Review of risk factors and prediction models for multidrug-resistant bacterial pulmonary infections in patients with chronic obstructive pulmonary disease

Abstract

Chronic obstructive pulmonary disease is a prevalent chronic respiratory disorder that often coexists with multidrug-resistant bacterial infections in the lungs, significantly increasing treatment complexity and patient mortality. Consequently, research on the prevention and management of chronic obstructive pulmonary disease complicated by pulmonary multidrug-resistant bacterial infections has attracted increasing attention. Establishing predictive models for chronic obstructive pulmonary disease complicated by multidrug-resistant bacterial infections based on clinical risk factors has become a crucial direction in current clinical research. This narrative review summarizes the limitations of currently available predictive models, particularly in the selection of major risk factors and model construction. It aims to provide guidance for the selection and optimization of future predictive model development methods. The goal is to enhance the predictive performance and clinical applicability of these models while laying a theoretical foundation for the transformation of diagnostic and therapeutic paradigms.

Keywords

Chronic obstructive pulmonary disease multidrug-resistant bacteria risk factors prediction models pulmonary infection

Introduction

Chronic obstructive pulmonary disease (COPD) is a chronic heterogeneous disease characterized by persistent airflow limitation, mainly caused by airway remodeling and alveolar structural abnormalities, and manifested as chronic cough, sputum production, and progressive dyspnea.¹ The pathogenesis of COPD primarily involves several core mechanisms, including chronic inflammation and immune dysregulation, which interact and promote each other, ultimately leading to lung tissue destruction and airflow limitation.^2–4 Due to population aging, the global prevalence of COPD has reached 10.3%.¹ Patients with COPD have reduced physical activity and limited social functioning, often accompanied by severe complications and comorbidities, leading to significantly impaired health-related quality of life.^1,5,6 It is estimated that more than 3 million people die from COPD each year,⁷ and by 2050, COPD is predicted to become one of the top four causes of disability-adjusted life years (DALYs),⁸ posing a serious threat to human health.

Due to irrational antibiotic use, bacterial resistance has become a global crisis,^9,10 and according to the University of Washington in the United States, approximately 4.95 million people died from bacterial resistance in 2019 alone.¹¹ With declining lung function, the incidence of multidrug-resistant (MDR) bacterial pulmonary infections gradually increases,^12–14 resulting in an elevated risk of death.¹¹ Therefore, early identification of high-risk patients and prevention of MDR bacterial infections are critical to improving patient outcomes.^15–17

Given the adverse impact of MDR bacterial infections in patients with COPD, an increasing number of prediction models have been applied in clinical research.^17,18 Existing prediction models are mainly built by analyzing patient demographic characteristics and clinical data using statistical methods, aiming to accurately identify high-risk patients and enable early intervention, thereby reducing the emergence and spread of MDR bacteria.^19–21 However, the performance of current models varies, and their generalizability needs improvement. Future research should focus on integrating multidimensional data from clinical, microbiological, and molecular fields, combined with artificial intelligence and large-scale data analytics, to establish more accurate and effective prediction models.^22–24

This review is a narrative review. Through a comprehensive analysis of the risk factors and predictive models for MDR bacterial infection in patients with COPD, especially by comparing the advantages and limitations of machine learning models with those of traditional models, it aims to provide theoretical guidance for the selection of predictive factors and modeling methods in future predictive model development.

Methods

Search scope

A comprehensive search of the PubMed and Web of Science databases was conducted. The search period spanned from the establishment of the databases to 1 October 2025.

Search terms used

A strategy combining subject headings and free-text terms was adopted. The English search terms included the following: “Chronic Obstructive Pulmonary Disease,” “COPD,” “Acute Exacerbation of Chronic Obstructive Pulmonary Disease,” “Multiple Resistant Bacteria,” “Infection by Multi-drug Resistant Bacteria,” “Multi-drug Resistant,” “Pulmonary Infection,” “Resistance Mechanism,” “Pathomechanism,” “Hazard,” “Prediction Model,” “Machine Learning,” “Regression Model,” and “Model Limitations.”

Inclusion and exclusion criteria

The inclusion criteria were as follows:

Study types include cohort studies, case-control studies, cross-sectional studies, randomized controlled trials, meta-analyses, and systematic reviews.

The focus of the studies is the construction and validation of prediction models for MDR bacterial infections in patients with COPD.

The study subjects are patients aged 18 years or older with COPD or pulmonary infection.

The predicted outcome is MDR bacterial infection in the lungs.

The exclusion criterion was studies for which full text cannot be obtained or from which relevant data cannot be extracted.

This review is guided by the Scale for the Assessment of Narrative Review Articles (SANRA).²⁵

Mechanisms and classification of antimicrobial resistance

Mechanisms and characteristics of MDR bacteria

MDR bacteria refer to bacterial strains resistant to three or more classes of antibiotics.²⁶ The emergence of MDR bacteria substantially increased treatment difficulty and posed serious challenges to clinical practice,^11,27 especially in intensive care units (ICUs) and among immunosuppressed patients, where infection rates have risen significantly and markedly increased the healthcare burden and mortality.^28–31

Bacteria develop resistance through multiple mechanisms, disseminating resistance genes among strains via horizontal gene transfer mediated by plasmids, transposons, and integrons,^32–39 and their resistance mechanisms are complex (Table 1), especially in chronic respiratory diseases such as COPD, where they often lead to lower respiratory tract colonization and recurrent infections, severely affecting patient outcomes.¹³

Table 1.

Mechanisms of antimicrobial resistance in MDR bacteria.

Resistance mechanism	Mechanistic principle	Classification
Reduced permeability	Mutations in structural genes encoding outer membrane porin (omp) proteins reduce or eliminate porin channels, thereby preventing antibiotics from entering the bacterial cell³³	ompF, ompC, ompE, etc.³³
Efflux pumps	Recognize and bind antibiotics entering the cell and actively pump them out, reducing intracellular drug concentration⁴⁰	RND, MFS, MATE, SMR, ABC, etc.⁴⁰
Modification or mutation of antibiotic targets	Mutations in genes encoding antibiotic target proteins or enzymatic modification of target proteins decrease or abolish affinity between antibiotics and their bacterial targets^33,41	Ribosomal target modification, mutations in cell-wall synthesis enzymes, mutations in DNA gyrase/topoisomerase, mutations in enzymes of the folate metabolic pathway, etc.⁴¹
Hydrolytic or inactivating enzymes	Hydrolyze key chemical bonds of antibiotic molecules or add chemical groups to specific functional groups, leading to antibiotic inactivation^33,42	β-lactamases, aminoglycoside-inactivating enzymes, chloramphenicol acetyltransferases, macrolide-inactivating enzymes, etc.^33,42
Metabolic alteration or auxotrophy	Mutations in genes involved in metabolic pathways cause metabolic dysregulation and reduced basal metabolism, thereby inhibiting antibiotic activity;⁴³ loss of the ability to synthesize essential nutrients leads to auxotrophy, and dormancy or extremely slow growth reduces antibiotic effects^33,44	Auxotrophic dormancy, metabolic dysregulation, increased antibiotic target proteins, etc.^43,44
Biological membrane	Acts as a physical barrier limiting antibiotic penetration and altering antibiotic structure, reducing activity;³³ induces resistant phenotypes via quorum-sensing systems;⁴⁵ heterogeneity in bacterial physiological states within the biofilm leads to persister cell formation; biofilm microenvironments promote horizontal gene transfer^46,47	Device-associated: endotracheal tubes, central venous catheters, artificial joints, etc.; tissue chronic infection-associated: chronic pulmonary infection, chronic ulcers, bone infections, etc.⁴⁷
Target protection proteins (TPPs)	Competitively bind to antibiotic targets in bacterial cells and induce structural alterations of targets, inhibiting antibiotic activity^48,49	Type I: TET ribosomal protection proteins; Type II: ABC-F ribosomal protection proteins; Type III: Fus-B ribosomal protection proteins⁴⁹
Self-repair systems	Reduce antibiotic entry and evade antibiotic attack through DNA damage repair, metabolic regulation, and biofilm-mediated cooperative defense^33,50,51	Molecular-level repair systems, cellular-level tolerance systems, population-level cooperative defense systems^50,51
Morphological alterations	Through changes in morphology, induce membrane invagination, inhibit phagosome–lysosome fusion, and form intracellular biofilms, allowing bacteria to tolerate antibiotics and survive^52,53	L-form bacteria, filamentation, small-colony variants, spherical cells, spores, etc.^52–55

MDR: multidrug-resistant; omp: outer membrane porin; RND: resistance-nodulation-division; MFS: major facilitator superfamily; MATE: multidrug and toxic compound extrusion; SMR: small multidrug resistance; ABC: ATP-binding cassette; TET: tetracyclines; ABC-F: ATP-binding cassette subfamily F proteins; Fus-B: fusidic acid resistance protein B; TPPs: target protection proteins.

MDR bacteria, with their complex mechanisms and broad resistance spectrum, pose significant challenges to clinical diagnosis and treatment and have become a serious public health threat,⁵⁶ making in-depth investigation of resistance mechanisms essential for developing early prevention strategies and improving outcomes.

Common types of MDR bacteria

Common MDR bacteria in COPD included Pseudomonas aeruginosa (PA), Escherichia coli, Klebsiella pneumoniae, Acinetobacter baumannii, and methicillin-resistant Staphylococcus aureus (MRSA).^4,57 Among these, PA was the most common and was closely associated with frequent acute exacerbations and mortality^58–61 Due to its genetic characteristics, PA tended to persist within the same clonal lineage during repeated infections, promoting the development of resistance genes.⁶² MDR A. baumannii was commonly found in patients with prior endotracheal intubation.^63,64 Resistant E. coli and K. pneumoniae often displayed resistance to various β-lactams and quinolones, and their production of β-lactamases and carbapenemases further complicated treatment.^59,65 MRSA was resistant to methicillin and several other antibiotics, greatly increasing treatment difficulty and mortality.⁶⁶

Studies have shown that MDR bacterial infections are independent risk factors for COPD progression and poor prognosis¹⁵; therefore, early identification and targeted antimicrobial strategies are important for improving patient outcomes.^15,67

Relationship between COPD and MDR bacterial infections

Pathophysiological mechanisms of COPD

The central mechanism of COPD is chronic inflammation, triggered mainly by smoking and environmental pollution, leading to epithelial hyperplasia, basement membrane thickening, and smooth muscle proliferation, which cause small airway remodeling and progressive decline in lung function.^68–70 Chronic inflammation also results in lung tissue destruction and loss of elastic recoil, leading to emphysema and further aggravating airflow limitation.^68,69

Another mechanism is immune dysregulation, as chronic inflammation activates immune cells such as neutrophils, lymphocytes, and macrophages, causing them to release large amounts of inflammatory mediators, triggering oxidative stress and lung tissue injury.^71,72 Chronic inflammation and oxidative stress accelerate lung aging and disease progression.⁶⁹ Immune dysregulation also induces systemic inflammation, contributing to cardiovascular disease, osteoporosis, and metabolic syndrome.^73,74 Additionally, COPD is often accompanied by lower airway microbiome alterations and chronic infections, which exacerbate airway inflammation and impair barrier defense, making patients more vulnerable to pathogen invasion.^75,76 Inflammation and infection also cause mucus hypersecretion, worsening airway obstruction and ventilatory dysfunction.^77,78

Thus, the pathophysiological mechanisms of COPD involved multiple interacting processes that not only lead to airway narrowing and tissue destruction but also weaken immunity, providing favorable conditions for MDR colonization and infection.

Epidemiological characteristics

Epidemiological data showed that patients with COPD have significantly higher MDR infection rates than individuals without COPD, which are associated with frequent hospitalizations, antibiotic exposure, and invasive procedures.^79–81 A case-control study reported that severe COPD was an independent risk factor for MDR infections, and that patients infected with carbapenem-resistant bacteria had a 30-day mortality rate as high as 37.6%.⁸² Therefore, the epidemiological characteristics of COPD with MDR infections include a high incidence and high mortality, which are closely related to disease severity and clinical management.

Risk factors for MDR bacterial infections in COPD

Patient-related factors

Age and sex

Studies indicate that older patients are more susceptible to MDR bacteria because of immune senescence, reduced physiological barrier function, and a higher prevalence of comorbidities.^38,83 Men have a higher risk of MDR colonization and infection than women, mainly because of androgen-related immunosuppression and higher rates of smoking, alcohol use, and occupational exposure.^83,84

COPD classification and disease duration

Alexopoulos Evangelos et al. found that, compared with patients with GOLD stage I, the frequency of acute exacerbations increased by 40% and 74.5% in patients with GOLD stage III and IV disease, respectively, and that patients with a disease duration of >10 years had 54.3% higher hospitalization rates and 75.5% higher ICU admission rates than those with a disease duration of <5 years.⁸⁵ Therefore, due to frequent antibiotic and glucocorticoid exposure, patients with GOLD stage III or higher disease or a disease duration of >10 years had an increased risk of MDR infection.^78,86

Comorbidities

Diabetes

Hyperglycemia in diabetes causes vascular changes, tissue ischemia, and impaired defense function while simultaneously providing nutrients for bacterial growth and impairing immune responses. Therefore, recurrent infections may facilitate MDR development and progression.^87,88

Malignancy

Malignancy is often associated with malnutrition and immune impairment, and antitumor therapies cause bone marrow suppression and damage to local defense barriers, increasing the risk of MDR infection.⁸⁹

Immunodeficiency

Patients with human immunodeficiency virus (HIV) or organ transplantation often exhibit immune deficiency, making them prone to frequent infections and MDR development.^90–92 A meta-analysis of patients with HIV and bacterial infections reported an MDR detection rate of up to 58.02%,⁹⁰ and immunodeficient patients with MDR infections had a significantly higher mortality risk.⁹³

Others

Studies have also found that patients with congestive heart failure, chronic renal failure, or cerebrovascular accidents have significantly higher risks of MDR pulmonary infections.⁹⁴

Malnutrition

Studies show that 30% of patients with COPD have malnutrition, especially those aged >60 years and those with severe lung impairment.⁹⁵ Malnutrition leads to protein deficiency and impaired immunity, increasing the risk of infection. Due to micronutrient deficiency and reduced nutrient intake, intestinal microbiota imbalance occurs, increasing the prevalence of intestinal MDR bacteria. Based on the gut–lung axis and the vicious cycle between malnutrition and infection, the risk of MDR pulmonary infections increases.⁹⁶

Clinical factors

Hospitalization frequency

MDR bacteria are widely present in hospitals, especially ICUs. Studies show that patients with COPD hospitalized ≥2 times because of acute exacerbations within 1 year have an increased risk of MDR infection.^18,97

Antibiotics

A retrospective study by Fang Ding et al. reported that frequent antibiotic use was an independent risk factor for MDR infections in patients with COPD.¹⁵ Frequent antibiotic use induces gene mutation and expression, promotes biofilm formation,³⁵ and facilitates the horizontal transfer of resistance genes, exacerbating the spread of MDR bacteria.^81,98

Glucocorticoids

Glucocorticoids have anti-inflammatory and immunosuppressive effects; long-term use suppresses innate and adaptive immunity, increasing infection risk. They also promote biofilm formation and horizontal gene transfer, inducing the emergence of MDR bacteria.⁹⁹

Invasive procedures

Invasive mechanical ventilation

Invasive mechanical ventilation is the main cause of ventilator-associated pneumonia (VAP). Studies show that when ventilation exceeds 48 h, the incidence of VAP reaches 27.7%, with MDR bacteria accounting for 43.65%.¹⁰⁰ Multiple studies have identified invasive mechanical ventilation as an independent risk factor for MDR infection.^101–103 Endotracheal intubation causes mucosal injury and impairs ciliary clearance, disrupting defense barriers; the tube serves as a site for colonization and biofilm formation, while the open airway increases the risks of aspiration, bacterial translocation, and cross-infection, leading to MDR development.^104,105

Other invasive procedures

Urinary catheterization was an independent risk factor for MDR infections, especially MRSA infection.⁹⁴ Destruction of urinary tract defenses and biofilm formation promote MDR bacterial growth, which may lead to bacteremia and pulmonary infection.¹⁰⁶ Nasogastric tube placement causes aspiration, intestinal dysbiosis, and bacterial translocation, significantly increasing the risk of pulmonary E. coli infection.¹⁰⁷ Continuous renal replacement therapy and central venous or arterial catheterization increase the risk of MDR bacteremia and secondary pulmonary infections.^97,108

Biomarkers

In recent years, multiple biomarkers have been identified as predictive factors for MDR infections and have been used in the construction of clinical prediction models. These biomarkers mainly include peripheral blood neutrophils, lymphocytes, the platelet-to-lymphocyte ratio (PLR), the neutrophil-to-lymphocyte ratio (NLR), eosinophils, C-reactive protein (CRP), procalcitonin (PCT), interleukin-6 (IL-6), and albumin.^97,109–113 The detection results of these biomarkers are more objective, and prediction models developed by integrating them with machine learning techniques often show better predictive performance.¹¹³

Lifestyle and environmental factors

Smoking

Smoking is closely associated with lung function decline, COPD exacerbations, and infections.¹⁵ Smoking damages the airway mucosa and lowers local defense function, promotes chronic airway and systemic inflammation, and increases the risk of lower airway MDR colonization and infection, especially in adolescents.^114,115

Air pollution

Inhalation of particulate matter and harmful gases aggravates inflammation and oxidative stress, damaging lung barrier function and immunity and creating favorable conditions for MDR invasion and colonization.¹¹⁶ Hospitals and waste treatment facilities provide environmental reservoirs for MDR bacteria, which spread through aerosols.^116,117

In summary, the co-occurrence of COPD and MDR bacterial infections results from the interplay of multiple risk factors, including host-related factors, clinical diagnosis and treatment, and environmental influences. The precise identification of high-risk patients and the early formulation of prevention and intervention strategies are pivotal to reducing the emergence of MDR bacteria and improving patient outcomes.

Socioeconomic factors

Studies indicate that the risk of MDR bacterial infections in patients with COPD is closely associated with socioeconomic factors.¹¹⁸ Populations with low socioeconomic status often live in substandard conditions with inadequate sanitation, which increases exposure to and the transmission of pathogens. Meanwhile, financial constraints may prevent patients from completing a full course of treatment. Low educational attainment leads to insufficient awareness of the disease and antimicrobial agents, predisposing patients to antibiotic misuse or premature treatment discontinuation and thereby facilitating the emergence of drug-resistant bacteria. Furthermore, economically underdeveloped regions typically face resource scarcity and inconsistent clinical diagnostic and therapeutic standards. This may result in delayed or nonstandardized care, which elevates the risk of infection and antibiotic exposure. These factors often act synergistically to further increase patients’ susceptibility to infections.^118,119

Current status of prediction model development

Common types of prediction models

Logistic regression models

Logistic regression is a classification model used to estimate event probability based on multiple independent variables. Model discrimination is typically evaluated using the area under the receiver operating characteristic curve, calibration using the Hosmer–Lemeshow test or calibration curves, internal validation using bootstrap or cross-validation, and external validation using datasets from other institutions or time periods; results are interpreted using odds ratios (ORs). A systematic review on acute exacerbation of COPD (AECOPD) prognosis prediction reported that 41 of 53 models used logistic regression, making it one of the most traditional and commonly used clinical modeling methods.²¹ It is widely applied to construct nomograms, model equations, and scoring systems.^115–117

Cox proportional hazards models

The Cox model identifies relationships between variables and time-to-event outcomes. Discrimination is evaluated using the concordance index, and calibration using calibration curves; results are interpreted using hazard ratios and 95% confidence intervals, and nomograms or survival curves are used to build prediction tools. A multicenter retrospective study used a Cox model and nomogram to predict the prognosis of elderly patients with pulmonary MDR infections,¹¹⁸ and Graul EL et al. used a Cox model and forest plot to assess the risk of nonfatal cardiovascular events after COPD exacerbation,¹¹⁹ with both studies showing satisfactory prediction performance.

Machine learning models

Machine learning, a subset of artificial intelligence, uses computer algorithms to analyze data, learn patterns, and make predictions or decisions. Common clinical machine learning models include random forests, support vector machines (SVMs), deep learning, and extreme gradient boosting (XGBoost). In elderly patients with COPD, SVMs achieved training and testing accuracies of 93.82% and 90.07%, respectively, effectively capturing nonlinear relationships.¹²⁰ Deep learning, based on multilayer neural networks, has shown strong predictive performance in studies using chest X-rays and pulmonary function data to predict COPD.¹²¹ Random forests outperformed traditional models in predicting in-hospital mortality among patients with AECOPD.¹²² In multiple studies predicting bacterial resistance, XGBoost demonstrated higher accuracy and predictive performance in both the training and validation sets.^123–125 These studies collectively demonstrated the superiority and potential of machine learning models in clinical practice.

Comparison of prediction models

Different prediction models exhibit significant differences in effectiveness and accuracy, especially between traditional statistical models and machine learning models, each with its own strengths and limitations (Table 2). Model selection and optimization should consider clinical requirements and data characteristics.

Table 2.

Comparison between traditional prediction models and machine learning models.

Model type	Representative models	Advantages	Disadvantages	Applicable scenarios
Traditional prediction models	Logistic regression model	Intuitive principles, results easy to interpret, can be visualized, and easy to operate¹²⁶	Difficult to handle nonlinear relationships and complex multicollinearity¹²⁷	Binary outcomes (e.g. infection vs. no infection, bleeding, etc.)
Traditional prediction models	Cox proportional hazards model	Gold standard for survival-time analysis; identifies effects of variables on time-to-event outcomes and provides precise hazard ratios¹²⁸	Requires proportional hazards assumption; estimates relative risk; sensitive to extreme survival times^129,130	Time-to-event outcomes (e.g. survival time, recurrence time)
Machine learning models	Random forest, XGBoost, support vector machine, deep learning, etc.	High prediction accuracy; able to handle complex nonlinear data, high-order interactions, and unstructured data^131,132	Require large data volume; poor interpretability; risk of overfitting¹³³	Nonlinear data, datasets with extensive interactions, high-dimensional data

XGBoost: extreme gradient boosting.

Discussion

Current predictive models still have numerous shortcomings. For example, data from different hospitals display heterogeneity, which makes them difficult to merge and standardize. Specimens for microbiological tests, such as sputum cultures, vary in quality and are easily contaminated by respiratory colonizing bacteria, resulting in false-positive results. Predictive factors also have limitations; critical information, such as a history of antibiotic exposure and medical contact, may be incompletely or inaccurately recorded.

Moreover, patients’ clinical status and the risk of MDR infection change dynamically, and predictive models have difficulty capturing this dynamic process. The models are mainly constructed based on single-center retrospective studies, leading to a high risk of bias. Most models lack adequate external validation, resulting in poor clinical generalizability.¹³⁴

Additionally, some studies indicate that differences in socioeconomic and demographic characteristics may affect model fairness. This suggests that these factors should be considered during model construction and evaluation to avoid introducing racial or socioeconomic biases.¹³⁵

Since machine learning models have demonstrated better predictive performance than traditional prediction models in predicting the risk of MDR bacterial infections in patients with COPD, future research should focus on multicenter external validation of these models, the scientific rigor of variable selection, and the introduction of calibration methods. Leveraging the advantages of artificial intelligence and big data analysis to apply machine learning models to clinical diagnosis and treatment may become key to overcoming the bottleneck in the prevention and control of MDR bacterial infections.

In summary, this review comprehensively analyzes the risk factors of COPD complicated by MDR bacterial infections, specifically covering biomarkers and socioeconomic factors. Moreover, the review systematically examines predictive models, with an emphasis on machine learning models. It compares the advantages and limitations of traditional models with those of machine learning models and identifies current research gaps. This provides researchers with a reference for selecting appropriate modeling methods. However, as a narrative review, this study has potential risks of subjective bias. Moreover, because the primary source of the literature was the PubMed database, the conclusions may lack sufficient representativeness.

Conclusion

The risk factors for COPD complicated by MDR infections span multiple dimensions, including patient characteristics, clinical diagnosis and treatment, the living environment, and socioeconomic status. Establishing scientifically accurate and clinically applicable predictive models is essential for the targeted management of COPD patients and MDR infections. Future research should utilize multidimensional data and incorporate artificial intelligence technologies into model development to enhance model accuracy and generalizability, thereby facilitating early disease prevention and control and improving patient outcomes.

Footnotes

Acknowledgments

The authors extend their sincere gratitude to all participating patients, whose contributions have greatly advanced the field of COPD and MDR research.

The authors used ChatGPT (OpenAI; GPT-4o, accessed September 2025) solely for language polishing. All content was verified and edited by the authors, who bear full responsibility for the final manuscript.

ORCID iDs

Deng Haibo

Luo Wei

Ethical considerations

The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Contributions

(I) Conception and design: Deng Haibo, Luo Wei;

(II) Literature screening: Deng Haibo, Wu Yonghong;

(III) Data analysis and interpretation: Deng Haibo, Wu Yonghong, Yan Min, Luo Wei;

(IV) Writing – original draft: Deng Haibo;

(V) Final approval of manuscript: All authors.

Funding

The authors received no financial support for the research, authorship, and/or publication of this article.

Declaration of conflicting interests

The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Data sharing statement

This article does not contain any unpublished data.

References

Global Strategy for the Diagnosis, Management, and Prevention of Chronic Obstructive Pulmonary Diseas, http://www.goldcopd.org (2025, accessed 30 August 2025).

Wang

Zhou

Wang

, et al. Progress in the mechanism and targeted drug therapy for COPD. Signal Transduct Target Ther 2020; 5: 248.

Rahman

. Pharmacological antioxidant strategies as therapeutic interventions for COPD. Biochim Biophys Acta 2012; 1822: 714–728.

Guo

Piao

, et al. Pathological mechanism and targeted drugs of COPD. Int J Chron Obstruct Pulmon Dis 2022; 17: 1565–1575.

Kharbanda

Anand

. Health-related quality of life in patients with chronic obstructive pulmonary disease: a hospital-based study. Indian J Med Res 2021; 153: 459–464.

Wills

Reyes

Amon

, et al. Cardiovascular disease as a moderator between airflow limitation and health-related quality of life among patients with chronic obstructive pulmonary disease. J Cardiovasc Nurs 2026; 41: 75–81.

GBD 2013 Mortality and Causes of Death Collaborators. Global, regional, and national age-sex specific all-cause and cause-specific mortality for 240 causes of death, 1990-2013: a systematic analysis for the global burden of disease study 2013. Lancet 2015; 385: 117–171.

GBD 2021 Forecasting Collaborators. Burden of disease scenarios for 204 countries and territories, 2022-2050: a forecasting analysis for the global burden of disease study 2021. Lancet 2024; 403: 2204–2256.

Salam

Al-Amin

Salam

, et al. Antimicrobial resistance: a growing serious threat for global public health. Healthcare (Basel) 2023; 11: 1946.

10.

Samreen, Ahmad

Malak

, et al. Environmental antimicrobial resistance and its drivers: a potential threat to public health. J Glob Antimicrob Resist 2021; 27: 101–111.

11.

Antimicrobial Resistance Collaborators. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. Lancet 2022; 399: 629–655. Erratum in: Lancet. 2022 Oct 1;400(10358):1102.

12.

Ritchie

Wedzicha

. Definition, causes, pathogenesis, and consequences of chronic obstructive pulmonary disease exacerbations. Clin Chest Med 2020; 41: 421–438.

13.

Nseir

Di Pompeo

Cavestri

, et al. Multiple-drug-resistant bacteria in patients with severe acute exacerbation of chronic obstructive pulmonary disease: prevalence, risk factors, and outcome. Crit Care Med 2006; 34: 2959–2966.

14.

Christenson

Smith

Bafadhel

, et al. Chronic obstructive pulmonary disease. Lancet 2022; 399: 2227–2242.

15.

Ding

Liu

, et al. Factors related to the progression of chronic obstructive pulmonary disease: a retrospective case-control study. BMC Pulm Med 2025; 25: 5.

16.

Morris

Cerceo

. Trends, epidemiology, and management of multi-drug resistant gram-negative bacterial infections in the hospitalized setting. Antibiotics (Basel) 2020; 9: 196.

17.

Llamosí

Sempere

Coronel

, et al. Combination of cefditoren and N-acetyl-l-cysteine shows a synergistic effect against multidrug-resistant Streptococcus pneumoniae biofilms. Microbiol Spectr 2022; 10: e0341522.

18.

Mussema

Beyene

Gashaw

. Bacterial isolates and antibacterial resistance patterns in a patient with acute exacerbation of chronic obstructive pulmonary disease in a tertiary teaching hospital, southwest Ethiopia. Can J Infect Dis Med Microbiol 2022; 2022: 9709253.

19.

Zhang

Feng

, et al. Research advances in predicting the expansion of hypertensive intracerebral hemorrhage based on CT images: an overview. PeerJ 2024; 12: e17556.

20.

Smith

Oakden-Rayner

Bird

, et al. Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis. Lancet Digit Health 2023; 5: e872–e881.

21.

Xin

, et al. Prognostic risk prediction model for patients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD): a systematic review and meta-analysis. Respir Res 2024; 25: 410.

22.

Zhao

Wang

, et al. A machine-learning-derived online prediction model for depression risk in COPD patients: a retrospective cohort study from CHARLS. J Affect Disord 2025; 377: 284–293.

23.

Hou

Min

Hou

, et al. Prediction of clinical deterioration within one year in chronic obstructive pulmonary disease using the systemic coagulation-inflammation index: a retrospective study employing multiple machine learning method. PeerJ 2025; 13: e18989.

24.

Moll

Silverman

. Precision approaches to chronic obstructive pulmonary disease management. Annu Rev Med 2024; 75: 247–262.

25.

Baethge

Goldbeck-Wood

Mertens

. SANRA-a scale for the quality assessment of narrative review articles. Res Integr Peer Rev 2019; 4: 5.

26.

Rafailidis

Kofteridis

. Proposed amendments regarding the definitions of multidrug-resistant and extensively drug-resistant bacteria. Expert Rev Anti Infect Ther 2022; 20: 139–146.

27.

Jean

Harnod

Hsueh

. Global threat of carbapenem-resistant gram-negative Bacteria. Front Cell Infect Microbiol 2022; 12: 823684.

28.

Duhaniuc

Păduraru

Nastase

, et al. Multidrug-Resistant Bacteria in immunocompromised patients. Pharmaceuticals (Basel) 2024; 17: 1151.

29.

Martins

APS

da Mata

CPSM

Dos Santos

, et al. Association between multidrug-resistant bacteria and outcomes in intensive care unit patients: a non-interventional study. Front Public Health 2024; 11: 1297350.

30.

Chen

Tang

, et al. Increased financial burdens and lengths of stay in patients with healthcare-associated infections due to multidrug-resistant bacteria in intensive care units: a propensity-matched case-control study. PLoS One 2020; 15: e0233265.

31.

Lakbar

Medam

Ronflé

, et al. Association between mortality and highly antimicrobial-resistant bacteria in intensive care unit-acquired pneumonia. Sci Rep 2021; 11: 16497.

32.

Marino

Maniaci

Lentini

, et al. The global burden of multidrug-resistant Bacteria. Epidemiologia (Basel) 2025; 6: 21.

33.

Zhang

Cheng

. The mechanism of bacterial resistance and potential bacteriostatic strategies. Antibiotics (Basel) 2022; 11: 1215.

34.

Eichenberger

Thaden

. Epidemiology and mechanisms of resistance of extensively drug resistant gram-negative Bacteria. Antibiotics (Basel) 2019; 8: 37.

35.

Miller

Arias

. ESKAPE Pathogens: antimicrobial resistance, epidemiology, clinical impact and therapeutics. Nat Rev Microbiol 2024; 22: 598–616.

36.

Liu

Wang

Walsh

, et al. Emergence of plasmid-mediated colistin resistance mechanism MCR-1 in animals and human beings in China: a microbiological and molecular biological study. Lancet Infect Dis 2016; 16: 161–168.

37.

Galindo-Méndez

Navarrete-Salazar

Pacheco-Vásquez

, et al. Detection of plasmid-mediated resistance against colistin in multi-drug-resistant gram-negative bacilli isolated from a tertiary hospital. Microorganisms 2023; 11: 1996.

38.

Assefa

. Multi-drug resistant gram-negative bacterial pneumonia: etiology, risk factors, and drug resistance patterns. Pneumonia (Nathan) 2022; 14: 4.

39.

Aggarwal

Mahajan

Pandiya

, et al. Antibiotic resistance: a global crisis, problems and solutions. Crit Rev Microbiol 2024; 50: 896–921.

40.

Thakur

Uniyal

Tiwari

. A comprehensive review on pharmacology of efflux pumps and their inhibitors in antibiotic resistance. Eur J Pharmacol 2021; 903: 174151.

41.

Mohammed

Salim

MTA

Anwer

, et al. Impact of target site mutations and plasmid associated resistance genes acquisition on resistance of Acinetobacter baumannii to fluoroquinolones. Sci Rep 2021; 11: 20136.

42.

Tooke

Hinchliffe

Bragginton

, et al. β-Lactamases and β-lactamase inhibitors in the 21st century. J Mol Biol 2019; 431: 3472–3500.

43.

Lopatkin

Bening

Manson

, et al. Clinically relevant mutations in core metabolic genes confer antibiotic resistance. Science 2021; 371: eaba0862.

44.

Wilson

Hauryliuk

Atkinson

, et al. Target protection as a key antibiotic resistance mechanism. Nat Rev Microbiol 2020; 18: 637–648.

45.

Høiby

Ciofu

Johansen

, et al. The clinical impact of bacterial biofilms. Int J Oral Sci 2011; 3: 55–65.

46.

Hanot

Lohou

Sonnet

. Anti-Biofilm agents to overcome Pseudomonas aeruginosa antibiotic resistance. Pharmaceuticals (Basel) 2025; 18: 92.

47.

Rather

Gupta

Mandal

. Microbial biofilm: formation, architecture, antibiotic resistance, and control strategies. Braz J Microbiol 2021; 52: 1701–1718.

48.

Sharkey

Edwards

O'Neill

. ABC-F proteins mediate antibiotic resistance through ribosomal protection. mBio 2016; 7: e01975.

49.

Ero

Yan

Gao

. Ribosome protection proteins-“new” players in the global arms race with antibiotic-resistant pathogens. Int J Mol Sci 2021; 22: 5356.

50.

Hao

Lou

Zhu

, et al. The multiple antibiotic resistance regulator MarR is a copper sensor in Escherichia coli. Nat Chem Biol 2014; 10: 21–28.

51.

Zhang

Rosner

Martin

. Transcriptional activation by MarA, SoxS and rob of two tolC promoters using one binding site: a complex promoter configuration for tolC in Escherichia coli. Mol Microbiol 2008; 69: 1450–1455.

52.

Mickiewicz

Kawai

Drage

, et al. Possible role of L-form switching in recurrent urinary tract infection. Nat Commun 2019; 10: 4379. Erratum in: Nat Commun. 2019 Nov 20;10(1):5254. doi: 10.1038/s41467-019-13256-5.

53.

Errington

Mickiewicz

Kawai

, et al. L-form bacteria, chronic diseases and the origins of life. Philos Trans R Soc Lond B Biol Sci 2016; 371: 20150494.

54.

Doğan

Sydow

Heiden

, et al. Klebsiella pneumoniae exhibiting a phenotypic hyper-splitting phenomenon including the formation of small colony variants. Front Cell Infect Microbiol 2024; 14: 1372704.

55.

Al-Kandari

Al-Temaimi

van Vliet

AHM

, et al. Thymol tolerance in Escherichia coli induces morphological, metabolic and genetic changes. BMC Microbiol 2019; 19: 294.

56.

van Duin

Paterson

. Multidrug-Resistant Bacteria in the community: an update. Infect Dis Clin North Am 2020; 34: 709–722.

57.

Estirado

Ceccato

Guerrero

, et al. Microorganisms resistant to conventional antimicrobials in acute exacerbations of chronic obstructive pulmonary disease. Respir Res 2018; 19: 119.

58.

Rodrigo-Troyano

Melo

Marcos

, et al. Pseudomonas aeruginosa in chronic obstructive pulmonary disease patients with frequent hospitalized exacerbations: a prospective multicentre study. Respiration 2018; 96: 417–424.

59.

Rodrigo-Troyano

Sibila

. The respiratory threat posed by multidrug resistant gram-negative bacteria. Respirology 2017; 22: 1288–1299.

60.

Eklöf

Sørensen

Ingebrigtsen

, et al. Pseudomonas aeruginosa and risk of death and exacerbations in patients with chronic obstructive pulmonary disease: an observational cohort study of 22 053 patients. Clin Microbiol Infect 2020; 26: 227–234.

61.

Martinez-García

Rigau

Barrecheguren

, et al. Long-term risk of mortality associated with isolation of Pseudomonas aeruginosa in COPD: a systematic review and meta-analysis. Int J Chron Obstruct Pulmon Dis 2022; 17: 371–382.

62.

Eklöf

Misiakou

Sivapalan

, et al. Persistence and genetic adaptation of Pseudomonas aeruginosa in patients with chronic obstructive pulmonary disease. Clin Microbiol Infect 2022; 28: 990–995.

63.

Poirel

Nordmann

. Carbapenem resistance in Acinetobacter baumannii: mechanisms and epidemiology. Clin Microbiol Infect 2006; 12: 826–836.

64.

Liu

Chen

, et al. Epidemiological and genetic characteristics of clinical carbapenem-resistant Acinetobacter baumannii strains collected countrywide from hospital intensive care units (ICUs) in China. Emerg Microbes Infect 2022; 11: 1730–1741.

65.

Jia

Zhu

, et al. Emergence of a novel NDM-5-producing sequence type 4523 Klebsiella pneumoniae strain causing bloodstream infection in China. Microbiol Spectr 2022; 10: e0084222.

66.

Zhang

Tian

, et al. Doxifluridine effectively kills antibiotic-resistant Staphylococcus aureus in chronic obstructive pulmonary disease. Microbiol Spectr 2024; 12: e0180524.

67.

Pailhoriès

Herrmann

Velo-Suarez

, et al. Antibiotic resistance in chronic respiratory diseases: from susceptibility testing to the resistome. Eur Respir Rev 2022; 31: 210259.

68.

Rodrigues

Cunha

CMCD

Soares

GMV

, et al. Mechanisms, pathophysiology and currently proposed treatments of chronic obstructive pulmonary disease. Pharmaceuticals (Basel) 2021; 14: 979.

69.

Zeng

, et al. Inflammation mechanism and research progress of COPD. Front Immunol 2024; 15: 1404615.

70.

Barnes

. Inflammatory mechanisms in patients with chronic obstructive pulmonary disease. J Allergy Clin Immunol 2016; 138: 16–27.

71.

Leap

Arshad

Cheema

, et al. Pathophysiology of COPD. Crit Care Nurs Q 2021; 44: 2–8.

72.

Russell

Genschmer

Blalock

. Extracellular vesicles as central mediators of COPD pathophysiology. Annu Rev Physiol 2022; 84: 631–654.

73.

van Beers

Gosker

Janssen

DJA

, et al. Cognitive performance in relation to metabolic disturbances in patients with COPD. Clin Nutr 2021; 40: 2061–2067.

74.

Reynaert

Vanfleteren

LEGW

Perkins

. The AGE-RAGE axis and the pathophysiology of multimorbidity in COPD. J Clin Med 2023; 12: 3366.

75.

Niculescu

Mitache

Grumezescu

, et al. From microbial ecology to clinical challenges: the respiratory microbiome’s role in antibiotic resistance. Pathogens 2025; 14: 355.

76.

Short

Carson

Devlin

, et al. Non-typeable Haemophilus influenzae chronic colonization in chronic obstructive pulmonary disease (COPD). Crit Rev Microbiol 2021; 47: 192–205.

77.

Shah

Singh

Wang

, et al. Mucus hypersecretion in chronic obstructive pulmonary disease and its treatment. Mediators Inflamm 2023; 2023: 8840594.

78.

MacLeod

Papi

Contoli

, et al. Chronic obstructive pulmonary disease exacerbation fundamentals: diagnosis, treatment, prevention and disease impact. Respirology 2021; 26: 532–551.

79.

Smith

Gill

Hall

, et al. Prevalence, pattern, risks factors and consequences of antibiotic resistance in COPD: a systematic review. COPD 2021; 18: 672–682.

80.

Uluç

Kutbay Özçelik

Akkütük Öngel

, et al. The prevalence of multidrug-resistant and extensively drug-resistant infections in respiratory intensive care unit, causative microorganisms and mortality. Infect Drug Resist 2024; 17: 4913–4919.

81.

Nseir

Ader

. Prevalence and outcome of severe chronic obstructive pulmonary disease exacerbations caused by multidrug-resistant bacteria. Curr Opin Pulm Med 2008; 14: 95–100.

82.

Dantas

Dalmas

Andrade

, et al. Predicting acquisition of carbapenem-resistant gram-negative pathogens in intensive care units. J Hosp Infect 2019; 103: 121–127.

83.

Wang

Wei

Zhao

, et al. Analysis of multidrug-resistant bacteria in 3223 patients with hospital-acquired infections (HAI) from a tertiary general hospital in China. Bosn J Basic Med Sci 2019; 19: 86–93.

84.

Kodde

Bonsignore

Köhler

, et al. Males are at higher risk of colonization and infection with multi-drug-resistant organisms than females. J Hosp Infect 2025; 155: 88–94.

85.

Alexopoulos

Malli

Mitsiki

, et al. Frequency and risk factors of COPD exacerbations and hospitalizations: a nationwide study in Greece (Greek obstructive lung disease epidemiology and health ecoNomics: GOLDEN study). Int J Chron Obstruct Pulmon Dis 2015; 10: 2665–2674.

86.

Pifarre

Falguera

Vicente-de-Vera

, et al. Characteristics of community-acquired pneumonia in patients with chronic obstructive pulmonary disease. Respir Med 2007; 101: 2139–2144.

87.

Guo

Song

Mei

, et al. Distribution of multidrug-resistant bacterial infections in diabetic foot ulcers and risk factors for drug resistance: a retrospective analysis. PeerJ 2023; 11: e16162.

88.

Carrillo-Larco

Anza-Ramírez

Saal-Zapata

, et al. Type 2 diabetes mellitus and antibiotic-resistant infections: a systematic review and meta-analysis. J Epidemiol Community Health 2022; 76: 75–84.

89.

Amanati

Sajedianfard

Khajeh

, et al. Bloodstream infections in adult patients with malignancy, epidemiology, microbiology, and risk factors associated with mortality and multi-drug resistance. BMC Infect Dis 2021; 21: 636.

90.

Assefa

Amare

Tigabie

, et al. Burden of multidrug-resistant bacteria among HIV-positive individuals in Ethiopia: a systematic review and meta-analysis. PLoS One 2024; 19: e0309418.

91.

Pouch

Satlin

. Carbapenem-resistant Enterobacteriaceae in special populations: solid organ transplant recipients, stem cell transplant recipients, and patients with hematologic malignancies. Virulence 2017; 8: 391–402.

92.

Freire

Pouch

Manesh

, et al. Burden and management of multi-drug resistant organism infections in solid organ transplant recipients across the world: a narrative review. Transpl Int 2024; 37: 12469.

93.

Almohaya

Fersovich

Weyant

, et al. The impact of colonization by multidrug resistant bacteria on graft survival, risk of infection, and mortality in recipients of solid organ transplant: systematic review and meta-analysis. Clin Microbiol Infect 2024; 30: 1228–1243.

94.

Seligman

Ramos-Lima

Oliveira Vdo

, et al. Risk factors for infection with multidrug-resistant bacteria in non-ventilated patients with hospital-acquired pneumonia. J Bras Pneumol 2013; 39: 339–348.

95.

Deng

Zhang

, et al. Global prevalence of malnutrition in patients with chronic obstructive pulmonary disease: systemic review and meta-analysis. Clin Nutr 2023; 42: 848–858.

96.

Lacey

Pickrum

Gonzalez

, et al. Dietary and water restriction leads to increased susceptibility to antimicrobial resistant pathogens. Sci Adv 2024; 10: eadi7438.

97.

Yang

Chen

, et al. Prognosis analysis and infection-related risk factors of multi-drug-resistant bacteria isolated from a general hospital in China, 2019-2023. J Hosp Infect 2025; 158: 29–37.

98.

Baran

Kwiatkowska

Potocki

. Antibiotics and bacterial resistance-A short story of an endless arms race. Int J Mol Sci 2023; 24: 5777.

99.

Hsu

, et al. Aetiology and prognostic risk factors of mortality in patients with pneumonia receiving glucocorticoids alone or glucocorticoids and other immunosuppressants: a retrospective cohort study. BMJ Open 2020; 10: e037419.

100.

Patil

. Incidence, bacteriology, and clinical outcome of ventilator-associated pneumonia at tertiary care hospital. J Nat Sci Biol Med 2017; 8: 46–55.

101.

Kuloglu

Unuvar

Cevahir

, et al. Risk factors and mortality rates of carbapenem-resistant gram-negative bacterial infections in intensive care units. J Intensive Med 2024; 4: 347–354.

102.

Chen

Sun

, et al. Risk factors of multidrug-resistant Bacteria in lower respiratory tract infections: a systematic review and meta-analysis. Can J Infect Dis Med Microbiol 2020; 2020: 7268519.

103.

Michels-Zetsche

Gassmann

Jasuja

, et al. Role of multidrug-resistant bacteria in weaning from invasive mechanical ventilation. Respir Res 2024; 25: 69.

104.

Howroyd

Gill

Thompson

, et al. Ventilator-associated pneumonia: mechanisms, an appraisal of current therapies and the role for inhaled antibiotics in prevention and treatment. Respir Med 2025; 247: 108275.

105.

Ulsamer

Bonilla

Pérez-Fernández

, et al. The pathogenesis of ventilator-associated pneumonia: old and new mechanisms. Expert Rev Respir Med 2025; 19: 655–671.

106.

Rodrigues

Passadouro

Gomes

, et al. Risk factors, length of stay and in-hospital mortality of methicillin-resistant Staphylococcus aureus infections: a case-control study. Acta Med Port 2020; 33: 174–182.

107.

Xiao

Shi

, et al. A retrospective analysis of risk factors and outcomes in patients with extended-spectrum beta-lactamase-producing Escherichia coli bloodstream infections. J Glob Antimicrob Resist 2019; 17: 147–156.

108.

Pan

Lou

Zeng

, et al. Infections caused by carbapenemase-producing Klebsiella pneumoniae: microbiological characteristics and risk factors. Microb Drug Resist 2019; 25: 287–296.

109.

Arab

Al-Kayali

Khouri

, et al. Resistance patterns of bacterial pathogens causing lower respiratory tract infections: aleppo-Syria. Ann Med Surg (Lond) 2023; 85: 2655–2661.

110.

Belayhun

Tilahun

Seid

, et al. Asymptomatic nasopharyngeal bacterial carriage, multi-drug resistance pattern and associated factors among primary school children at debre berhan town, north shewa, Ethiopia. Ann Clin Microbiol Antimicrob 2023; 22: 9.

111.

Zhang

Chen

Dai

, et al. Associations between air pollutants and risk of respiratory infection: patient-based bacterial culture in sputum. Environ Geochem Health 2022; 44: 4007–4016.

112.

Abelenda-Alonso

Rombauts

Burguillos

, et al. One air, one health: air pollution in the era of antimicrobial resistance. Clin Microbiol Infect 2021; 27: 947–948.

113.

Wozniak

Cuningham

Ledingham

, et al. Contribution of socio-economic factors in the spread of antimicrobial resistant infections in Australian primary healthcare clinics. J Glob Antimicrob Resist 2022; 30: 294–301.

114.

Omulo

Lofgren

Lockwood

, et al. Carriage of antimicrobial-resistant bacteria in a high-density informal settlement in Kenya is associated with environmental risk-factors. Antimicrob Resist Infect Control 2021; 10: 18.

115.

Wang

Zhang

Meng

, et al. Development and validation of a nomogram model for predicting MDRO infections in elderly ICU patients with pulmonary infections. Aging Clin Exp Res 2025; 37: 218.

116.

Luo

, et al. Prediction model of in-hospital death for acute exacerbation of chronic obstructive pulmonary disease patients admitted to intensive care unit: the PD-ICU score. Respiration 2025; 104: 85–99.

117.

Wang

Yuan

Zhong

, et al. Development and validation of a nomogram for predicting bacterial infections in patients with acute exacerbation of chronic obstructive pulmonary disease. Exp Ther Med 2024; 29: 3.

118.

Wang

Dai

, et al. Establishment and validation of models for the risk of multi-drug resistant Bacteria infection and prognosis in elderly patients with pulmonary infection: a multicenter retrospective study. Infect Drug Resist 2023; 16: 6549–6566.

119.

Graul

Nordon

Rhodes

, et al. Temporal risk of nonfatal cardiovascular events after chronic obstructive pulmonary disease exacerbation: a population-based study. Am J Respir Crit Care Med 2024; 209: 960–972.

120.

Zhang

Chang

Zhang

, et al. [Comparison of the predictive performance of logistic regression, BP neural network and support vector machine model for the risk of acute exacerbation of readmission in elderly patients with chronic obstructive pulmonary disease within 30 days]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue 2022; 34: 819–824. Chinese.

121.

Schroeder

Bigolin Lanfredi

, et al. Prediction of obstructive lung disease from chest radiographs via deep learning trained on pulmonary function data. Int J Chron Obstruct Pulmon Dis 2021; 15: 3455–3466.

122.

Ruan

Huang

, et al. Machine learning-based prediction of in-hospital mortality in patients with pneumonic chronic obstructive pulmonary disease exacerbations. J Asthma 2024; 61: 212–221.

123.

Song

Zhu

, et al. Machine learning-based prediction model for patients with recurrent Staphylococcus aureus bacteremia. BMC Med Inform Decis Mak 2025; 25: 99.

124.

Ardila

Yadalam

González-Arroyave

. Integrating whole genome sequencing and machine learning for predicting antimicrobial resistance in critical pathogens: a systematic review of antimicrobial susceptibility tests. PeerJ 2024; 12: e18213.

125.

Jiang

Wang

Tian

, et al. Predicting carbapenem-resistant Pseudomonas aeruginosa infection risk using XGBoost model and explainability. Sci Rep 2025; 15: 19737.

126.

Ruan

, et al. Tracking epidemiological characteristics and risk factors of multi-drug resistant Bacteria in intensive care units. Infect Drug Resist 2023; 16: 1499–1509.

127.

Ullmann

Heinze

Hafermann

, et al. Evaluating variable selection methods for multivariable regression models: a simulation study protocol. PLoS One 2024; 19: e0308543.

128.

McLernon

Giardiello

Van Calster

, et al. Assessing performance and clinical usefulness in prediction models with survival outcomes: practical guidance for cox proportional hazards models. Ann Intern Med 2023; 176: 105–114.

129.

Jiang

, et al. Limitations of the cox proportional hazards model and alternative approaches in metachronous recurrence research. Gastric Cancer 2024; 27: 1348–1349.

130.

Samawi

Yin

. On cox proportional hazards model performance under different sampling schemes. PLoS One 2023; 18: e0278700.

131.

Yang

Zheng

Zhang

, et al. Screening the best risk model and susceptibility SNPs for chronic obstructive pulmonary disease (COPD) based on machine learning algorithms. Int J Chron Obstruct Pulmon Dis 2024; 19: 2397–2414.

132.

Deo

. Machine learning in medicine. Circulation 2015; 132: 1920–1930.

133.

Handelman

Kok

Chandra

, et al. Edoctor: machine learning and the future of medicine. J Intern Med 2018; 284: 603–619.

134.

Wei

Zhou

, et al. Systematic review and meta-analysis of prediction models for multidrug-resistant organism infections in comprehensive intensive care units. J Glob Antimicrob Resist 2025; 44: 139–145.

135.

Wang

Zhou

, et al. Assessing fairness in machine learning models: a study of racial bias using matched counterparts in mortality prediction for patients with chronic diseases. J Biomed Inform 2024; 156: 104677.