ROC AUC Research Articles

Identification of RTS,S/AS01 vaccine-induced humoral biomarkers predictive of protection against controlled human malaria infection.

BACKGROUNDThe mechanism(s) responsible for the efficacy of WHO-recommended malaria vaccine RTS,S/AS01 are not completely understood. We previously identified RTS,S vaccine-induced Plasmodium falciparum circumsporozoite protein-specific (PfCSP-specific) antibody measures associated with protection from controlled human malaria infection (CHMI). Here, we tested the protection-predicting capability of these measures in independent CHMI studies.METHODSVaccine-induced total serum antibody (immunoglobulins, Igs) and subclass antibody (IgG1 and IgG3) responses were measured by biolayer interferometry and the binding antibody multiplex assay, respectively. Immune responses were compared between protected and nonprotected vaccinees using univariate and multivariate logistic regression.RESULTSBlinded prediction analysis showed that 5 antibody binding measures, including magnitude-avidity composite of serum Ig specific for PfCSP, major NANP repeats and N-terminal junction, and PfCSP- and NANP-specific IgG1 subclass magnitude, had good prediction accuracy (area under the receiver operating characteristic curves [ROC AUC] > 0.7) in at least 1 trial. Furthermore, univariate analysis showed a significant association between these antibody measures and protection (odds ratios 2.6-3.1). Multivariate modeling of combined data from 3 RTS,S CHMI trials identified the combination of IgG1 NANP binding magnitude plus serum NANP and N-junction Ig binding magnitude-avidity composite as the best predictor of protection (95% confidence interval for ROC AUC 0.693-0.834).CONCLUSIONThese results reinforce our previous findings and provide a tool for predicting protection in future trials.TRIAL REGISTRATIONClinicalTrials.gov NCT03162614, NCT03824236, NCT01366534, and NCT01857869.FUNDINGThis study was supported by Bill & Melinda Gates Foundation's Global Health-Discovery Collaboratory grants (INV-008612 and INV-043419) to GDT.

Dental Composite Performance Prediction Using Artificial Intelligence.

There is a need to increase the performance and longevity of dental composites and accelerate the translation of novel composites to the market. This study explores artificial intelligence (AI), specifically machine learning (ML), to predict the performance outcomes (POs) of dental composites from their composite attributes (CAs). An extensive dataset from over 200 publications was built and refined to 233 samples with 17 CAs and 7 POs. Nine ML models were evaluated for PO prediction performance using classified data, and Five ML models were evaluated for PO regression analysis. The KNN model excelled in predicting flexural modulus (FlexMod), Decision Tree model in flexural strength (FlexStr) and volumetric shrinkage (ShrinkV), and Logistic Regression and SVM models in shrinkage stress (ShrinkStr). Receiver operating characteristic area under the curve (ROC AUC) analysis confirmed these results but found that Random Forest was more effective for FlexStr and ShrinkV, suggesting the possibility of Decision Tree overfitting the data. Regression analysis revealed that the Voting Regressor was superior for FlexMod and ShrinkV predictions, while Decision Tree Regression was optimal for FlexStr and ShrinkStr. Feature importance analysis indicated TEGDMA is a key contributor to FlexMod and ShrinkV, BisGMA and UDMA to FlexStr, and depth of cure, degree of monomer-to-polymer conversion, and filler loading to ShrinkStr. There is a need to conduct a full analysis using multiple ML models because different models predict different POs better, and for a large, comprehensive dataset to train robust AI models to facilitate the prediction and optimization of composite properties and support the development of new dental materials.

Stroke recurrence prediction using machine learning and segmented neural network risk factor aggregation

Stroke has remained a major cause of mortality and disability in the United States for years, and its recurrence significantly increased the risks. For predicting stroke recurrence, traditional data aggregation methods have limitations in effectively handling the numerous subcategories of stroke risk factors. This pilot study proposed a Segmented Neural Network-Driven Aggregation (SNA) method, and it aimed to improve the prediction model’s accuracy. Utilizing the TriNetX diagnosis dataset, we processed various risk factors and demographic information through traditional and our proposed data aggregation techniques. We applied logistic regression and random forest classifiers to predict stroke recurrence. Our findings revealed that using the SNA method significantly outperformed other aggregation methods for both classifiers. Using the SNA method with a random forest classifier achieved higher accuracy (84.2%) and a better balance between sensitivity and specificity (AUC of ROC = 0.928, AUC of PR = 0.940) compared to other combinations. These results showed the potential of machine-learning supervised encoding methods in stroke recurrence predictions, providing implications for clinical practice and future epidemiological research.

Digital voice analysis as a biomarker of acromegaly.

There is a considerable diagnostic delay in acromegaly contributing to increased morbidity. Voice changes due to orofacial and laryngeal changes are common in acromegaly. Our aim was to explore the use of digital voice analysis as a biomarker for acromegaly using broad acoustic analysis and machine learning. Voice recordings from patients with acromegaly and matched controls were collected using a mobile phone at Swedish university hospitals. Anthropometric and clinical data and the Voice Handicap Index (VHI) were assessed. Digital voice analysis of a sustained and stable vowel [a] resulted in 3274 parameters, which were used for training of machine learning models classifying the speaker as "acromegaly" or "control". The machine learning model was trained with 76% of the data and the remaining 24% was used to assess its performance. For comparison, voice recordings of 50 pairs of participants were assessed by 12 experienced endocrinologists. We included 151 Swedish patients with acromegaly (13% biochemically active and 10% newly diagnosed) and 139 matched controls. The machine learning model identified patients with acromegaly more accurately [area under the receiver operating curve (ROC AUC) 0.84] than experienced endocrinologists (ROC AUC 0.69). Self-reported voice problems were more pronounced in patients with acromegaly than matched controls (median VHI 6 vs 2, P < .01) with higher prevalence of clinically significant voice handicap (VHI ≥20: 22.5% vs 3.6%). Digital voice analysis can identify patients with acromegaly from short voice recordings with high accuracy. Patients with acromegaly experience more voice disorders than matched controls.

Sample size for assessing a diagnostic accuracy of AI-based software in radiology

Introduction. Determining the minimum sample size for solving various tasks is an extremely important and at the same time unexplored problem. There are many methods, but most of them are not applicable for AI-based software validation.Aim: To consider a methodology for determining a balance of classes “norm”/ “abnormality” and propose a statistical approach to determine the data amount necessary for testing AI-based software (validation).Material and Methods. The results of AI-based software were analyzed using dataset of mammograms. Mammograms were classified by the presence of breast cancer (“abnormality”) and the absence of breast cancer (“norm”). The general set contains 123,301 unique studies. The original balance of classes in the study was “norm” 89.3%/“abnormality” 10.7%. As the results of AI-based software (ML-algorithm), a probability of the presence of pathology in the entire study was taken. The following values were used as empirical data (GT): 0 – in case of Bi-RADS classes 1 or 2 diagnosed by a doctor, and 1 – in case of Bi-RADS classes 3, 4, 5. Each data sample is transferred to AI-based software for processing. Quality metrics are calculated based on its results: AUC ROC. All the described actions were repeated 10,000 times for all the studied balances of “norm”/”abnormality”. Based on the results of AUC ROC calculations, mean values were calculated for different random data series with the same balances. Mean AUC ROC values were subjected to analysis.Results. A maximum value of the coefficient of variation of AUC ROC values for 10% “abnormality” share is achieved at the number of studies equal to 190; for the 20% share, it is 80 studies; for the 30% share – 120 studies, for the 40% share – 110 studies, and for the 50% share – 70 studies.Conclusion. Summarizing the conducted study results, it can be concluded that when testing AI-based software, it is necessary to consider that the number of studies reflecting the greatest heterogeneity of AUC ROC values (the largest deviation from the mean value) is different for various class balances. If the purpose of validation is to establish the worst-case behavior of AUC ROC values, then for the studied AI-based software, the “abnormality” share should be 10%, and the number of studies 190. If the validation is carried out under conditions of a limited amount of data, then the “abnormality” share should be 50% and the number of studies equal to 70.

Combining Computational Fluid Dynamics, Structural Analysis, and Machine Learning to Predict Cerebrovascular Events: A Mild ML Approach

Background/Objectives: Cerebrovascular events, such as strokes, are often preceded by the rupture of atherosclerotic plaques in the carotid arteries. This work introduces a novel approach to predict the occurrence of such events by integrating computational fluid dynamics (CFD), structural analysis, and machine learning (ML) techniques. The objective is to develop a predictive model that combines both imaging and non-imaging data to assess the risk of carotid atherosclerosis and subsequent cerebrovascular events, ultimately improving clinical decision-making. Methods: A multidisciplinary approach was employed, utilizing 3D reconstruction techniques and blood-flow simulations to extract key plaque characteristics. These were combined with patient-specific clinical data for risk evaluation. The study involved 134 asymptomatic individuals diagnosed with carotid artery disease. Data imbalance was addressed using two distinct approaches, with the optimal method chosen for training a Gradient Boosting Tree (GBT) classifier. The model’s performance was evaluated in terms of accuracy, sensitivity, specificity, and ROC AUC. Results: The best-performing GBT model achieved a balanced accuracy of 88%, with a ROC AUC of 0.92, a sensitivity of 0.88, and a specificity of 0.91. This demonstrates the model’s high predictive power in identifying patients at risk for cerebrovascular events. Conclusions: The proposed method effectively combines CFD, structural analysis, and ML to predict cerebrovascular event risk in patients with carotid artery disease. By providing clinicians with a tool for better risk assessment, this approach has the potential to significantly enhance clinical decision-making and patient outcomes.

Machine learning-based identification and validation of aging-related genes in cardiomyocytes from patients with atrial fibrillation.

Aging is a key risk factor for atrial fibrillation (AF), a prevalent cardiac disorder among the elderly. This study aims to elucidate the genetic underpinnings of AF in the context of aging. We analyzed 12,403 genes from the GSE2240 database and 279 age-related genes from the CellAge database. Machine learning algorithms, including support vector machines and random forests, were employed to identify genes significantly associated with AF. Among the genes studied, 76 were found to be potential candidates in the development of AF. Notably, four genes - PTTG1, AR, RAD21, and YAP1 - stood out with a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 0.9, signifying high predictive power. Logistic regression, validated through 10-fold cross-validation and Bootstrap resampling, was determined as the most suitable model for internal validation. The discovery of these four genes could improve diagnostic accuracy for AF in the aged population. Additionally, our drug prediction model indicates that bisphenol A and cisplatin, among other substances, could be promising in treating age-associated AF, offering potential pathways for clinical intervention.

HeteroKGRep: Heterogeneous Knowledge Graph based Drug Repositioning

The process of developing new drugs is both time-consuming and costly, often taking over a decade and billions of dollars to obtain regulatory approval. Additionally, the complexity of patent protection for novel compounds presents challenges for pharmaceutical innovation. Drug repositioning offers an alternative strategy to uncover new therapeutic uses for existing medicines. Previous repositioning models have been limited by their reliance on homogeneous data sources, failing to leverage the rich information available in heterogeneous biomedical knowledge graphs. We propose HeteroKGRep, a novel drug repositioning model that utilizes heterogeneous graphs to address these limitations. HeteroKGRep is a multi-step framework that first generates a similarity graph from hierarchical concept relations. It then applies SMOTE over-sampling to address class imbalance before generating node sequences using a heterogeneous graph neural network. Drug and disease embeddings are extracted from the network and used for prediction. We evaluated HeteroKGRep on a graph containing biomedical concepts and relations from ontologies, pathways and literature. It achieved state-of-the-art performance with 99% accuracy, 95% AUC ROC and 94% average precision on predicting repurposing opportunities. Compared to existing homogeneous approaches, HeteroKGRep leverages diverse knowledge sources to enrich representation learning. Based on heterogeneous graphs, HeteroKGRep can discover new drug-disease associations, leveraging de novo drug development. This work establishes a promising new paradigm for knowledge-guided drug repositioning using multimodal biomedical data.

Machine learning-based prediction model of lower extremity deep vein thrombosis after stroke.

This study aimed to apply machine learning (ML) techniques to develop and validate a risk prediction model for post-stroke lower extremity deep vein thrombosis (DVT) based on patients' limb function, activities of daily living (ADL), clinical laboratory indicators, and DVT preventive measures. We retrospectively analyzed 620 stroke patients. Eight ML models-logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT), neural network (NN), extreme gradient boosting (XGBoost), Bayesian (NB), and K-nearest neighbor (KNN)-were used to build the model. These models were extensively evaluated using ROC curves, AUC, PR curves, PRAUC, accuracy, sensitivity, specificity, and clinical decision curves (DCA). Shapley's additive explanation (SHAP) was used to determine feature importance. Finally, based on the optimal ML algorithm, different functional feature set models were compared with the Padua scale to select the best feature set model. Our results indicated that the RF algorithm demonstrated superior performance in various evaluation metrics, including AUC (0.74/0.73), PRAUC (0.58/0.58), accuracy (0.75/0.77), and sensitivity (0.78/0.80) in both the training set and test set. DCA analysis revealed that the RF model had the highest clinical net benefit. SHAP analysis showed that D-dimer had the most significant influence on DVT, followed by age, Brunnstrom stage (lower limb), prothrombin time (PT), and mobility ability. The RF algorithm can predict post-stroke DVT to guide clinical practice.

Bank Direct Marketing Campaign Success Prediction

Nowadays, there are more new and innovative bank marketing strategies available that contribute to customer engagement and acquisition. Banks must launch marketing campaigns that can successfully attract customers from other competitors. Therefore, the purpose of the research is to apply Machine Learning techniques in predicting the success of a bank’s direct marketing campaign using supervised classification algorithms. Six algorithms are implemented which are Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Gaussian Naïve Bayes (GNB) and Extreme Gradient Boosting (XGBoost). In this paper, feature selection is performed, and 8 selected features are used to make the prediction. The experimental result shows that the Random Forest model has the highest accuracy and ROC AUC score which makes it the champion model in this paper. Still, these results may vary according to the nature of data preprocessing and algorithms implemented.

Cluster of differentiation-44 as a novel biomarker of lupus nephritis and its role in kidney inflammation and fibrosis.

CD44 is a transmembrane glycoprotein implicated in tissue inflammation and fibrosis. We investigated its role in kidney inflammation and fibrosis in a murine model of lupus nephritis (LN), and the clinico-pathological association of serum CD44 level in patients with biopsy-proven Class III/IV ± V LN. NZB/W F1 mice were treated with control IgG or anti-CD44 monoclonal antibody for 4 weeks and disease parameters assessed. Serum CD44 level in LN patients was determined by ELISA. Control groups included healthy subjects and patients with non-renal SLE or non-lupus renal disease. CD44 expression was absent in the normal kidney, but it was expressed in proximal and distal tubular epithelial cells and infiltrating cells in renal biopsies from patients with active proliferative LN. ScRNA-Seq datasets confirmed that CD44 was predominantly expressed in tubular cells and all immune cells identified in LN patients including tissue resident, inflammatory and phagocytic macrophages, Treg cells, effector and central memory CD4+ T cells, resident memory CD8+ T cells and naïve and activated B cells. Treatment of NZB/W F1 mice with anti-CD44 antibody preserved kidney histology and reduced proteinuria, tubulo-interstitial infiltration of CD3+, CD4+ and CD19+ immune cells, and mediators of kidney fibrosis compared to Control mice. Longitudinal studies showed that serum CD44 level increased prior to clinical renal flare by 4.5 months and the level decreased after treatment. ROC curve analysis showed that CD44 level distinguished patients with active LN from healthy subjects and patients with quiescent LN, active non-renal lupus, and non-lupus CKD (ROC AUC of 0.99, 0.96, 0.99 and 0.99 respectively). CD44 level correlated with leukocyte infiltration and interstitial inflammation scores in active LN kidney biopsies. Our findings suggest that CD44 plays a pathogenic role in renal parenchymal inflammation and fibrosis in active LN and monitoring CD44 may facilitate early diagnosis of flare.

ПРИМЕНЕНИЕ КОЛИЧЕСТВЕННОГО МЕТОДА В ИССЛЕДОВАНИИ ОПОЛЗНЕВОЙ ВОСПРИИМЧИВОСТИ СЕЛЕОПАСНОГО БАССЕЙНА РЕКИ АГСУЧАЙ

The article uses a quantitative method to analyze dangerous landslide processes occurring in the mudflow-prone Agsuchay River basin, taking into account the active development of tourism and recreational activities in the Shamakhi-Ismayilli region. In order to identify landslide susceptibility and the potential manifestation of landslides, the “weight” of 9 factors associated with landslides was determined, including hypsometry, slope angles (slope steepness), slope exposure, geological structure (lithology), distance from faults, average annual precipitation, distance to the erosion networks, distance to roads and land use. By summing up all the landslide formation factors without exception and multiplying them by their “weight”, a map of landslide susceptibility of the mudflow-prone Agsuchay River basin was compiled. The reliability of the obtained models was assessed using the AUC ROC (area under the error curve) analysis, which showed a fairly high efficiency (up to 72 %) of the applied method.

Dual-energy subtraction radiography (DESR): a systematic review and meta-analysis of pulmonary nodule detection

PurposeThis study examined the literature to compare the accuracy, sensitivity, and specificity of dual-energy subtraction radiography (DESR) with conventional radiography (CR) in the detection of pulmonary nodules. To our knowledge, no meta-analysis has been conducted to compare DESR with CR. Material and MethodsThe authors searched Pubmed using the terms “Dual-energy subtraction radiography,” and “Dual-Energy Chest Radiography.” Only studies comparing the detection of pulmonary nodules between DESR and CR were included. Studies utilizing artificial intelligence were excluded. The primary study outcomes analyzed were the mean difference of Receiver Operating Characteristic Area under the Curve (ROC AUC), mean difference of sensitivity, and mean difference of specificity. ResultsTwenty-three studies between 1994 - 2022 were included. Of these twenty-three, eighteen reported ROC AUC statistics. The difference between DESR ROC AUC (mean = 0.7702, SD = 0.1361) and CR ROC AUC (mean = 0.7106, SD = 0.1183) was 0.0597 (p<0.001).Sensitivity data was reported for thirteen of the twenty-three selected studies. The difference between DESR sensitivity (mean = 0.5753, SD = 0.1546) and CR sensitivity (mean = 0.4391, SD = 0.1007) was 0.136 (p<0.001).Specificity data was reported for ten of the twenty-three selected studies. The difference between DESR specificity (mean = 0.753, SD = 0.1575) and CR specificity (mean = 0.764, SD = 0.1168) was -0.011 (p=0.767). This was not statistically significant. ConclusionDESR showed superior sensitivity and ROC AUC values compared to CR in detecting pulmonary nodules. There was no difference in specificity.

CNVoyant a machine learning framework for accurate and explainable copy number variant classification

The precise classification of copy number variants (CNVs) presents a significant challenge in genomic medicine, primarily due to the complex nature of CNVs and their diverse impact on rare genetic diseases (RGDs). This complexity is compounded by the limitations of existing methods in accurately distinguishing between benign, uncertain, and pathogenic CNVs. Addressing this gap, we introduce CNVoyant, a machine learning-based multi-class framework designed to enhance the clinical significance classification of CNVs. Trained on a comprehensive dataset of 52,176 ClinVar entries across pathogenic, uncertain, and benign classifications, CNVoyant incorporates a broad spectrum of genomic features, including genome position, disease-gene annotations, dosage sensitivity, and conservation scores. Models to predict the clinical significance of copy number gains and losses were trained independently. Final models were selected after testing 29 machine learning architectures and 10,000 hyperparameter combinations each for deletions and duplications via fivefold cross-validation. We validate the performance of CNVoyant by leveraging a comprehensive set of 21,574 CNVs from the DECIPHER database, a highly regarded resource known for its extensive catalog of chromosomal imbalances linked to clinical outcomes. Compared to alternative approaches, CNVoyant shows marked improvements in precision-recall and ROC AUC metrics for binary pathogenic classifications while going one step further, offering multi-classification of clinical significance and corresponding SHAP explainability plots. Additionally, when provided germline CNV calls from real-world RGD cases with diagnostic CNV(s), CNVoyant correctly classified all diagnostic CNVs as having pathogenic significance with high confidence. This large-scale validation demonstrates CNVoyant’s superior accuracy and underscores its potential to aid genomic researchers and clinical geneticists in interpreting the clinical implications of real CNVs.

Return management in e-commerce firms: A machine learning approach to predict product returns and examine variables influencing returns

The advent of technology with internet penetration has led to exponential growth in sales through online mediums worldwide. Although the growth has increased sales and created opportunities for many firms and sellers to flourish, it also brings in the challenge of customer returns, making it a formidable challenge for businesses. For effective return handling and control, predicting product returns correctly is of utmost importance for firms. The study comprehensively examines the return management process, elucidating its multiple features and characteristics, focusing on the types of returns and the involvement of various stakeholders. Logistic regression, random forest, and gradient-boosting machine learning techniques were used on a data set to scrutinize critical variables influencing returns. Comparing the models using the ROC curve and AUC, gradient boosting performed better in predicting returns than other models. The study identifies significant variables affecting e-commerce return rates, such as total order amount, product category, and cash on delivery charge, an additional fee charged on this mode of payment. Managerial insights recommend that firms conduct due diligence and thorough assessments before introducing products from specific vendors. Quality improvement in certain categories of products, incentivizing card payments, and nominalizing the cash on delivery fees, which could be seen as burdensome by customers, are some of the steps firms need to reduce returns. Strategies like confirming weekend orders and updating replenishment times regularly by vendors can help firms mitigate returns effectively. The study contributes to the academic understanding of return management in e-commerce and offers actionable insights for practitioners.

High affective temperamental load as a clinical marker of bipolar disorder: applications in low-resource settings

Objective We aimed to test the performance of the short version of the Temperamental Evaluation of Memphis, Pisa, Paris, and San Diego-Auto questionnaire (Short-TEMPS-A) as a tool for bipolar disorder (BD) status detection in an outpatient sample with affective disorders, using Cyclothymic-Hyperthymic High Temperamental Load (HTL-CH) as the criterion for a positive test. Methods We enrolled 201 euthymic female and male adult outpatients (73.1% female; mean age 47.3 ± 16 years), with BD (42.79%), and other affective disorders (major depressive disorder (20.9%), or anxiety disorders (36.32%)) in a public general hospital in South-Central Chile. Diagnosis was made using the Structured Clinical Interview for axis I. All subjects completed the Short-TEMPS-A. HTL-CH was defined using a cutoff of ≥75% in the hyperthymic or cyclothymic subscales of the Short-TEMPS-A. We estimated the HTL-CH likelihood of BD versus non-BD using multiple logistic regression modeling to control for possible confounders. The performance of HTL-CH as a tool for BD status evaluation was assessed using area under receiver operating characteristic curve (AUC ROC) analysis. Results Patients with HTL-CH had an OR = 7.55 (CI95% = 2.11–26.96) of having a BD status. HTL-CH showed good psychometric properties for BD status detection, correctly classifying 74.13% of patients. AUC ROC was 0.74 (CI95%=0.68–0.81). Conclusions HTL-CH, as assessed by the Short-TEMPS-A, was able to detect BD status accurately and reliably in affective outpatients. The Short-TEMPS-A might be a useful tool in aiding clinicians to detect BD, particularly during initial assessment of affective patients in low-resource settings.

Predicting Heart Disease through Machine Learning Methods

Heart diseases including heart attacks, cause about 31% of global deaths, remaining a significant health threat despite preventability. Limited tech advancements and awareness, especially in developing nations, amplify this challenge. Machine learning offers promise in tackling this issue, with studies advocating ensemble methods for accurate predictive models. These models analyze extensive medical data to efficiently predict heart diseases, undergoing stages like data exploration, feature selection, model implementation, and comparative analysis. A model using Logistic Regression, Naive Bayes, and Random Forest initially identified top-performing models, later refined to CatBoost, RandomForest, and XGBoost through cross-validation and tuning. A hybrid model, combining Logistic Regression, CatBoost, and RandomForest, achieved a 97% accuracy, showcasing improved precision, recall, F1 score, and ROC AUC. This underscores machine learning's potential in enhancing predictive accuracy and refining strategies to combat heart diseases effectively.

Machine learning for automated classification of lung collagen in a urethane-induced lung injury mouse model.

Dysregulation of lung tissue collagen level plays a vital role in understanding how lung diseases progress. However, traditional scoring methods rely on manual histopathological examination introducing subjectivity and inconsistency into the assessment process. These methods are further hampered by inter-observer variability, lack of quantification, and their time-consuming nature. To mitigate these drawbacks, we propose a machine learning-driven framework for automated scoring of lung collagen content. Our study begins with the collection of a lung slide image dataset from adult female mice using second harmonic generation (SHG) microscopy. In our proposed approach, first, we manually extracted features based on the 46 statistical parameters of fibrillar collagen. Subsequently, we pre-processed the images and utilized a pre-trained VGG16 model to uncover hidden features from pre-processed images. We then combined both image and statistical features to train various machine learning and deep neural network models for classification tasks. We employed advanced unsupervised techniques like K-means, principal component analysis (PCA), t-distributed stochastic neighbour embedding (t-SNE), and uniform manifold approximation and projection (UMAP) to conduct thorough image analysis for lung collagen content. Also, the evaluation of the trained models using the collagen data includes both binary and multi-label classification to predict lung cancer in a urethane-induced mouse model. Experimental validation of our proposed approach demonstrates promising results. We obtained an average accuracy of 83% and an area under the receiver operating characteristic curve (ROC AUC) values of 0.96 through the use of a support vector machine (SVM) model for binary categorization tasks. For multi-label classification tasks, to quantify the structural alteration of collagen, we attained an average accuracy of 73% and ROC AUC values of 1.0, 0.38, 0.95, and 0.86 for control, baseline, treatment_1, and treatment_2 groups, respectively. Our findings provide significant potential for enhancing diagnostic accuracy, understanding disease mechanisms, and improving clinical practice using machine learning and deep learning models.

SACrA score to predict the initiation of renal replacement therapy in critically ill patients: a single-center retrospective study

Background Acute kidney injury (AKI) is a prevalent complication in critically ill patients that affects the timing of renal replacement therapy (RRT) initiation. This study aimed to develop and validate the SACrA score for predicting non-emergent initiations (BUN ≥112 mg/dL or oliguria for >72 h) of RRT in critically ill patients. Methods We conducted a retrospective cohort study using data from two cohorts. The derivation cohort included patients admitted to the ICU between November 2021 and December 2023, whereas the validation cohort included patients admitted between September 2019 and October 2021. The primary outcome was non-emergent RRT initiation. The multivariate logistic regression with stepwise selection based on the Akaike information criterion finalized the model, including the variables, such as sex, albumin (Alb), creatinine (Cr), and APACHE II score (SACrA). Results The derivation and validation cohorts comprised 470 and 476 patients, respectively. The SACrA score showed a strong predictive performance for non-emergent RRT initiation in both the cohorts. Cohort 1 had an ROC–AUC of 0.971, with a calibration slope of 0.982 and an intercept of 0.009, whereas cohort 2 had an ROC–AUC of 0.918, with a calibration slope of 0.988 and an intercept of 0.004. Conclusions The SACrA score is a robust tool for predicting non-emergent RRT initiation in critically ill patients using readily available clinical variables. Though additional data are needed to validate the SACrA score, our analysis suggests the tool may help clinicians make informed decisions, reduce unnecessary RRT, and thereby improve patient outcomes.

External validation of the parsimonious EuroLung risk models: analysis of the Brazilian Lung Cancer Registry.

The purpose of this study was to assess performance in the Brazilian Lung Cancer Registry Database by using the parsimonious EuroLung risk models for morbidity and mortality. The EuroLung1 and EuroLung2 models were tested and evaluated through calibration (calibration plot, Brier score, and the Hosmer-Lemeshow test) and discrimination (ROC AUCs), in a national multicenter registry of 1,031 patients undergoing anatomic lung resection. The evaluation of performance in Brazilian health care facilities utilizing risk-adjustment models, specifically EuroLung1 and EuroLung2, revealed substantial miscalibration, as evidenced by calibration plots and Hosmer-Lemeshow tests in both models. In terms of calibration, EuroLung1 exhibited a calibration plot with overlapping points, characterized by a slope of 1.11 and a Brier score of 0.15; the Hosmer-Lemeshow test yielded a statistically significant p-value of 0.015; and the corresponding ROC AUC was 0.678 (95% CI: 0.636-0.721). The EuroLung2 model displayed better calibration, featuring fewer overlapping points in the calibration plot, with a slope of 1.22, with acceptable discrimination, as indicated by a ROC AUC of 0.756 (95% CI: 0.670-0.842). Both models failed to accurately predict morbidity and mortality outcomes in this specific health care context. Discrepancies between the EuroLung model predictions and outcomes in Brazil underscore the need for model refinement and for a probe into inefficiencies in the Brazilian health care system.