Frailty, a multidimensional geriatric syndrome closely associated with aging, manifests as an excessive decline in reserve and function across multiple physiological systems, leading to diminished responsiveness to minor stressors. It is highly prevalent among hospitalized patients and significantly increases the risk of adverse health outcomes, including hospitalization, falls, disability, and mortality [1]. It is noteworthy that heart failure (HF), similar to frailty, represents a complex clinical syndrome with a persistently increasing hospitalization prevalence, which has become a significant global public health concern [2, 3]. Additionally, clinical observations indicate that hospitalized HF patients frequently present with concurrent acute infections. This comorbid condition may lead to prolonged hospital stays, increased short-term readmission rates, and elevated post-discharge mortality [4].

Previous research primarily focuses on univariate analyses of the relationship between risk factors and frailty in populations with chronic diseases [5]. A cohort study involving 936 sepsis patients only demonstrated the association between frailty and mortality risk in individuals with a single acute illness [6]. Furthermore, existing studies have largely concentrated on assessing hospitalization and mortality risks in chronic HF patients [7]. However, research on frailty-related risk factors in patients with comorbidities (concurrent acute and chronic conditions) remains limited. In clinical settings, HF—a prevalent chronic condition—is primarily characterized by significant fluid retention. In contrast, infections, as representative acute cases, typically manifest with distinct fluid exudation as their pathological hallmark. These overlapping pathological mechanisms may collectively result in excessive fluid overload, clinically manifested as bilateral lower extremity edema and secondary decline in muscle strength, thereby significantly increasing the risk of prolonged bed rest. Thus, HF patients during acute infection episodes exhibit elevated rates of adverse clinical outcomes, including prolonged hospitalization, worsening or secondary infections, deep vein thrombosis, increased need for invasive mechanical ventilation, and even in-hospital mortality. These complications not only negatively impact disease prognosis but also pose significant challenges to clinical management. To summarize, HF and acute infections frequently coexist as comorbidities in hospitalized patients, with such comorbid cases typically presenting severe symptoms and poor clinical outcomes. In this context, frailty may influence disease progression through two distinct pathways: exacerbating symptom severity and precipitating earlier onset of adverse outcomes [8, 9].

Similarly, current research on HF prediction models primarily focuses on forecasting patient mortality and readmission risk [10]. Moreover, most existing machine learning studies tend to overlook the application of visualization techniques, while the predictive accuracy of conventional models remains suboptimal. These limitations substantially constrain clinicians’ ability to comprehend disease progression and make precise prognostic assessments intuitively. Notably, compared to traditional statistical methods and standard machine learning techniques, machine learning visualization tools and technologies are more adept at handling complex interactions or nonlinear relationships among variables. They can efficiently process vast amounts of clinical data, offering distinct advantages in disease prediction, multivariate analysis, and personalized treatment—effectively serving as an additional reliable “virtual clinician” for patients. This not only enhances clinicians’ confidence but also ensures more comprehensive and professional disease management for patients [11, 12]. For instance, in tumor imaging analysis, machine learning visualization techniques can precisely identify malignant lesion areas, with interpretability that aligns with pathological findings, thereby significantly improving clinical trust [13].

To solve these disadvantages, this study aims to investigate frailty-associated risk factors in patients with concurrent HF and acute infections, and to develop a frailty prediction model utilizing multiple machine learning algorithms. Additionally, a clinically accessible online calculator will be developed and deployed to accurately identify high-risk individuals and tailor appropriate interventions based on individual risk factors. Ultimately, this approach seeks to reduce the incidence of frailty or even reverse its progression in affected patients.

All patients were assessed for frailty using the Clinical Frailty Scale (CFS), with scores ranging from 1 (very fit) to 9 (terminally ill). According to the CFS scoring criteria, a score ≤ 4 indicates a non-frail state, while a score ≥ 5 is classified as frail. The CFS was conducted by nurses during the patient’s hospitalization, with the results systematically documented in the electronic medical record system. The CFS includes the Activities of Daily Living (ADL) scale (eating, bathing, grooming (toothbrushing, face washing, shaving, hair combing), dressing (fastening shoes, buttoning clothes), bowel control, bladder control and toilet use, transfers (bed-to-chair mobility), ambulation (walking 45 meters on level ground), stair climbing) and the Instrumental Activities of Daily Living (IADL) scale (telephone usage, shopping, meal preparation, housekeeping, laundry, transportation, medication management, financial handling).

All clinical data were extracted from the electronic medical record system, including: (1) demographic characteristics: age, sex, literacy, marital status, Body Mass Index (BMI), hospital days, capacity for action, smoking, drinking, and NYHA functional class; (2) medication use: angiotensin receptor neprilysin inhibitor (ARNI), angiotensin-converting enzyme inhibitor (ACEI) / angiotensin receptor blocker (ARB), sodium-glucose cotransporter protein-2 (SGLT-2) inhibitors, beta receptor blockers, mineralocorticoid receptor antagonist (MRA), calcium channel blocker (CCB), loop diuretics, thiazide diuretics, nitrates, statins, antiplatelet drugs, anticoagulants, cardiac glycosides, soluble guanylate cyclase (sGC) stimulators; (3) comorbidities: hypertension, diabetes mellitus, hyperlipidemia, coronary heart disease, atrial fibrillation, fatty liver disease, cirrhosis, chronic obstructive pulmonary disease (COPD), chronic cor pulmonale, renal insufficiency, osteoporosis, cerebral infarction, malignant tumor; (4) infection characteristics: pulmonary infection, urinary tract infection, abdominal infection, skin and soft tissue infection, bloodstream infection, sepsis, septic shock; (5) admission vital signs: first recorded blood pressure (systolic blood pressure, diastolic blood pressure) and heart rate; (6) biomarkers: white blood cell, lymphocyte percentage, neutrophil percentage, red blood cell, hemoglobin, mean corpuscular hemoglobin concentration (MCHC), platelet, D-dimer, alanine aminotransferase, aspartate aminotransferase, serum albumin, total bilirubin, urea, creatinine, uric acid, serum potassium, serum sodium, total cholesterol, triglycerides, high-density lipoprotein, low-density lipoprotein, estimated glomerular filtration rate (eGFR), interleukin-6, procalcitonin, c-reactive protein, B-type natriuretic peptide (BNP), N-terminal pro-BNP (NT-proBNP), elevated natriuretic peptide levels were defined as BNP>100pg/mL or NT-proBNP>300pg/mL [15]; (7) echocardiography: left ventricular ejection fraction (LVEF), aortic diameter (AOD), left atrial diameter (LAD), interventricular septum diameter (IVSD), left ventricular end diastolic diameter (LVEDD), left ventricular posterior wall diameter (LVPWD), left ventricular end systolic diameter (LVESD).

The dataset was randomly split into training and testing sets in a 7:3 ratio. The training set was used for variable selection and model development, while the testing set evaluated model performance. Continuous variables were standardized using Z-scores, and categorical variables were encoded via one-hot encoding [17, 18]. Variables significantly associated with frailty (p < 0.05) in univariate analysis were retained for further analysis. Significant variables were further analyzed using the least absolute shrinkage and selection operator (LASSO) regression. By tuning the hyperparameter lambda (λ), LASSO performs feature selection through L1 regularization, shrinking the coefficients of weakly correlated variables to zero [19]. Variables with non-zero coefficients were selected from LASSO regression. To assess multicollinearity, variables with a variance inflation factor (VIF) ≥ 5 were excluded to ensure feature independence [20].

During model optimization, hyperparameters were tuned via grid search with 10-fold cross-validation. The grid search exhaustively evaluated all possible hyperparameter combinations within predefined ranges to identify the optimal configuration. The final model was evaluated through: (1) performance metrics on the testing set, including the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, specificity, accuracy, precision, recall, and F1-score; (2) calibration curves to evaluate the agreement between predicted and observed probabilities, complemented by Brier scores quantifying overall calibration error; (3) decision curve analysis (DCA) to quantify net clinical benefit, including standardized net benefit rates and optimal risk thresholds. To interpret the model, SHapley Additive exPlanations (SHAP) were applied to quantify feature contributions [21]. For clinical translation, an interactive web application was developed to visualize predictions.

This study included 81 clinically relevant variables, six of which contained missing values (Supplementary Table S2). Missing values were imputed using the KNN algorithm. Univariate analysis identified 37 variables significantly associated with frailty (p < 0.05; Table 1). LASSO regression with 10-fold cross-validation was applied, and using the “1-standard error” rule (1-SE criterion), we selected the λ value corresponding to one standard deviation from the minimum cross-validated error (λ = 0.02382322; Supplementary Table S3). This process retained 11 independent predictors with non-zero coefficients: thiazide diuretics use, serum albumin, eGFR, lymphocyte percentage, MCHC, capacity for action, age, LVEF, NYHA functional class, history of cerebral infarction, and smoking.

There was no substantial multicollinearity between the variables, with all VIF values < 1.5 (Supplementary Table S3). Using the above 11 variables, we developed eight ML models: logistic regression (LR), random forest (RF), eXtreme Gradient Boosting (XGBoost), light gradient boosting machines (LightGBM), support vector machine (SVM), categorical boosting (CatBoost), naive bayes (NB), and multilayer perceptron (MLP). The hyperparameters of each model were optimized by grid search, and the specific parameters are shown in Supplementary Table S4.

This study developed a machine learning prediction model for the occurrence of frailty in HF patients with acute infections. The prevalence of frailty in our cohort was 80.3%, which is largely consistent with the findings reported by Vidán et al [22]. The study employed eight machine learning models, with the XGBoost model demonstrating optimal performance. Through XGBoost model analysis, significant predictors associated with frailty were identified, including thiazide diuretics use, serum albumin, eGFR, lymphocyte percentage, MCHC, capacity for action, age, LVEF, NYHA functional class, history of cerebral infarction, and smoking.

This study demonstrates the model’s innovation and practical value through the following aspects: first, we incorporate well-established pharmacotherapy for HF patients with concurrent acute infections in frailty risk prediction—an advancement over previous models that omitted this critical risk factor. This refinement enhances clinical medication guidance and identifies novel intervention targets for frailty prevention. Second, the introduced XGBoost model exhibits exceptional predictive performance, with AUROC (0.872) and AUPRC (0.969) metrics significantly outperforming other comparative models. As one of the most widely utilized machine learning models in medical research, XGBoost has become a vital tool in clinical decision support systems due to its computational efficiency and superior predictive accuracy, demonstrating significant clinical applicability [23]. Additionally, this study employs SHAP to enhance the interpretability of the XGBoost model. SHAP-based visual analysis effectively reveals the predictive contributions of feature variables, enabling clinicians to precisely identify key risk predictors of frailty in patients with HF complicated by acute infections. This provides reliable evidence-based support for developing personalized treatment strategies. Finally, we successfully developed an interactive web-based application to facilitate real-time clinical data input and visual risk prediction output. This tool significantly improves clinical workflow efficiency and allows clinicians to dynamically monitor disease progression trends, offering immediate decision-making support for precision medicine. In summary, this study successfully transforms a static predictive model into a dynamic clinical decision support system by integrating a full-process framework of “patient feature input, SHAP-based real-time computation, and visualized output.” This innovative breakthrough not only facilitates the practical translation of machine learning models into clinical settings but also provides a scalable technical approach for advancing intelligent clinical decision-making.

The novelty of this study lies in the pioneering discovery that patients receiving thiazide diuretics therapy exhibit a significantly lower risk of potential frailty compared to those not treated with this medication. This observed association may be attributed to several mechanisms. First, thiazide diuretics primarily reduce cardiac preload and afterload by decreasing blood volume, thereby alleviating symptoms such as dyspnea and edema while improving exercise tolerance [24]. Second, a previous multicenter, randomized, double-blind clinical trial on acute decompensated HF demonstrated that adding oral thiazide diuretics to intravenous loop diuretics mitigated adverse effects like hypokalemia, consequently preventing muscle weakness. This suggests thiazide diuretics may offer more favorable potassium-sparing effects [25]. Furthermore, in infected patients, thiazide diuretics can effectively alleviate fluid exudation caused by primary lesions. Taking pulmonary infection as an example, increased sputum production often leads to persistent or refractory cough, with some patients showing poor response to conventional expectorant therapy. For HF patients during acute infections, thiazide diuretics not only exert their inherent diuretic effects but also significantly improve symptoms of cough and dyspnea associated with pulmonary infection by modulating infection-related fluid exudation mechanisms, consequently improving the patients’ frailty condition [26, 27]. Therefore, the management of infection-associated fluid exudation is crucial, and this clinical issue warrants considerable attention.

A comparative evaluation provides compelling evidence for the significance of thiazide diuretics. Clinically, loop diuretics, as first-line agents for HF treatment, exhibit significant clinical limitations despite their widespread use. The primary concern is their propensity to induce severe electrolyte imbalances, compounded by the increasingly prevalent phenomenon of diuretic resistance. Research demonstrates that combination therapy not only effectively addresses diuretic resistance but also significantly reduces adverse drug reactions [28]. However, current studies predominantly focus on combining loop diuretics with mineralocorticoid receptor antagonists [29], while the potential of thiazide diuretics remains underinvestigated. Compared to loop diuretics, thiazide diuretics exert a milder diuretic effect, and their synergistic combination with loop diuretics has gained clinical recognition. This dual-therapy approach enhances diuresis, promotes weight loss, and significantly alleviates edema [25]. Our study is the first to reveal the potential role of thiazide diuretics in HF patients with acute infections. These findings align with current trends in diuretics research and reinforce the clinical relevance of thiazide diuretics. Consequently, the judicious addition of thiazide diuretics in clinical practice may serve as a preventive strategy against frailty in patients with HF and acute infections. This finding highlights the potential role of thiazide diuretics in frailty prevention beyond their conventional diuretic effects. In summary, beyond offering clinicians an optimized diuretic strategy, this discovery opens new avenues for research into pharmacological frailty prevention, carrying substantial clinical implications.

The findings revealed significantly lower serum albumin levels in the frail group compared to the non-frail group. The relationship between frailty and serum albumin can be explained through the following mechanisms: first, frail elderly individuals exhibit systemic functional decline, including compromised masticatory function. This impairment often leads to inadequate food breakdown during chewing, particularly affecting the digestion and absorption of protein-rich foods. Second, frailty adversely affects gastrointestinal function, further hindering nutrient assimilation. Third, during acute infections, frail patients demonstrate more pronounced protein catabolism compared to their non-frail counterparts [30]. Therefore, for patients with HF complicated by acute infections, nutritional management is critically important. Moreover, micronutrient supplementation (particularly of calcium, iron, zinc, and magnesium) may significantly aid in restoring serum albumin levels [31].

eGFR, a key indicator of renal function, demonstrated an inverse relationship with frailty in this study. A decline in eGFR leads to overactivation of the renin-angiotensin-aldosterone system (RAAS), exacerbating fluid retention. This fluid accumulation is particularly detrimental in HF patients, whose pre-existing fluid overload further restricts mobility and accelerates frailty progression [32]. While eGFR decline is irreversible, the judicious selection of nephroprotective pharmacological agents may help slow the progression of renal insufficiency, thereby delaying the onset of frailty. Furthermore, lymphocyte percentage serves as a key indicator of immune system function, with its decline reflecting impaired immunity and significantly elevating frailty risk [33]. During acute infections, lymphocyte percentage emerges as a clinically significant predictor of frailty among various infection markers. Notably, evidence suggests that enhanced physical activity may prevent immunosenescence and mitigate frailty progression [34].

MCHC, a key diagnostic parameter for anemia, reflects the hemoglobin concentration within red blood cells. A low MCHC often indicates potential iron deficiency in the body. Iron is an essential element for erythropoiesis, and its deficiency can impair hemoglobin synthesis, reducing the oxygen-carrying capacity of red blood cells. This leads to systemic tissue hypoxia, which may manifest as muscle weakness, fatigue, and decreased exercise tolerance [35, 36]. Furthermore, chronic hypoxia can disrupt mitochondrial function, decreasing adenosine triphosphate (ATP) production and limiting energy supply for daily activities, thereby accelerating frailty progression [37]. Therefore, increasing dietary iron intake may help improve frailty status in these patients.

This study demonstrates that patients who remain ambulatory are less prone to frailty compared to those who are wheelchair-dependent or bedridden. Therefore, for patients with HF and acute infections, exercise-based rehabilitation should be prioritized to improve mobility. Although physical activity increases myocardial oxygen demand and may transiently worsen HF symptoms, judicious exercise promotes muscle recovery, enhances the capacity for action, and reduces frailty riskࣧprovided the intensity remains within individualized thresholds [38]. This necessitates careful supervision by experienced clinicians to optimize the risk-benefit balance. In summary, personalized exercise prescriptions should be implemented for this population to achieve measurable benefits. In addition, our study found that advanced age significantly increases the likelihood of frailty development, which aligns with previous reports [39]. The study also highlights associations between decreased LVEF, elevated NYHA functional class, history of cerebral infarction, smoking, and elevated frailty risk.

This study developed a frailty prediction model for patients with HF complicated by acute infections. The model incorporates 11 readily accessible predictors. A key innovation of this study lies in its pioneering inclusion of thiazide diuretics within the frailty prediction system, a breakthrough that addresses a critical research gap in pharmacological interventions for frailty among HF patients with acute infections. We also developed a clinically accessible online calculator that enables clinicians to input patient clinical data in real-time and instantly obtain frailty risk assessment results. This tool facilitates the early identification of high-risk individuals and supports the implementation of personalized interventions.