OBJECTIVE: To explore the efficacy of a Thalassemia risk assessment software for the screening of thalassemia mutation carriers and distribution of thalassemia genotypes detected by screening. METHODS: A total of 6 040 individuals were evaluated at Leshan Maternal and Child Health Care Hospital between 2022 and 2024 using the commonly used clinical thalassemia risk assessment method and the thalassemia screening software, respectively, and the performance indicators of the two methods were compared and analyzed against the result of thalassemia gene testing. This study was approved by the Ethics Committee of our hospital (Ethics No.: LfyLL[2022]005). RESULTS: The high-risk rate by the thalassemia screening software was 11.19%, with a sensitivity of 95.12%, specificity of 93.28%, positive predictive value of 43.20%, negative predictive value of 99.72%, and the area under the ROC curve (AUC) was 0.942. The thalassemia gene detection rate of the high-risk samples screened was 4.83%. The high-risk screening rate of the conventional method was 2.50%, with a sensitivity of 51.22%, specificity of 93.28%, positive predictive value of 80.79%, negative predictive value of 97.40%, and the AUC was 0.754. The thalassemia gene detection rate of the high-risk samples was 2.02%. CONCLUSION The software can effectively detect thalassemia carriers and significantly reduce the missed detection compared with conventional method, thereby significantly improve the efficacy of screening.
Humans ; Thalassemia/diagnosis* ; Software ; Female ; Genetic Testing/methods* ; Male ; Mutation ; Adult ; Genotype ; ROC Curve ; Risk Assessment

INTRODUCTION: Obstructive sleep apnoea (OSA) is a serious but underdiagnosed condition. Demand for the gold standard diagnostic polysomnogram (PSG) far exceeds its availability. More efficient diagnostic methods are needed, even in tertiary settings. Machine learning (ML) models have strengths in disease prediction and early diagnosis. We explored the use of ML with oximetry, demographic and anthropometric data to diagnose OSA. METHODS: A total of 2,996 patients were included for modelling and divided into test and training sets. Seven commonly used supervised learning algorithms were trained with the data. Sensitivity (recall), specificity, positive predictive value (PPV) (precision), negative predictive value, area under the receiver operating characteristic curve (AUC) and F1 measure were reported for each model. RESULTS: In the best performing four-class model (neural network model predicting no, mild, moderate or severe OSA), a prediction of moderate and/or severe disease had a combined PPV of 94%; one out of 335 patients had no OSA and 19 had mild OSA. In the best performing two-class model (logistic regression model predicting no-mild vs. moderate-severe OSA), the PPV for moderate-severe OSA was 92%; two out of 350 patients had no OSA and 26 had mild OSA. CONCLUSION Our study showed that the prediction of moderate-severe OSA in a tertiary setting with an ML approach is a viable option to facilitate early identification of OSA. Prospective studies with home-based oximeters and analysis of other oximetry variables are the next steps towards formal implementation.
Humans ; Oximetry/methods* ; Sleep Apnea, Obstructive/diagnosis* ; Male ; Female ; Middle Aged ; Machine Learning ; Polysomnography ; Adult ; Anthropometry ; ROC Curve ; Aged ; Algorithms ; Predictive Value of Tests ; Sensitivity and Specificity ; Neural Networks, Computer ; Demography

INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

INTRODUCTION: The diagnosis of sarcopenia relies on key indicators such as handgrip strength, walking speed and muscle mass. Developing a composite index that integrates these measures could enhance clinical evaluation in older adults. This study aimed to standardise and combine these metrics to establish a z score for the sarcopenia composite index (ZoSCI) tailored for the ageing population. Additionally, we explore the risk factors associated with ZoSCI to provide insights into early prevention and intervention strategies. METHOD: This retrospective study analysed data between January 2017 and December 2021 from an elderly health programme in Taiwan, applying the Asian Working Group for Sarcopenia criteria to assess sarcopenia. ZoSCI was developed by standardising handgrip strength, walking speed and muscle mass into z scores and integrating them into a composite index. Receiver operating characteristic (ROC) curve analysis was used to determine optimal cut-off values, and multiple regression analysis identified factors influencing ZoSCI. RESULTS: Among the 5047 participants, the prevalence of sarcopenia was 3.7%, lower than the reported global prevalence of 3.9-15.4%. ROC curve analysis established optimal cut-off points for distinguishing sarcopenia in ZoSCI: -1.85 (sensitivity 0.91, specificity 0.88) for males and -1.97 (sensitivity 0.93, specificity 0.88) for females. Factors associated with lower ZoSCI included advanced age, lower education levels, reduced exercise frequency, lower body mass index and creatinine levels. CONCLUSION This study introduces ZoSCI, a new compo-site quantitative indicator for identifying sarcopenia in older adults. The findings highlight specific risk factors that can inform early intervention. Future studies should validate ZoSCI globally, with international collaborations to ensure broader applicability.
Humans ; Sarcopenia/physiopathology* ; Male ; Aged ; Female ; Retrospective Studies ; Hand Strength ; Taiwan/epidemiology* ; ROC Curve ; Aged, 80 and over ; Risk Factors ; Walking Speed ; Geriatric Assessment/methods* ; Prevalence ; Muscle, Skeletal ; Middle Aged

BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

BACKGROUND: Concurrent chemo-radiotherapy (CCRT) is the standard treatment for locally advanced cervical cancer (LACC), but there are still many patients who suffer tumor recurrence. However, valuable predictors of treatment outcomes remain limited. This study aimed to assess the value of the serum immune biomarkers to predict the prognosis. METHODS: We reviewed cervical cancer patients treated with CCRT between January 2014 and May 2018 at Peking Union Medical College Hospital. The systemic immune inflammation index (SII), systemic inflammation response index (SIRI), and lactate dehydrogenase (LDH) were calculated using blood samples. The relationship between immune markers and the treatment outcome was analyzed. The area under the receiver operating characteristic (ROC) curve was used to evaluate the predictive efficiency. The Cox proportional hazards model and log-rank were used to predict overall survival (OS) and disease-free survival (DFS). RESULTS: This study included 667 patients. Among them, 195 (29.2%) patients were defined as treatment failure, including 127 (19.0%) patients with pelvic failure, 94 (14.1%) distant failure, and 25 (3.7%) concurrent pelvic and distant failure. It revealed that the tumor stage, size, metastatic lymph nodes (MLNs), and serum immune biomarkers, such as SII, SIRI, and LDH, were significantly related to treatment outcomes. We demonstrated that the optimal cut-off of the SII, SIRI, and LDH were 970.4 × 10 9 /L, 1.3 × 10 9 /L, and 207.52 U/L, respectively. Importantly, this study presented that LDH level had the highest OR (OR = 4.2; 95% CI [2.3-10.8]). Furthermore, the OS and DFS for patients with pre-SII ≥970.5 × 10 9 /L were significantly worse than those with pre-SII <970.5 × 10 9 /L. Similarly, pre-SIRI ≥1.25 × 10 9 /L and pre-LDH ≥207.5 U/L were related to poor survival outcomes. CONCLUSIONS This study demonstrated that the baseline SII, SIRI, and LDH levels can be used to accurately and effectively predict the treatment outcomes after CCRT and long-term prognosis. Our results may offer additional prognostic information in clinical, which helps to detect the potential recurrent metastasis in time.
Humans ; Female ; Uterine Cervical Neoplasms/drug therapy* ; Middle Aged ; Adult ; Aged ; Chemoradiotherapy/methods* ; L-Lactate Dehydrogenase/blood* ; Treatment Outcome ; Disease-Free Survival ; Prognosis ; ROC Curve ; Biomarkers, Tumor/blood* ; Proportional Hazards Models

OBJECTIVE: To elucidate the predictive value of norepinephrine equivalence (NEE) score on the 28-day death risk in patients with sepsis and provide evidence for its application in the diagnosis and treatment of sepsis and septic shock. METHODS: A retrospective cohort study was conducted based on the data of patients with sepsis from Medical Information Mart for Intensive Care-IV 2.2 (MIMIC-IV 2.2). The patients who received vasoactive agents within 6 hours after the diagnosis of sepsis or septic shock were enrolled, and they were divided into survival and non-survival groups based on their 28-day outcomes. The baseline characteristics, vital signs, and treatment data were collected. Multivariate Cox regression analysis was performed to identify factors influencing the 28-day death risk. Receiver operator characteristic curve (ROC curve) was drawn to analyze the predictive value of various parameters on the 28-day death risk of septic patients. Kaplan-Meier survival curve was used to evaluate cumulative survival rate in patients classified by different quantitative parameters based on the cut-off values obtained from ROC curve analysis. RESULTS: A total of 7 744 patients who met the Sepsis-3 diagnostic criteria and received vasopressor treatment within 6 hours post-diagnosis were enrolled, of which 5 997 cases survived and 1 747 died, with the 28-day mortality of 22.6%. Significant differences were observed between the two groups regarding age, gender, height, body weight, race, type of intensive care unit (ICU), acute physiology and chronic health evaluation II (APACHE II) score, sequential organ failure assessment (SOFA) score, Charlson comorbidity index (CCI) score, underlying comorbidities, and vital signs. Compared with the survival group, the non-survival group had poorer blood routine, liver and kidney function, coagulation function, blood gas analysis and other indicators. Multivariate Cox regression analysis revealed that age > 65 years old [hazard ratio (HR) = 0.892, 95% confidence interval (95%CI) was 0.801-0.994, P = 0.039] and male (HR = 0.735, 95%CI was 0.669-0.808, P < 0.001) were protective factors for 28-day death in patients with sepsis, and NEE score (HR = 1.040, 95%CI was 1.021-1.060, P < 0.001), shock index (HR = 1.840, 95%CI was 1.675-2.022, P < 0.001), APACHE II score (HR = 1.076, 95%CI was 1.069-1.083, P < 0.001), SOFA score (HR = 1.035, 95%CI was 1.015-1.056, P < 0.001), and CCI score (HR = 1.135, 95%CI was 1.115-1.155, P < 0.001) were independent risk factors for 28-day death in septic patients. ROC curve analysis showed that the area under the ROC curve (AUC) of NEE score for predicting the 28-day death risk of septic patients was 0.743 (95%CI was 0.730-0.756), which was comparable to the predictive value of APACHE II score (AUC = 0.742, 95%CI was 0.729-0.755) and ratio of mean arterial pressure (MAP)/NEE score (MAP/NEE; AUC = 0.738, 95%CI was 0.725-0.751, both P > 0.05), and better than SOFA score (AUC = 0.609, 95%CI was 0.594-0.624), CCI score (AUC = 0.658, 95%CI was 0.644-0.673), shock index (AUC = 0.613, 95%CI was 0.597-0.629) and ratio of diastolic blood pressure (DBP)/NEE score (DBP/NEE; AUC = 0.735, 95%CI was 0.721-0.748, all P < 0.05). According to the cut-off values of APACHE II and NEE scores obtained from ROC curve analysis, the patients were stratified for Kaplan-Meier survival curve analysis, and the results showed that the 28-day cumulative survival rate in the septic patients with an APACHE II score ≤ 22.5 was significantly higher than that in those with an APACHE II > 22.5 (Log-Rank test: χ² = 848.600, P < 0.001), and the 28-day cumulative survival rate in the septic patients with an NEE score ≤0.120 was significantly higher than that in those with an NEE score > 0.120 (Log-Rank test: χ² = 832.449, P < 0.001). CONCLUSIONS NEE score is an independent risk factor for 28-day death in septic patients who received vasoactive treatment within 6 hours of diagnosis and possesses significant predictive value. It can be used for severity stratification in sepsis management.
Humans ; Retrospective Studies ; Sepsis/diagnosis* ; Male ; Female ; Norepinephrine/therapeutic use* ; Middle Aged ; Aged ; Prognosis ; Predictive Value of Tests ; Shock, Septic/mortality* ; Adult ; ROC Curve ; Risk Factors ; Survival Rate ; Aged, 80 and over

OBJECTIVE: To identify early potential risk factors for hospital-acquired pneumonia (HAP) in patients with mild traumatic brain injury (mTBI), construct a risk prediction model, and evaluate its predictive efficacy. METHODS: A case-control study was conducted using clinical data from mTBI patients admitted to the neurosurgery department of Changzhou Second People's Hospital from September 2021 to September 2023. The patients were divided into two groups based on whether they developed HAP. Clinical data within 48 hours of admission were statistically analyzed to identify factors influencing HAP occurrence through univariate analysis. Least absolute shrinkage and selection operator (LASSO) regression analysis was employed for feature selection to identify the most influential variables. The dataset was divided into training and validation sets in a 7:3 ratio. A multivariate Logistic regression analysis was then performed using the training set to construct the prediction model, exploring the risk factors for HAP in mTBI patients and conducting internal validation in the validation set. Receiver operator characteristic curve (ROC curve), decision curve analysis (DCA), and calibration curve were utilized to assess the sensitivity, specificity, decision value, and predictive accuracy of the prediction model. RESULTS: A total of 677 mTBI patients were included, with 257 in the HAP group and 420 in the non-HAP group. The significant differences were found between the two groups in terms of age, maximum body temperature (MaxT), maximum heart rate (MaxHR), maximum systolic blood pressure (MaxSBP), minimum systolic blood pressure (MinSBP), maximum respiratory rate (MaxRR), cause of injury, and laboratory indicators [C-reactive protein (CRP), procalcitonin (PCT), neutrophil count (NEUT), erythrocyte sedimentation rate (ESR), fibrinogen (FBG), fibrinogen equivalent units (FEU), prothrombin time (PT), activated partial thromboplastin time (APTT), total cholesterol (TC), lactate dehydrogenase (LDH), prealbumin (PAB), albumin (Alb), blood urea nitrogen (BUN), serum creatinine (SCr), hematocrit (HCT), hemoglobin (Hb), platelet count (PLT), glucose (Glu), K⁺, Na⁺], suggesting they could be potential risk factors for HAP in mTBI patients. After LASSO regression analysis, the key risk factors were enrolled in the multivariate Logistic regression analysis. The results revealed that the cause of injury being a traffic accident [odds ratio (OR) = 2.199, 95% confidence interval (95%CI) was 1.124-4.398, P = 0.023], NEUT (OR = 1.330, 95%CI was 1.214-1.469, P < 0.001), ESR (OR = 1.053, 95%CI was 1.019-1.090, P = 0.003), FBG (OR = 0.272, 95%CI was 0.158-0.445, P < 0.001), PT (OR = 0.253, 95%CI was 0.144-0.422, P < 0.001), APTT (OR = 0.689, 95%CI was 0.578-0.811, P < 0.001), Alb (OR = 0.734, 95%CI was 0.654-0.815, P < 0.001), BUN (OR = 0.720, 95%CI was 0.547-0.934, P = 0.016), and Na⁺ (OR = 0.756, 95%CI was 0.670-0.843, P < 0.001) could serve as main risk factors for constructing the prediction model. Calibration curves demonstrated good calibration of the prediction model in both training and validation sets with no evident over fitting. ROC curve analysis showed that the area under the ROC curve (AUC) of the prediction model in the training set was 0.943 (95%CI was 0.921-0.965, P < 0.001), with a sensitivity of 83.6% and a specificity of 91.5%. In the validation set, the AUC was 0.917 (95%CI was 0.878-0.957, P < 0.001), with a sensitivity of 90.1% and a specificity of 85.0%. DCA indicated that the prediction model had a high net benefit, suggesting practical clinical applicability. CONCLUSIONS The cause of injury being a traffic accident, NEUT, ESR, FBG, PT, APTT, Alb, BUN, and Na⁺ are identified as major risk factors influencing the occurrence of HAP in mTBI patients. The prediction model constructed using these parameters effectively assesses the likelihood of HAP in mTBI patients.
Humans ; Risk Factors ; Case-Control Studies ; Logistic Models ; Healthcare-Associated Pneumonia/epidemiology* ; Brain Injuries, Traumatic/complications* ; Male ; Female ; ROC Curve ; Pneumonia/etiology* ; Middle Aged ; Adult

OBJECTIVE: To develop and compare risk prediction models for in-hospital post-cardiac arrest brain injury (PCABI) in critically ill patients using nomograms and random forest algorithms, aiming to identify the optimal model for early identification of high-risk PCABI patients and providing evidence for precise treatment. METHODS: A retrospective cohort study was used to collect the first-time in-hospital cardiac arrest (IHCA) patients admitted to the intensive care unit (ICU) from 2008 to 2019 in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) as the study population, and the patients' age, gender, body mass, health insurance utilization, first vital signs and laboratory tests within 24 hours of ICU admission, mechanical ventilation, and critical care scores were extracted. Independent influencing factors of PCABI were identified through univariate and multivariate Logistic regression analyses. The included patients were randomly divided into a training cohort and an internal validation cohort in a 7:3 ratio, and the PCABI risk prediction model was constructed by the nomogram and random forest algorithm, respectively, and the model was evaluated by receiver operator characteristic curve (ROC curve), the calibration curve, and the decision curve analysis (DCA), and after the better model was selected, 179 patients admitted to Tianjin Medical University General Hospital as the external validation cohort for external evaluation were collected by using the same inclusion and exclusion criteria. RESULTS: A total of 1 419 patients with without traumatic brain injury who had their first-time IHCA were enrolled, including 995 in the training cohort (including 176 PCABI and 819 non-PCABI) and 424 in the internal validation cohort (including 74 PCABI and 350 non-PCABI). Univariate and multivariate analysis showed that age, potassium, urea nitrogen, sequential organ failure assessment (SOFA), acute physiology and chronic health evaluation III (APACHE III), and mechanical ventilation were independent influences on the occurrence of PCABI in patients with IHCA (all P < 0.05). Combining the above variables, we constructed a nomogram model and a random forest model for comparison, and the results show that the nomogram model has better predictive efficacy than the random forest model [nomogram model: area under the ROC curve (AUC) of the training cohort = 0.776, with a 95% credible interval (95%CI) of 0.741-0.811; internal validation cohort AUC = 0.776, with a 95%CI of 0.718-0.833; random forest model: AUC = 0.720, with a 95%CI of 0.653-0.787], and they performed similarly in terms of calibration curves, but the nomogram performed better in terms of decision curve analysis (DCA); at the same time, the nomogram model was robust in terms of external validation cohort (external validation cohort AUC = 0.784, 95%CI was 0.692-0.876). CONCLUSIONS A nomogram risk prediction model for the occurrence of PCABI in critically ill patients was successfully constructed, which performs better than the random forest model, helps clinicians to identify the risk of PCABI in critically ill patients at an early stage and provides a theoretical basis for early intervention.
Humans ; Critical Illness ; Retrospective Studies ; Heart Arrest/complications* ; Nomograms ; Brain Injuries/etiology* ; Intensive Care Units ; Algorithms ; Male ; Female ; Middle Aged ; ROC Curve ; Risk Factors ; Risk Assessment ; Logistic Models ; Aged

OBJECTIVE: To explore the predictive efficacy of the early lactic acid/albumin ratio (LAR) for the occurrence of acute skin failure (ASF) in patients with sepsis. METHODS: A retrospective study was conducted to collect the clinical data of 115 patients with sepsis admitted to the intensive care unit (ICU) of the First Affiliated Hospital of Dalian Medical University from June 2022 to March 2024. The patients' gender, age, length of ICU stay, past medical history, and severity scores, use of mechanical ventilation or vasoactive drugs, albumin (Alb), lactic acid (Lac), mean arterial pressure (MAP), and blood gas analysis indicators within 24 hours of ICU admission were collected, and LAR was calculated. The patients were divided into two groups based on whether they developed ASF, and the clinical data between the two groups were compared. Multivariate Logistic regression analysis was used to screen the risk factors for the occurrence of ASF in patients with sepsis. The receiver operator characteristic curve (ROC curve) was drawn to analyze the predictive value of LAR for the occurrence of ASF in patients with sepsis. RESULTS: A total of 115 patients with sepsis were enrolled in the final analysis, among whom 35 developed ASF and 80 did not. The incidence of ASF was 30.43%. Univariate analysis showed that compared with the non-ASF group, the ASF group had higher acute physiology and chronic health evaluation II (APACHE II) score, proportion of using vasoactive drugs, Lac, and LAR as well as lower Alb and MAP, with statistically significant differences. Multivariate Logistic regression analysis was conducted on the factors with statistical significance in the univariate analysis, and the results showed that Alb [odds ratio (OR) = 0.639, 95% confidence interval (95%CI) was 0.474-0.862, P = 0.003], Lac (OR = 17.228, 95%CI was 1.517-195.641, P = 0.022), MAP (OR = 0.905, 95%CI was 0.855-0.959, P = 0.001), and LAR (OR < 0.001, 95%CI was < 0.001-0.005, P = 0.033) were independent risk factors for the occurrence of ASF in patients with sepsis. ROC curve analysis showed that the area under the ROC curve (AUC) of LAR for predicting the occurrence of ASF in patients with sepsis was 0.867 (95%CI was 0.792-0.943), which was superior to Alb, Lac, and MAP [AUC (95%CI) was 0.739 (0.648-0.829), 0.844 (0.760-0.929), and 0.860 (0.783-0.937), respectively]. When the optimal cut-off value of LAR was 0.11, the sensitivity was 65.7%, the specificity was 96.3%, and the Youden index was 0.620. Patients were grouped based on the optimal cut-off value of LAR, and the results showed that the incidence of ASF in the LAR > 0.11 group was significantly higher than that in the LAR ≤ 0.11 group [88.89% (24/27) vs. 12.50% (11/88), P < 0.05]. CONCLUSIONS LAR has early predictive value for the occurrence of ASF in patients with sepsis, and its efficacy is superior to that of Lac or Alb alone.
Humans ; Sepsis/blood* ; Retrospective Studies ; Lactic Acid/blood* ; Male ; Female ; Intensive Care Units ; Middle Aged ; Risk Factors ; Predictive Value of Tests ; Serum Albumin/analysis* ; ROC Curve ; Aged