD) score, the investigation for a possible explanation could be arduous. In this article we tested the ability of Bayesian Network (BN) to identify factors determining the negative discrepancy between expected and actual outcomes recorded in four Italian intensive care units (ICUs).

METHODS

A BN was implemented to predict the extent of the expected-observed distance quantified by the VLAD score. BN performance was compared with those of a set of tools including Linear Model, Random Forest Regression Tree analysis, Artificial Neural Networks and Support Vector Machine.

RESULTS

BN allows the identification of critical areas responsible for bad performance. Compared with other techniques, BN always explains a higher variance percentage and it shows similar or superior discrimination ability.

CONCLUSIONS

BN, being able to guide interpretation of covariates role by means of a graphic representation of relationships, confirms its utility particularly where many interactions between predictors exist and when a coherent set of theories regarding which variables are related and how is not available.