Moderate Accuracy Research Articles

Plasma procalcitonin and urine interleukin-8, neutrophil gelatinase–associated lipocalin, and calprotectin in the diagnostic process of a urinary tract infection at the emergency department

ObjectivesThis study aimed to assess the usefulness of plasma procalcitonin and urine IL-8 (interleukin-8), NGAL (neutrophil gelatinase–associated lipocalin), and calprotectin for diagnosis of urinary tract infections (UTIs) at the emergency department (ED). MethodsIn adults presenting at the ED with UTI suspicion, biomarker performance was compared with that of routine diagnostics (urine dipstick, automated urinalysis). Patients with a urine catheter, leukopenia, or neither (standard) were analyzed separately. ResultsA UTI was clinically diagnosed in 91 of 196 episodes (46.4%) (standard: 29/67 [43.2%]; catheter: 46/73 [63.0%]; leukopenia: 17/60 [28.3%]; four patients had both). Procalcitonin did not discriminate between UTI and no UTI. Urinary biomarker levels were elevated in UTI episodes (median, µg/mmol creatinine: NGAL, 7.8 vs 46.3; IL-8, 6.1 vs 76.6; calprotectin, 23.9 vs 265.4); the three subgroups also had higher levels. Biomarker cut-off values (90% sensitivity) showed low specificity (range 20.8-64.9%) and moderate accuracy (58.6-75.4%). The biomarkers performed similarly to routine diagnostics, except for patients with leukopenia, who exhibited nonsignificantly higher area under the curve values. All urinary biomarkers correlated positively with urine leukocyte count. ConclusionPlasma procalcitonin could not accurately diagnose UTI. Urine IL-8, NGAL, and calprotectin showed no additional value relative to routine diagnostics, except a minor improvement in patients with leukopenia. These urine biomarkers seem to predominantly reflect leukocyturia.

Diagnostic Accuracy of Ultrasound Imaging and Shear Wave Elastography to Discriminate Patients with Chronic Neck Pain from Asymptomatic Individuals

Objectives: The aim of this study was to determine and compare the capability of several B-mode ultrasound (US) and shear wave elastography (SWE) metrics to differentiate subjects with chronic non-specific neck pain from asymptomatic subjects. Methods: A diagnostic accuracy study recruiting a sample of patients with chronic neck pain and asymptomatic controls was conducted. Data collection included sociodemographic information (i.e., gender, age, height, weight and body mass index), clinical information (pain intensity assessed using the Visual Analogue Scale and pain-related disability using the Neck Disability Index) and B-mode ultrasound and shear wave elastography features of the cervical multifidus muscle (cross-sectional area, perimeter, mean echo intensity, fat infiltration, shear wave speed and Young’s modulus). After analyzing between-group differences for left/right sides, cases and controls, and males and females, the area under the receiver operating characteristic (ROC) curve, the optimal cut-off point, the sensitivity, the specificity, the positive likelihood ratio (LR) and negative LR for each metric were calculated. A total of 316 individuals were recruited in this study (n = 174 cases with neck pain and n = 142 asymptomatic controls). Results: No significant differences (p > 0.05) were found between cases and controls for most variables, except for fatty infiltration, which was significantly higher in chronic neck pain cases (p < 0.001). Gender differences were significant across all US and SWE metrics (all, p < 0.001 except p = 0.015 for fatty infiltrates). A slight asymmetry was observed between the left and right sides for area (p = 0.038). No significant interactions between group, gender and side (all metrics, p > 0.008) were identified. Fatty infiltration was the most effective discriminator, with a ROC value of 0.723, indicating acceptable discrimination. The optimal cut-off point for fatty infiltration was 25.77, with a moderate balance between sensitivity (59.8%) and specificity (20.5%). However, its positive likelihood ratio (LR) of 0.75 suggests limited usefulness in confirming the condition. Conclusions: Fatty infiltration was significantly higher in individuals with chronic idiopathic neck pain compared to those without symptoms, while other muscle metrics were similar between both groups. However, since fat infiltration had moderate diagnostic accuracy and the other metrics showed poor discriminatory power, US cannot be used solely to discriminate patients with idiopathic neck pain.

Diagnostic accuracy and added value of dynamic chest radiography in detecting pulmonary embolism: A retrospective study

PurposeThis study aimed to assess the diagnostic performance of dynamic chest radiography (DCR) and investigate its added value to chest radiography (CR) in detecting pulmonary embolism (PE). MethodsOf 775 patients who underwent CR and DCR in our hospital between June 2020 and August 2022, individuals who also underwent contrast-enhanced CT (CECT) of the chest within 72 h were included in this study. PE or non-PE diagnosis was confirmed by CECT and the subsequent clinical course. The enrolled patients were randomized into two groups. Six observers, including two thoracic radiologists, two cardiologists, and two radiology residents, interpreted each chest radiograph with and without DCR using a crossover design with a washout period. Diagnostic performance was compared between CR with and without DCR in the standing and supine positions. ResultsSixty patients (15 PE, 45 non-PE) were retrospectively enrolled. The addition of DCR to CR significantly improved the sensitivity, specificity, accuracy, and area under the curve (AUC) in the standing (35.6–70.0 % [P < 0.0001], 84.8–93.3 % [P = 0.0010], 72.5–87.5 % [P < 0.0001], and 0.66–0.85 [P < 0.0001], respectively) and supine (33.3–65.6 % [P < 0.0001], 78.5–92.2 % [P < 0.0001], 67.2–85.6 % [P < 0.0001], and 0.62–0.80 [P = 0.0002], respectively) positions for PE detection. No significant differences were found between the AUC values of DCR with CR in the standing and supine positions (P = 0.11) or among radiologists, cardiologists, and radiology residents (P = 0.14–0.68). ConclusionsIncorporating DCR with CR demonstrated moderate sensitivity, high specificity, and high accuracy in detecting PE, all of which were significantly higher than those achieved with CR alone, regardless of scan position, observer expertise, or experience.

6689 A Multicentric Study for Validation of the Diagnostic Accuracy of ACR-TIRADS in a Mexican population

Abstract Disclosure: M. Romero Ibarguengoitia: None. I.A. Villarreal-Ondarza: None. J. Mercado Basurto: None. A. González Cantu: None. The diagnostic performance of ultrasonographic ACR-TIRADS classification to evaluate thyroid nodules is poorly studied in a Mexican population. The aim was to assess the diagnostic accuracy of ACR-TIRADS classification for identifying malignant thyroid nodules in adults aged &amp;gt;18 years. This retrospective research study was conducted in 4 medical centers in Northern Mexico from 2022 to 23 to obtain ACR-TIRADS classification of nodules from thyroid ultrasound. Information about Bethesda classification after fine needle aspiration and cytology from thyroidectomy was analyzed for diagnostic performance tests. A total of 160 patients were included. Thyroid nodules were classified as TIRADS 3 in 12%, TIRADS 4 in 44%, and TIRADS 5 in 41%. Twenty-six (16%) were classified as Bethesda 1, 39 (24%) were classified as Bethesda 5, and 30 (19%) were classified as Bethesda 6. The sensitivity (S) of TIRADS 4 was 41%, specificity (E) was 50%, positive predictive value (PPV) was 59%, negative predictive value (NPV) was 32%, and accuracy was 44%. The S of TIRADS 5 was 51%, E 77%, PPV 80%, NPV 47%, and accuracy of 61%. When comparing with other populations, the performance was the same as the Turkish (their accuracy was 59.93%) population but lower than a population from China (their accuracy was 86%) and Germany (PPV 100% for TIRADS 5). The proportion of malignancy in our sample compared with a reference sample from Germany was lower, 36 vs. 85% for TIRADS 3, 59 vs. 85% for TIRADS 4, and 80% vs. 100%, p&amp;lt; 0.001. Concerning Bethesda's classification, the proportion of malignancy was the same according to the reference sample from the American Thyroid Association. In conclusion, there was a moderate accuracy of the ACR-TIRADS classification system in our population, the same in comparison with the Turkish population; slightly lower than what is reported in a population from Germany and China. Presentation: 6/1/2024

Turkey’s Hydropower Potential in the Near Future and the Possible Impacts of Climate Change—A Case Study of the Euphrates–Tigris Basin

Hydropower is becoming an important renewable energy source in Turkey, but the ever-changing atmospheric and climatic conditions of Turkey make it very difficult to be projected efficiently. Thus, an efficient estimation technique is crucial for it to be adopted as a reliable energy source in the future. This study evaluates Turkey’s hydropower potential in the Euphrates–Tigris Basin under changing climatic conditions. We adapted an empirical equation to model reservoir outflows, considering the site-specific characteristics of 14 major dams. Initial results from employing a model with a constant empirical coefficient, α, yielded moderate predictive accuracy, with R2 values ranging from 0.289 to 0.612. A polynomial regression identified optimal α values tailored to each dam’s surface area, significantly improving model performance. The adjusted α reduced predictive bias and increased R2 values, enhancing forecast reliability. Seasonal analysis revealed distinct hydropower trends: Ataturk Dam showed a notable decrease of 5.5% in hydropower generation up to 2050, while Birecik and Keban Dams exhibited increases of 2.5% and 2.2%, respectively. By putting these discoveries into practice, water resource management may become more robust and sustainable, which is essential for meeting Turkey’s rising energy needs and preparing for future climatic challenges. This study contributes valuable insights for optimizing reservoir operations, ensuring long-term hydropower sustainability, and enhancing the resilience of water resource management systems globally.

Cardiovascular Risk Factors as Independent Predictors of Diabetic Retinopathy in Type II Diabetes Mellitus: The Development of a Predictive Model.

Background: Diabetic retinopathy (DR) is a leading cause of blindness in patients with type 2 diabetes mellitus (T2DM). Cardiovascular risk factors, such as hypertension, obesity, and dyslipidemia, may play a crucial role in the development and progression of DR, though the evidence remains mixed. This study aimed to assess cardiovascular risk factors as independent predictors of DR and to develop a predictive model for DR progression in T2DM patients. Methods: A retrospective cross-sectional study was conducted on 377 patients with T2DM who underwent a comprehensive eye exam. Clinical data, including blood pressure, lipid profile, BMI, and smoking status, were collected. DR staging was determined through fundus photography and classified as No DR, Non-Proliferative DR (NPDR), and Mild, Moderate, Severe, or Proliferative DR (PDR). A Multivariate Logistic Regression was used to evaluate the association between cardiovascular risk factors and DR presence. Several machine learning models, including Random Forest, XGBoost, and Support Vector Machines, were applied to assess the predictive value of cardiovascular risk factors and identify key predictors. Model performance was evaluated using accuracy, precision, recall, and ROC-AUC. Results: The prevalence of DR in the cohort was 41.6%, with 34.5% having NPDR and 7.1% having PDR. A multivariate analysis identified systolic blood pressure (SBP), LDL cholesterol, and body mass index (BMI) as independent predictors of DR progression (p < 0.05). The Random Forest model showed a moderate predictive ability, with an AUC of 0.62 for distinguishing between the presence and absence of DR XGBoost showing a better performance, featuring a ROC-AUC of 0.68, while SBP, HDL cholesterol, and BMI were consistently identified as the most important predictors across models. After tuning, the XGBoost model showed a notable improvement, with an ROC-AUC of 0.72. Conclusions: Cardiovascular risk factors, particularly BP and BMI, play a significant role in the progression of DR in patients with T2DM. The predictive models, especially XGBoost, showed moderate accuracy in identifying DR stages, suggesting that integrating these risk factors into clinical practice may improve early detection and intervention strategies for DR.

Diagnostic accuracy of subclavian vein versus inferior vena cava collapsibility index for predicting postinduction hypotension: An observational study.

Hypotension following induction of general anesthesia (GA) is commonly observed. Ultrasound (US) measurement of collapsibility index (CI) of the inferior vena cava (IVC) for predicting postinduction hypotension has been studied. As there is limited data available comparing the diagnostic accuracy of subclavian vein (SCV) versus IVC-CI, we performed this observational study. A total of 132 adult patients scheduled for elective surgery under GA were enrolled. US measurements of three readings of maximum and minimum diameters of SCV and IVC were recorded during both quiet and deep breathing, and the mean of three values was calculated. CI was derived using the formula: (dmax - dmin) × 100/dmax. Subsequently, GA was administered using standard technique, irrespective of the findings of SCV and IVC measurements. The administered drugs and dosage were recorded. Hemodynamic parameters were collected at baseline and then at every minute for the first 20 min. The primary objective was to compare the diagnostic accuracies of SCV-CI and IVC-CI for prediction of postinduction hypotension during quiet breathing. The secondary objectives were to compare the diagnostic accuracies during deep breathing and find the correlation between IVC-CI and SC-CI during quiet and deep breathing, incidence of hypotension, and time required to acquire US images. Fifty-seven patients developed postinduction hypotension. During quiet breathing, SCV-CI ≥10% had a sensitivity of 68% and specificity of 56% (area under curve [AUC] [95% confidence interval {CI}] of 0.659 [0.56-0.75]; P = 0.002), while IVC-CI ≥34% had a sensitivity of 70% and specificity of 59% (AUC [95% CI] of 0.672 [0.58-0.76]; P = 0.001) for prediction of postinduction hypotension. During deep breathing, both SCV-CI and IVC-CI had moderate accuracy (P = 0.001 for both). Pearson's correlation showed a significant positive correlation between SCV-CI and IVC-CI with a correlation coefficient (r) of 0.313 during quiet breathing and 0.379 during deep breathing (P < 0.001). The time required for acquiring US images was significantly less for SCV compared to IVC during both quiet and deep breathing (P < 0.001 for both). Both SCV-CI and IVC-CI were found to have good and comparable diagnostic accuracy for the prediction of postinduction hypotension. We also found a significant positive correlation between SCV-CI and IVC-CI. In comparison to IVC, US scanning of SCV took lesser time to acquire the images.

Diagnostic accuracy of the Fibrosis-4 index for advanced liver fibrosis in nonalcoholic fatty liver disease with type 2 diabetes: A systematic review and meta-analysis.

The Fibrosis-4 index (FIB-4) is a noninvasive test widely used to rule out advanced liver fibrosis (AF) in patients with nonalcoholic fatty liver disease (NAFLD). However, its diagnostic accuracy in NAFLD patients with type 2 diabetes mellitus (T2DM) is controversial due to the high prevalence of AF in this population. Research focusing on the diagnostic accuracy of FIB-4 for liver fibrosis as validated by liver histology in NAFLD patients with T2DM was included, and 12 studies (n=5,624) were finally included in the meta-analysis. Sensitivity, specificity, hierarchical summary receiver operating characteristic (HSROC), positive predictive values (PPVs), and negative predictive values (NPVs) at low cutoffs (1.3-1.67) and high cutoffs (2.67-3.25) for ruling in and out AF were calculated. At low cutoffs, the meta-analysis revealed a sensitivity of 0.74, specificity of 0.62, and HSROC of 0.75. At high cutoffs, the analysis showed a sensitivity of 0.33, specificity of 0.92, and HSROC of 0.85, suggesting FIB-4 as useful for identifying or excluding AF. In subgroup analyses, high mean age and F3 prevalence were associated with lower sensitivity. The calculated NPV and PPV were 0.82 and 0.49 at low cutoffs, whereas the NPV was 0.28 and the PPV was 0.70 at high cutoffs. There were insufficient estimated NPVs <0.90 at a hypothesized prevalence of AF >30% at an FIB-4 cutoff range of 1.3-1.67. Collectively, FIB-4 has moderate diagnostic accuracy for identifying or excluding AF in NAFLD patients with T2DM, but more evidence must be accumulated due to the limited number of currently reported studies and their heterogeneity.

Diagnosing retinal disorders with artificial intelligence: the role of large language models in interpreting pattern electroretinography data

Aims: To evaluate the diagnostic accuracy of Claude-3, a large language model, in detecting pathological features and diagnosing retinitis pigmentosa and cone-rod dystrophy using pattern electroretinography data. Methods: A subset of pattern electroretinography measurements from healthy individuals, patients with retinitis pigmentosa and cone-rod dystrophy was randomly selected from the PERG-IOBA dataset. The pattern electroretinography and clinical data, including age, gender, visual acuities, were provided to Claude-3 for analysis and diagnostic predictions. The model’s accuracy was assessed in two scenarios: “first choice,” evaluating the accuracy of the primary differential diagnosis and “top 3,” evaluating whether the correct diagnosis was included within the top three differential diagnoses. Results: A total of 46 subjects were included in the study: 20 healthy individuals, 13 patients with retinitis pigmentosa, 13 patients with cone-rod dystrophy. Claude-3 achieved 100% accuracy in detecting the presence or absence of pathology. In the “first choice” scenario, the model demonstrated moderate accuracy in diagnosing retinitis pigmentosa (61.5%) and cone-rod dystrophy (53.8%). However, in the “top 3” scenario, the model’s performance significantly improved, with accuracies of 92.3% for retinitis pigmentosa and 76.9% for cone-rod dystrophy. Conclusion: This is the first study to demonstrate the potential of large language models, specifically Claude-3, in analyzing pattern electroretinography data to diagnose retinal disorders. Despite some limitations, the model’s high accuracy in detecting pathologies and distinguishing between specific diseases highlights the potential of large language models in ocular electrophysiology. Future research should focus on integrating multimodal data, and conducting comparative analyses with human experts.

Prediction of adverse maternal and perinatal outcomes associated with pre-eclampsia and hypertensive disorders of pregnancy: a systematic review and meta-analysis

Hypertensive disorders of pregnancy are a leading cause of maternal and perinatal morbidity and mortality. If women at high risk for developing complications could be identified early, level of care could be triaged, limited resources could be correctly allocated and targeted interventions to prevent complications could be implemented. We updated a systematic review and meta-analysis and added single outcomes. Women with hypertensive disorders of pregnancy were included. Exposures were tests predicting adverse maternal and/or perinatal outcomes. We searched Medline, Embase, CINAHL, and Cochrane library from January 2016-February 2024. We included studies identified from the previous review. We calculated effect measures. For similar predictive tests and outcomes, area under the receiver-operating-characteristic curve (AUROC) were pooled. This study was registered by PROSPERO: CRD42022336368. Of the 2898 studies identified, 80 were included. Thirty were added from the previous review resulting in 110 included studies with 506,178 women. Despite more than 1500 tests being performed, most outcomes could not be pooled due to heterogeneity in populations, tests, and outcome definitions. For maternal outcomes, only studies reporting on the Pre-eclampsia Integrated Estimate of RiSk (fullPIERS) model could be pooled. For the composite outcome within 48-h the AUROC was 0.78 (95% CI 0.71-0.86, N=8). There was significant heterogeneity (I 2 =95.7%). For perinatal outcomes, data were pooled for pulsatility index in the umbilical artery and soluble FMS-like tyrosine kinase-1 (sFlt-1)/placental growth factor (PlGF) ratio. Biomarkers like the sFlt-1/PlGF ratio showed promising predictive performance for some outcomes but were not externally validated. Despite including over 100 studies with more than 1500 predictors, we were unable to pool any single maternal outcomes and only a few individual perinatal outcomes. The fullPIERS model was externally validated, showing moderate accuracy which varied across studies and should be validated in each new population. Angiogenic biomarkers showed promise but need validation. Future studies should use standardized outcome measures and validate promising tests. VB is supported by the Swedish Research Council, Grant number 2020-01481. University of Gothenburg.

The severity of gambling in clinical samples of gamblers: profiles and prediction of the impulsivity and emotions.

Impulsivity and emotion impairments have been noted in individuals with gambling disorder (GD). However, little research has investigated the influence of impulsivity and emotions on the severity of gambling in clinical populations. This study aimed to examine: (i) differences in emotions and impulsivity traits according to the severity of gambling in individuals with GD, (ii) the mediating effects of emotion in the relationship between impulsivity traits and gambling severity, and (iii) the predictive effects of emotion and impulsivity traits on GD severity. The study included 214 participants seeking treatment for GD who completed assessments for emotions (Patient Health Questionnaire-9 [PHQ-9], 7-item Generalized Anxiety [GAD-7]), impulsivity traits (Barratt Impulsiveness Scale [BIS], Self-control Scale [SCS]), and GD severity (DSM-5). Participants were categorized into mild (n = 78), moderate (n = 63), and severe (n = 73) gambling severity groups. Significant differences in emotions and impulsivity traits were observed across these groups. The severe GD group exhibited higher levels of depression, anxiety, and impulsivity traits, along with lower self-control, compared to the moderate and mild groups. Mediation analyses demonstrated that negative emotions mediated the association between impulsivity traits and the severity of gambling. More specifically, the indirect effects of impulsivity traits through PHQ-9 and GAD-7 were found to be significant, indicating a mediating role of emotions. Moreover, a predictive model incorporating emotion and impulsivity traits showed moderate accuracy in predicting the severity of gambling, with an area under the receiver operating characteristic curve of 0.714. This study highlights the distinct pathways through which impulsivity traits operate and emphasizes the need for prevention and treatment strategies that consider impulsivity traits and emotions for different levels of gambling severity.

FacePsy: An Open-Source Affective Mobile Sensing System - Analyzing Facial Behavior and Head Gesture for Depression Detection in Naturalistic Settings

Depression, a prevalent and complex mental health issue affecting millions worldwide, presents significant challenges for detection and monitoring. While facial expressions have shown promise in laboratory settings for identifying depression, their potential in real-world applications remains largely unexplored due to the difficulties in developing efficient mobile systems. In this study, we aim to introduce FacePsy, an open-source mobile sensing system designed to capture affective inferences by analyzing sophisticated features and generating real-time data on facial behavior landmarks, eye movements, and head gestures - all within the naturalistic context of smartphone usage with 25 participants. Through rigorous development, testing, and optimization, we identified eye-open states, head gestures, smile expressions, and specific Action Units (2, 6, 7, 12, 15, and 17) as significant indicators of depressive episodes (AUROC=81%). Our regression model predicting PHQ-9 scores achieved moderate accuracy, with a Mean Absolute Error of 3.08. Our findings offer valuable insights and implications for enhancing deployable and usable mobile affective sensing systems, ultimately improving mental health monitoring, prediction, and just-in-time adaptive interventions for researchers and developers in healthcare.

Role of lymphocyte-to-monocyte ratio as a predictive marker for diabetic coronary artery disease: A cross-sectional study.

The lymphocyte to monocyte ratio (LMR) is considered a marker of systemic inflammation in cardiovascular disease and acts as predictor of mortality in coronary artery disease. To investigate the predictive role of LMR in diabetic coronary artery disease patients. This cross-sectional study was conducted at tertiary care super-specialty hospital at New Delhi, India. A total of 200 angiography-proven coronary artery disease (CAD) patients were enrolled and grouped into two categories: Group I [CAD patients with type 2 diabetes mellitus (T2DM) and glycated hemoglobin (HbA1c) levels ≥ 6.5%], and Group II (CAD patients without T2DM and HbA1c levels < 6.5%). Serum lipoproteins, HbA1c, and complete blood count of enrolled patients were analyzed using fully automatic analyzers. The logistic regression analysis showed an odds ratio of 1.48 (95%CI: 1.28-1.72, P < 0.05) for diabetic coronary artery disease patients (Group I) in unadjusted model. After adjusting for age, gender, diet, smoking, and hypertension history, the odds ratio increased to 1.49 (95%CI: 1.29-1.74, P < 0.01) in close association with LMR. Further adjustment for high cholesterol and triglycerides yielded the same odds ratio of 1.49 (95%CI: 1.27-1.75, P < 0.01). Receiver operating characteristic curve analysis revealed 74% sensitivity, 64% specificity, and 0.74 area under the curve (95%CI: 0.67-0.80, P < 0.001), suggesting moderate predictive accuracy for diabetic CAD patients. LMR showed positive association with diabetic coronary artery disease, with moderate predictive accuracy. These findings have implications for improving CAD management in diabetics, necessitating further research and targeted interventions.

Economic impact of mortality prediction by predictive model at first and second treatment for bovine respiratory disease.

To evaluate a predictive model's ability to determine cattle mortality following first and second treatment for bovine respiratory disease and to understand the differences in net returns comparing predictive models to the status quo. 2 boosted decision tree models were constructed, 1 using data known at first treatment and 1 with data known at second treatment. Then, the economic impact of each outcome (true positive, true negative, false positive, and false negative) was estimated using various market values to determine the net return per head of using the predictive model to determine which animals should be culled at treatment. This was compared to the status quo to determine the difference in net return. The models constructed for the prediction of mortality performed with moderate accuracy (areas under the curve > 0.7). The economic analysis found that the models at a high specificity (> 90%) could generate a positive net return in comparison to status quo. This study showed that predictive models may be a useful tool to make culling decisions and could result in positive net returns. Bovine respiratory disease is the costliest health condition experienced by cattle on feed. Feedyard record-keeping systems generate vast amounts of data that could be used in predictive models to make management decisions. It is essential to understand the accuracy of predictions made via machine learning. However, the economic impact of implementing predictive models in a feedyard will influence adoption.

Automated Three-Dimensional Imaging and Pfirrmann Classification of Intervertebral Disc Using a Graphical Neural Network in Sagittal Magnetic Resonance Imaging of the Lumbar Spine.

This study aimed to develop a graph neural network (GNN) for automated three-dimensional (3D) magnetic resonance imaging (MRI) visualization and Pfirrmann grading of intervertebral discs (IVDs), and benchmark it against manual classifications. Lumbar IVD MRI data from 300 patients were retrospectively analyzed. Two clinicians assessed the manual segmentation and grading for inter-rater reliability using Cohen's kappa. The IVDs were then processed and classified using an automated convolutional neural network (CNN)-GNN pipeline, and their performance was evaluated using F1 scores. Manual Pfirrmann grading exhibited moderate agreement (κ = 0.455-0.565) among the clinicians, with higher exact match frequencies at lower lumbar levels. Single-grade discrepancies were prevalent except at L5/S1. Automated segmentation of IVDs using a pretrained U-Net model achieved an F1 score of 0.85, with a precision and recall of 0.83 and 0.88, respectively. Following 3D reconstruction of the automatically segmented IVD into a 3D point-cloud representation of the target intervertebral disc, the GNN model demonstrated moderate performance in Pfirrmann classification. The highest precision (0.81) and F1 score (0.71) were observed at L2/3, whereas the overall metrics indicated moderate performance (precision: 0.46, recall: 0.47, and F1 score: 0.46), with variability across spinal levels. The integration of CNN and GNN offers a new perspective for automating IVD analysis in MRI. Although the current performance highlights the need for further refinement, the moderate accuracy of the model, combined with its 3D visualization capabilities, establishes a promising foundation for more advanced grading systems.

Self-Perceived Lactose Intolerance Versus Confirmed Lactose Intolerance in Irritable Bowel Syndrome: A Systematic Review.

Disorders of gut-brain interaction (DGBI) are prevalent, affecting 20-40% of the population, with irritable bowel syndrome (IBS) being the most common and impactful. While congenital lactose intolerance is rare, lactase deficiency in adults is widespread, causing gastrointestinal symptoms like bloating and diarrhea. Self-perceived lactose intolerance often overestimates symptoms, impacting dietary choices and quality of life, necessitating better understanding and management for improved patient outcomes. This article evaluates the diagnostic accuracy of self-reported lactose intolerance in patients with lactose intolerance and IBS through a systematic review. A systematic literature search was conducted using PubMed, EMBASE, and SCOPUS, including terms related to IBS, lactose intolerance, and self-reported symptoms, without applying filters to ensure comprehensive coverage. Inclusion criteria focused on observational studies with adult participants diagnosed with lactose intolerance, addressing symptoms and lactose malabsorption, while excluding non-English articles, reviews, editorials, and studies involving pediatric subjects. The systematic review analyzed six studies with 845 participants, revealing significant variability and moderate accuracy in self-reported lactose intolerance for diagnosing actual lactose intolerance in IBS patients. Hydrogen breath tests (HBTs) showed that self-reported symptoms often led to false positives, underscoring the need for objective diagnostic tools and standardized criteria. The findings highlight the complexity of diagnosing lactose intolerance in IBS patients and suggest that lactose-free diets and routine HBT should not be recommended without clear indications. The rigorous selection process ensured the inclusion of high-quality, relevant studies, thereby enhancing the reliability and validity of the review's findings. These studies revealed that a lactose-free diet should not be routinely recommended for IBS patients, nor should the routine use of HBT to identify lactose malabsorption in this group. Future research should focus on better understanding the factors influencing lactose perception and tolerance, which is crucial for more effective management of lactose intolerance in IBS patients.

Remote and Proximal Sensors Data Fusion: Digital Twins in Irrigation Management Zoning.

The scientific field of precision agriculture employs increasingly innovative techniques to optimize inputs, maximize profitability, and reduce environmental impact. However, obtaining a high number of soil samples is challenging in order to make precision agriculture viable. There is a trade-off between the amount of data needed and the time and resources spent to obtain these data compared to the accuracy of the maps produced with more or fewer points. In the present study, the research was based on an exhaustive dataset of apparent electrical conductivity (aEC) containing 3906 points distributed along 26 transects with spacing between each of up to 40 m, measured by the proximal soil sensor EM38-MK2, for a grain-producing area of 72 ha in São Paulo, Brazil. A second sparse dataset was simulated, showing only four transects with a 400 m distance and, in the end, only 162 aEC points. The aEC map via ordinary kriging (OK) from the grid with 26 transects was considered the reference, and two other mapping approaches were used to map aEC via sparse grid: kriging with external drift (KED) and geographically weighted regression (GWR). These last two methods allow the increment of auxiliary variables, such as those obtained by remote sensors that present spatial resolution compatible with the pivot scale, such as data from the Landsat-8, Aster, and Sentinel-2 satellites, as well as ten terrain covariates derived from the Alos Palsar digital elevation model. The KED method, when used with the sparse dataset, showed a relatively good fit to the aEC data (R2 = 0.78), with moderate prediction accuracy (MAE = 1.26, RMSE = 1.62) and reasonable predictability (RPD = 1.76), outperforming the GWR method, which had the weakest performance (R2 = 0.57, MAE = 1.78, RMSE = 2.30, RPD = 0.81). The reference aEC map using the exhaustive dataset and OK showed the highest accuracy with an R2 of 0.97, no systematic bias (ME = 0), and excellent precision (RMSE = 0.56, RPD = 5.86). Management zones (MZs) derived from these maps were validated using soil texture data from clay samples measured at 0-10 cm depth in a grid of 72 points. The KED method demonstrated the highest potential for accurately defining MZs for irrigation, producing a map that closely resembled the reference MZ map, thereby providing reliable guidance for irrigation management.

Extent of resection and underlying liver disease influence the accuracy of the preoperative risk assessment with the American College of Surgeons Risk Calculator

BackgroundLiver surgery is associated with a significant risk of postoperative complications, depending on the extent of liver resection and the underlying liver disease. Therefore, adequate patient selection is crucial. This study aimed to assess the accuracy of the American College of Surgeons Risk Calculator (ACS-RC) by considering liver parenchyma quality and the type of liver resection. MethodsPatients who underwent open or minimally invasive liver resection for benign or malignant indications between January 2019 and March 2023 at the University Hospital Basel were included. Brier score and feature importance analysis were performed to investigate the accuracy of the ACS-RC. ResultsA total of 376 patients were included in the study, 214 (57%) who underwent partial hepatectomy, 89 (24%) who underwent hemihepatectomy, and 73 (19%) who underwent trisegmentectomy. Most patients had underlying liver diseases, with 143 (38%) patients having fibrosis, 75 patients (20%) having steatosis, and 61 patients (16%) having cirrhosis. The ACS-RC adequately predicted surgical site infection (Brier score of 0.035), urinary tract infection (Brier score of 0.038), and death (Brier score of 0.046), and moderate accuracy was achieved for serious complications (Brier score of 0.216) and overall complications (Brier score of 0.180). Compared with the overall cohort, the prediction was limited in patients with cirrhosis, fibrosis, and steatosis and in those who underwent hemihepatectomy and trisegmentectomy. The inclusion of liver parenchyma quality improved the prediction accuracy. ConclusionThe ACS-RC is a reliable tool for estimating 30-day postoperative morbidity, particularly for patients with healthy liver parenchyma undergoing partial liver resection. However, accurate perioperative risk prediction should be adjusted for underlying liver disease and extended liver resections.

Machine learning in paediatric haematological malignancies: a systematic review of prognosis, toxicity and treatment response models.

Machine Learning (ML) has demonstrated potential in enhancing care in adult oncology. However, its application in paediatric haematological malignancies is still emerging, necessitating a comprehensive review of its capabilities and limitations in this area. A literature search was conducted through Ovid. Studies included focused on ML models in paediatric patients with haematological malignancies. Studies were categorised into thematic groups for analysis. Twenty studies, primarily on leukaemia, were included in this review. Studies were organised into thematic categories such as prognoses, treatment responses and toxicity predictions. Prognostic studies showed AUC scores between 0.685 and 0.929, indicating moderate-high predictive accuracy. Treatment response studies demonstrated AUC scores between 0.840 and 0.875, reflecting moderate accuracy. Toxicity prediction studies reported high accuracy with AUC scores from 0.870 to 0.927. Only five studies (25%) performed external validation. Significant heterogeneity was noted in ML tasks, reporting formats, and effect measures across studies, highlighting a lack of standardised reporting and challenges in data comparability. The clinical applicability of these ML models remains limited by the lack of external validation and methodological heterogeneity. Addressing these challenges through standardised reporting and rigorous external validation is needed to translate ML from a promising research tool into a reliable clinical practice component. Key message: Machine Learning (ML) significantly enhances predictive models in paediatric haematological cancers, offering new avenues for personalised treatment strategies. Future research should focus on developing ML models that can integrate with real-time clinical workflows. Addition to literature: Provides a comprehensive overview of current ML applications and trends. It identifies limitations to its applicability, including the limited diversity in datasets, which may affect the generalisability of ML models across different populations. Encourages standardisation and external validation in ML studies, aiming to improve patient outcomes through precision medicine in paediatric haematological oncology.

Predictive value of perioperative NT-proBNP levels for acute kidney injury in patients with compromised renal function undergoing cardiac surgery: a case control study

BackgroundAcute kidney injury (AKI) significantly increases morbidity and mortality following cardiac surgery, especially in patients with pre-existing renal impairments. N-terminal pro-B-type natriuretic peptide (NT-proBNP) is a marker of cardiac stress and dysfunction, conditions often exacerbated during cardiac surgery and prevalent in chronic kidney disease (CKD) patients. Elevated NT-proBNP levels can indicate underlying cardiac strain, hemodynamic instability and volume overload. This study evaluated the association between perioperative changes in NT-proBNP levels and the incidence of AKI in this particular patient group.MethodsThis retrospective study involved patients with impaired renal function (eGFR 15–60 ml/min/1.73 m²) who underwent cardiac surgery from July to December 2022. It analyzed the association between the ratio of preoperative and ICU admittance post-surgery NT-proBNP levels and the development of AKI and AKI stage 2–3, based on KDIGO criteria, using multivariate logistic regression models. Restricted cubic spline analysis assessed non-linear associations between NT-proBNP and endpoints. Subgroup analysis was performed to assess the heterogeneity of the association between NT-proBNP and endpoints in subgroups.ResultsAmong the 199 participants, 116 developed postoperative AKI and 16 required renal replacement therapy. Patients with AKI showed significantly higher postoperative NT-proBNP levels compared to those without AKI. Decreased baseline eGFR and increased post/preoperative NT-proBNP ratios were associated with higher AKI risk. Specifically, the highest quantile post/preoperative NT-proBNP ratio indicated an approximately seven-fold increase in AKI risk and a ninefold increase in AKI stage 2–3 risk compared to the lowest quantile. The area under the receiver operating characteristic curve for predicting AKI and AKI stage 2–3 using NT-proBNP were 0.63 and 0.71, respectively, demonstrating moderate accuracy. Subgroup analysis demonstrated that the positive association between endpoints and logarithmic transformed post/preoperative NT-proBNP levels was consistently robust in subgroup analyses stratified by age, sex, surgery, CPB application, hypertension, diabetes status and fluid balance.ConclusionPerioperative NT-proBNP level changes are predictive of postoperative AKI in patients with pre-existing renal deficiencies undergoing cardiac surgery, aiding in risk assessment and patient management.