Submit to JPM Review for JPM Propose a Special Issue

Journal Browser

Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Journal of Personalized Medicine (ISSN 2075-4426). This special issue belongs to the section "Epidemiology".

Deadline for manuscript submissions: closed (25 October 2023) | Viewed by 10671

Share This Special Issue

Special Issue Editor

Dr. Franca Dipaola

E-Mail Website
Guest Editor

1. Internal Medicine, Humanitas Clinical and Research Center-IRCCS, Rozzano, 20089 Milan, Italy
2. Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, 20090 Milan, Italy
Interests: syncope; risk stratification; cardiovascular autonomic disorders; machine learning; evidence-based medicine
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning (ML) has been promisingly applied in cardiovascular medicine in recent years, both for disease diagnosis and in prognosis prediction.

Compared with traditional statistical techniques, ML algorithms can analyze a larger number of variables by performing greater numbers of mathematical operations and better define complex relationships between risk factors and outcomes of interest, strengthening the predictive process.

Furthermore, the possibility to automatically extract and classify prognostic determinants from large patient populations could generate significant progress in individual risk stratification, thus promoting the optimization of patients’ diagnostic/therapeutic workup and personalization of care.

The extraction and integration of data from various possible sources (clinical measurements and observations, biological -omics, experimental results, wearable devices) make cardiovascular disease particularly suitable for the application of ML techniques.

However, at present, the lack of generalizability, reproducibility, and standardized methodologies for developing and validating ML-based prognostic models reduces the quality of the available evidence and limits their implementation in clinical practice.

The aim of the present Special Issue is to collect original research articles and reviews that will provide updates and future perspectives regarding the application and implementation of ML to the risk stratification of patients suffering from cardiovascular disease.

Dr. Franca Dipaola
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Personalized Medicine is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

coronary artery disease
heart failure
arrhythmias
stroke
syncope
electrocardiography
echocardiography
prognosis
precision medicine
machine learning

Published Papers (7 papers)

Download All Papers

Editorial

Jump to: Research

3 pages, 184 KiB

Open AccessEditorial

Syncope—Do We Need AI?

by Brian Olshansky, Milena A. Gebska and Samuel L. Johnston

J. Pers. Med. 2023, 13(5), 740; https://doi.org/10.3390/jpm13050740 - 27 Apr 2023

Cited by 1 | Viewed by 1011

Abstract

Syncope is a form of transient loss of consciousness (TLOC) resulting from cerebral hypoperfusion and is characterized by rapid onset, short duration and spontaneous complete recovery [...] Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

Research

Jump to: Editorial

14 pages, 1555 KiB

Open AccessArticle

A Hybrid Model for 30-Day Syncope Prognosis Prediction in the Emergency Department

by Franca Dipaola, Mauro Gatti, Roberto Menè, Dana Shiffer, Alessandro Giaj Levra, Monica Solbiati, Paolo Villa, Giorgio Costantino and Raffaello Furlan

J. Pers. Med. 2024, 14(1), 4; https://doi.org/10.3390/jpm14010004 - 20 Dec 2023

Viewed by 943

Abstract

Syncope is a challenging problem in the emergency department (ED) as the available risk prediction tools have suboptimal predictive performances. Predictive models based on machine learning (ML) are promising tools whose application in the context of syncope remains underexplored. The aim of the present study was to develop and compare the performance of ML-based models in predicting the risk of clinically significant outcomes in patients presenting to the ED for syncope. We enrolled 266 consecutive patients (age 73, IQR 58–83; 52% males) admitted for syncope at three tertiary centers. We collected demographic and clinical information as well as the occurrence of clinically significant outcomes at a 30-day telephone follow-up. We implemented an XGBoost model based on the best-performing candidate predictors. Subsequently, we integrated the XGboost predictors with knowledge-based rules. The obtained hybrid model outperformed the XGboost model (AUC = 0.81 vs. 0.73, p < 0.001) with acceptable calibration. In conclusion, we developed an ML-based model characterized by a commendable capability to predict adverse events within 30 days post-syncope evaluation in the ED. This model relies solely on clinical data routinely collected during a patient’s initial syncope evaluation, thus obviating the need for laboratory tests or syncope experienced clinical judgment. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures

Figure 1

22 pages, 3576 KiB

Open AccessArticle

Mapping the Heartbeat of America with ChatGPT-4: Unpacking the Interplay of Social Vulnerability, Digital Literacy, and Cardiovascular Mortality in County Residency Choices

by Mohammed M. Ali, Subi Gandhi, Samian Sulaiman, Syed H. Jafri and Abbas S. Ali

J. Pers. Med. 2023, 13(12), 1625; https://doi.org/10.3390/jpm13121625 - 21 Nov 2023

Viewed by 1342

Abstract

Cardiovascular disease remains a leading cause of morbidity and mortality in the United States (US). Although high-quality data are accessible in the US for cardiovascular research, digital literacy (DL) has not been explored as a potential factor influencing cardiovascular mortality, although the Social Vulnerability Index (SVI) has been used previously as a variable in predictive modeling. Utilizing a large language model, ChatGPT4, we investigated the variability in CVD-specific mortality that could be explained by DL and SVI using regression modeling. We fitted two models to calculate the crude and adjusted CVD mortality rates. Mortality data using ICD-10 codes were retrieved from CDC WONDER, and the geographic level data was retrieved from the US Department of Agriculture. Both datasets were merged using the Federal Information Processing Standards code. The initial exploration involved data from 1999 through 2020 (n = 65,791; 99.98% complete for all US Counties) for crude cardiovascular mortality (CCM). Age-adjusted cardiovascular mortality (ACM) had data for 2020 (n = 3118 rows; 99% complete for all US Counties), with the inclusion of SVI and DL in the model (a composite of literacy and internet access). By leveraging on the advanced capabilities of ChatGPT4 and linear regression, we successfully highlighted the importance of incorporating the SVI and DL in predicting adjusted cardiovascular mortality. Our findings imply that just incorporating internet availability in the regression model may not be sufficient without incorporating significant variables, such as DL and SVI, to predict ACM. Further, our approach could enable future researchers to consider DL and SVI as key variables to study other health outcomes of public-health importance, which could inform future clinical practices and policies. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures

Figure 1

20 pages, 3150 KiB

Open AccessArticle

Comparing Machine Learning Classifiers for Predicting Hospital Readmission of Heart Failure Patients in Rwanda

by Theogene Rizinde, Innocent Ngaruye and Nathan D. Cahill

J. Pers. Med. 2023, 13(9), 1393; https://doi.org/10.3390/jpm13091393 - 18 Sep 2023

Viewed by 1139

Abstract

High rates of hospital readmission and the cost of treating heart failure (HF) are significant public health issues globally and in Rwanda. Using machine learning (ML) to predict which patients are at high risk for HF hospital readmission 20 days after their discharge has the potential to improve HF management by enabling early interventions and individualized treatment approaches. In this paper, we compared six different ML models for this task, including multi-layer perceptron (MLP), K-nearest neighbors (KNN), logistic regression (LR), decision trees (DT), random forests (RF), and support vector machines (SVM) with both linear and radial basis kernels. The outputs of the classifiers are compared using performance metrics including the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. We found that RF outperforms all the remaining models with an AUC of 94% while SVM, MLP, and KNN all yield 88% AUC. In contrast, DT performs poorly, with an AUC value of 57%. Hence, hospitals in Rwanda can benefit from using the RF classifier to determine which HF patients are at high risk of hospital readmission. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures

Figure 1

13 pages, 323 KiB

Open AccessArticle

Epigenetic Signatures in Hypertension

by Gerardo Alfonso Perez and Victor Delgado Martinez

J. Pers. Med. 2023, 13(5), 787; https://doi.org/10.3390/jpm13050787 - 1 May 2023

Cited by 2 | Viewed by 1393

Abstract

Clear epigenetic signatures were found in hypertensive and pre-hypertensive patients using DNA methylation data and neural networks in a classification algorithm. It is shown how by selecting an appropriate subset of CpGs it is possible to achieve a mean accuracy classification of 86% for distinguishing control and hypertensive (and pre-hypertensive) patients using only 2239 CpGs. Furthermore, it is also possible to obtain a statistically comparable model achieving an 83% mean accuracy using only 22 CpGs. Both of these approaches represent a substantial improvement over using the entire amount of available CpGs, which resulted in the neural network not generating accurate classifications. An optimization approach is followed to select the CpGs to be used as the base for a model distinguishing between hypertensive and pre-hypertensive individuals. It is shown that it is possible to find methylation signatures using machine learning techniques, which can be applied to distinguish between control (healthy) individuals, pre-hypertensive individuals and hypertensive individuals, illustrating an associated epigenetic impact. Identifying epigenetic signatures might lead to more targeted treatments for patients in the future. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures

Figure 1

11 pages, 621 KiB

Open AccessArticle

Novel Machine Learning Approach to Predict and Personalize Length of Stay for Patients Admitted with Syncope from the Emergency Department

by Sangil Lee, Avinash Reddy Mudireddy, Deepak Kumar Pasupula, Mehul Adhaduk, E. John Barsotti, Milan Sonka, Giselle M. Statz, Tyler Bullis, Samuel L. Johnston, Aron Z. Evans, Brian Olshansky and Milena A. Gebska

J. Pers. Med. 2023, 13(1), 7; https://doi.org/10.3390/jpm13010007 - 20 Dec 2022

Cited by 6 | Viewed by 2043

Abstract

Background: Syncope, a common problem encountered in the emergency department (ED), has a multitude of causes ranging from benign to life-threatening. Hospitalization may be required, but the management can vary substantially depending on specific clinical characteristics. Models predicting admission and hospitalization length of stay (LoS) are lacking. The purpose of this study was to design an effective, exploratory model using machine learning (ML) technology to predict LoS for patients presenting with syncope. Methods: This was a retrospective analysis using over 4 million patients from the National Emergency Department Sample (NEDS) database presenting to the ED with syncope between 2016–2019. A multilayer perceptron neural network with one hidden layer was trained and validated on this data set. Results: Receiver Operator Characteristics (ROC) were determined for each of the five ANN models with varying cutoffs for LoS. A fair area under the curve (AUC of 0.78) to good (AUC of 0.88) prediction performance was achieved based on sequential analysis at different cutoff points, starting from the same day discharge and ending at the longest analyzed cutoff LoS ≤7 days versus >7 days, accordingly. The ML algorithm showed significant sensitivity and specificity in predicting short (≤48 h) versus long (>48 h) LoS, with an AUC of 0.81. Conclusions: Using variables available to triaging ED clinicians, ML shows promise in predicting hospital LoS with fair to good performance for patients presenting with syncope. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures

Figure 1

16 pages, 2302 KiB

Open AccessArticle

Prediction of All-Cause Mortality Following Percutaneous Coronary Intervention in Bifurcation Lesions Using Machine Learning Algorithms

by Jacopo Burrello, Guglielmo Gallone, Alessio Burrello, Daniele Jahier Pagliari, Eline H. Ploumen, Mario Iannaccone, Leonardo De Luca, Paolo Zocca, Giuseppe Patti, Enrico Cerrato, Wojciech Wojakowski, Giuseppe Venuti, Ovidio De Filippo, Alessio Mattesini, Nicola Ryan, Gérard Helft, Saverio Muscoli, Jing Kan, Imad Sheiban, Radoslaw Parma, Daniela Trabattoni, Massimo Giammaria, Alessandra Truffa, Francesco Piroli, Yoichi Imori, Bernardo Cortese, Pierluigi Omedè, Federico Conrotto, Shao-Liang Chen, Javier Escaned, Rosaly A. Buiten, Clemens Von Birgelen, Paolo Mulatero, Gaetano Maria De Ferrari, Silvia Monticone and Fabrizio D’Ascenzo Show full author list Hide full author list

J. Pers. Med. 2022, 12(6), 990; https://doi.org/10.3390/jpm12060990 - 17 Jun 2022

Cited by 3 | Viewed by 1924

Abstract

Stratifying prognosis following coronary bifurcation percutaneous coronary intervention (PCI) is an unmet clinical need that may be fulfilled through the adoption of machine learning (ML) algorithms to refine outcome predictions. We sought to develop an ML-based risk stratification model built on clinical, anatomical, and procedural features to predict all-cause mortality following contemporary bifurcation PCI. Multiple ML models to predict all-cause mortality were tested on a cohort of 2393 patients (training, n = 1795; internal validation, n = 598) undergoing bifurcation PCI with contemporary stents from the real-world RAIN registry. Twenty-five commonly available patient-/lesion-related features were selected to train ML models. The best model was validated in an external cohort of 1701 patients undergoing bifurcation PCI from the DUTCH PEERS and BIO-RESORT trial cohorts. At ROC curves, the AUC for the prediction of 2-year mortality was 0.79 (0.74–0.83) in the overall population, 0.74 (0.62–0.85) at internal validation and 0.71 (0.62–0.79) at external validation. Performance at risk ranking analysis, k-center cross-validation, and continual learning confirmed the generalizability of the models, also available as an online interface. The RAIN-ML prediction model represents the first tool combining clinical, anatomical, and procedural features to predict all-cause mortality among patients undergoing contemporary bifurcation PCI with reliable performance. Full article

(This article belongs to the Special Issue Cardiovascular Disease Risk Stratification in the Era of Machine Learning and Personalized Medicine)

► Show Figures