Receiver Operating Characteristic Curve Research Articles

Machine learning-based prediction of antibiotic resistance in Mycobacterium tuberculosis clinical isolates from Uganda

BackgroundEfforts toward tuberculosis management and control are challenged by the emergence of Mycobacterium tuberculosis (MTB) resistance to existing anti-TB drugs. This study aimed to explore the potential of machine learning algorithms in predicting drug resistance of four anti-TB drugs (rifampicin, isoniazid, streptomycin, and ethambutol) in MTB using whole-genome sequence and clinical data from Uganda. We also assessed the model’s generalizability on another dataset from South Africa.ResultsWe trained ten machine learning algorithms on a dataset comprising of 182 MTB isolates with clinical data variables (age, sex, HIV status) and SNP mutations across the entire genome as predictor variables and phenotypic drug-susceptibility data for the four drugs as the outcome variable. Model performance varied across the four anti-TB drugs after a five-fold cross validation. The best model was selected considering the highest Mathews Correlation Coefficient (MCC) and Area Under the Receiver Operating Characteristic Curve (AUC) score as key metrics. The Logistic regression excelled in predicting rifampicin resistance (MCC: 0.83 (95% confidence intervals (CI) 0.73–0.86) and AUC: 0.96 (95% CI 0.95–0.98) and streptomycin (MCC: 0.44 (95% CI 0.27–0.58) and AUC: 0.80 (95% CI 0.74–0.82), Extreme Gradient Boosting (XGBoost) for ethambutol (MCC: 0.65 (95% CI 0.54–0.74) and AUC: 0.90 (95% CI 0.83–0.96) and Gradient Boosting (GBC) for isoniazid (MCC: 0.69 (95% CI 0.61–0.78) and AUC: 0.91 (95% CI 0.88–0.96). The best performing model per drug was only trained on the SNP dataset after excluding the clinical data variables because intergrating them with SNP mutations showed a marginal improvement in the model’s performance. Despite the high MCC (0.18 to 0.72) and AUC (0.66 to 0.95) scores for all the best models with the Uganda test dataset, LR model for rifampicin and streptomycin didn’t generalize with the South Africa dataset compared to the GBC and XGBoost models. Compared to TB profiler, LR for RIF was very sensitive and the GBC for INH and XGBoost for EMB were very specific on the Uganda dataset. TB profiler outperformed all the best models on the South Africa dataset. We identified key mutations associated with drug resistance for these antibiotics. HIV status was also identified among the top significant features in predicting drug resistance.ConclusionLeveraging machine learning applications in predicting antimicrobial resistance represents a promising avenue in addressing the global health challenge posed by antimicrobial resistance. This work demonstrates that integration of diverse data types such as genomic and clinical data could improve resistance predictions while using machine learning algorithms, support robust surveillance systems and also inform targeted interventions to curb the rising threat of antimicrobial resistance.

Predictive role of neutrophil percentage-to-albumin ratio, neutrophil-to-lymphocyte ratio, and systemic immune-inflammation index for mortality in patients with MASLD

There are no studies discussing the significance of neutrophil-to-lymphocyte ratio (NLR), neutrophil-percentage-to-albumin ratio (NPAR), and systemic immune-inflammation index (SII) in predicting poor prognosis in patients with metabolic dysfunction associated steatotic liver disease (MASLD); this study aimed to investigate the relationship between these three inflammatory markers and all-cause mortality and cardiovascular disease (CVD) mortality in patients with MASLD. Survival data for 3970 participants were obtained from National Death Index (NDI) records associated with the National Health and Nutrition Examination Survey (NHANES) dataset, the associations of NPAR, NLR, and SII with all-cause and CVD mortality were analyzed using multivariate COX regression modeling, restricted cubic spline (RCS) was used to explore nonlinear relationships and to determine the inflection point, regrouping was done according to the nonlinear inflection point, using multivariate COX regression modeling, subgroup analysis, and the Kaplan-Meier survival curves to evaluate differences in risk of death between the two groups. Time-dependent receiver operating characteristic curve (ROC) analysis was conducted to assess the predictive efficacy of NPAR, NLR, and SII on survival outcomes. Multivariate COX regression and RCS analyses revealed a positive linear correlation between NLR and all-cause and CVD mortality, whereas a nonlinear relationship was found between NPAR and SII and all-cause and CVD mortality. Further reclassified into two groups according to the inflection point, multivariate COX regression analyses showed a significant difference in the risk of death between the two NPAR groups (HR 1.37, 95% CI = (1.01, 1.86) for all-cause mortality and HR 2.03, 95% CI = (1.24, 3.32) for CVD mortality ) and no difference in the risk of death between the two SII groups (HR 1.11, 95% CI = (0.87, 1.42) for all-cause mortality and HR 1.35, 95% CI = (0.86, 2.12) for CVD mortality), and Kaplan-Meier survival curves showed that both all-cause and CVD mortality rates were higher in patients with MASLD above the NPAR inflection point (log-rank P < 0.05). Subgroup analyses showed that the associations between high levels of NPAR and all-cause mortality were generally consistent across populations (P interaction > 0.05). Also, COPD subgroups had a significant effect on the correlation between high levels of NPAR and CVD mortality (P interaction < 0.05). Time-dependent ROC show the predictive value of NPAR, NLR, and SII for all-cause and CVD mortality in MASLD patients. The correlation between NPAR and mortality was nonlinear, and NLR was linearly and positively correlated with mortality, Measuring NPAR and NLR may be useful in assessing risk and predicting prognosis in populations of patients with MASLD.

Exploration and comparison of stress hyperglycemia-related indicators to predict clinical outcomes in patients with spontaneous intracerebral hemorrhage.

Spontaneous intracerebral hemorrhage (ICH) is a prevalent hemorrhagic stroke characterized by a significant fatality rate and severe neurological impairments. Stress hyperglycemia has been confirmed to have a significant prognostic role in a range of diseases. However, studies on the association between stress hyperglycemia and the outcome of ICH have not currently been reported. Critically ill patients diagnosed with ICH in the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were included in our study. Logistic regression and Cox regression were used to analyze the correlation between stress hyperglycemia and the outcome of ICH. The predictive ability of different glucose metrics was demonstrated by the receiver-operating characteristic (ROC) curve and was further compared by the integrated discrimination improvement (IDI) index. A total of 880 ICH patients in the MIMIC-IV database were included in this study. In logistic regression and Cox regression, blood glucose level (BGL), glycemic gap (GG), and stress hyperglycemia ratio (SHR) were independent predictors of unfavorable outcomes in ICH after adjustment for other confounders. The IDI results indicated that the 5-day maximum stress hyperglycemia ratio had better predictive performance than glycemic gap and blood glucose level in-hospital mortality and 1-year mortality, and the predictive performance of the 5-day maximum stress hyperglycemia ratio was better than that of stress hyperglycemia ratio measured at admission. In the age-stratified subgroup analysis, the 5-day maximum stress hyperglycemia ratio was more sensitive in predicting long-term outcomes in the young subgroup than in the elderly subgroup. The 5-day maximum stress hyperglycemia ratio is strongly correlated with an elevated risk of mortality in ICH patients and displays a better predictive ability than glycemic gap and blood glucose level in the short/long-term prognosis of ICH.

Evaluation of predictive performance for new vertebral compression fracture between Hounsfield units value and vertebral bone quality score following percutaneous vertebroplasty or kyphoplasty

Rationale and ObjectivesNew vertebral compression fractures (NVCF) are very common in patients following percutaneous vertebroplasty (PVP) or kyphoplasty (PKP). The study aims to evaluate the comparative predictive performance of vertebral bone quality (VBQ) score and Hounsfield units (HU) value in forecasting NVCF after surgery. Materials and MethodsThis study retrospectively analyzed patients who underwent PVP/PKP at our institution between 2020 and 2021. The VBQ score and HU value were obtained from preoperative magnetic resonance imaging (MRI) and computed tomography (CT) scans, respectively. Subsequently, the forecasting capabilities of these two parameters were assessed by contrasting their receiver operating characteristic (ROC) curve. ResultsA total of 303 eligible patients (56 with NVCF and 247 without) were identified in the study. Six relevant literature factors were identified and included in the multivariate analysis revealed that lower HU value (OR = 0.967, 95% CI = 0.953-0.981, P < 0.001) and higher VBQ score (OR = 3.964, 95% CI = 2.369-6.631, P < 0.001) emerged as independent predictors of NCVF occurrence. Compared to the ROC curve of the HU value, demonstrating a diagnostic accuracy of 83.2% (95% CI = 77.5%-88.9%, P < 0.001), the VBQ score was 85.8%. And, a statistically significant negative correlation was observed between the VBQ score and the T-score (r = -0.529, P < 0.001). ConclusionIn patients undergoing PVP/PKP, VBQ score, and HU value are independently associated with the occurrence of NVCF. Assessing the HU value and the VBQ score could play an effective role in planning PVP/PKP operations.

The Prognostic Role of RDW in Hospitalized Heart Failure Patients with and Without Chronic Kidney Disease

Background: Chronic kidney disease (CKD) and heart failure (HF) are interrelated conditions that exacerbate each other through mechanisms like fluid retention, neurohormonal activation, and inflammation. Red blood cell distribution width (RDW), a measure of red blood cell size variability, has emerged as a potential prognostic marker in HF. This study aimed to assess the prognostic value of RDW in HF patients, both with and without CKD, focusing on all-cause mortality and HF rehospitalizations. Methods: This observational retrospective study included 171 patients hospitalized for acute decompensated HF in a tertiary university hospital in Greece. Patients were divided into two groups based on their estimated glomerular filtration rate (eGFR), as Group 1 (eGFR &lt; 60 mL/min/1.73 m2) and Group 2 (eGFR ≥ 60 mL/min/1.73 m2). RDW was measured upon admission, and outcomes of interest were all-cause mortality and HF rehospitalizations over a median follow-up period of 6.1 months. Statistical analyses included Kaplan–Meier survival curves, whereas the discrimination traits of RDW were evaluated by constructing receiver operating characteristic (ROC) curves and by calculating the area under the ROC curve (AUC). A p-value &lt;0.05 was indicative of a statistically important result. Results: Patients in Group 1 (eGFR &lt; 60 mL/min/1.73 m2) were older (80 (73–86) vs. 75 (62–83)) and manifested higher median RDW values (16.6 (15.0–18.8) vs. 15.6 (14.1–17.8)) and received less frequent (57.9% vs. 75%) mineralocorticoid receptor antagonists (MRAs) as compared to those in Group 2 (eGFR ≥ 60 mL/min/1.73 m2). RDW demonstrated better prognostic value in predicting combined mortality and rehospitalization outcomes in Group 2 patients (area under the curve: 0.70; 95% CI (0.62–0.80)) compared to those in Group 1 (area under the curve: 0.53; 95% CI (0.35–0.72)). No statistically significant differences (p = 0.579) were observed in survival between patients with high (≥15%) and low (&lt;15%) RDW values in the overall population, though trends favored worse outcomes with elevated RDW. Similarly, no significant differences (p = 0.374) were observed in survival between patients with high (Group 2) and low (Group 1) eGFR values. Conclusions: RDW appears to be a meaningful prognostic biomarker for HF patients, particularly in those without CKD. Further multicenter studies are needed to validate its clinical utility and potential for guiding treatment in this high-risk population.

High level of systemic immune inflammation index elevates delirium risk among patients in intensive care unit

Evidence regarding the effect of systemic immune-inflammation index on delirium occurrence is limited. This study aimed to investigate the association between SII and delirium in intensive care unit (ICU) patients. Methods: Information was extracted from Medical Information Mart for Intensive Care-IV. Four logistic regression model was established and incorporated with subgroup analysis and restricted cubic spline (RCS). The cutoff value of SII was acquired from receiver operator characteristic curve (ROC), and propensity score matching (PSM) was utilized to attenuate the confounding effect. Survival analysis was utilized to evaluate the relationship between SII and 30-day or 90-day all-cause mortality. Results: Among the 7,518 participants, 1,685 cases of delirium occurred. Individuals in the highest quartile of SII exhibited a heightened delirium risk, with a significant multivariable-adjusted odds ratio (OR) of 3.12(2.24,4.33). Tendency analysis, subgroup analysis and PSM together confirmed the positive relationship. Results of Cox regression displayed the risk of both 30-day and 90-day mortality increased about 50% in the higher-SII group. Conclusion: Higher levels of SII is positively associated with the occurrence of delirium and increased all-cause mortality risk.

Enhancing corneal ectasia susceptibility detection: analysis of a new algorithm (BAD-D v4)

Accurate detection of post-refractive ectasia susceptibility is essential during preoperative evaluation for laser vision correction (LVC) due to the risk of progressive corneal ectasia and vision decline post-surgery. Despite improved screening and a reduced incidence from 0.66 to 0.033%, iatrogenic ectasia remains a concern due to the severe vision loss it can cause, highlighting the need for more accurate detection tools. A new optimized version of the Belin/Ambrósio Enhanced Ectasia Display version 4 (BAD-D v4) was developed and validated across 26 international centers to enhance the detection of keratoconus and very asymmetric ectasia and to assess the risk of post-refractive ectasia. Analyzing a dataset of 3,886 eyes from 3,351 patients, including normal, keratoconus (KC), and cases with very asymmetric ectasia (VAE) categories, having one eye with normal topography (VAE-NT and the fellow eye with clinical ectasia (VAE-E). The study utilized an optimized logistic regression algorithm improving diagnostic accuracy. The BAD-D v4 showed superior efficacy in differentiating normal eyes from ectatic conditions, with Area Under the Receiver Operating Characteristic Curve (AUROC) scores of 0.997 and 0.998 in training and testing samples for normal versus clinical ectasia. Additionally, in Normal vs. Disease (KC + VAE), the AUROC was 0.974 and 0.966, and in the challenging Normal vs. VAE-NT diverse group, it scored 0.905 and 0.858. These results outperformed the current version (BAD-D v3) and were comparable to the Pentacam Random Forest Index in all tested scenarios, highlighting the potential of BAD-D v4 in early ectasia detection, without altering the index scale or the end-user experience.

PerSceptoMed 1.0: An advanced machine learning model for demographic-based antibiotic susceptibility prediction in Pseudomonas aeruginosa infections

BackgroundAntimicrobial resistance caused by Pseudomonas aeruginosa is a pressing global health issue impacting both hospitals and communities. MethodologyWe analyzed demographic and susceptibility data from 1087 samples, and tested them against five different antibiotics at the Institute of Medical Sciences & SUM Hospital. Eight machine learning algorithms (linear: multiple linear regression, generalized linear model-elastic net regularization, support vector machine-linear kernel, linear discriminant analysis; non-linear: support vector machine-radial basis function kernel, decision tree, k-nearest neighbors, kernel k-nearest neighbors), were evaluated to develop the PerSceptoMed 1.0 model for susceptibility prediction. Performance metrics such as accuracy, Matthews Correlation Coefficient, Hamming loss, 0/1 loss, and Receiver Operating Characteristic curves were computed. Statistical analysis was conducted to compare model performance. ResultsGender disparities were observed, with male patients showing higher infection rates, potentially due to occupational exposure, microbiome differences, comorbidities, and healthcare-seeking behaviors. age, clinical status, and antibiotic susceptibility were significant factors, complicating treatment strategies. Infections extended to outpatient departments, indicating a shift from hospital to community settings. Kernel k-nearest neighbors exhibited strong predictive capabilities, improving accuracy from 84.39% pre-balancing to 91.01% post-balancing, and an Area Under the Curve of 0.92. Statistical tests showed significant performance variations among models. ConclusionThe study highlights the importance of gender-sensitive approaches in infection management and the superior performance of nonlinear models in decoding complex data patterns. PerSceptoMed 1.0 demonstrates promise in enhancing antimicrobial resistance management by providing actionable insights based on demographic data.

Psychological distress in biliary tract malignancy patients: influencing factors and development of a predictive nomogram model

ObjectiveThis study aims to investigate the psychological distress and its influencing factors in patients with biliary tract malignant tumors, alongside the development of a predictive model.MethodsA total of 219 patients diagnosed with biliary tract malignant tumors who were admitted to the Department of Liver Surgery at Fudan University Shanghai Cancer Center from July 2021 to May 2023, were selected using a convenience sampling method. Research tools involve psychological distress management screening tools, a demographic questionnaire, self-rating anxiety and depression scales, and the Chinese version of the Memorial Symptom Assessment Scale. Bootstrap method was utilized for repeated sampling to identify relevant factors influencing psychological distress in biliary tract cancer patients. The R software was employed to create a nomogram model, and the model’s accuracy and predictive performance were assessed using the receiver operating characteristic curve (ROC) and the Hosmer-Lemeshow test.ResultsThe average score of psychological distress among the 219 patients was (3.91 ± 2.44), with a psychological distress detection rate of 54.8%. Regression model results indicated that factors such as the presence of distant metastasis, comorbidity with other major diseases, poor sleep quality, anxiety, and severity of anxiety and depression were the primary influencers of psychological distress.ConclusionThe detection rate of psychological distress in patients with biliary tract malignant tumors is notably high. The predictive model constructed in this study exhibits good predictive efficacy and clinical value, providing valuable reference for healthcare professionals in developing targeted intervention strategies.

Comparison of Acute Physiology and Chronic Health Evaluation II and Sequential Organ Failure Assessment intensive care unit scoring system as mortality predictors in intensive care unit patients with sepsis

Background: Sepsis is a life-threatening organ dysfunction caused by a deregulated host response to infection. It is one of the leading causes of in-hospital mortality and morbidity among patients. It also results in significant morbidity and financial burden. Aims and Objectives: (1) To study the etiological profile of patients admitting with sepsis to ICU. (2) To compare between APACHE II and SOFA ICU scoring system of patients with sepsis at admission and at 24 h in predicting the 5th-day mortality. Materials and Methods: This was a single center hospital based prospective, observational, study conducted in patients in ICUs of ESICMC PGIMSR and Model Hospital Rajajinagar, Bangalore. Patients over age 18 years admitted in ICU who have fulfilled the criteria for sepsis were included in our study. Their clinical profile, APACHE II and SOFA scores were evaluated and followed up to 5th day of admission and data were compared with respect to patients’ outcome in the form of survival. Results: In this study, out of 53 patients the maximum number of patients belong to the age groups of &gt;60 years (23 patients). Male-to-female distribution in this study noted was 30 and 23 patients, respectively. Aspiration Pneumonitis (17%) and Community-Acquired Pneumonia (17%) were the most common causes of septic. Out of 53 patients, 31 patients did not survive. In this study, it was observed that the SOFA scoring had the highest specificity (87.10%) and APACHE II had the highest sensitivity (96.77%) at admission. However at 24 h of admission, both the highest sensitivity and highest specificity was more for APACHE II score. The most area under the Receiver-operating characteristic curve was better for SOFA score (AUROC=58.0%) at admission than APACHE II score with AUROC of 53.7%, however AUROC of both SOFA and APACHE II score calculated at 24 h of admission were equally good in predicting 5th-day mortality. Conclusion: We found that the SOFA score outperformed APACHE II scores in predicting survival in septic shock patients at admission. SOFA and APACHE II calculated at 24 h of admission and both scores provided equal efficacy in predicting 5th-day mortality in patients with sepsis.

NLRP3 inflammasome in expressed prostatic secretions as a potential biomarker of chronic prostatitis/chronic pelvic pain syndrome.

Pyroptosis has been implicated in the progression of chronic prostatitis (CP)/chronic pelvic pain syndrome (CPPS). The present study was performed to explore the diagnostic value of the levels of the pyroptosis-related protein nucleotide-binding oligomerization domain, leucine-rich repeat and pyrin domain-containing 3 (NLRP3) inflammasome in the expressed prostatic secretions (EPS) of patients with CP. A total of 167 CP patients, including 85 National Institutes of Health (NIH)-IIIA CP patients and 82 NIH-IIIB CP patients, as well as 80 benign prostatic hyperplasia (BPH) patients and 80 healthy controls, were enrolled. The levels of NLRP3, interleukin 1 beta (IL-1β), and interleukin 18 (IL-18) in EPS were detected using an enzyme-linked immunosorbent assay (ELISA). Disease severity was assessed using the Bergman CP scale. Differences in EPS NLRP3 inflammasome levels between the groups were analyzed, and receiver operating characteristic (ROC) curves were used to investigate the clinical value of the NLRP3 inflammasome in the diagnosis of CP. The numerical rating scale (NRS), the National Institutes of Health Chronic Prostatitis Symptom Index (NIH-CPSI) and the Danish Prostatic Symptom Score (DAN-PSS-1) were applied to evaluate symptom severity. The cutoff value of NLRP3 expression was calculated using R language. NLRP3 inflammasome levels in EPS were significantly higher in CP patients of NIH-IIIA and NIH-IIIB compared to the BPH patients and controls. NLRP3 levels in EPS were positively associated with Bergman grade. In addition, NRS levels were in a positive relationship with NIH-CPSI and DAN-PSS-1. The ROC curve analysis demonstrated that NLRP3 in EPS may act as a decent indicator for the diagnosis of CP/CPPS. The cutoff value of EPS NLRP3 expression was ≥55.25 ng/mL. NLRP3 levels in EPS were significantly higher in NIH-IIIA and NIH-IIIB patients compared to BPH patients and healthy controls. NLRP3 inflammasome levels in EPS may be valuable as diagnostic indicators, and targeting chemokines may present a promising approach to treatment for those suffering from CPPS.

Characterizing the role of left ventricular indices and biventricular interaction in bronchopulmonary dysplasia-associated pulmonary hypertension in extreme prematurity.

Bronchopulmonary dysplasia (BPD) is a common respiratory morbidity in preterm infants. The onset of pulmonary hypertension leads to worse respiratory outcomes. The contribution of left ventricular diastolic dysfunction in BPD-PH is well reported. We evaluated the serial left ventricular (LV) function and possible ventricular interdependence among BPD-PH. Single-centre, prospective observational study. Infants <28 weeks of gestation included. 80 infants were enrolled. The incidence of BPD-PH was 23%. The BPD-PH group had a high incidence of hemodynamically significant ductus arteriosus (83% vs 56%,p <0.018), longer oxygen days (96.2±68.1 vs 59.35±52,p< 0.008), and prolonged hospital stay (133.8±46 vs 106.5±38 days,p<0.005). Serial tissue Doppler imaging showed prolonged left ventricle (LV) isovolumetric contraction time (IVCT)(31.05±3.3 vs 26.8±4.4ms,p<0.001), and myocardial performance index (MPI) (0.43±0.03 vs 0.37±0.04,p<0.001) from 33 weeks. The changes in IVCT (35.9±6.7 vs 27.9±4.5ms, p<0.001), isovolumetric relaxation time (IVRT) (50±6.5 vs 39.9±5.8ms,p <0.001), and MPI (0.48±0.05 vs 0.36±0.03,p <0.001) persisted at 36 weeks. The receiver operator characteristic curve showed LV MPI >40 has 83% sensitivity and 65% specificity (AUC 0.77, p<0.001) in the diagnosis of PH. The BPD-PH group had a higher LV E/E' ratio (13.1±4.4 vs 11.4±3.4, p <0.02). Pearson correlation test showed a moderate positive correlation between RV MPI and LV MPI (r= 0.585, p <0.001). Significant LV diastolic dysfunction was observed in BPD-PH. This is the first study to show biventricular strain and possible ventricular interdependence in BPD-PH. The prolonged LV IVRT and MPI may be a novel echocardiographic indicator of BPD-PH.

Diagnostic value of sFlt-1/PlGF-1 ratio and plasma PROK1 for adverse pregnancy outcomes in women with hypertensive disease of pregnancy.

Hypertensive disease of pregnancy (HDP) is one of the most important causes of increased maternal mortality and perinatal complications during pregnancy. We investigated the pregnancy outcomes of 156 HDP patients (65 gestational hypertension [GH], 13 chronic hypertension [CH], 74 preeclampsia-eclampsia [PE-EC], and 4 superimposed on PE [CH with PE]). In patients with different types of HDP, levels of soluble fms like tyrosine kinase-1 (sFlt-1), placental growth factor (PlGF)-1, and prokinin-1 (PROK1) were measured and compared. The predictive efficacy of these indicators was evaluated using receiving operating characteristics curves and area under the curve. Results showed that the PE cohort had a higher sFlt-1/PlGF ratio (46.12 [39.24, 68.85]) and PROK1 (498.84 [213.67, 678.30] pg/mL) level than the GH (sFlt-1/PlGF, 32.3 [21.98, 58.00], PROK1 300.77[250.0, 345.29]pg/mL) and CH cohort (sFlt-1/PlGF, 37.49 [32.68, 39.68], PROK1, 281.48 [229.25, 453.94]pg/mL). In the HDP cohort, 54 patients experienced adverse pregnancy events, and the sFlt-1/PlGF ratio, PROK1, and the combined indicators (sFlt-1/PlGF ratio and PROK1) were excellent predictors of adverse pregnancy events, especially for PE patients.

Detection of basal cell carcinoma by machine learning-assisted ex vivo confocal laser scanning microscopy.

Ex vivo confocal laser scanning microscopy (EVCM) is an emerging imaging modality that enables near real-time histology of whole tissue samples. However, the adoption of EVCM into clinical routine is partly limited because the recognition of modality-specific diagnostic features requires specialized training. Therefore, we aimed to build a machine learning algorithm for the detection of basal cell carcinoma (BCC) in images acquired using EVCM and, in turn, facilitate the examiner's decision-making process. In this proof-of-concept study, histologically confirmed BCC fresh tissue samples were used to generate 50 EVCM images to train and assess a convolutional neural network architecture (MobileNet-V1) via tenfold cross-validation. Overall sensitivity and specificity of the model for detecting BCC and tumor-free regions on EVCM images compared to expert evaluation were 0.88 and 0.85, respectively. We constructed receiver operator characteristic and precision-recall curves from the aggregated tenfold cross-validation to assess the model's performance; the area under the curve was 0.94 and 0.87, respectively. Subsequently, the performance of one of the selected machine learning models was assessed with 19 new EVCM images of tumor-containing (n = 10) and 9 tumor-free (n = 9) skin tissue. A sensitivity of 0.83 and a specificity of 0.92 were achieved for the BCC group. The specificity for the tumor-free control group was 0.98. The deep learning model developed in our study holds the potential to assist the diagnostic decision-making process and diminish the training time of novices by depicting tumor-positive regions in EVCM images.

Development and validation of a prediction model for the prognosis of renal cell carcinoma with liver metastases: a population-based cohort study

BackgroundCurrent studies on the establishment of prognostic model for renal cell carcinoma (RCC) with liver metastases (LM) were scarce. This study aimed to develop nomograms to predict the prognosis of RCC with LM.MethodsPatients diagnosed with RCC between 2010 and 2021 from the Surveillance, Epidemiology, and End Results (SEER) database were selected. The eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) machine learning algorithms were used to screen for the most influential factors affecting prognosis, and the Venn diagram method was employed for further refinement. Subsequently, a nomogram related to brain metastases was constructed. The performance of the nomograms was evaluated through receiver operating characteristics (ROC) curves, calibration plots, C-index, time-dependent C-index, and decision curve analysis (DCA). Kaplan–Meier (K-M) survival curves were used to provide additional verification of the clinical efficacy of the nomogram.ResultsThis research comprised 2,395 RCC patients with LM. The Venn diagram demonstrated that age, histological type, grade, AJCC T stage, AJCC N stage, surgery, chemotherapy, marital status, and lung metastasis were highly relevant variables to patients with LM. The AUC, C-index, calibration curves, and DCA curves showed excellent performance of the nomogram. Additionally, the prognostic nomogram accurately classified RCC with LM patients into low- and high-risk groups for mortality.ConclusionThis study developed a novel nomogram to predict the prognostic factors of RCC with LM, providing a valuable reference for making accurate clinical decisions.

Association of “a body shape index” with the risk of developing colorectal cancer in U.S. patients with metabolic syndrome: evidence from the NHANES 1999–2018

BackgroundColorectal cancer (CRC) is the third most common cancer worldwide and presents a significant challenge to public health. Metabolic syndrome (MetS) is a condition that is predominantly characterized by abdominal obesity and metabolic abnormalities such as hypertension, hyperglycemia, and hyperlipidemia, and it is one of the critical risk factors for CRC. Traditional anthropometric measures have limitations in accurately assessing the risk associated with abdominal obesity. This study aimed to investigate the association between “A Body Shape Index” (ABSI) and the risk of developing CRC among individuals with MetS utilizing data from the National Health and Nutrition Examination Survey (NHANES).MethodsThis cross-sectional study conducted a statistical analysis of all adult participants who met the diagnostic criteria for MetS in the NHANES data from 1999 to 2018. The ABSI was calculated to quantify abdominal obesity. ABSI is derived from a formula that incorporates waist circumference (WC), body mass index (BMI), and height, and is calculated as ABSI = WC / (BMI^(2/3) × Height^(1/2)). Multivariate logistic regression modeling was used to examine the independent association between ABSI and CRC incidence. Receiver Operating Characteristic (ROC) curves were employed to analyze the ability of ABSI compared to traditional metrics in identifying CRC risk.ResultsThis study involved 16,018 MetS patients with a mean age of 51.8 years, of whom 50.3% were male and 49.7% were female. Logistic regression adjusted for confounders revealed a significant association between an elevated ABSI and an increased risk of developing CRC (odds ratio (OR): 1.433, 95% confidence interval (CI): 1.116 to 1.841; P = 0.005). ROC analyses confirmed that the predictive accuracy of the ABSI for the risk of developing CRC area under the curve (AUC): (0.668, 95% CI: 0.624 to 0.713) surpassed that of traditional measurement methods.ConclusionAmong individuals with MetS, the ABSI is linked to an elevated risk of developing CRC. Compared with traditional anthropometric indices, the ABSI is a superior predictive marker for the risk of developing CRC.

Ankle proprioception and functional performance in patients with Achilles tendinopathy.

The purpose of this study was to investigate differences in ankle plantar flexion proprioception and lower extremity function between Achilles tendinopathy (AT) patients and healthy controls. 17 patients with midportion AT (age 22.0±3.0, 7 females, and 10 males) and 17 healthy controls (age 21.5±2.1, 7 females, and 10 males) were recruited. The following tests were performed randomly: the ankle plantar flexion active movement extent discrimination assessment (AMEDA), weight-bearing lunge test (WBLT), single leg hop test, figure-of-eight hop test, Y Balance Test (YBT), and lower extremity functional test (LEFT). Group comparisons were made between the AT and healthy groups, and receiver operator characteristic (ROC) curves were used to analyze the ability of tests to differentiate between participants with and without AT. Results showed that the AT group performed significantly worse in the ankle proprioception test (p=0.016), single leg hop test (p=0.001), figure-of-eight hop test (p<0.001), unilateral LEFT (p=0.001), and LEFT injury risk score (p=0.001) than healthy controls. No significant between group difference was found in WBLT and YBT. Diagnostic analysis showed that the AMEDA (p=0.018), single leg hop test (p=0.003), figure-of-eight hop test (p=0.002), and LEFT (p=0.001) could differentiate between patients with AT and the healthy individuals. The current study demonstrated that ankle proprioception and functional performance involving explosive jump are impaired in patients with AT, suggesting poorer dynamic neuromuscular function and a higher risk of lower limb injury in this population, and furthermore, these tests should be considered in the assessment for AT.

Prognostic value of advanced lung cancer inflammation index in heart failure patients: A comprehensive analysis.

The prognosis of heart failure (HF) is closely linked to inflammation and nutritional status. The advanced lung cancer inflammation index (ALI) is a composite indicator consisting of several parameters used to assess inflammation and nutritional status. Our study aimed to investigate the prognostic value of ALI in HF patients. The data from Study 1, which included 1359 HF patients, were extracted from the National Health and Nutrition Examination Survey (NHANES) database spanning the years 1999 to 2018. Study 2 analysed data from patients with HF who underwent cardiac magnetic resonance imaging examinations from 2020 to 2023. Kaplan-Meier curve analysis, Cox proportional hazard model, time-dependent receiver operating characteristic (ROC) curve and restricted cubic spline (RCS) were used to evaluate the relationship between ALI and long-term prognosis of patients with HF in Study 1. Logistic regression analysis was used to evaluate the correlation between ALI and left ventricular reverse remodelling, and RCS was used to determine any dose-response relationship. Spearman correlation was used to evaluate the relationship between ALI and indicators of cardiac structural changes. Study 1 found that the average age of the patients was 68years [inter-quartile range (IQR) 58-76], the proportion of males was 54.3%, and there were 699 all-cause mortality and 293 cardiovascular mortality cases. After adjusted by multivariable Cox regression analysis, elevated ALI levels were significantly associated with increased risks of all-cause [hazard ratio (HR)=0.58, 95% confidence interval (CI)=0.42-0.79, P<0.001] and cardiovascular mortality (HR=0.61, 95% CI=0.38-0.97, P=0.036) in patients with HF. A linear negative correlation was observed between ALI and both all-cause (P=0.0011 and P<0.001, P for nonlinear=0.3993) and cardiovascular mortality (P=0.0011, P for nonlinear=0.5198). Time-dependent ROC curves showed the predictive value of ALI for all-cause mortality [area under the curve (AUC)=0.678 in 3years, AUC=0.674 in 5years and AUC=0.683 in 10years] and cardiovascular mortality (AUC=0.694 in 3years, AUC=0.685 in 5years and AUC=0.697 in 10years). Study 2 included 79 patients; the average age of the patients was 44years (IQR 35-55); and the proportion of males was 74.7%. Adjusted multivariable logistic regression analysis indicated that high ALI levels were associated with left ventricular reverse remodelling (LVRR) in patients with HF following discharge from the hospital [odds ratio (OR)=3.16, 95% CI=1.06-10.8, P=0.049]. Spearman analysis revealed a correlation between ALI and extracellular volume (ECV) (r=-0.25, P=0.023). ALI is associated with all-cause and cardiovascular mortality risk and structural changes in the heart in patients with HF.

Correlation between admission blood glucose, fibrinogen, and slow blood flow during primary PCI for acute ST segment elevation myocardial infarction

BackgroudCoronary slow flow (CSF) is a common phenomenon of coronary microcirculation dysfunction, and is closely related to elevated blood glucose and fibrinogen (FIB) levels. However, whether immediate blood glucose and FIB levels affect coronary blood flow during primary percutaneous coronary intervention (PCI) remains unclear.ObjectiveTo explore the correlation between admission blood glucose (ABG), fibrinogen (FIB) and slow blood flow during primary PCI for acute ST segment elevation myocardial infarction (STEMI).MethodsA total of 497 patients who underwent coronary angiography in the cardiology department of the 904th Hospital of the Joint Logistics Support Force from December 2018 to December 2022 due to STEMI were selected consecutively, and then were divided into two groups based on whether slow blood flow occurred during primary PCI: slow blood flow group (n = 117) and control group (n = 380). Detecting the ABG, FIB and other indicators of patients in each group, and using logistic regression analysis and receiver operating characteristic (ROC) curve to analyze independent risk factors for slow blood flow during primary PCI, and further evaluating the prognosis of patients.ResultsThe levels of ABG and FIB in patients with slow blood flow were significantly higher than those in the control group (P &amp;lt; 0.05). The results of multivariate logistic regression analysis suggested that FIB and ABG were independent risk factors for slow blood flow during primary PCI (both P &amp;lt; 0.05). ROC curve analysis showed that ABG, FIB, and their combination all had predictive value for slow blood flow during primary PCI (all P &amp;lt; 0.05), and the area under the curve (AUC) of the combined indicator was higher than that of any single indicator, with statistical significance (P &amp;lt; 0.05). KM curve analysis suggested that the prognosis of patients in slow blood flow group were poor.ConclusionBoth elevated ABG and FIB could predict slow blood flow during primary PCI, and the diagnostic value of the combined indicator was superior to that of any single indicator, which could be used for the evaluation of slow blood flow during primary PCI, so as to evaluate the prognosis of patients with STEMI.

Linguistic and clinical validation of the Chinese version of the Acute Cystitis Symptom Score (ACSS) questionnaire in Taiwanese women with uncomplicated acute cystitis

Purpose: The Acute Cystitis Symptom Score (ACSS) questionnaire is designed to diagnose acute cystitis in women. By quantifying the severity of symptoms, ACSS provides objective diagnostic criteria. The aim of this study is to translate the ACSS questionnaire into a Chinese version and validate its clinical use for diagnosing acute cystitis in Taiwanese women. Materials and methods: After rigorously translating the ACSS questionnaire into traditional Chinese used by the Mandarin-speaking Taiwanese people, it was clinically validated. Women aged 20 and above with suspected acute cystitis were recruited as the patients, and healthy women undergoing health check-ups as controls. Discriminative ability was assessed by comparing ACSS scores between the 2 groups, and the optimal diagnostic cutoff was determined using receiver operating characteristics analysis. In the patient group, treatment response was evaluated as patient-reported outcome by comparing ACSS scores pretreatment and posttreatment. Results: A total of 89 and 43 participants were recruited for the patient and control groups, respectively. The total score of typical symptoms between the patient and the control groups was significantly different (P &lt; 0.001). After antibiotic treatment, the total score of typical symptoms in the patient group significantly decreased (P &lt; 0.001). Using receiver operating characteristics curve analysis, the best cutoff score for diagnosing acute cystitis was 4, with a sensitivity and a specificity of 75.3% and 95.3%, respectively. Conclusion: After clinical validation, the Chinese version of the ACSS questionnaire can now be used as a symptom-oriented diagnostic and patient-reported outcome tool for acute cystitis in the Mandarin-speaking female population in Taiwan.