Concordance Correlation Research Articles

Volumetric Assessment of Traumatic Intracranial Hematomas: Is ABC/2 Reliable?

Accurate measurement of traumatic intracranial hematoma volume is important for assessing disease progression and prognosis, as well as for serving as an important end-point in clinical trials aimed at preventing hematoma expansion. While the ABC/2 formula has traditionally been used for volume estimation in spontaneous intracerebral hemorrhage, its adaptation to traumatic hematomas lacks validation. This study aimed to compare the accuracy of ABC/2 with computer-assisted volumetric analysis (CAVA) in estimating the volumes of traumatic intracranial hematomas. We performed a dual-center observational study that included adult patients with moderate-to-severe traumatic brain injury. Volumes of intracerebral, subdural (SDHs), and epidural hematomas from admission computed tomography scans were measured using ABC/2 and CAVA, and compared using the Wilcoxon signed-rank test, Spearman's rank correlation, Lin's concordance correlation coefficient (CCC), and Bland-Altman plots. Prognostic significance for outcomes was evaluated through logistic and linear regression models. In total, 1,179 patients with 1,543 hematomas were included. Despite a high correlation (Spearman coefficients between 0.95 and 0.98) and excellent concordance (Lin's CCC from 0.89 to 0.96) between ABC/2 and CAVA, ABC/2 overestimated hematoma volumes compared with CAVA, in some instances exceeding 50 ml. Bland-Altman analysis highlighted wide limits of agreement, especially in SDH. While both methods demonstrated comparable accuracy in predicting outcomes, CAVA was slightly better at predicting craniotomies and midline shift. We conclude that while ABC/2 provides a generally reliable volumetric assessment suitable for descriptive purposes and as baseline variables in studies, CAVA should be the gold standard in clinical situations and studies requiring more precise volume estimations, such as those using hematoma expansion as an outcome.

Applying the V.E.R.A. method to entheses of the humerus: An assessment of repeatability and reproducibility

AbstractThe “Validated Entheses‐based Reconstruction of Activity” (V.E.R.A.) method has proven to be a reliable method for the quantification and analysis of entheses. However, this method has only been successfully applied to human hand bones and animal long bones. This study tests the general applicability of the V.E.R.A. method to the human humerus, focusing on evaluating its reliability and repeatability. The sample included 23 humeri of unknown origin and background. The V.E.R.A. method was applied to six entheses of the humerus, comprising the subscapularis, supraspinatus, infraspinatus, teres minor, common extensor origin, and common flexor origin. Lin's concordance correlation coefficient (CCC) and percentage of error statistics were used to measure intraobserver error. Interobserver error was assessed through analysis of variance (ANOVA) tests, the intraclass correlation coefficient (ICC), and Lin's CCC. Intraobserver rates were between 1.83% and 3.23%. Interobserver error values were excellent, with no significant differences found in the ANOVA tests; Lin's CCC values were all above 0.90, with only the common extensor origin being 0.87; and ICC values were all above 0.97. Our results showed that the V.E.R.A. method is highly reliable and reproducible for the six entheses of the human humerus selected for this study. These results demonstrate the vast potential for the V.E.R.A. method to be applied to other parts of the human skeleton.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis.

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is a primary method for quantifying tar spot early in the season, as these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1) without the need for empirical search of the optimal Decision Making Input Parameters (DMIPs), while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar-spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image, and (ii) a pre-trained Convolutional Neural Network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we utilized datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1-score, linear regression, and Lin's concordance correlation), showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achievd 73.7% mean Dice values (overall accuracy), compared to 30.8% for SCDA v1. The enhanced F1-score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects.

Evaluation of left ventricular ejection fraction by a new automatic tool on a pocket ultrasound device: Concordance study with cardiac magnetic resonance imaging.

Assessment of left ventricular ejection fraction (LVEF) is one of the primary objectives of echocardiography. The gold standard assessment technique in emergency medicine is eyeballing. A new tool is now available on pocket ultrasound devices (PUD): automatic LVEF. The primary aim of this study was to evaluate the concordance between LVEF values estimated by automatic LVEF with PUD and by cardiac magnetic resonance imaging (MRI). This was a prospective, monocentric, and observational study. All adult patients with an indication for cardiac MRI underwent a point-of-care ultrasound. Blinded to the MRI results, the emergency physician assessed LVEF using the automatic PUD tool and by visual evaluation. Sixty patients were included and analyzed. Visual estimation of LVEF was feasible for all patients and automatic evaluation for 52 (87%) patients. Lin's concordance correlation coefficient between automatic ejection fraction with PUD and by cardiac MRI was 0.23 (95% CI, 0.03-0.40). Concordance between LVEF estimated by the automatic ejection fraction with PUD and LVEF estimated by MRI was non-existent.

German translation, cultural adaptation for Austria and validation of the Neurological Sleep Index - Multiple Sclerosis (NSI-MS).

To translate, culturally adapt, and validate the Neurological Sleep Index - Multiple Sclerosis (NSI-MS) for use in Austrian German-speaking populations with multiple sclerosis (pwMS). Following established guidelines, the NSI-MS diurnal sleepiness (DS), non-restorative nocturnal sleep (NRNS), and fragmented nocturnal sleep (FNS) scales underwent forward-backward translation, with content and face validity, and cultural adaptation to Austria established. Construct validity was evaluated using Rasch analysis. Known-groups validity was examined, and comparisons were made with scales measuring MS fatigue, daytime sleepiness, sleep quality, anxiety, and depression. Reliability was assessed through Cronbach's alpha, Person Separation Index, Lin's concordance correlation coefficient, measurement error, and floor and ceiling effects. Data were merged with a historic English dataset for comparison between English/German language versions. The translation and cultural adaptation of the NSI-MS-G were successful. Pretesting involved 30 pwMS, while the validation included 400 pwMS with mild-to-severe disability. The DS, NRNS, and FNS scales exhibited good fit parameters, were unidimensional, and invariant. NSI-MS-G scales demonstrated excellent convergent and known-groups validity, internal consistency, person separation reliability, test-retest reliability, adequate measurement error, and low floor and ceiling effects. Pooling English and German datasets revealed that person estimates for the NRNS and FNS scales are equivalent across versions, unlike the DS scale. The NSI-MS-G demonstrates validity, reliability, and responsiveness in assessing DS, NRNS, and FNS in pwMS, generating interval-level data, and shows equivalence between its English and German versions. Register: German Clinical Trials Register (DRKS); URL: https://drks.de/search/en/trial/DRKS00025573; Identifier: DRKS00025573.

Deep learning models for separate segmentations of intracerebral and intraventricular hemorrhage on head CT and segmentation quality assessment.

The volume measurement of intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) provides critical information for precise treatment of patients with spontaneous ICH but remains a big challenge, especially for IVH segmentation. However, the previously proposed ICH and IVH segmentation tools lack external validation and segmentation quality assessment. This study aimed to develop a robust deep learning model for the segmentation of ICH and IVH with external validation, and to provide quality assessment for IVH segmentation. In this study, a Residual Encoding Unet (REUnet) for the segmentation of ICH and IVH was developed using a dataset composed of 977 CT images (all contained ICH, and 338 contained IVH; a five-fold cross-validation procedure was adopted for training and internal validation), and externally tested using an independent dataset consisting of 375 CT images (all contained ICH, and 105 contained IVH). The performance of REUnet was compared with six other advanced deep learning models. Subsequently, three approaches, including Prototype Segmentation (ProtoSeg), Test Time Dropout (TTD), and Test Time Augmentation (TTA), were employed to derive segmentation quality scores in the absence of ground truth to provide a way to assess the segmentation quality in real practice. For ICH segmentation, the median (lower-quantile-upper quantile) of Dice scores obtained from REUnet were 0.932 (0.898-0.953) for internal validation and 0.888 (0.859-0.916) for external test, both of which were better than those of other models while comparable to that of nnUnet3D in external test. For IVH segmentation, the Dice scores obtained from REUnet were 0.826 (0.757-0.868) for internal validation and 0.777 (0.693-0.827) for external tests, which were better than those of all other models. The concordance correlation coefficients between the volumes estimated from the REUnet-generated segmentations and those from the manual segmentations for both ICH and IVH ranged from 0.944 to 0.987. For IVH segmentation quality assessment, the segmentation quality score derived from ProtoSeg was correlated with the Dice Score (Spearman r=0.752 for the external test) and performed better than those from TTD (Spearman r=0.718) and TTA (Spearman r=0.260) in the external test. By setting a threshold to the segmentation quality score, we were able to identify low-quality IVH segmentation results by ProtoSeg. The proposed REUnet offers a promising tool for accurate and automated segmentation of ICH and IVH, and for effective IVH segmentation quality assessment, and thus exhibits the potential to facilitate therapeutic decision-making for patients with spontaneous ICH in clinical practice.

Reliability and benefit of estimated continuous cardiac output measurement using shunt-side SpO2 monitor in hemodialysis.

Estimated continuous cardiac output (esCCO) is a novel technology that enables non-invasive and continuous monitoring of cardiac output. We compared the concordance in accuracies among esCCO measurements in the shunt limb and non-shunt limb. In this single-center prospective observational study, we include Japanese patients who underwent dialysis at our center between April 27, 2021, and February 28, 2023. Clinical accuracy of esCCO was evaluated in the shunted and non-shunted bilateral digits. Agreement between the measurements was analyzed using Lin's congruent correlation and Bland-Altman analysis. For 43 individuals, Lin's concordance correlation coefficient was 0.9887 (95% confidence interval of 0.9886-0.9887) indicating good agreement. The values of esCCO measured in the shunt and non-shunt limbs were compatible. The percentage errors for the 43 patients with arterio-venous fistula (AVF) or arterio-venous graft (AVG), 32 with AVF, and 11 with AVG were 9.3%, 9.3%, and 8.9%, respectively. esCCO could be used in shunt as well as non-shunt limbs during dialysis, allowing continuous and non-invasive hemodynamic monitoring.

Intraoperative zero-heat-flux thermometry overestimates nasopharyngeal temperature by 0.39°C: an observational study in patients undergoing congenital heart surgery.

During surgery for congenital heart disease (CHD) temperature management is crucial. Vesical (Tves) and nasopharyngeal (TNPH) temperature are usually measured. Whereas Tves slowly responds to temperature changes, TNPH carries the risk of bleeding. The zero-heat-flux (ZHF) temperature monitoring systems SpotOn™ (TSpotOn), and Tcore™ (Tcore) measure temperature non-invasively. We evaluated accuracy and precision of the non-invasive devices, and of Tves compared to TNPH for estimating temperature. In this prospective observational study in pediatric and adult patients accuracy and precision of TSpotOn, Tcore, and Tves were analyzed using the Bland-Altman method. Proportion of differences (PoD) and Lin´s concordance correlation coefficient (LCC) were calculated. Data of 47 patients resulted in sets of matched measurements: 1073 for TSpotOn vs. TNPH, 874 for Tcore vs. TNPH, and 1102 for Tves vs. TNPH. Accuracy was - 0.39°C for TSpotOn, -0.09°C for Tcore, and 0.07°C for Tves. Precisison was between - 1.12 and 0.35°C for TSpotOn, -0.88 to 0.71°C for Tcore, and - 1.90 to 2.05°C for Tves. PoD ≤ 0.5°C were 71% for TSpotOn, 71% for Tcore, and 60% for Tves. LCC was 0.9455 for TSpotOn, 0.9510 for Tcore, and 0.9322 for Tves. Temperatures below 25.2°C (TSpotOn) or 27.1 (Tcore) could not be recorded non-invasively, but only with Tves. Trial registration German Clinical Trials Register, DRKS00010720.

Quantitative metrics of bone quality determined at the distal radius using photon-counting CT.

To determine the accuracy of photon-counting-detector CT (PCD-CT) at deriving bone morphometric indices and demonstrate utility in vivo in the distal radius. Ten cadaver wrists were scanned using PCD-CT and high-resolution peripheral quantitative CT (HRpQCT). Correlation between PCD-CT and HRpQCT morphometric indices was determined. Agreement was assessed by Lin's concordance correlation coefficient (Lin's CCC). Wrist PCD-CTs of patients between 02/2022 and 08/2023 were also evaluated for clinical utility. Morphometric indices of the in vivo distal radii were extracted and compared between patients with or without osteoporosis. In cadavers, strong correlation between PCD-CT and HRpQCT was observed for cortical thickness (Spearman correlation, ρ, 0.85), trabecular spacing (ρ = 0.98), and trabecular bone volume fraction (ρ = 0.68). Moderate negative correlation (ρ = - 0.49) was observed for trabecular thickness. PCD-CT shows good agreement to HRpQCT for cortical thickness, trabecular spacing, and trabecular bone volume fraction (Lin's CCC = 0.80, 0.94, and 0.86, respectively) but poor agreement (Lin's CCC = - 0.1) for trabecular thickness. In forty participants (31 adults and 9 pediatric), bone morphometrics indices for cortical thickness, trabecular thickness, trabecular spacing, and trabecular bone volume fraction were 0.99mm (IQR, 0.89-1.06), 0.38mm (IQR, 0.25-0.40), 0.82mm (IQR, 0.72-1.05), and 0.28 (IQR, 0.25-0.33), respectively. Patients with osteoporosis had statistically significantly larger trabecular spacing (p = 0.025) and lower trabecular volumetric bone mineral density (p = 0.042). This study demonstrates the agreement of PCD-CT to HRpQCT in cadavers of most cortical and bone morphometrics examined and provide in vivo quantitative metrics of bone microarchitecture from routine clinical PCD-CT images of the distal radius.

Deep learning-based automated angle measurement for flatfoot diagnosis in weight-bearing lateral radiographs

This study aimed to develop and evaluate a deep learning-based system for the automatic measurement of angles (specifically, Meary’s angle and calcaneal pitch) in weight-bearing lateral radiographs of the foot for flatfoot diagnosis. We utilized 3960 lateral radiographs, either from the left or right foot, sourced from a pool of 4000 patients to construct and evaluate a deep learning-based model. These radiographs were captured between June and November 2021, and patients who had undergone total ankle replacement surgery or ankle arthrodesis surgery were excluded. Various methods, including correlation analysis, Bland–Altman plots, and paired T-tests, were employed to assess the concordance between the angles automatically measured using the system and those assessed by clinical experts. The evaluation dataset comprised 150 weight-bearing radiographs from 150 patients. In all test cases, the angles automatically computed using the deep learning-based system were in good agreement with the reference standards (Meary’s angle: Pearson correlation coefficient (PCC) = 0.964, intraclass correlation coefficient (ICC) = 0.963, concordance correlation coefficient (CCC) = 0.963, p-value = 0.632, mean absolute error (MAE) = 1.59°; calcaneal pitch: PCC = 0.988, ICC = 0.987, CCC = 0.987, p-value = 0.055, MAE = 0.63°). The average time required for angle measurement using only the CPU to execute the deep learning-based system was 11 ± 1 s. The deep learning-based automatic angle measurement system, a tool for diagnosing flatfoot, demonstrated comparable accuracy and reliability with the results obtained by medical professionals for patients without internal fixation devices.

Developing mapping algorithms to predict EQ-5D health utility values from Bath Ankylosing Spondylitis Disease Activity Index and Bath Ankylosing Spondylitis Functional Index among patients with Ankylosing Spondylitis

BackgroundPreference-based measures of health-related quality of life (HRQoL), such as the EQ-5D or the SF-6D, are essential for health economic evaluation. However, they are rarely included in clinical trials of ankylosing spondylitis (AS). This study aims to develop mapping algorithms to predict EQ-5D-3L and EQ-5D-5L health utility scores from the Bath Ankylosing Disease Activity Index (BASDAI) and the Bath Ankylosing Spondylitis Functional Index (BASFI).MethodsPatients with AS were recruited from the largest tertiary hospital in Shandong province, China, between December 2019 and October 2020. Patients were selected by convenience sampling method according to the following criteria: (1) diagnosed with AS according to the New York criteria; (2) aged 18 years and above; and (3) without mental disorders; (4) able to understand the questionnaires; (5) without serious complications. There were 243 patients who completed the face-to-face questionnaire survey, and 5 cases with missing values in key variables were excluded. Ordinary least squares, censored least absolute deviations, Tobit, adjusted limited dependent variable mixture model and beta-mixture model (BM) in the direct approach and ordered logit and multinomial logit (Mlogit) model in the response approach were used to develop mapping algorithms. Mean absolute error, root mean square error, Spearman’s correlation coefficient and concordance correlation coefficient were used to access predictive performance.ResultsThe 238 patients with AS had a mean age of 35.19 (SD = 9.59) years, and the majority (74.47%) were male. The observed EQ-5D-3L and EQ-5D-5L health utility values were 0.88 (SD = 0.12) and 0.74 (SD = 0.27), respectively. The EQ-5D-5L had higher conceptual overlap with the BASDAI and BASFI than the EQ-5D-3L did. The Mlogit was the best-performing model for the EQ-5D-3L, and the BM showed better performance in predicting EQ-5D-5L than other direct and indirect mapping models did.ConclusionThis study demonstrates that the EQ-5D-5L, rather than EQ-5D-3L, should be selected as the target outcome measure of HRQoL in patients with AS in China, and the BM mapping algorithm could be used to predict EQ-5D-5L values from BASDAI and BASFI for health economic evaluation.

68 Use of artificial intelligence to derive International Metastatic Renal Cell Carcinoma Database Consortium (IMDC) elements from unstructured medical records

Abstract Background Artificial intelligence technologies invoking large language models (LLMs) may be able to automate data collection for the IMDC registry, an otherwise labor-intensive process. We evaluate a proprietary tool (HopeLLM) in expediting data abstraction. Methods We utilized a City of Hope-managed IMDC data set that includes patients with metastatic renal cell carcinoma. From this data set, we randomly selected patients who initiated care after 2018 and had sufficient treatment-related information within the Epic electronic health record system to determine HopeLLM performance. Patient identification numbers were manually extracted to prompt HopeLLM for data abstraction. We compared treatment start and end dates between manually registered information and HopeLLM estimations. The difference ratio in months was compared between the two sources. Lin’s concordance correlation coefficient was performed to quantify the rate of agreement between both sources. Results Among 513 records, 91 patients were randomly selected. A total of 164 lines of treatment were recorded manually in the registry, and 146 were recorded by HopeLLM. A total of 75 lines of treatment were unique to the registry, while 42 were unique to HopeLLM. There were 117 unmatched lines of treatment between the registry and HopeLLM, which were not considered for concordance analysis. We recorded a difference (median (IQR)) of 0 mos (0-0.09 mos) for start dates between the registry and HopeLLM, with a concordance correlation coefficient of 0.99 (95%CI 0.99-0.99). We recorded a difference of 2.15 mos (0.46-5.54 mos) for end dates between the registry and HopeLLM, with a concordance correlation coefficient of 0.92 (95%CI 0.88-0.95). Conclusions HopeLLM can streamline data abstraction from unstructured medical records onto the IMDC database, as it accurately predicts treatment start and end dates for patients with metastatic renal cell carcinoma.

Fast model calibration for predicting the response of breast cancer to chemotherapy using proper orthogonal decomposition

Constructing digital twins for predictive tumor treatment response models can have a high computational demand that presents a practical barrier for their clinical adoption. In this work, we demonstrate that proper orthogonal decomposition, by which a low-dimensional representation of the full model is constructed, can be used to dramatically reduce the computational time required to calibrate a partial differential equation model to magnetic resonance imaging (MRI) data for rapid predictions of tumor growth and response to chemotherapy. In the proposed formulation, the reduction basis is based on each patient’s own MRI data and controls the overall size of the “reduced order model”. Using the full model as the reference, we validate that the reduced order mathematical model can accurately predict response in 50 triple negative breast cancer patients receiving standard of care neoadjuvant chemotherapy. The concordance correlation coefficient between the full and reduced order models was 0.986 ± 0.012 (mean ± standard deviation) for predicting changes in both tumor volume and cellularity across the entire model family, with a corresponding median local error (inter-quartile range) of 4.36 % (1.22 %, 15.04 %). The total time to estimate parameters and to predict response dramatically improves with the reduced framework. Specifically, the reduced order model accelerates our calibration by a factor of (mean ± standard deviation) 378.4 ± 279.8 when compared to the full order model for a non-mechanically coupled model. This enormous reduction in computational time can directly help realize the practical construction of digital twins when the access to computational resources is limited.

Fully Automatic Quantitative Measurement of Equilibrium Radionuclide Angiocardiography Using a Convolutional Neural Network.

The aim of this study was to generate deep learning-based regions of interest (ROIs) from equilibrium radionuclide angiography datasets for left ventricular ejection fraction (LVEF) measurement. Manually drawn ROIs (mROIs) on end-systolic and end-diastolic images were extracted from reports in a Picture Archiving and Communications System. To reduce observer variability, preprocessed ROIs (pROIs) were delineated using a 41% threshold of the maximal pixel counts of the extracted mROIs and were labeled as ground-truth. Background ROIs were automatically created using an algorithm to identify areas with minimum counts within specified probability areas around the end-systolic ROI. A 2-dimensional U-Net convolutional neural network architecture was trained to generate deep learning-based ROIs (dlROIs) from pROIs. The model's performance was evaluated using Lin's concordance correlation coefficient (CCC). Bland-Altman plots were used to assess bias and 95% limits of agreement. A total of 41,462 scans (19,309 patients) were included. Strong concordance was found between LVEF measurements from dlROIs and pROIs (CCC = 85.6%; 95% confidence interval, 85.4%-85.9%), and between LVEF measurements from dlROIs and mROIs (CCC = 86.1%; 95% confidence interval, 85.8%-86.3%). In the Bland-Altman analysis, the mean differences and 95% limits of agreement of the LVEF measurements were -0.6% and -6.6% to 5.3%, respectively, for dlROIs and pROIs, and -0.4% and -6.3% to 5.4% for dlROIs and mROIs, respectively. In 37,537 scans (91%), the absolute LVEF difference between dlROIs and mROIs was <5%. Our 2-dimensional U-Net convolutional neural network architecture showed excellent performance in generating LV ROIs from equilibrium radionuclide angiography scans. It may enhance the convenience and reproducibility of LVEF measurements.

Impacts of heat stress on the accuracy of an ear-tag accelerometer for monitoring rumination and eating behavior in dairy-beef cross cattle using an automated gold standard

Accelerometer-based technologies can be utilized for precision monitoring of feeding behaviors, but limited information is available regarding the impact of varying environmental conditions on sensor performance. The objective of this study was to determine if a commercially available ear-tag sensor (CM; CowManager SensOor, Agis Automatisering BV) could accurately quantify eating and rumination time under heat stress conditions. Data obtained from CM sensors was compared with data collected using an automated gold standard (RW; Rumiwatch System; Itin+Hoch). Automated measurements were obtained from 2 experiments in which cattle were exposed to heat stress conditions. In the principal study (Experiment 1), 3428 h of data were collected from 9 Holstein × Angus steers (470.9 ± 23.9 kg) subjected to either thermoneutral (TN; 21.0°C; 64.0% humidity; temperature-humidity index [THI] = 67; 12- and 12-h light and dark cycle; n = 1714 h), or heat stress conditions (HS; cyclical daily temperatures to mimic diurnal patterns; 0800 - 2000 h: 33.6°C, 40.0% RH, THI: 83.5; 2000 - 0800 h: 23.2°C, 70.0% RH; THI: 70.3; n = 1714 h). Data (n = 719 h) from 6 Holstein x Angus steers (487.9 ± 9.1 kg) were obtained from a subsequent experiment (Experiment 2) to confirm consistency of ear-tag accelerometer performance under elevated THI (HS conditions as described above). In Experiment 1, CM was capable of quantifying rumination time with high accuracy under TN conditions (concordance correlation coefficient [CCC]: 0.75 - 0.81). Overall, agreement between CM and the automated gold standard declined 6 - 7% during HS, which was most apparent later in the day when cattle had been subjected to HS for multiple hours (moderate agreement; CCC: 0.68). Accuracy for rumination time was also only moderate for data collected during Experiment 2 (CCC: 0.55 - 0.61). In contrast, CM reported total eating (eating with the head down + head up while masticating) time with moderate accuracy for TN (CCC: 0.53 - 0.54), only achieved negligible to low accuracy during HS (CCC: 0.39 - 0.44 [Experiment 1] and 0.17 - 0.34 [Experiment 2]). Sensor performance did improve when CM eating time was compared specifically to the time spent with the head down reported by RW; HS still negatively influenced sensor performance, however, with high agreement during TN (CCC: 0.72 - 0.73) but low to moderate agreement during HS (CCC: 0.65 - 0.69 [Experiment 1] and 0.40 - 0.58 [Experiment 2]). Results of this study suggest accuracy of ear-tag accelerometers may be impaired when cattle are subjected to heat stress.

Repeatability and reproducibility of deep learning features for lung adenocarcinoma subtypes with nodules less than 10 mm in size: a multicenter thin-slice computed tomography phantom and clinical validation study.

Deep learning features (DLFs) derived from radiomics features (RFs) fused with deep learning have shown potential in enhancing diagnostic capability. However, the limited repeatability and reproducibility of DLFs across multiple centers represents a challenge in the clinically validation of these features. This study thus aimed to evaluate the repeatability and reproducibility of DLFs and their potential efficiency in differentiating subtypes of lung adenocarcinoma less than 10 mm in size and manifesting as ground-glass nodules (GGNs). A chest phantom with nodules was scanned repeatedly using different thin-slice computed tomography (TSCT) scanners with varying acquisition and reconstruction parameters. The robustness of the DLFs was measured using the concordance correlation coefficient (CCC) and intraclass correlation coefficient (ICC). A deep learning approach was used for visualizing the DLFs. To assess the clinical effectiveness and generalizability of the stable and informative DLFs, three hospitals were used to source 275 patients, in whom 405 nodules were pathologically differentially diagnosed as GGN lung adenocarcinoma less than 10 mm in size and were retrospectively reviewed for clinical validation. A total of 64 DLFs were analyzed, which revealed that the variables of slice thickness and slice interval (ICC, 0.79±0.18) and reconstruction kernel (ICC, 0.82±0.07) were significantly associated with the robustness of DLFs. Feature visualization showed that the DLFs were mainly focused around the nodule areas. In the external validation, a subset of 28 robust DLFs identified as stable under all sources of variability achieved the highest area under curve [AUC =0.65, 95% confidence interval (CI): 0.53-0.76] compared to other DLF models and the radiomics model. Although different manufacturers and scanning schemes affect the reproducibility of DLFs, certain DLFs demonstrated excellent stability and effectively improved diagnostic the efficacy for identifying subtypes of lung adenocarcinoma. Therefore, as the first step, screening stable DLFs in multicenter DLFs research may improve diagnostic efficacy and promote the application of these features.

Center of Pressure Measurement Accuracy via Insoles with a Reduced Pressure Sensor Number during Gaits.

The objective was to compare simplified pressure insoles integrating different sensor numbers and to identify a promising range of sensor numbers for accurate center of pressure (CoP) measurement. Twelve participants wore a 99-sensor Pedar-X insole (100 Hz) during walking, jogging, and running. Eight simplified layouts were simulated, integrating 3-17 sensors. Concordance correlation coefficients (CCC) and root mean square errors (RMSE) between the original and simplified layouts were calculated for time-series mediolateral (ML) and anteroposterior (AP) CoP. Differences between layouts and between gait types were assessed via ANOVA and Friedman test. Concordance between the original and simplified layouts varied across layouts and gaits (CCC: 0.43-0.98; χ(7)2 ≥ 34.94, p < 0.001). RMSEML and RMSEAP [mm], respectively, were smaller in jogging (5 ± 2, 15 ± 9) than in walking (8 ± 2, 22 ± 4) and running (7 ± 4, 20 ± 7) (ηp2: 0.70-0.83, p < 0.05). Only layouts with 11+ sensors achieved CCC ≥ 0.80 in all tests across gaits. The 13-sensor layout achieved CCC ≥ 0.95 with 95% confidence, representing the most promising compromise between sensor number and CoP accuracy. Future research may refine sensor placement, suggesting the use of 11-13 sensors. For coaches, therapists, and applied sports scientists, caution is recommended when using insoles with nine or fewer sensors. Consulting task-specific validation results for the intended products is advisable.

Comparison of causes of stillbirth and child deaths as determined by verbal autopsy and minimally invasive tissue sampling.

In resource-limited settings where vital registration and medical death certificates are unavailable or incomplete, verbal autopsy (VA) is often used to attribute causes of death (CoD) and prioritize resource allocation and interventions. We aimed to determine the CoD concordance between InterVA and CHAMPS's method. The causes of death (CoDs) of children <5 were determined by two methods using data from seven low- and middle-income countries (LMICs) enrolled in the Child Health and Mortality Prevention Surveillance (CHAMPS) network. The first CoD method was from the DeCoDe panel using data from Minimally Invasive Tissue Sampling (MITS), whereas the second method used Verbal Autopsy (VA), which utilizes the InterVA software. This analysis evaluated the agreement between the two using Lin's concordance correlation coefficient. The overall concordance of InterVA4 and DeCoDe in assigning causes of death across surveillance sites, age groups, and causes of death was poor (0.75 with 95% CI: 0.73-0.76) and lacked precision. We found substantial differences in agreement by surveillance site, with Mali showing the lowest and Mozambique and Ethiopia the highest concordance. The InterVA4 assigned CoD agrees poorly in assigning causes of death for U5s and stillbirths. Because VA methods are relatively easy to implement, such systems could be more useful if algorithms were improved to more accurately reflect causes of death, for example, by calibrating algorithms to information from programs that used detailed diagnostic testing to improve the accuracy of COD determination.

Comparability analysis of the HNT-1P Huvitz non contact tonometer for the measurement of intraocular pressure.

To evaluate the diagnostic validity of the HNT-1P non-contact tonometer (Huvitz) as a tool for accurately measuring intraocular pressure (IOP) in patients with healthy eyes, compared to the Goldmann applanation tonometer (GAT), which is the Gold Standard method for measurement of IOP. Observational, descriptive, transversal study using 148 eyes of 74 healthy patients without a diagnosis of glaucoma or other ophthalmological diseases. Three measurements of IOP were taken in each eye, using three tonometers: HNT-1P, ICR100, and GAT. The median IOP (quartiles) and mean IOP (SD) its statistical significance were calculated, and comparisons were made between the mean and median IOP values found in three groups: GAT-HNT, GAT-ICR, and HNT-ICR. The difference in mean and median IOP was analyzed in each of the three study groups, and its statistical significance and concordance correlation coefficient (CCC) were calculated. The median IOP with HNT-1P was statistically significantly lower than the median IOP with GAT, (1.1 mmHg, p < 0.001). The median IOP with HNT-1P was also lower than the median IOP with ICR100. As an additional result, the median IOP with GAT was lower than the median IOP with ICR. The CCC was moderate for HNT-ICR (0.72) and low for GAT-HNT and GAT-ICR (0.43 and 0.38, respectively). HNT-1P (Huvitz) provides statistically significantly lower IOP values than those obtained with GAT. HNT-1P could be used for screening of ocular hypertension in postoperative patients. The IOP measurement obtained with HNT-1P should be confirmed with GAT. HNT-1P yields lower IOP values than those obtained with ICR.

Evaluating predictive equations for energy requirements throughout breast cancer trajectory: A comparative study

Background & AimsAccurately estimating resting energy requirements is crucial for optimizing energy intake, particularly in the context of patients with varying energy needs, such as individuals with cancer. We sought to evaluate the agreement between resting energy expenditure (REE) predicted by 40 equations and that measured by reference methods in women undergoing active breast cancer treatment stage (I-IV) and post-completion (i.e., survivors). MethodsData from 4 studies were combined. REE values estimated from 40 predictive equations identified by a systematic search were compared with REE assessed by indirect calorimetry (IC) using a metabolic cart (MC-REE N=46) or a whole-room indirect calorimeter (WRIC-REE N=44). Agreement between methods was evaluated using Bland-Altman and Lin's concordance coefficient correlation (Lin's CCC). Results90 participants (24 % survivors, 61.1% had early-stage breast cancer I or II, mean age: 56.8 ± 11 years; body mass index: 28.7 ± 6.4 kg/m2) were included in this analysis. Mean MC-REE and WRIC-REE values were 1389 ± 199 kcal/day and 1506 ± 247 kcal/day, respectively. Limits of agreement were wide for all equations compared to both MC and WRIC (∼ 300kcal for both methods), including the most commonly used ones, such as Harris-Benedict and Mifflin ST. Jeor equations; none had a bias within ±10% of measured REE, and all had low agreement per Lin's CCC analysis (< 0.90). The Korth equation exhibited the best performance against WRIC and the Lvingston-Kohlstadt equation against MC. Similar patterns of bias were observed between survivors and patients and between patients with stages I-III versus IV cancer. ConclusionMost equations failed to accurately predict REE at the group level, and none were effective at the individual level. This inaccuracy has significant implications for women with or surviving breast cancer, who may experience weight gain, maintenance, or loss due to inaccurate energy needs estimations. Therefore, our research underscores the need for further efforts to improve REE estimation.