Heart & Lung最新文献

{"title":"The association of social determinants of health and depressive symptoms with quality of life among rural patients with coronary heart disease and heart failure","authors":"Ashmita Thapa Ph.D., RN (Post-doctoral Research Associate) ,&nbsp;Geunyeong Cha Ph.D., RN (Post-doctoral Research Associate) ,&nbsp;Jia-Rong Wu Ph.D., RN, FAHA, FAAN (Professor) ,&nbsp;Martha J. Biddle Ph.D., RN, APRN, CCNS, FAHA (Professor) ,&nbsp;Abigail Latimer PhD, MSW, LCSW, APHSW-C (Assistant Professor) ,&nbsp;Mark B Dignan PhD, MPH (Professor) ,&nbsp;Chin-Yen Lin Ph.D., RN (Assistant Professor) ,&nbsp;JungHee Kang Ph.D., RN (Assistant professor) ,&nbsp;Debra K. Moser PhD, RN, FAHA, FAAN (Professor)","doi":"10.1016/j.hrtlng.2025.09.006","DOIUrl":"10.1016/j.hrtlng.2025.09.006","url":null,"abstract":"<div><h3>Background</h3><div>There are significant health disparities among rural populations, especially in the prevalence and management of coronary heart disease and heart failure. Social determinants of health (SDOH) play a crucial role in these disparities, influencing access to care, mental health, and overall quality of life (QOL). Depressive symptoms, common among rural patients with coronary heart disease and heart failure, may further exacerbate these challenges by mediating the relationship between SDOH and QOL.</div></div><div><h3>Objectives</h3><div>We aimed to examine the association between SDOH and QOL among rural patients with coronary heart disease and heart failure, as well as to determine whether depressive symptoms mediate this relationship.</div></div><div><h3>Methods</h3><div>A cross-sectional analysis (<em>N</em> = 124) was conducted using data from a randomized controlled trial. The Protocol for Responding to and Assessing Patient Assets, Risks, and Experiences questionnaire was used to measure SDOH, depressive symptoms were assessed using the Patient Health Questionnaire-9, and QOL was evaluated using Short Form-12. We performed hierarchical multiple regression and mediation analyses.</div></div><div><h3>Results</h3><div>Higher SDOH risk scores were significantly associated with lower QOL (<em>B</em>= -0.319; <em>p</em> &lt; 0.001). Depressive symptoms mediated this relationship (indirect effect: a*<em>b</em> = -0.624, 95 % confidence interval (CI)= [-1.045, -0.273]), suggesting that individuals with higher SDOH risk had worse depressive symptoms, which in turn led to lower QOL.</div></div><div><h3>Conclusion</h3><div>The SDOH were associated with QOL in rural patients with coronary heart disease and heart failure, and depressive symptoms mediated this relationship. Findings highlight the need for targeted interventions addressing both social determinants and mental health to improve QOL.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 58-64"},"PeriodicalIF":2.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145088231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of the getting into light exercise for heart failure (GENTLE-HF) randomized controlled trial on physical-psychological outcomes and exercise adherence","authors":"Jane Kim BSN, RN ,&nbsp;Ha Do Byon PhD, MS, MPH, RN ,&nbsp;Katherine Platz PhD, RN ,&nbsp;Gabriela Toledo PhD ,&nbsp;Jill Howie-Esquivel PhD, AC/FNP-BC, FAAN","doi":"10.1016/j.hrtlng.2025.09.003","DOIUrl":"10.1016/j.hrtlng.2025.09.003","url":null,"abstract":"<div><h3>Background</h3><div>Few investigators have tested the effect of alternative, gentle exercise interventions among patients with stable heart failure (HF).</div></div><div><h3>Objectives</h3><div>In a 6-month online gentle exercise vs education only intervention program, we evaluated: 1) Change in physical and psychological function; 2) whether age or sex moderates the efficacy of the intervention on physical function; 3) the relationship between quality of life (QOL) and exercise adherence.</div></div><div><h3>Methods</h3><div>Data from the GEtting iNTo Light Exercise for HF (GENTLE-HF) randomized controlled trial (<em>n</em> = 61) was analyzed. Measures included physical function, psychological function, QOL, and exercise adherence. ANCOVA-approach general linear models were used to examine physical and psychological function, adjusting for age, years of education, baseline scores, and grouping (control or intervention). The moderating effects of age and sex were tested by incorporating interaction terms into the ANCOVA-based models. Pearson correlation analysis was used to examine the relationship between QOL and adherence.</div></div><div><h3>Results</h3><div>Compared to control, the intervention group had improved upper body strength (<em>p</em> = .004), lower body strength (<em>p</em> = .002), and endurance (<em>p</em> = .003). Age moderated the effect of the intervention on upper body strength (<em>p</em> = .012) and endurance (<em>p</em> = .028). Exercise adherence was high at 84.4 %. Greater QOL was associated with higher adherence (<em>p</em> = .039).</div></div><div><h3>Conclusions</h3><div>The online yoga intervention led to improved physical function, had an additional positive effect for participants over 65 years, and had high adherence rates. These findings can inform future large-scale yoga studies that may influence future study designs and supplement physical activity guidelines, ultimately improving patient outcomes.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 47-57"},"PeriodicalIF":2.6,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145076645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing DeepSeek and GPT-4o in ECG interpretation: Is AI improving over time?","authors":"Serkan Günay, Ahmet Öztürk, Anılcan Tahsin Karahan, Mert Barindik, Seval Komut, Yavuz Yiğit","doi":"10.1016/j.hrtlng.2025.08.007","DOIUrl":"https://doi.org/10.1016/j.hrtlng.2025.08.007","url":null,"abstract":"<p><strong>Background: </strong>DeepSeek is a recently launched large language model (LLM), whereas GPT-4o is an advanced ChatGPT version whose electrocardiography (ECG) interpretation capabilities have been previously studied. However, DeepSeek's performance in this domain remains unexplored.</p><p><strong>Objectives: </strong>This study aims to evaluate DeepSeek's accuracy in ECG interpretation and compare it with GPT-4o, emergency medicine specialists, and cardiologists. A secondary aim is to assess any performance changes in GPT-4o over one year.</p><p><strong>Methods: </strong>Between February 9 and March 1, 2025, 40 ECG images (20 daily routine, 20 more challenging) from the book 150 ECG Cases were evaluated by both GPT-4o and DeepSeek, each model tested 13 times. The accuracy of their responses was compared with previously collected answers from 12 cardiologists and 12 emergency medicine specialists. GPT-4o's 2025 performance was compared to its 2024 results on identical ECGs.</p><p><strong>Results: </strong>GPT-4o outperformed DeepSeek with higher median correct answers on daily routine (14 vs. 12), more challenging (13 vs. 10), and total ECGs (27 vs. 22) with statistically significant differences (p=0.048, p<0.001, p<0.001). A moderate agreement was observed between the responses provided by GPT-4o (p<0.001, Fleiss Kappa=0.473), while a substantial agreement was observed in the responses provided by DeepSeek (p<0.001, Fleiss Kappa=0.712). No significant year-over-year improvement was observed in GPT-4o's performance.</p><p><strong>Conclusion: </strong>This first evaluation of DeepSeek in ECG interpretation reveals its performance is lower than that of GPT-4o and human experts. While GPT-4o demonstrates greater accuracy, both models fall short of expert-level performance, underscoring the need for caution and further validation before clinical integration.</p>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"All-inclusive hearts: bridging gaps in heart failure treatment","authors":"Janet Roman DNP, ACNP-BC, ACHPN, CHFN, FAAHFN","doi":"10.1016/j.hrtlng.2025.08.004","DOIUrl":"10.1016/j.hrtlng.2025.08.004","url":null,"abstract":"","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"74 ","pages":"Page A1"},"PeriodicalIF":2.6,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145058776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic value of non-invasive endothelial function index in emergency department patients with undifferentiated chest pain","authors":"Randa Dhaoui ,&nbsp;Tesnim Hassine ,&nbsp;Khaoula bel Haj Ali ,&nbsp;Marwa Toumia ,&nbsp;Feten Lamti ,&nbsp;Adel Sekma ,&nbsp;Hamdi Boubaker ,&nbsp;Hajer Yaakoubi ,&nbsp;Asma Zorgati ,&nbsp;Riadh Boukef ,&nbsp;Wahid Bouida ,&nbsp;Mohamed Amine Msolli ,&nbsp;Semir Nouira","doi":"10.1016/j.hrtlng.2025.09.005","DOIUrl":"10.1016/j.hrtlng.2025.09.005","url":null,"abstract":"<div><h3>Background</h3><div>Stratifying the cardiovascular risk for patients consulting for chest pain (CP) is sometimes difficult. An easy method to predict the prognosis in these patients could be helpful.The aim of the study was to determine the prognostic performance of endothelial function assessment using endothelial peripheral arterial tonometry (Endo-PAT).</div></div><div><h3>Methods</h3><div>This was a prospective study conducted in emergency departments (ED) from March 2016 to September 2017, including patients presenting to the ED for non-traumatic CP. All patients underwent assessment of peripheral endothelial function, by reactive hyperemia index (RHI), using Endo-PAT device. RHI &lt;1.19 identified endothelial dysfunction. Patients were followed by telephone contact, during one month, for major adverse cardiovascular events (MACE). The prognostic performance of RHI was determined by the area under Receiver Operating Characteristic (ROC) curve.</div></div><div><h3>Results</h3><div>We studied 503 patients with non-traumatic CP. During 1-month follow up, 4.6 % patients had developed MACE. These patients had lower RHI compared to those without MACE (1.24 [IQR: 1.14–1.38] vs 1.50 [IQR: 1.24–1.85], <em>p</em> = 0.04). Area under the ROC Curve at 30-day follow-up was 0.74 for RHI associated to TIMI risk score. The sensitivity, the specificity, the positive and negative predictive value for prediction of MACE at the best cut-off of RHI were 35 %, 83 %, 9 % and 96 % respectively. The addition of RHI to TIMI score improves the sensitivity and negative predictive value.</div></div><div><h3>Conclusion</h3><div>Combined to TIMI score, RHI testing is a good prognostic tool in patients with undifferentiated CP.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 34-39"},"PeriodicalIF":2.6,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of BUG-SAFE (Bougie guide safe percutaneous tracheostomy) to prevent airway loss in critically Ill patients: Cohort study","authors":"Perez-Garzón Michel ,&nbsp;Muñoz Claros Conny ,&nbsp;Abello-Sánchez Mauricio ,&nbsp;Quecano-Rosas Cesar","doi":"10.1016/j.hrtlng.2025.08.005","DOIUrl":"10.1016/j.hrtlng.2025.08.005","url":null,"abstract":"<div><h3>Background</h3><div>The Bougie Guide Safe Percutaneous Tracheostomy (BUG-SAFE) technique is a novel approach designed to reduce airway loss and complications during tracheostomy in ventilated patients.</div></div><div><h3>Methods</h3><div>We conducted a retrospective cohort study of ICU patients (2020–2023) undergoing tracheostomy with the BUG-SAFE technique to facilitate prolonged weaning from mechanical ventilation.</div></div><div><h3>Results</h3><div>Of 1286 ICU admissions, 128 patients were included. Complications occurred in 17.2 % (mainly bleeding), and one death (0.7 %) was reported. No cases of hypoxemia or airway loss were observed. Risk of complications was associated with ICU stay, ventilation duration, APACHE II scores, and oxygen debt. BUG-SAFE showed a high sensitivity for detecting complication-related mortality. The technique also reduces aerosolization, enhancing safety for healthcare providers.</div></div><div><h3>Conclusions</h3><div>BUG-SAFE is a safe, feasible bedside technique with low complication rates. It ensures airway security and minimizes aerosol generation, making it suitable for both patients and healthcare personnel.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 40-46"},"PeriodicalIF":2.6,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Symptoms on the first day after discharge from the intensive care unit:A cross-sectional study","authors":"Mette Kure Nikolaisen MSc, RN, CCN ,&nbsp;Kristin Hofsø PhD, RN, CCN ,&nbsp;Tone Rustøen PhD, RN ,&nbsp;Johan Ræder PhD, MD ,&nbsp;Milada Hagen PhD ,&nbsp;Brita Fosser Olsen PhD, RN, CCN","doi":"10.1016/j.hrtlng.2025.09.004","DOIUrl":"10.1016/j.hrtlng.2025.09.004","url":null,"abstract":"<div><h3>Background</h3><div>Data on intensive care unit (ICU) patients’ symptom experiences shortly after ICU discharge are scarce.</div></div><div><h3>Objectives</h3><div>To determine prevalence, frequency, severity and distress of symptoms, and to investigate if possible predictive demographic and clinical factors are associated with a high number of symptoms the first day after ICU discharge.</div></div><div><h3>Methods</h3><div>In a cross-sectional study in Norway, thirty-two symptoms were evaluated in adult ICU survivors using the Memorial Symptom Assessment Scale. Data on prevalence (yes/no), frequency and severity (4-point scales) and distress (5-point scales) were collected. Possible associations between selected predictive demographic and clinical factors and having a high number (i.e.≥12) of symptoms were analysed using logistic regression analyses.</div></div><div><h3>Results</h3><div>The patients (<em>n</em>=155) reported a median of 12 symptoms (range:0–22). Lack of energy and dry mouth were most prevalent (83%). Lack of energy, dry mouth, and difficulty sleeping were most frequent (median=4). Problems with sexual interest/activity (median=3.5), lack of energy, dry mouth, difficulty sleeping, pain, vomiting, feeling sad and worrying were most severe (median=3), and problems with sexual interest/activity (median=4), difficulty sleeping, vomiting, feeling sad and worrying (median=3) were most distressing. Patients admitted to surgical wards were more than twice as likely to report a high number of symptoms (OR=2.23;95% CI [1.08,4.63]) than those admitted to medical wards (<em>p</em>=0.031).</div></div><div><h3>Conclusions</h3><div>Half of ICU survivors self-reported ≥12 symptoms the first day after ICU discharge. The most prevalent symptoms were not the most distressful, highlighting the need to screen for multiple symptoms and dimensions to provide target symptom relief and optimize rehabilitation.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 26-33"},"PeriodicalIF":2.6,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of AI chatbots for patient education and information on chronic obstructive pulmonary disease","authors":"Pınar Merç ,&nbsp;Cansu Şahbaz Pirinççi ,&nbsp;Emine Cihan","doi":"10.1016/j.hrtlng.2025.09.002","DOIUrl":"10.1016/j.hrtlng.2025.09.002","url":null,"abstract":"<div><h3>Background</h3><div>Chronic obstructive pulmonary disease (COPD) is a chronic and progressive disease that affects patients' quality of life and functional capacity. With its widespread use and ease of access, AI chatbots stand out as an alternative source of patient-centered information and education.</div></div><div><h3>Objectives</h3><div>To evaluate the readability and accuracy of information provided by ChatGPT, Gemini, and DeepSeek in COPD.</div></div><div><h3>Methods</h3><div>Ten most frequently asked questions and answers regarding COPD in English were provided using three AI chatbots (ChatGPT-4 Turbo, Gemini 2.0 Flash, DeepSeek R1). Readability was assessed using the Flesch-Kincaid Grade Level (FKGL), while information quality was analyzed by five physiotherapists based on the guidelines. Responses were graded using a 4-point system from “excellent response requiring no explanation” to “unsatisfactory requiring significant explanation.” Statistical analyses were performed on SPSS.</div></div><div><h3>Results</h3><div>Overall, all three AI chatbots responded to questions with similar quality, with Gemini 2.0 providing a statistically higher quality response to question 4 (<em>p</em> &lt; 0.05). In terms of readability of the answers, DeepSeek was found to have better readability on Q5 (12.01), Q8 (9.24), Q9 (13.1) and Q10 (8.73) compared to ChatGPT (Q5:13.9, Q8:11.92, Q9:17.15, Q10:9.88) and Gemini (Q5:18.22, Q8:15.47, Q9:17.42, Q10:9.38). Gemini was observed to produce more complex and academic level answers on more questions (Q4, Q5, Q8).</div></div><div><h3>Conclusions</h3><div>ChatGPT, Gemini, and DeepSeek provided evidence-based answers to frequently asked patient questions about COPD. DeepSeek showed better readability performance for many questions. AI chatbots may serve as a valuable clinical tool for COPD patient education and disease management in the future.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 21-25"},"PeriodicalIF":2.6,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The genetic support for the causal relationship between 91 circulating inflammatory proteins and pneumothorax: A two-sample mendelian randomization study","authors":"Changshuai Zhou ,&nbsp;Ran Zhang","doi":"10.1016/j.hrtlng.2025.09.001","DOIUrl":"10.1016/j.hrtlng.2025.09.001","url":null,"abstract":"<div><h3>Background</h3><div>Pneumothorax, a common pleural disease, has an unclear pathogenesis. Observational studies suggest that inflammation may directly or indirectly contribute to the development of pneumothorax.</div></div><div><h3>Objectives</h3><div>To investigate the causal relationship between circulating inflammatory proteins and pneumothorax using Mendelian randomization (MR) analysis.</div></div><div><h3>Methods</h3><div>We conducted a two-sample Mendelian randomization (MR) analysis by combining genome-wide association study (GWAS) data on 91 circulating inflammatory proteins with pneumothorax GWAS data. Five MR methods were applied: Inverse Variance Weighted (IVW), MR-Egger, Weighted Median, Weighted Mode, and Simple Mode. Directionality was assessed using the MR Steiger test. Sensitivity analyses included Cochran’ s Q test, the MR-PRESSO global test, the MR-Egger regression intercept test, and a leave-one-out analysis. To further mitigate confounding, multivariable MR analyses were conducted using GWAS data on biological and phenotypic age as covariates.</div></div><div><h3>Results</h3><div>Four inflammatory proteins were causally associated with pneumothorax. Protective proteins included Interleukin-17A (IL-17A) [OR = 0.83, 95 % CI (0.69, 0.99), <em>p</em> = 0.04] and SIR2-like protein 2 (SIRT2) [OR = 0.72, 95 % CI (0.57, 0.93), <em>p</em> = 0.01]. Risk-associated proteins included Interleukin-13 (IL-13) [OR = 1.23, 95 % CI (1.03, 1.47), <em>p</em> = 0.02] and TNF-related apoptosis-inducing ligand (TRAIL) [OR = 1.22, 95 % CI (1.02, 1.44), <em>p</em> = 0.02]. Multivariable MR confirmed the robustness of the associations, particularly for IL-13. Sensitivity analyses revealed no substantial pleiotropy or heterogeneity.</div></div><div><h3>Conclusions</h3><div>The results yield novel perspectives on the etiological association between systemic inflammatory mediators and pneumothorax pathogenesis, potentially identifying candidate biomarkers for risk stratification and therapeutic targeting in pneumothorax management.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 13-20"},"PeriodicalIF":2.6,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of in-hospital mortality in patients with acute myocardial infarction following primary percutaneous coronary intervention: A machine learning approach","authors":"Bayu Fandhi Achmad PhD, RN ,&nbsp;Jun-Neng Roan M.D., PhD ,&nbsp;Chao-Hung Wang M.D., PhD ,&nbsp;Mei-Ling Tsai M.S., PhD ,&nbsp;Shan-Tair Wang PhD ,&nbsp;Hsing-Mei Chen PhD, RN","doi":"10.1016/j.hrtlng.2025.08.006","DOIUrl":"10.1016/j.hrtlng.2025.08.006","url":null,"abstract":"<div><h3>Background</h3><div>In-hospital mortality in patients with acute myocardial infarction (AMI) following primary percutaneous coronary intervention (pPCI) remains a significant concern. Developing a predictive model of in-hospital mortality is crucial for identifying high-risk patients, guiding clinical decisions, and preventing in-hospital mortality. Machine learning (ML) may analyze patterns in large datasets and provide accurate predictions of in-hospital mortality in AMI patients following pPCI.</div></div><div><h3>Objectives</h3><div>To develop and validate a model for predicting in-hospital mortality in AMI patients following pPCI using ML algorithms.</div></div><div><h3>Methods</h3><div>1968 AMI patients after pPCI were identified from the SCIENCE database between 2019 and 2023. Four supervised ML algorithms (Random Forest, XGBoost, AdaBoost, and Logistic Regression) were used to construct the models. The performance of the models was evaluated by the area under the curve (AUC), accuracy, sensitivity, specificity, and F1-score.</div></div><div><h3>Results</h3><div>The overall in-hospital mortality rate was 17.68 %. The model constructed using the Random Forest provided the best performance for discriminating between patients with a status of alive and dead, with an AUC of 0.976. The models constructed from the XGBoost and AdaBoost algorithms had lower discriminatory performance than the RF model, with AUCs of 0.975 and 0.974, respectively. The model based on the LR algorithm had the lowest AUC of 0.973.</div></div><div><h3>Conclusions</h3><div>A predictive model constructed using the RF algorithm performed the best for predicting in-hospital mortality in AMI patients following pPCI. Implementing the model in a clinical setting may assist nurses/physicians in identifying high-risk patients, prioritizing them for appropriate treatment, and potentially reducing in-hospital mortality.</div></div>","PeriodicalId":55064,"journal":{"name":"Heart & Lung","volume":"75 ","pages":"Pages 1-12"},"PeriodicalIF":2.6,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145020836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}