scholarly journals Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
M Lewis ◽  
J Figueroa
Keyword(s):  
Heart Failure ◽  
Deep Learning ◽  
Prediction Models ◽  
Evaluation Metrics ◽  
Gradient Boosting ◽  
Learning Models ◽  
Private Company ◽  
Preventable Hospitalizations ◽  
Targeted Interventions ◽  
Ed Visits

Abstract   Recent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable utilization. The goal of this paper was to compare deep learning approaches with traditional logistic regression (LR) to predict preventable utilization among HF patients. We conducted a prognostic study using data on 93,260 HF patients continuously enrolled for 2-years in a large U.S. commercial insurer to develop and validate prediction models for three outcomes of interest: preventable hospitalizations, preventable emergency department (ED) visits, and preventable costs. Patients were split into training, validation, and testing samples. Outcomes were modeled using traditional and enhanced LR and compared to gradient boosting model and deep learning models using sequential and non-sequential inputs. Evaluation metrics included precision (positive predictive value) at k, cost capture, and Area Under the Receiver operating characteristic (AUROC). Deep learning models consistently outperformed LR for all three outcomes with respect to the chosen evaluation metrics. Precision at 1% for preventable hospitalizations was 43% for deep learning compared to 30% for enhanced LR. Precision at 1% for preventable ED visits was 39% for deep learning compared to 33% for enhanced LR. For preventable cost, cost capture at 1% was 30% for sequential deep learning, compared to 18% for enhanced LR. The highest AUROCs for deep learning were 0.778, 0.681 and 0.727, respectively. These results offer a promising approach to identify patients for targeted interventions. FUNDunding Acknowledgement Type of funding sources: Private company. Main funding source(s): internally funded by Diagnostic Robotics Inc.

scholarly journals Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Maor Lewis ◽  
Guy Elad ◽  
Moran Beladev ◽  
Gal Maor ◽  
Kira Radinsky ◽  
...  
Keyword(s):  
Heart Failure ◽  
Deep Learning ◽  
Prediction Models ◽  
Evaluation Metrics ◽  
Gradient Boosting ◽  
Learning Approaches ◽  
Learning Models ◽  
Preventable Hospitalizations ◽  
Targeted Interventions ◽  
Ed Visits

AbstractRecent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable utilization. The goal of this paper was to compare deep learning approaches with traditional logistic regression (LR) to predict preventable utilization among HF patients. We conducted a prognostic study using data on 93,260 HF patients continuously enrolled for 2-years in a large U.S. commercial insurer to develop and validate prediction models for three outcomes of interest: preventable hospitalizations, preventable emergency department (ED) visits, and preventable costs. Patients were split into training, validation, and testing samples. Outcomes were modeled using traditional and enhanced LR and compared to gradient boosting model and deep learning models using sequential and non-sequential inputs. Evaluation metrics included precision (positive predictive value) at k, cost capture, and Area Under the Receiver operating characteristic (AUROC). Deep learning models consistently outperformed LR for all three outcomes with respect to the chosen evaluation metrics. Precision at 1% for preventable hospitalizations was 43% for deep learning compared to 30% for enhanced LR. Precision at 1% for preventable ED visits was 39% for deep learning compared to 33% for enhanced LR. For preventable cost, cost capture at 1% was 30% for sequential deep learning, compared to 18% for enhanced LR. The highest AUROCs for deep learning were 0.778, 0.681 and 0.727, respectively. These results offer a promising approach to identify patients for targeted interventions.

scholarly journals Deep Learning Models for Predicting Monthly TAIEX to Support Making Decisions in Index Futures Trading

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3268
Author(s):  
Duy-An Ha ◽  
Chia-Hung Liao ◽  
Kai-Shien Tan ◽  
Shyan-Ming Yuan
Keyword(s):  
Deep Learning ◽  
Prediction Models ◽  
Stock Index ◽  
Gradient Boosting ◽  
Learning Models ◽  
Futures Trading ◽  
Convolutional Network ◽  
Stock Market Forecasting ◽  
Extreme Gradient Boosting ◽  
Stop Loss

Futures markets offer investors many attractive advantages, including high leverage, high liquidity, fair, and fast returns. Highly leveraged positions and big contract sizes, on the other hand, expose investors to the risk of massive losses from even minor market changes. Among the numerous stock market forecasting tools, deep learning has recently emerged as a favorite tool in the research community. This study presents an approach for applying deep learning models to predict the monthly average of the Taiwan Capitalization Weighted Stock Index (TAIEX) to support decision-making in trading Mini-TAIEX futures (MTX). We inspected many global financial and economic factors to find the most valuable predictor variables for the TAIEX, and we examined three different deep learning architectures for building prediction models. A simulation on trading MTX was then performed with a simple trading strategy and two different stop-loss strategies to show the effectiveness of the models. We found that the Temporal Convolutional Network (TCN) performed better than other models, including the two baselines, i.e., linear regression and extreme gradient boosting. Moreover, stop-loss strategies are necessary, and a simple one could be sufficient to reduce a severe loss effectively.

scholarly journals ECG-AI: electrocardiographic artificial intelligence model for prediction of heart failure

2021 ◽  
Author(s):  
Oguz Akbilgic ◽  
Liam Butler ◽  
Ibrahim Karabayir ◽  
Patricia P Chang ◽  
Dalane W Kitzman ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Heart Failure ◽  
Convolutional Neural Network ◽  
Prediction Models ◽  
Smoking Status ◽  
Characteristic Curve ◽  
Gradient Boosting ◽  
Model Output ◽  
Light Gradient

Abstract Aims Heart failure (HF) is a leading cause of death. Early intervention is the key to reduce HF-related morbidity and mortality. This study assesses the utility of electrocardiograms (ECGs) in HF risk prediction. Methods and results Data from the baseline visits (1987–89) of the Atherosclerosis Risk in Communities (ARIC) study was used. Incident hospitalized HF events were ascertained by ICD codes. Participants with good quality baseline ECGs were included. Participants with prevalent HF were excluded. ECG-artificial intelligence (AI) model to predict HF was created as a deep residual convolutional neural network (CNN) utilizing standard 12-lead ECG. The area under the receiver operating characteristic curve (AUC) was used to evaluate prediction models including (CNN), light gradient boosting machines (LGBM), and Cox proportional hazards regression. A total of 14 613 (45% male, 73% of white, mean age ± standard deviation of 54 ± 5) participants were eligible. A total of 803 (5.5%) participants developed HF within 10 years from baseline. Convolutional neural network utilizing solely ECG achieved an AUC of 0.756 (0.717–0.795) on the hold-out test data. ARIC and Framingham Heart Study (FHS) HF risk calculators yielded AUC of 0.802 (0.750–0.850) and 0.780 (0.740–0.830). The highest AUC of 0.818 (0.778–0.859) was obtained when ECG-AI model output, age, gender, race, body mass index, smoking status, prevalent coronary heart disease, diabetes mellitus, systolic blood pressure, and heart rate were used as predictors of HF within LGBM. The ECG-AI model output was the most important predictor of HF. Conclusions ECG-AI model based solely on information extracted from ECG independently predicts HF with accuracy comparable to existing FHS and ARIC risk calculators.

scholarly journals Machine Learning Approach to Reduce Alert Fatigue Using a Disease Medication–Related Clinical Decision Support System: Model Development and Validation (Preprint)

2020 ◽  
Author(s):  
Tahmina Nasrin Poly ◽  
Md.Mohaimenul Islam ◽  
Muhammad Solihuddin Muhtar ◽  
Hsuan-Chia Yang ◽  
Phung Anh (Alex) Nguyen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Prediction Models ◽  
Clinical Decision ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Models ◽  
Alert Fatigue ◽  
Machine Learning Models

BACKGROUND Computerized physician order entry (CPOE) systems are incorporated into clinical decision support systems (CDSSs) to reduce medication errors and improve patient safety. Automatic alerts generated from CDSSs can directly assist physicians in making useful clinical decisions and can help shape prescribing behavior. Multiple studies reported that approximately 90%-96% of alerts are overridden by physicians, which raises questions about the effectiveness of CDSSs. There is intense interest in developing sophisticated methods to combat alert fatigue, but there is no consensus on the optimal approaches so far. OBJECTIVE Our objective was to develop machine learning prediction models to predict physicians’ responses in order to reduce alert fatigue from disease medication–related CDSSs. METHODS We collected data from a disease medication–related CDSS from a university teaching hospital in Taiwan. We considered prescriptions that triggered alerts in the CDSS between August 2018 and May 2019. Machine learning models, such as artificial neural network (ANN), random forest (RF), naïve Bayes (NB), gradient boosting (GB), and support vector machine (SVM), were used to develop prediction models. The data were randomly split into training (80%) and testing (20%) datasets. RESULTS A total of 6453 prescriptions were used in our model. The ANN machine learning prediction model demonstrated excellent discrimination (area under the receiver operating characteristic curve [AUROC] 0.94; accuracy 0.85), whereas the RF, NB, GB, and SVM models had AUROCs of 0.93, 0.91, 0.91, and 0.80, respectively. The sensitivity and specificity of the ANN model were 0.87 and 0.83, respectively. CONCLUSIONS In this study, ANN showed substantially better performance in predicting individual physician responses to an alert from a disease medication–related CDSS, as compared to the other models. To our knowledge, this is the first study to use machine learning models to predict physician responses to alerts; furthermore, it can help to develop sophisticated CDSSs in real-world clinical settings.

scholarly journals Recurrent disease progression networks for modelling risk trajectory of heart failure

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245177
Author(s):  
Xing Han Lu ◽  
Aihua Liu ◽  
Shih-Chieh Fuh ◽  
Yi Lian ◽  
Liming Guo ◽  
...  
Keyword(s):  
Heart Failure ◽  
Deep Learning ◽  
Disease Progression ◽  
Recurrent Events ◽  
Network Models ◽  
Medical Intervention ◽  
Learning Models ◽  
Neural Network Models ◽  
Real Patient

Motivation Recurrent neural networks (RNN) are powerful frameworks to model medical time series records. Recent studies showed improved accuracy of predicting future medical events (e.g., readmission, mortality) by leveraging large amount of high-dimensional data. However, very few studies have explored the ability of RNN in predicting long-term trajectories of recurrent events, which is more informative than predicting one single event in directing medical intervention. Methods In this study, we focus on heart failure (HF) which is the leading cause of death among cardiovascular diseases. We present a novel RNN framework named Deep Heart-failure Trajectory Model (DHTM) for modelling the long-term trajectories of recurrent HF. DHTM auto-regressively predicts the future HF onsets of each patient and uses the predicted HF as input to predict the HF event at the next time point. Furthermore, we propose an augmented DHTM named DHTM+C (where “C” stands for co-morbidities), which jointly predicts both the HF and a set of acute co-morbidities diagnoses. To efficiently train the DHTM+C model, we devised a novel RNN architecture to model disease progression implicated in the co-morbidities. Results Our deep learning models confers higher prediction accuracy for both the next-step HF prediction and the HF trajectory prediction compared to the baseline non-neural network models and the baseline RNN model. Compared to DHTM, DHTM+C is able to output higher probability of HF for high-risk patients, even in cases where it is only given less than 2 years of data to predict over 5 years of trajectory. We illustrated multiple non-trivial real patient examples of complex HF trajectories, indicating a promising path for creating highly accurate and scalable longitudinal deep learning models for modeling the chronic disease.

scholarly journals Characterising the nationwide burden and predictors of unkept outpatient appointments in the National Health Service in England: A cohort study using a machine learning approach

PLoS Medicine ◽  
2021 ◽  
Vol 18 (10) ◽  
pp. e1003783
Author(s):  
Sion Philpott-Morgan ◽  
Dixa B. Thakrar ◽  
Joshua Symons ◽  
Daniel Ray ◽  
Hutan Ashrafian ◽  
...  
Keyword(s):  
Machine Learning ◽  
National Health Service ◽  
Health Service ◽  
National Health ◽  
Outpatient Clinic ◽  
Gradient Boosting ◽  
Learning Models ◽  
Targeted Interventions ◽  
Outpatient Appointments ◽  
Machine Learning Models

Background Unkept outpatient hospital appointments cost the National Health Service £1 billion each year. Given the associated costs and morbidity of unkept appointments, this is an issue requiring urgent attention. We aimed to determine rates of unkept outpatient clinic appointments across hospital trusts in the England. In addition, we aimed to examine the predictors of unkept outpatient clinic appointments across specialties at Imperial College Healthcare NHS Trust (ICHT). Our final aim was to train machine learning models to determine the effectiveness of a potential intervention in reducing unkept appointments. Methods and findings UK Hospital Episode Statistics outpatient data from 2016 to 2018 were used for this study. Machine learning models were trained to determine predictors of unkept appointments and their relative importance. These models were gradient boosting machines. In 2017–2018 there were approximately 85 million outpatient appointments, with an unkept appointment rate of 5.7%. Within ICHT, there were almost 1 million appointments, with an unkept appointment rate of 11.2%. Hepatology had the highest rate of unkept appointments (17%), and medical oncology had the lowest (6%). The most important predictors of unkept appointments included the recency (25%) and frequency (13%) of previous unkept appointments and age at appointment (10%). A sensitivity of 0.287 was calculated overall for specialties with at least 10,000 appointments in 2016–2017 (after data cleaning). This suggests that 28.7% of patients who do miss their appointment would be successfully targeted if the top 10% least likely to attend received an intervention. As a result, an intervention targeting the top 10% of likely non-attenders, in the full population of patients, would be able to capture 28.7% of unkept appointments if successful. Study limitations include that some unkept appointments may have been missed from the analysis because recording of unkept appointments is not mandatory in England. Furthermore, results here are based on a single trust in England, hence may not be generalisable to other locations. Conclusions Unkept appointments remain an ongoing concern for healthcare systems internationally. Using machine learning, we can identify those most likely to miss their appointment and implement more targeted interventions to reduce unkept appointment rates.

scholarly journals Efficient selective screening for heart failure in elderly men and women from the community: A diagnostic individual participant data meta-analysis

2018 ◽  
Vol 25 (4) ◽  
pp. 437-446 ◽  
Author(s):  
Rogier F Kievit ◽  
Aisha Gohar ◽  
Arno W Hoes ◽  
Michiel L Bots ◽  
Evelien ES van Riet ◽  
...  
Keyword(s):  
Heart Failure ◽  
Cross Validation ◽  
Prediction Models ◽  
Meta Analysis ◽  
Older Individuals ◽  
Men And Women ◽  
Clinical Model ◽  
Targeted Interventions ◽  
C Statistic ◽  
Increased Risk

Background Prevalence of undetected heart failure in older individuals is high in the community, with patients being at increased risk of morbidity and mortality due to the chronic and progressive nature of this complex syndrome. An essential, yet currently unavailable, strategy to pre-select candidates eligible for echocardiography to confirm or exclude heart failure would identify patients earlier, enable targeted interventions and prevent disease progression. The aim of this study was therefore to develop and validate such a model that can be implemented clinically. Methods and results Individual patient data from four primary care screening studies were analysed. From 1941 participants >60 years old, 462 were diagnosed with heart failure, according to criteria of the European Society of Cardiology heart failure guidelines. Prediction models were developed in each cohort followed by cross-validation, omitting each of the four cohorts in turn. The model consisted of five independent predictors; age, history of ischaemic heart disease, exercise-related shortness of breath, body mass index and a laterally displaced/broadened apex beat, with no significant interaction with sex. The c-statistic ranged from 0.70 (95% confidence interval (CI) 0.64–0.76) to 0.82 (95% CI 0.78–0.87) at cross-validation and the calibration was reasonable with Observed/Expected ratios ranging from 0.86 to 1.15. The clinical model improved with the addition of N-terminal pro B-type natriuretic peptide with the c-statistic increasing from 0.76 (95% CI 0.70–0.81) to 0.89 (95% CI 0.86–0.92) at cross-validation. Conclusion Easily obtainable patient characteristics can select older men and women from the community who are candidates for echocardiography to confirm or refute heart failure.

scholarly journals A Comparative Analysis of Novel Deep Learning and Ensemble Learning Models to Predict the Allergenicity of Food Proteins

Foods ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 809
Author(s):  
Liyang Wang ◽  
Dantong Niu ◽  
Xinjie Zhao ◽  
Xiaoya Wang ◽  
Mengzhen Hao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Ensemble Learning ◽  
Food Allergen ◽  
Gradient Boosting ◽  
Learning Models ◽  
Food Proteins ◽  
Deep Model ◽  
Allergen Identification ◽  
Machine Learning Models

Traditional food allergen identification mainly relies on in vivo and in vitro experiments, which often needs a long period and high cost. The artificial intelligence (AI)-driven rapid food allergen identification method has solved the above mentioned some drawbacks and is becoming an efficient auxiliary tool. Aiming to overcome the limitations of lower accuracy of traditional machine learning models in predicting the allergenicity of food proteins, this work proposed to introduce deep learning model—transformer with self-attention mechanism, ensemble learning models (representative as Light Gradient Boosting Machine (LightGBM) eXtreme Gradient Boosting (XGBoost)) to solve the problem. In order to highlight the superiority of the proposed novel method, the study also selected various commonly used machine learning models as the baseline classifiers. The results of 5-fold cross-validation showed that the area under the receiver operating characteristic curve (AUC) of the deep model was the highest (0.9578), which was better than the ensemble learning and baseline algorithms. But the deep model need to be pre-trained, and the training time is the longest. By comparing the characteristics of the transformer model and boosting models, it can be analyzed that, each model has its own advantage, which provides novel clues and inspiration for the rapid prediction of food allergens in the future.

Sign in / Sign up

Export Citation Format

Share Document