Yuying Fan

Background: Prognosis among patients with acute myocardial infarction (AMI) shows substantial heterogeneity, making precise identification of high-risk phenotypes essential for improving long-term outcomes. Machine learning techniques were used to identify such phenotypes by integrating multidimensional data and to examine their association with major adverse cardiovascular events (MACE). Methods: A total of 1,139 patients with AMI were enrolled from the First Affiliated Hospital of Harbin Medical University between March 2023 and June 2024. Multidimensional data, including clinical features, metabolic characteristics, and behavioral patterns, were collected. Phenotyping was performed using a hierarchical clustering algorithm. Associations between derived phenotypes and 1-year MACE were evaluated using Kaplan–Meier survival analysis and multivariable Cox regression models. Shapley Additive Explanations (SHAP) values derived from an XGBoost model were used to quantify the contributions of individual variables to cluster assignment. Results: Hierarchical clustering identified two clinical phenotypes with differing pathophysiological characteristics. Cluster 2 ( n = 243, 21.3%) exhibited a high-risk “frailty–inflammation” phenotype, characterized by impaired activities of daily living, elevated risk of falls and pressure ulcers, increased high-sensitivity C-reactive protein (hs-CRP) levels, and poor health behaviors. Compared with Cluster 1, patients in Cluster 2 showed a higher hazard of 1-year MACE (unadjusted HR = 4.17; 95% CI: 3.237–5.371; P < 0.001) and a markedly increased risk of all-cause mortality (HR = 12.162; 95% CI: 7.445–19.868; P < 0.001). After adjustment using the minimal sufficient confounding model (M3, incorporating 17 prespecified confounders), Cluster 2 membership remained significantly associated with an increased risk of 1-year MACE (adjusted HR = 2.726; 95% CI 1.986–3.743; P < 0.001) and all-cause mortality (adjusted HR = 4.35; 95% CI 2.393–7.905; P < 0.001). In multivariable Cox regression analysis, Cluster 2 membership was identified as an independent predictor for MACE. Conclusions: Integration of multidimensional data using machine learning identifies a high-risk “frailty–inflammation” phenotype in patients with AMI. This phenotype offers a comprehensive biological–functional–behavioral framework for risk stratification and may support early and precise clinical interventions to reduce long-term adverse outcomes. However, despite its potential clinical value, the current evidence is insufficient to support direct translation into routine clinical practice until independent cohort validation is performed. Future multi-center studies are warranted to confirm the robustness and generalizability of this approach, and to prospectively evaluate whether phenotype-guided intervention strategies can improve long-term outcomes.

Previous studies have shown that the maintenance hemodialysis (MHD) severity is pyramidal, with variations in self-management capabilities and supportive care needs generated by different patients during daily care procedures. This study aimed to explore the potential categories of self-management abilities and supportive care needs of patients undergoing MHD to inform the development of personalized intervention programs. We conducted a cross-sectional study using a self-made general data questionnaire, a hemodialysis self-management instrument, and an assessment of the supportive care needs of 302 outpatients undergoing MHD at two medical institutions (a tertiary hospital and a tertiary specialized hospital). Latent profile analysis was employed to classify self-management ability and supportive care needs. According to the latent profile analysis, the self-management and supportive care needs of MHD patients can be divided into three categories: the Self-Determination Model (72.7%), the Collaborative Support Model (20.0%), and the Comprehensive Care Model (7.3%). Statistically significant differences were observed in payment methods and caregiver health (P < 0.05). Among the 11 dimensions, nine showed statistically significant differences across the three profiles (Kruskal–Wallis H test, all P < 0.001), including all seven supportive care needs dimensions and two self-management dimensions (problem-solving and emotional processing). No significant differences were observed in self-care execution (P = 0.421) or partnership (P = 0.808). Medical staff can combine the self-management ability and supportive care needs of patients undergoing MHD to formulate personalized and targeted nursing intervention programs for different patients, which may help to improve patients’ self-management ability, respond to their care needs, and thus potentially contribute to the improvement of their quality of life.

This study aims to investigate the incidence and risk factors of caregiving unpreparedness among informal caregivers of adult ICU patients transferred to general wards, and to develop and validate a predictive model for caregiving unpreparedness. A cross-sectional study following the TRIPOD statement was conducted. Data were collected from 323 pairs of ICU patients and their informal caregivers who were transferred to general wards at the Second Affiliated Hospital of Harbin Medical University, Heilongjiang Province, between May and December 2024. Whether caregiving unpreparedness occurred was used as the outcome measure. LASSO and logistic regression identified risk factors and constructed a nomogram. Receiver operating characteristic (ROC) curve analysis and calibration curves were used to assess the discrimination and calibration of the predictive model. Decision curve analysis was performed to evaluate the clinical net benefit of the model. Of the 323 caregivers, 230 (71.2%) experienced caregiving unpreparedness. Six factor-caregiving experience, co-caregiver, disease knowledge, anxiety, depression, and patient self-paid status-were included in the nomogram. The area under the ROC curve was 0.863 (training) and 0.744 (validation). Calibration curves showed close alignment between predicted and actual probabilities. Decision curve analysis showed a net benefit for threshold probabilities of 0 to 0.75. The nomogram developed in this study effectively predicts caregiving unpreparedness among informal caregivers of ICU patients transferred to general wards and may assist healthcare professionals in identifying high-risk populations for caregiving unpreparedness.

End-stage renal disease (ESRD) is associated with high morbidity and mortality. Identifying patients with stage 4 chronic kidney disease (CKD) at risk of short-term progression to ESRD remains challenging. Accurate prediction can improve advanced care planning and patient outcomes. This study aimed to develop and validate a machine learning (ML) model for predicting progression within 25 weeks (approximately six months) of ESRD in patients with stage 4 CKD. Electronic health records (EHRs) of patients with stage 4 CKD were analyzed. Nine ML models including Ridge regression (Ridge), random forest (RF), and eXtreme Gradient Boosting (XGBoost) were used to predict short-term progression to ESRD within 25 weeks. The models were trained and externally validated using the data of 346 and 105 patients. Of the 451 patients with stage 4 CKD, 219 developed ESRD. Among the evaluated models, XGBoost demonstrated the best overall performance. In the internal validation, it achieved an area under the curve (AUC) of 0.93, an accuracy of 0.90, and an F1 score of 0.89. In the external validation, XGBoost maintained the highest AUC (0.85), accuracy (0.79), and F1 score (0.79), along with the highest average precision (0.89) and a low log-loss (0.48), indicating strong discriminative ability and good generalizability. The top predictive features included high-density lipoprotein cholesterol, Alb, Cys C, ApoB, FGB, Bun, Neutrophil, and Total cholesterol. This study demonstrated the feasibility of ML for assessing ESRD prognosis based on easily accessible clinical features. XGBoost demonstrated superior performance in both internal and external validation, suggesting its potential for future patient screening.

Post-traumatic growth (PTG) has been increasingly observed in various trauma groups. However, few studies have longitudinally explored PTG in intensive care unit (ICU) patients using qualitative methods. This study aimed to explore PTG pathways in ICU patients and offer reference data and methodological insights for personalized interventions. A phenomenological longitudinal study was conducted among patients transferred from ICU between May 2023 and February 2024. Four interview points were determined: Day two after transfer to ICU (T0), the 1st month after transfer out of ICU (T1), the 3rd month after transfer out of ICU (T2), and the 6th month after transfer out of ICU (T3). 21 cases were included. Two PTG trajectories were identified: "sublimation PTG trajectory" and "compound dual-path PTG trajectory," comprising four periods: "trauma response," "growth transition," "collapse," and "transition recovery." Fifteen themes emerged, including "the persistent presence of avoidance responses," with details shown in figures and tables. PTG in ICU patients showed shared and individualized patterns. Clinicians should recognize key time points, support self-healing, and tailor extended care. A multidisciplinary aftercare model combining online and in-person services is recommended for long-term recovery.

Introduction: Autogenous arteriovenous fistula (AVF) is the preferred vascular access in patients undergoing maintenance hemodialysis (MHD). However, complications such as thrombosis may occur. This study aimed to construct and validate a machine learning-based risk-prediction model for AVF thrombosis, hypothesizing that such a model can effectively predict occurrences, providing a foundation for early clinical intervention. Methods: The retrospective longitudinal study included a total of 270 patients who underwent MHD at the Hemodialysis Center of the Second Affiliated Hospital of Harbin Medical University between March 2021 and December 2022. During this study, baseline data and scale information of patients between March 2020 and December 2021 were collected. We recorded outcome indicators between March 2021 and December 2022 for subsequent analyses. Five machine learning models were developed (artificial neural network, logistic regression, ridge classification, random forest, and adaptive boosting). The sensitivity (recall), specificity, accuracy, and precision of each model were evaluated. The effect size of each variable was analyzed and ranked. Models were assessed using the area under the receiver-operating characteristic (AUROC) curve. Results: Among the 270 included patients, 105 had AVF thrombosis (55 male and 50 female patients; age range, 29–79 years; mean age, 56.72 years; standard deviation [SDs], ±13.10 years). Conversely, 165 patients did not have AVF thrombosis (99 male and 66 female patients; age range, 23–79 years; mean age, 53.58 years; SD, ± 13.33 years). During the observation period, approximately 52.6% of patients with AVF experienced long-term complications. The most common complications associated with AVF were thrombosis (105; 38.9%), aneurysm formation (27; 10%), and excessively high output flow (10; 3.7%). Fifty-four (20%) patients with AVF required intervention because of complications associated with vascular access. The AUROC curve of the testing set was between 0.858 and 0.903. Conclusion: In this study, we developed five machine learning models to predict the risk of AVF thrombosis, providing a reference for early clinical intervention.

Background: The aim of this meta-analysis is to systematically evaluate and summarize the risk factors of intensive care unit acquired weakness (ICU-AW), to provide evidence-based evidence for the formulation of prevention strategies for ICU-AW. Methods: PubMed, EMBASE, Web of Science, CBM (China Biology Medicine, China), Chinese National Knowledge Infrastructure, Chinese WANFANG, and VIP will be searched to define relevant risk factors for ICU-AW. The databases search period is from January 1, 2005 to August 13, 2021. The Newcastle Ottawa Scale (NOS) is used to evaluate the quality of the included studies. RevMan 5.3 analysis software will be used for meta-analysis. Results: This systematic review and meta-analysis included a total of 12 cohort studies, including 9 international journals and 3 Chinese journals, with a total of 1950 patients, of which 856 had ICU-AW. The results showed that the significant risk factors for ICU-AW included female (odds ratio [OR] = 1.34, 95% confidence interval [CI]: 1.06–1.71; P = .02), mechanical ventilation days (OR = 3.04, 95% CI: 1.82–4.26; P < .00001), age (OR = 6.33, 95% CI: 5.05–7.61; P < .00001), length of intensive care unit (ICU) stay (OR = 3.78, 95% CI: 2.06–5.51; P < .0001), infectious disease (OR = 1.67, 95% CI: 1.20–2.33; P = .002), renal replacement therapy (OR = 1.59, 95% CI: 1.11–2.28; P = .01), use of aminoglucoside drugs (OR = 2.51, 95% CI: 1.54–4.08; P = .0002), sepsis related organ failure assessment (SOFA) score (OR = 1.07, 95% CI: 0.24–1.90; P = .01), hyperglycemia (OR = 2.95, 95% CI: 1.70-5.11; P = .0001). Conclusion: This meta-analysis provides comprehensive evidence-based on the assessment of the risk factors for ICU-AW, their multifactorial etiology was confirmed. This study indicated that female, mechanical ventilation days, age, length of ICU stay, infectious disease, renal replacement therapy, use of aminoglucoside drugs, SOFA score, and hyperglycemia are independent risk factors for ICU-AW. We have not found consistent evidence that corticosteroids, neuromuscular blockers, sepsis have any effect on ICU-AW risk.

Background: Poor physical functioning (PF) is a common issue among critically ill patients. It was suggested that reasonable nutrition accelerates PF recovery. However, the details and types of nutritional interventions on the PF of different intensive care unit (ICU) patients at present have not been well analyzed yet. This study aimed to systematically synthesize nutritional interventions on PF in different ICU populations. Methods: Whittemore and Knafl’s framework was employed. PubMed, EMBASE, Web of Science, CINAHL Plus with Full Text, and Cochrane Library were searched to obtain studies from January 2010 to September 2020, with a manual search of the included studies’ references. Record screening, data extraction, and quality appraisal were conducted independently by each reviewer before reaching an agreement after discussion. Results: Twelve studies were included reporting the effects of early parenteral nutrition, early enteral nutrition, early goal-directed nutrition, early adequate nutrition, higher protein delivery, higher energy delivery, low energy delivery, energy and protein delivery, intermittent enteral feeding on PF like muscle mass, muscle strength, and function. Function was the most common outcome but showed little improvements. Muscle strength outcomes improved the most. The mechanically ventilated were the most popular target ICU population. The commenced time of the interventions is usually within 24 to 48 hours after ICU admission. Conclusion: Research on nutritional interventions on critically ill patients’ PF is limited, but most are of a high level of evidence. Few intervention studies specified their evidence basis. Qualitative studies investigating timeframe of initiating feeding, perspectives of the patients’ perspectives and caregivers are warranted to advance research and further discuss this topic.

Aim This study aimed to develop a patient classification system that stratifies patients admitted to the intensive care unit based on their disease severity and care needs. Background Classifying patients into homogenous groups based on clinical characteristics can optimize nursing care. However, an objective method for determining such groups remains unclear. Methods Predictors representing disease severity and nursing workload were considered. Patients were clustered into subgroups with different characteristics based on the results of a clustering algorithm. A patient classification system was developed using a partial least squares regression model. Results Data of 300 patients were analyzed. Cluster analysis identified three subgroups of critically patients with different levels of clinical trajectories. Except for blood potassium levels (P=0.29), the subgroups were significantly different according to disease severity and nursing workload. The predicted value ranges of the regression model for Classes A, B, and C were 2.03. The model was shown to have good fit and satisfactory prediction efficiency using 200 permutation tests. Conclusions Classifying patients based on disease severity and care needs enables the development of tailored nursing programs for each subgroup. Implications for Nursing Management The patient classification system can help nurse managers identify homogeneous patient groups and further improve the management of critically ill patients.

Introduction: Intensive care unit-acquired weakness (ICU-AW) occurs in 25% to 100% of critically ill patients, and is associated with prolonged mechanical ventilation, extended ICU stay, and total hospital stay, increased hospital costs, higher risk of death, impaired physical function, and decreased quality of life. However, there are not any current guidelines that mention management of ICU-AW. The present study will evaluate the effects of a combination of early nutrition and early exercise compared to those of either early exercise alone or the standard care for patients in ICUs. Methods: This is a 3-arm, parallel, randomized controlled trial including an estimated 147 critically ill patients aged ≥18 years recruited from the ICUs of 2 hospitals in Heilongjiang, China. Patients will be prospectively randomized 1:1:1 to receive early mobilization, early nutrition combined with early mobilization, or standard care (minimal exercises, experience-based initiation and enrollment of nutrition support). Outcomes are assessed at ICU discharge after baseline. The primary outcome is occurrence of ICU-AW according to the Medical Research Council scale at the end of treatment. Muscle strength, organ failure, functional independence, self-care ability, time of ICU stay, duration of mechanical ventilation, and ICU mortality are secondary outcome measures. Discussion: This trial has the potential to identify a novel strategy for preventing or managing ICU-AW. The findings may increase the clinical knowledge about nutrition and mobilization interventions for people with ICU-AW, and contribute to the formation of practice guidelines for managing this condition. Trial registration number: ChiCTR2000033482