Predicting 30-day Readmission in Heart Failure using Machine Learning Techniques

Kerexeta, Jon; Artetxe, Arkaitz; Escolar, Vanessa; Lozano, Ainara; Larburu, Nekane

doi:10.5220/0006542103080315

Cited by 6 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is article presents the methodology to develop predictive models for HF decompensations prediction based on ambulatory patients' telemonitored data, extending the study for readmissions detection [9]. e results on these studies have been successfully implemented in a telemedicine system, called INCAR.…”

Section: Discussionmentioning

confidence: 99%

“…Our hypothesis is that with the usage of artificial intelligence (AI) by means of, for instance, predictive models, it is possible to detect decompensations of ambulatory patients and reduce false alerts. In this context, this research extends the study for readmissions detection [9] and presents predictive models of a telemedicine system for heart failure patients, called INCAR. INCAR has been developed to (i) be generally applicable in HF patients, (ii) improve the clinical practice by developing an accurate system that detects the risk of decompensation and suggest actions to prevent them on time, (iii) allow professionals to maintain an efficient and personalized support and follow-up of patient, (iv) give patients support when required and guide them in risk situations, informing clinicians accordingly, and (v) reduce HF patients admission and readmission rate, which have a high economic impact.…”

Section: Introductionmentioning

confidence: 87%

See 1 more Smart Citation

Artificial Intelligence to Prevent Mobile Heart Failure Patients Decompensation in Real Time: Monitoring-Based Predictive Model

Larburu

Artetxe

Escolar

et al. 2018

Mobile Information Systems

Self Cite

View full text Add to dashboard Cite

Rapid advances in ICT and collection of large amount of mobile health data are giving room to new ways of treating patients. Studies suggest that telemonitoring systems and predictive models for clinical support and patient empowerment may improve several pathologies, such as heart failure, which admissions rate is high. In the current medical practice, clinicians make use of simple rules that generate large number of false alerts. In order to reduce the false alerts, in this study, the predictive models to prevent decompensations that may lead into admissions are presented. They are based on mobile clinical data of 242 heart failure (HF) patients collected for a period of 44 months in the public health service of Basque Country (Osakidetza). The best predictive model obtained is a combination of alerts based on monitoring data and a questionnaire with a Naive Bayes classifier using Bernoulli distribution. This predictive model performs with an AUC = 67% and reduces the false alerts per patient per year from 28.64 to 7.8. This way, the system predicts the risk of admission of ambulatory patients with higher reliability than current alerts.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 87%

Artificial Intelligence to Prevent Mobile Heart Failure Patients Decompensation in Real Time: Monitoring-Based Predictive Model

Larburu

Artetxe

Escolar

et al. 2018

Mobile Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, they merged unsupervised and supervised techniques of classification, and subsequently, merged DT and NB. They proved that the former method had better accuracy than the latter method with regard to readmission prediction [31]. Finally, Alajmani and Elazhary [14] used LR, multi-layer perceptron (MLP), NB, SVM, and DT to predict hospital readmission and evaluate accuracy among models.…”

Section: Related Workmentioning

confidence: 99%

Assessing Advanced Machine Learning Techniques for Predicting Hospital Readmission

Alajmani¹,

Jambi²

2020

IJACSA

View full text Add to dashboard Cite

Predicting the probability of hospital readmission is one of the most important healthcare problems for satisfactory, high-quality service in chronic diseases such as diabetes, in order to identify needful resources such as rooms, medical staff, beds, and specialists. Unfortunately, not many studies in the literature address this issue. Most studies involve forecasting the probability of diseases. For prediction, several machine learning methods can be implemented. Nonetheless, comparative studies that identify the most effective approaches for the method prediction are also insufficient. With this aim, our paper introduces a comparative study in the literature across five popular methods to predict the probability of hospital readmission in patients suffering from diabetes. The selected techniques include linear discriminant analysis, instance-based learning (K-nearest neighbors), and ensemble-based learning (random forest, AdaBoost, and gradient boosting) techniques. The study showed that the best performance was in random forest whereas the worst performance was shown by linear discriminant analysis.

show abstract

“…Current studies make use of several techniques to predict the outcome of a patient. These studies commonly relied on traditional statistical techniques such as regression models [2], but recently more sophisticated techniques based on machine learning, such as neural networks, have been also widely applied [3]- [8]. These studies usually present a model with own and specific datasets and their results are presented as the accuracy or sensitivity to predict outcomes, such as survival rates.…”

Section: A Data Mining Techniquesmentioning

confidence: 99%

Exploring Breast Cancer Patterns for Different Outcomes using Artificial Intelligence

Larburu¹,

Arrue²,

Muro³

et al. 2018

2018 IEEE 20th International Conference on E-Health Networking, Applications and Services (Healthcom)

Self Cite

View full text Add to dashboard Cite

Breast Cancer is a complex disease characterized by multiple variables obtained from several data-sources, such as clinical, genetic or image sources. Over the past decades, various studies have tried to predict the outcome of breast cancer with the support of these data, and big advances have been done in this direction. However, only a few reports describe the causal relationships among the variables and outcomes, such as adverse events and survival rate, and usually they are very limited to a specific dataset. This research work presents a novel system that using data mining and visual analytics tools depicts in an intuitive way the patterns associated with different outcomes, such as treatment response and adverse events related to a treatment. For that the system processes heterogenous data coming from a real setting for primary breast cancer. This way clinicians can explore in a dynamic, fast and intuitive way whether certain group of patients are prone to certain outcomes.

show abstract

Predicting 30-day Readmission in Heart Failure using Machine Learning Techniques

Cited by 6 publications

References 0 publications

Artificial Intelligence to Prevent Mobile Heart Failure Patients Decompensation in Real Time: Monitoring-Based Predictive Model

Artificial Intelligence to Prevent Mobile Heart Failure Patients Decompensation in Real Time: Monitoring-Based Predictive Model

Assessing Advanced Machine Learning Techniques for Predicting Hospital Readmission

Exploring Breast Cancer Patterns for Different Outcomes using Artificial Intelligence

Contact Info

Product

Resources

About