Pub Date : 2025-03-01DOI: 10.1016/j.ejim.2024.08.025
Giuseppe Lippi
{"title":"Oh no, all we needed was monkeypox!","authors":"Giuseppe Lippi","doi":"10.1016/j.ejim.2024.08.025","DOIUrl":"10.1016/j.ejim.2024.08.025","url":null,"abstract":"","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":"133 ","pages":"Pages 119-120"},"PeriodicalIF":5.9,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142134351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1016/j.ejim.2025.01.020
Domenico Scrutinio , Federica Amitrano , Pietro Guida , Armando Coccia , Gaetano Pagano , Gianni D'addio , Andrea Passantino
Background
Assessing the relative performance of machine learning (ML) methods and conventional statistical methods in predicting prognosis in heart failure (HF) still remains a challenging research field.
Methods
The primary outcome was three-year mortality. The following 5 machine learning approaches were used for modeling: Random Forest (RF), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Multilayer perceptron. We compared the performance of the best performing ML models to the MAGGIC (Meta-analysis Global Group in Chronic Heart Failure) score and a novel logistic regression model (LRM) developed using the same set of variables used to develop the machine learning models. The performance was determined based on discrimination, calibration, and net benefit.
Results
The XGBoost and the RF were the best performing ML models. The XGBoost provided the highest discrimination (C-statistic: 0.793) and the lowest Brier score (0.178); the RF model had a C-statistic of 0.779 and provided the highest area under the precision‐recall curve (0.636). Both models were well calibrated. Both the XGboost and RF models outperformed MAGGIC score. The LRM had a C-statistic of 0.811 and a Brier score of 0.160 and was well calibrated. The XGBoost, RF, and LRM gave a higher net benefit than MAGGIC score; the XGBoost, RF, and logistic regression model gave similar net benefit.
Conclusions
RF and XGBoost models outperformed MAGGIC in predicting mortality. However, they did not offer any improvement over a logistic regression model built using the same set of covariates considered in the ML modeling.
{"title":"Prediction of mortality in heart failure by machine learning. Comparison with statistical modeling","authors":"Domenico Scrutinio , Federica Amitrano , Pietro Guida , Armando Coccia , Gaetano Pagano , Gianni D'addio , Andrea Passantino","doi":"10.1016/j.ejim.2025.01.020","DOIUrl":"10.1016/j.ejim.2025.01.020","url":null,"abstract":"<div><h3>Background</h3><div>Assessing the relative performance of machine learning (ML) methods and conventional statistical methods in predicting prognosis in heart failure (HF) still remains a challenging research field.</div></div><div><h3>Methods</h3><div>The primary outcome was three-year mortality. The following 5 machine learning approaches were used for modeling: Random Forest (RF), Gradient Boosting, Extreme Gradient Boosting (XGBoost), Support Vector Machine, and Multilayer perceptron. We compared the performance of the best performing ML models to the MAGGIC (Meta-analysis Global Group in Chronic Heart Failure) score and a novel logistic regression model (LRM) developed using the same set of variables used to develop the machine learning models. The performance was determined based on discrimination, calibration, and net benefit.</div></div><div><h3>Results</h3><div>The XGBoost and the RF were the best performing ML models. The XGBoost provided the highest discrimination (C-statistic: 0.793) and the lowest Brier score (0.178); the RF model had a C-statistic of 0.779 and provided the highest area under the precision‐recall curve (0.636). Both models were well calibrated. Both the XGboost and RF models outperformed MAGGIC score. The LRM had a C-statistic of 0.811 and a Brier score of 0.160 and was well calibrated. The XGBoost, RF, and LRM gave a higher net benefit than MAGGIC score; the XGBoost, RF, and logistic regression model gave similar net benefit.</div></div><div><h3>Conclusions</h3><div>RF and XGBoost models outperformed MAGGIC in predicting mortality. However, they did not offer any improvement over a logistic regression model built using the same set of covariates considered in the ML modeling.</div></div>","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":"133 ","pages":"Pages 106-112"},"PeriodicalIF":5.9,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-28DOI: 10.1016/j.ejim.2025.02.032
Alexander Schmitt, Michael Behnes, Ibrahim Akin, Tobias Schupp
{"title":"Ischemic heart failure etiology: A misleading definition?<sup>✰</sup>.","authors":"Alexander Schmitt, Michael Behnes, Ibrahim Akin, Tobias Schupp","doi":"10.1016/j.ejim.2025.02.032","DOIUrl":"https://doi.org/10.1016/j.ejim.2025.02.032","url":null,"abstract":"","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":" ","pages":""},"PeriodicalIF":5.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143538009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-28DOI: 10.1016/j.ejim.2025.02.030
Mario Bo, Marco Proietti, Roberto Presta
{"title":"Catheter ablation of atrial fibrillation in older patients: The need for a comprehensive evaluation and management.","authors":"Mario Bo, Marco Proietti, Roberto Presta","doi":"10.1016/j.ejim.2025.02.030","DOIUrl":"https://doi.org/10.1016/j.ejim.2025.02.030","url":null,"abstract":"","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":" ","pages":""},"PeriodicalIF":5.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143537984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-27DOI: 10.1016/j.ejim.2025.02.025
Alain Putot, Nicolas Garin, Jordi Rello, Virginie Prendki
Pneumonia is a leading cause of death and functional decline in the older population. Diagnosis of pneumonia conventionally includes the presence of respiratory signs and symptoms, systemic signs of infection and a radiographic demonstration of lung involvement. Pneumonia diagnosis in the very old patient is compromised by atypical and unspecific presentation, resulting in a high proportion of false positive diagnosis. Chest radiograph is frequently of low quality and inconclusive in older patients. Computed tomography scan and chest ultrasound may provide valuable diagnostic confirmation in uncertain cases. Bacterial pneumonia has been mainly studied, but viruses, among which influenza, SARS-CoV-2, and respiratory syncytial virus, are increasingly recognized as major players. The decision to treat pneumonia is usually based on a triple assessment of diagnostic probability, disease severity and the general assessment of the patient (frailty, comorbidities, place of living, and goals of care). Antimicrobial treatment is probabilistic, targeting common pathogens. The optimal antibiotic treatment depends on epidemiological data, setting of acquisition, comorbidities, risk factors for methicillin-resistant Staphylococcus aureus, Pseudomonas aeruginosa, or aspiration pneumonia, and severity. Recent controlled trials have demonstrated the non-inferiority of short regimen in non-severe community acquired pneumonia, even in older individuals and a five-day antibiotic treatment is recommended in case of clinical improvement. Pneumonia management in older patients requires a comprehensive approach, including control of comorbidities (particularly cardiovascular), nutritional support, rehabilitation, and prevention of aspiration. Finally, pneumonia may be a pre-terminal event in many patients, requiring advanced-care planning and prompt instauration of palliative management.
{"title":"Comprehensive management of pneumonia in older patients.","authors":"Alain Putot, Nicolas Garin, Jordi Rello, Virginie Prendki","doi":"10.1016/j.ejim.2025.02.025","DOIUrl":"https://doi.org/10.1016/j.ejim.2025.02.025","url":null,"abstract":"<p><p>Pneumonia is a leading cause of death and functional decline in the older population. Diagnosis of pneumonia conventionally includes the presence of respiratory signs and symptoms, systemic signs of infection and a radiographic demonstration of lung involvement. Pneumonia diagnosis in the very old patient is compromised by atypical and unspecific presentation, resulting in a high proportion of false positive diagnosis. Chest radiograph is frequently of low quality and inconclusive in older patients. Computed tomography scan and chest ultrasound may provide valuable diagnostic confirmation in uncertain cases. Bacterial pneumonia has been mainly studied, but viruses, among which influenza, SARS-CoV-2, and respiratory syncytial virus, are increasingly recognized as major players. The decision to treat pneumonia is usually based on a triple assessment of diagnostic probability, disease severity and the general assessment of the patient (frailty, comorbidities, place of living, and goals of care). Antimicrobial treatment is probabilistic, targeting common pathogens. The optimal antibiotic treatment depends on epidemiological data, setting of acquisition, comorbidities, risk factors for methicillin-resistant Staphylococcus aureus, Pseudomonas aeruginosa, or aspiration pneumonia, and severity. Recent controlled trials have demonstrated the non-inferiority of short regimen in non-severe community acquired pneumonia, even in older individuals and a five-day antibiotic treatment is recommended in case of clinical improvement. Pneumonia management in older patients requires a comprehensive approach, including control of comorbidities (particularly cardiovascular), nutritional support, rehabilitation, and prevention of aspiration. Finally, pneumonia may be a pre-terminal event in many patients, requiring advanced-care planning and prompt instauration of palliative management.</p>","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":" ","pages":""},"PeriodicalIF":5.9,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143532017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1016/j.ejim.2025.02.028
Jacopo Francesco Imberti, Davide Antonio Mei, Giuseppe Boriani
{"title":"Atrial fibrillation screening: The importance of the patient perspective.","authors":"Jacopo Francesco Imberti, Davide Antonio Mei, Giuseppe Boriani","doi":"10.1016/j.ejim.2025.02.028","DOIUrl":"https://doi.org/10.1016/j.ejim.2025.02.028","url":null,"abstract":"","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":" ","pages":""},"PeriodicalIF":5.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143505287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1016/j.ejim.2025.02.022
Linghua Fu, Yao Du, Pingping Yang, Jinzhu Hu, Qi Chen
{"title":"Glucagon-like peptide-1 receptor agonist for patients with heart failure with preserved ejection fraction and obesity.","authors":"Linghua Fu, Yao Du, Pingping Yang, Jinzhu Hu, Qi Chen","doi":"10.1016/j.ejim.2025.02.022","DOIUrl":"https://doi.org/10.1016/j.ejim.2025.02.022","url":null,"abstract":"","PeriodicalId":50485,"journal":{"name":"European Journal of Internal Medicine","volume":" ","pages":""},"PeriodicalIF":5.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143505318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号