International Journal of General Medicine最新文献

{"title":"High-Mobility Group Box-1 as a Predictor for Malignant Brain Edema Following Mechanical Thrombectomy in Acute Ischemic Stroke Patients.","authors":"Xiao Chen, Yan E, Wei Wang, Yong Huang, Xueting Xin, Gang Chen","doi":"10.2147/IJGM.S529326","DOIUrl":"10.2147/IJGM.S529326","url":null,"abstract":"<p><strong>Background and purpose: </strong>Emerging experimental evidence has established that high-mobility group box 1 (HMGB-1) plays a pivotal role in cerebral ischemia pathogenesis, primarily through mediating neuroinflammatory cascades following ischemic injury. This study sought to investigate the potential association between circulating HMGB-1 levels and the risk of malignant brain edema (MBE) in patients undergoing mechanical thrombectomy (MT).</p><p><strong>Methods: </strong>This study prospectively recruited patients presenting with large vessel occlusive stroke in the anterior circulation and receiving MT treatment. Serum HMGB-1 levels were quantitatively assessed for all participants upon hospital admission. MBE was defined as defined as a midline shift of ≥5 mm observed on follow-up neuroimaging after MT. Multivariate logistic regression analyses were conducted to investigate the potential correlation between serum HMGB-1 concentrations and MBE development.</p><p><strong>Results: </strong>Among the cohort of 261 eligible patients (mean age: 69.7 years; male: 166 [63.6%]), 59 individuals (22.6%; 95% confidence interval [CI]: 17.6%-28.3%) developed MBE. After adjusted for demographic characteristics and other potential confounders, multivariate logistic regression demonstrated that higher serum HMGB-1 levels were associated with an increased risk of MBE (odds ratios [OR], highest vs lowest quartile: 3.130; 95% CI, 1.077-9.098; <i>P</i> = 0.036). In addition, restricted cubic spline analysis revealed a dose-response relationship between elevated serum HMGB-1 levels and MBE risk (<i>P</i> for non-linearity=0.764).</p><p><strong>Conclusion: </strong>This study confirmed that elevated circulating HMGB-1 levels were significantly associated with MBE after MT. These findings suggested that HMGB-1 could serve as a predictive biomarker for post-MT MBE risk, potentially enabling early identification of high-risk patients who may benefit from intensified monitoring or targeted therapeutic interventions.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3393-3400"},"PeriodicalIF":2.1,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12206528/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predictive Value of TRUS and CEUS Parameters for Lymph Node Metastasis in Rectal Cancer: A Retrospective Study.","authors":"Shitao Su, Xuanzhang Huang, Xigui Li, Jun Meng, Jianyuan Huang","doi":"10.2147/IJGM.S519039","DOIUrl":"10.2147/IJGM.S519039","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the predictive value of transrectal ultrasound (TRUS) combined with qualitative and quantitative parameters of contrast-enhanced ultrasound (CEUS) for lymph node metastasis (LNM) in rectal cancer (RC).</p><p><strong>Patients and methods: </strong>This retrospective study analyzed preoperative clinical data, qualitative and quantitative TRUS and CEUS parameters, and postoperative pathological data from 535 patients with RC confirmed by surgical pathology. Independent predictors of LNM were identified through univariate and multivariate binary logistic regression analysis. Two predictive models were developed: one based on TRUS/CEUS parameters, and another combining ultrasonographic parameters with clinical indicators. Model calibration was evaluated using the Hosmer-Lemeshow test, and diagnostic performance was quantified via receiver operating characteristic (ROC) curve analysis.</p><p><strong>Results: </strong>Multivariate analysis revealed ultrasonographic tumor (uT) stage(OR=1.751,P=0.042), ultrasonographic nodal (uN) stage (OR=2.279,P<0.001), peak intensity ratio(PI-ratio: OR=0.799,P<0.001), and slope ratio (S-ratio: OR=0.997,P=0.008) as independent predictors of LNM. When incorporating clinical indicators, the combined model identified uN stage (OR=2.351,P<0.001), PI-ratio (OR=0.784,P<0.001), PI-difference (OR=0.997,P=0.011), S-ratio (OR=1.046,P=0.048), CEA (OR=2.324,P<0.001), and CA199 (OR=3.020,P=0.003) as significant predictors. The US model demonstrated an AUC of 0.792 (95% CI: 0.755-0.829), while the combined model achieved superior performance with an AUC of 0.815 (95% CI: 0.780-0.850) (Z=-2.076, P=0.038). Both models showed satisfactory calibration (Hosmer-Lemeshow test: P>0.05).</p><p><strong>Conclusion: </strong>The predictive model constructed based on preoperative TRUS combined with CEUS quantitative parameters, along with its combined model incorporating clinical biomarkers (CEA, CA199), can effectively predict LNM in RC, providing a non-invasive and quantifiable preoperative assessment tool for clinical practice.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3335-3345"},"PeriodicalIF":2.1,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gustave Roussy Immune Score (GRImScore) as a Novel Prognostic Index for Stage III Gastric Cancer Patients: A Real-World Retrospective Study.","authors":"Xiaofeng Zhao, Fen Zhang, Panpan Xing, Chunyan Jiang, Danqing Li, Dianchao Wu","doi":"10.2147/IJGM.S515795","DOIUrl":"10.2147/IJGM.S515795","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to investigate whether Gustave Roussy immune score (GRImScore) serves as a novel prognostic index for predicting survival in patients with advanced gastric cancer.</p><p><strong>Methods: </strong>GRImScore was based on three objective markers: (1) albumin level (<3.5 g/L = 1 point, ≥3.5 g/L = 0 point); (2) lactate dehydrogenase level (≥250 U/L = 1 point, <250 U/L = 0 point); (3) neutrophil to lymphocyte ratio (NLR) (≥2.70 = 1 point, <2.70 = 0 point). According to GRImScore, these patients were divided into low GRImScore group (0 points) and high GRImScore group (1, 2, or 3 points). Kaplan-Meier method was applied to draw survival curves for disease free survival (DFS) and overall survival (OS), and differences among these groups were analyzed using Log rank tests. Univariate and multivariate Cox proportional hazards models were used to analyze the relationship between the enrolled parameters and OS. Nomograms were developed based on the results of multivariate Cox regression analysis using the consistency index (C-index) and decision curve analyses (DCA) for internal validation.</p><p><strong>Results: </strong>Based on GRImScore, 134 patients were in low GRImScore group and 61 were in high GRImScore group. The median DFS and OS in low GRImScore group were significantly longer than that in high GRImScore group (DFS: 40.52 months vs 22.83 months, χ²=7.033, <i>P</i>=0.0080; OS: 55.07 months vs 31.83 months, χ²=6.328, <i>P</i>=0.0119). According to multivariable Cox analysis, GRImScore was significantly associated with DFS (HR, 2.798; 95% CI: 1.711-11.008, <i>P</i> = 0.001) and OS (HR, 2.631; 95% CI: 1.645-10.725, <i>P</i> = 0.001). The nomogram constructed by multivariate Cox analysis showed good performance in predicting DFS (C-index: 0.717, 95% CI: 0.595-0.814) and OS (C-index: 0.725, 95% CI: 0.605-0.819).</p><p><strong>Conclusion: </strong>GRImScore, a novel prognostic index, is a prognostic indicator for patients with advanced gastric cancer. Nomograms based on the GRImScore showed good predictive ability.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3373-3391"},"PeriodicalIF":2.1,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205707/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Prognostic and Early Efficacy Prediction Value of Baseline C-Reactive Protein-Albumin-Lymphocyte (CALLY) Index in Advanced Pancreatic Cancer.","authors":"Liangxue Zhu, Yuanyuan Kong, Yajun Xing, Mingyun Wang","doi":"10.2147/IJGM.S529776","DOIUrl":"10.2147/IJGM.S529776","url":null,"abstract":"<p><strong>Purpose: </strong>In this retrospective study, we aimed to investigate the prognostic and early efficacy prediction value of baseline CALLY index in advanced pancreatic cancer.</p><p><strong>Patients and methods: </strong>We analyzed the clinical and follow-up data of 252 metastatic pancreatic cancer patients diagnosed at Nanjing Gaochun People's Hospital from January 2019 to June 2024. The optimal cut-off for the CALLY index was determined by maximizing Youden's index (J = sensitivity + specificity - 1) through receiver operating characteristic (ROC) curve analysis. Early treatment efficacy was evaluated according to RECIST 1.1 criteria based on radiological assessments at 6~9 weeks after initiating first-line therapy. The effect of the CALLY index on survival and early efficacy in first-line treatment was analyzed using the Kaplan-Meier method and the Cox proportional hazards model. The CALLY index was calculated as: (Albumin × Lymphocyte)/(CRP × 104).</p><p><strong>Results: </strong>The cut-off value of the CALLY index for predicting survival was determined at 0.27. The area under the curve (AUC) was 0.725. With a cut-off value of 0.27, patients were divided into two groups: those with CALLY ≥0.27 and those with CALLY <0.27. The median overall survival was 12 and 5 months respectively (P < 0.01). CALLY Index ≥ 0.27 was associated with better survival outcomes. Cox regression analysis revealed that a low CALLY index (<0.27) was independent predictors of poor prognosis. CALLY index of 0.27 for predicting early efficacy in advanced pancreatic cancer patients with an area under the curve (AUC) of 0.73, and there was a statistically significant difference in early efficacy of first-line therapy between the high and low CALLY groups (P = 0.022).</p><p><strong>Conclusion: </strong>Our findings suggest that the baseline CALLY index is a promising predictive biomarker for early efficacy and prognosis of patients with Pancreatic cancer, though its reliability requires validation in multicenter prospective studies.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3363-3372"},"PeriodicalIF":2.1,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205749/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of Intraoperative Dexamethasone on Postoperative Complications and Long-Term Survival in Patients with Non-Small Cell Lung Cancer: A retrospective Propensity Score-Matched Study.","authors":"Wenzhi Zhu, Liping Zhu, Xiaoyi Wang, Hongyu Tan","doi":"10.2147/IJGM.S524652","DOIUrl":"10.2147/IJGM.S524652","url":null,"abstract":"<p><strong>Objective: </strong>This study investigated the impact of intraoperative dexamethasone on postoperative complications and long-term survival in patients with non-small cell lung cancer (NSCLC) undergoing surgery.</p><p><strong>Methods: </strong>Patients with NSCLC who underwent lung resection between January 1, 2006, and December 31, 2009, were included. Patients receiving dexamethasone formed the dexamethasone (DXM) group, while those who did not were assigned to the non-dexamethasone (non-DXM) group. Propensity score matching (PSM) was applied to minimize confounding bias. The primary endpoint was the incidence of postoperative complications.</p><p><strong>Results: </strong>Of the 579 patients included, 224 received intraoperative DXM, while 355 did not. PSM produced a matched cohort of 400 patients (200 in each group). After matching, the DXM group had significantly lower incidences of postoperative pneumonia (P < 0.05), reduced intensive care unit (ICU) ICU occupancy, and shorter postoperative hospital stays (PHS) compared with the non-DXM group (P < 0.05). No significant differences were observed in overall survival (OS) or recurrence-free survival (RFS) between the groups.</p><p><strong>Conclusion: </strong>Intraoperative DXM use reduced the incidence of postoperative pneumonia, ICU occupancy, and PHS. However, no clear association was found between intraoperative DXM use and long-term survival outcomes in NSCLC patients.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3347-3361"},"PeriodicalIF":2.1,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12206909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association Between the Circadian Rhythm of Arterial Blood Pressure and White Matter Lesions in Hospitalized Hypertensive Patients: A Cross-Sectional Study.","authors":"Yu Shen, Wenwen Xiang, Shenjian Chen, Zhou Hou, Daojun Hong","doi":"10.2147/IJGM.S521364","DOIUrl":"10.2147/IJGM.S521364","url":null,"abstract":"<p><strong>Background: </strong>White matter lesions (WMLs) are associated with an increased risk of stroke, cognitive impairment, and vascular dementia. Hypertension stands as the most significant modifiable independent risk factor contributing to WMLs. However, little is known about the relationship between WMLs and altered circadian rhythms of blood pressure (BP) in patients with essential hypertension.</p><p><strong>Methods: </strong>This cross-sectional observational study enrolled patients diagnosed with essential hypertension. Participants were stratified into mild, moderate, and severe WMLs subgroups based on Fazekas scale assessments, with a control group of individuals without WMLs. All participants underwent 24-hour ambulatory BP monitoring and were classified according to circadian rhythm patterns: dipper, non-dipper, and antidipper. Comparative analyses were performed on demographic characteristics, ambulatory BP profiles, and circadian rhythm patterns across groups. Univariate analysis and multivariate logistic regression were employed to identify independent risk factors for WMLs.</p><p><strong>Results: </strong>33 in the control group and 112 in the WMLs group were included. There were significant differences in age, history of diabetes mellitus and cardiovascular disease (<i>p</i><0.05). Compared with the control group, mean 24h systolic BP (SBP), mean daytime SBP (DSBP), and mean nocturnal SBP (NSBP) were greater in the WMLs group, and 24hSBPSD, DSBPSD, DDBPSD, and NSBPSD were greater in the WMLs group (<i>p</i><0.05). The circadian rhythms were significantly different between the WMLs group and the control group (<i>p</i><0.05). Age, non-dipper, and antidipper pattern were found to be independent risk factors for WMLs. Multivariate logistic regression revealed that age (OR 1.128 CI 1.082-1.175, <i>p</i><0.001) and the non-dipper pattern (OR 4.855 CI 1.062-22.184, <i>p</i>=0.042) were independent risk factors for WMLs.</p><p><strong>Conclusion: </strong>Age and non-dipper and antidipper patterns are associated with an increased risk of WMLs. Non-dipper BP is an independent risk factor for WMLs. Middle-aged and elderly people with primary hypertension with non-dipper BP need to manage and control nocturnal BP.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3323-3333"},"PeriodicalIF":2.1,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204095/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144527830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence, Awareness, and Factors Associated with Hypertension Among Adults in Rural Southwestern Uganda: A Baseline Survey.","authors":"Grace Kansiime, Edwin Nuwagira, Paul Stephen Obwoya, Joseph Baruch Baluku, Michael Kanyesigye, Christine Twesiime, Peter Ssebutinde, Rose Muhindo, Anthony Muyingo, Keneth Kananura, Pliers Denis Tusingwire, Esther C Atukunda, Robert Kalyesubula, Francis Bajunirwe, Anthony Muiru","doi":"10.2147/IJGM.S522911","DOIUrl":"10.2147/IJGM.S522911","url":null,"abstract":"<p><strong>Background: </strong>Hypertension is the leading cause of preventable deaths globally. However, reports on its prevalence and risk factors in rural sub-Saharan Africa have been inconsistent, making targeted interventions challenging. This study examines the prevalence, awareness, and associated factors of hypertension among adults in a rural community in southwestern Uganda.</p><p><strong>Methods: </strong>We conducted a baseline survey in Ngango, Mbarara district, enrolling adults aged 18-79 years from eleven villages. Research assistants and community health workers recruited participants from their homes using the WHO STEPS questionnaire, collecting data on demographics, lifestyle behaviors (tobacco and alcohol use, diet, and physical activity), and other risk factors. Blood pressure (BP) was measured three times, with hypertension defined as BP ≥140/90 mmHg or self-reported antihypertensive use. Logistic regression was applied to identify factors associated with hypertension.</p><p><strong>Results: </strong>A total of 953 adults were enrolled, with a median age of 43 years (IQR: 30-57). Women accounted for 61.5%, and only 43.5% recalled ever having their blood pressure measured. Hypertension prevalence was 27.3%, with 61.5% of cases undiagnosed. Among those receiving treatment (27.7%), 65.3% had controlled blood pressure. Despite 66.8% of participants reporting regular physical activity, 63.7% were overweight. The key factors associated with hypertension included age over 40 years (OR: 2.26), consuming fewer than three servings of fruits or vegetables per week (OR: 1.62), and being overweight (OR: 1.57) or obese (OR: 2.73).</p><p><strong>Conclusion: </strong>Hypertension is highly prevalent in rural southwestern Uganda, underscoring the need for targeted interventions-especially within a relatively young and physically active population.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3289-3300"},"PeriodicalIF":2.1,"publicationDate":"2025-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12199733/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144505624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasonic Parameters as Biomarkers for Tumor Staging and Aggressiveness in Breast Cancer: Correlation with GP73 and miR-27a.","authors":"Zi-Yu Tao, Rong Rong, Lei-Ping Zhou","doi":"10.2147/IJGM.S521769","DOIUrl":"10.2147/IJGM.S521769","url":null,"abstract":"<p><strong>Objective: </strong>To investigate correlations between CEUS parameters and serum GP73/miR-27a in breast cancer.</p><p><strong>Methods: </strong>In the study, 117 highly suspected breast cancer diagnosed and treated in our hospital during March 2022 to April 2024 were included. Meanwhile, pathologic examination was used as the gold standard for diagnosis in this study. The 117 subjects were divided into breast cancer group (69 cases) and non-breast cancer group (48 cases). Both groups underwent contrast-enhanced ultrasound (CEUS), and the parameters of peak intensity (PI), time to peak (TTP), wash-inslope (WIS), gradient (Grad) were recorded. The levels of GP73 and miR-27 in serum of both groups were examined. The relationship between ultrasonography parameters and serum GP73 and miR-27a expression levels was evaluated by correlation analysis.</p><p><strong>Results: </strong>CEUS parameters (PI, WIS, Grad) in cancer patients were significantly higher than benign group (P<0.05), while TTP was lower. GP73 and miR-27a levels were elevated in cancer patients (P<0.05), with stage III-IV showing higher values than stage I-II (P<0.05). GP73 correlated positively with Grad (r=0.330, P=0.006), while miR-27a correlated with WIS (r=0.311, P=0.009) and Grad (r=0.424, P<0.001). ROC analysis revealed AUCs of 0.771-0.776 for individual parameters and 0.945 for combined markers.</p><p><strong>Conclusion: </strong>CEUS parameters and serum GP73/miR-27a levels correlate with breast cancer severity, demonstrating synergistic diagnostic value (AUC=0.945), supporting their combined use for early detection and progression assessment.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3313-3321"},"PeriodicalIF":2.1,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12198353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144505645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advances in Machine Learning for Mechanically Ventilated Patients.","authors":"Yue Xu, Jingjing Xue, Yunfeng Deng, Lili Tu, Yu Ding, Yibing Zhang, Xinrui Yuan, Kexin Xu, Liangmei Guo, Na Gao","doi":"10.2147/IJGM.S515170","DOIUrl":"10.2147/IJGM.S515170","url":null,"abstract":"<p><strong>Background: </strong>Mechanical ventilation, a key ICU life-support tech, carries risks. ML can optimize patient management, improving clinical decisions, patient outcomes, and resource use.</p><p><strong>Objective: </strong>This review aims to summarize the current applications, challenges, and future directions of machine learning in managing mechanically ventilated patients, focusing on prediction models for extubation readiness, oxygenation management, ventilator parameter optimization, clinical prognosis, and pulmonary function assessment.</p><p><strong>Methods: </strong>Multiple databases, including PubMed, Web of Science, CNKI and Wanfang Data were systematically searched for studies on machine learning in mechanical ventilation management. Keywords included mechanical ventilation, machine learning, weaning, etc. We reviewed recent studies on using machine learning to predict successful extubation, optimize oxygenation targets, personalize ventilator settings, forecast mechanical ventilation duration and clinical outcomes. The review also examined challenges of integrating machine learning into clinical practice, such as data integration, model interpretability, and real - time performance requirements.</p><p><strong>Results: </strong>Machine learning models have demonstrated significant potential in predicting successful extubation, optimizing oxygenation strategies through non-invasive blood gas prediction, and dynamically adjusting ventilator parameters using reinforcement learning. These models have also shown promise in predicting mechanical ventilation duration, clinical prognosis and pulmonary function parameters. However, challenges remain, including data heterogeneity, model generalizability, workflow integration, and the need for multicenter validation.</p><p><strong>Conclusion: </strong>Machine learning shows great potential for improving intensive care quality and efficiency in mechanically ventilated patients. However, challenges like model interpretability, real-time performance, clinical and validation remain. Future research needs to focus on these limitations via large-scale, multicenter trials, better data standardization, and improved physician training to safely and effectively integrate ML into clinical practice. Collaboration among medical, engineering, and ethical experts is also essential for advancing this promising field.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3301-3311"},"PeriodicalIF":2.1,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12191144/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144496158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Construction and Validation of a Hospital Mortality Risk Model for Advanced Elderly Patients with Heart Failure Based on Machine Learning.","authors":"Shuai Shang, Meng Wei, Huasheng Lv, Xiaoyan Liang, Yanmei Lu, Baopeng Tang","doi":"10.2147/IJGM.S514972","DOIUrl":"10.2147/IJGM.S514972","url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to develop and validate a model based on machine learning algorithms to predict the risk of in-hospital death among advanced elderly patients with Heart Failure (HF).</p><p><strong>Methods: </strong>A total of 4580 advanced elderly patients who were admitted to the hospital and diagnosed with HF from May 2012 to September 2023 were included in this study, among whom 552 cases (12.5%) died. The least absolute shrinkage and selection operator (LASSO) regression and Boruta feature selection were used to screen the baseline variables to identify the variables significantly associated with death. Subsequently, seven different machine learning models were constructed and their prediction performances were evaluated. The Shapley Additive Explanations (SHAP) values were used to analyze the impact of key variables on the model prediction results.</p><p><strong>Results: </strong>A total of seven variables significantly associated with death were selected by LASSO regression and Boruta feature selection, including white blood cell count (WBC), neutrophil percentage (Neut %), C-reactive protein (CRP), D-dimer, glycated serum protein (GSP), N-terminal pro-B-type natriuretic peptide (NT-ProBNP), and body mass index (BMI). Among all the models, the extreme gradient boosting (XGB) model performed the best, with an area under the curve (AUC) value of 0.933, a sensitivity of 0.79, a specificity of 0.89, a recall of 0.79, and an F1 score of 0.59 on the validation set. The SHAP analysis showed that CRP, BMI, NT-ProBNP, D-dimer, and GSP were the main influencing factors for death.</p><p><strong>Conclusion: </strong>This study successfully constructed a prediction model for the in-hospital death risk of advanced elderly patients with HF, and the XGB model exhibited excellent prediction performance. This model can be used for the early clinical identification of high-risk patients and thus provide support for individualized treatment strategies.</p>","PeriodicalId":14131,"journal":{"name":"International Journal of General Medicine","volume":"18 ","pages":"3277-3288"},"PeriodicalIF":2.1,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12186748/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144484316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}