Model Calibration Research Articles

Structural health monitoring of a curved roadway bridge: model calibration and collapse simulation aspects

Structural health monitoring of a curved roadway bridge: model calibration and collapse simulation aspects

Feasibility of low-cost particulate matter sensors for long-term environmental monitoring: Field evaluation and calibration

Low-cost sensor networks offer the potential to reduce monitoring costs while providing high-resolution spatiotemporal data on pollutant levels. However, these sensors come with limitations, and many aspects of their field performance remain underexplored. During October to December 2023, this study deployed two identical low-cost sensor systems near an urban standard monitoring station to record PM2.5 and PM10 concentrations, along with environmental temperature and humidity. Our evaluation of the monitoring performance of these sensors revealed a broad data distribution with a systematic overestimation; this overestimation was more pronounced in PM10 readings. The sensors showed good consistency (R2 > 0.9, NRMSE<5 %), and normalization residuals were tracked to assess stability, which, despite occasional environmental influences, remained generally stable. A lateral comparison of four calibration models (MLR, SVR, RF, XGBoost) demonstrated superior performance of RF and XGBoost over others, particularly with RF showing enhanced effectiveness on the test set. SHAP analysis identified sensor readings as the most critical variable, underscoring their pivotal role in predictive modeling. Relative humidity consistently proved more significant than dew point and temperature, with higher RH levels typically having a positive impact on model outputs. The study indicates that, with appropriate calibration, sensors can supplement the sparse networks of regulatory-grade instruments, enabling dense neighborhood-scale monitoring and a better understanding of temporal air quality trends.

External Validation and Further Exploration of Fall Prediction Models Based on Questionnaires and Daily-Life Trunk Accelerometry

Ambulatory measurements of trunk accelerations can provide valuable insight into the amount and quality of daily life activities. Such information has been used to create models to identify individuals at high risk of falls. However, external validation of such prediction models is lacking, yet crucial for clinical implementation. We externally validated 3 previously described fall prediction models. Complete questionnaires and 1-week trunk acceleration data were obtained from 263 community-dwelling people (mean age 71.8 years, 68.1% female). To validate models, we first used the coefficients and optimal cutoffs from the original cohort, then recalibrated the original models, as well as optimized parameters based on our new cohort. Among all participants, 39.9% experienced falls during a 6-month follow-up. All models showed poor precision (0.20-0.49), poor sensitivity (0.32-0.58), and good specificity (0.45-0.89). Calibration of the original models had limited effect on model performance. Using coefficients and cutoffs optimized on the external cohort also had limited benefits. Lastly, the odds ratios in our cohort were different from those in the original cohort, which indicated that gait characteristics, except for the index of harmonicity ML (medial-lateral direction), were not statistically associated with falls. Fall risk prediction in our cohort was not as effective as in the original cohort. Recalibration as well as optimized model parameters resulted in a limited increase in accuracy. Fall prediction models are highly specific to the cohort studied. This highlights the need for large representative cohorts, preferably with an external validation cohort.

Calibration of soil and water assessment model for its potential impact on climate change

Calibration of soil and water assessment model for its potential impact on climate change

Parameter calibration of discrete element model for gluten densification molding.

The densified powder material is convenient for storage and transportation, with broad market application prospects. In this study, the discrete element model parameters required for simulating gluten densification were calibrated using the Hertz-Mindlin with JKR contact model. Initially, physical testing techniques were utilized to assess the size distribution, density, and angle of repose (AoR) of gluten particles. Following this, the Plackett-Burman test, the steepest ascent test, and the Box-Behnken test were conducted, and the significant factors were obtained: The coefficient of rolling friction (P-P) was 1.038, the coefficient of static friction (P-P) was 0.071, and the surface energy (P-P) was 0.047. Finally, the AoR and densification simulations were performed under the optimal parameter combination, along with validation tests. The results showed that the relative error between the simulated and tested AoR was 0.52%. The compression ratio and compression force curves of simulated and actual were similar.

Prediction of CCL2 in breast cancer based on enhanced MRI radiomics model with integrated bioinformatics analysis and machine learning.

e12509 Background: Breast cancer is the most common malignant tumor in women. According to the 2023 Cancer Statistics Report, breast cancer has surpassed lung cancer to become the most common malignant tumor. Its incidence and mortality both rank first among female malignant tumors. This study proposes non-invasive prediction of CCL2 mRNA expression in breast cancer tissue through enhanced MRI radiomics, while integrating bioinformatics analysis to explore the underlying molecular mechanisms and their association with the immune microenvironment. Methods: Excluding criteria were applied to select primary solid tumor samples with RNA-seq data (n = 840) from the TCGA-BRCA database. Enhanced MRI imaging data (n = 98) intersecting with the TCGA-BRCA data were obtained from TCIA-BRCA. The imaging data were randomly divided into training (n = 70) and testing sets (n = 28) in a 7:3 ratio. A feature subset was selected, and a model was constructed using the support vector machine (SVM) algorithm in the training set. The predictive performance of the model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and the Hosmer-Lemeshow goodness-of-fit test. The calibration of the radiomics prediction model was assessed using the Brier score, and the clinical utility of the radiomics prediction model was demonstrated by drawing decision curves (DCA). External validation of the model was performed using a validation set. The radiomics score (RS) was calculated using the LR radiomics model and categorized as a binary variable (Low/High RS). Subsequently, KEGG pathway, immune-related genes, and gene mutation analysis were conducted based on the CCL2 high and low expression levels. Results: A total of 1810 radiomic features were obtained with ICC values ≥ 0.75. Subsequently, the mRMR (Maximum relevance, minimum redundancy) method, and the optimal 7 feature subsets were further identified using the RFE (Recursive feature elimination) algorithm. The SVM model demonstrated favorable predictive performance, with an AUC value of 0.822 for the training set and 0.779 for the validation set, as indicated by the ROC curve. Calibration curve and Hosmer-Lemeshow goodness-of-fit test revealed good consistency between the radiomic predictive model for the probability of high gene expression and the actual values (P &gt; 0.05). Additionally, the decision curve analysis (DCA) demonstrated high clinical utility of the model. The TNF-α signaling pathway was found to influence the occurrence and development of breast cancer. Furthermore, the degree of Plasma Cell infiltration was observed to be highest in breast cancer. Conclusions: The CCL2 model constructed using a combination of machine learning and radiomic features, can non-invasively predict the prognosis of breast cancer treatment and exhibits good generalizability.

Accelerated aging among survivors of childhood leukemia and lymphoma: Estimates of early onset and excess morbidity from the COMPASS model.

10028 Background: Cohort studies have detected an increased risk of accelerated aging among survivors of childhood cancer but the timing and magnitude are not known. Methods: To predict the clinical course of diseases of aging— cancer and cardiovascular disease — among survivors of childhood leukemia and lymphoma compared to the general population, we developed the Cancer Outcomes Microsimulation: Pediatric and Adolescent SurvivorShip (COMPASS) model. The model simulates 8 severe, disabling or life-threatening chronic health conditions (CHCs), including 4 subsequent cancers (breast, colorectal, glial tumors, sarcomas) and 4 cardiovascular diseases (heart failure, myocardial infarction/coronary artery disease, valvular disease, stroke), and excess mortality risks among survivors diagnosed between 1970 and 1999 over the course of their lifetimes. Treatment-related risks varied by patient characteristics (sex, age at diagnosis, diagnosis) and treatment exposures (chemotherapy, radiation dose) and were based on data from the Childhood Cancer Survivor Study (CCSS). Age-related risks and competing mortality were based on national databases (SEER, NHLBI, CDC Wonder). We used model calibration to identify parameter sets that generated outcomes consistent with observed data. Model outcomes included cumulative CHC risk. For comparisons to the general population, age-, sex, and diagnosis year-matched individuals who faced only age-related risks were simulated. Results: Among survivors representative of CCSS participants, the model estimated that 45% of leukemia and 65% of lymphoma survivors will develop at least 1 of the 8 CHCs by age 65. Compared to the estimated 20% cumulative risk for the general population, this represented a two- to three-fold excess morbidity risk among survivors. The age at which 20% of survivors developed at least 1 CHC was 51 years for leukemia and 42 years for lymphoma, suggesting an early onset of 14 and 21 years compared to the general population. Outcomes varied by diagnosis and treatment era due to competing risk changes. Among leukemia survivors diagnosed in the 1990s vs. 1970s, cumulative late recurrence mortality by age 40 (11% to 1%) declined. This combined with a reduction in radiation exposure (79% to 24%) resulted in a greater proportion living into adulthood and developing CHCs by age 65 (38% to 48%). In contrast, among lymphoma survivors, the proportion projected to develop a CHC by age 65 remained stable during the same period (62% to 65%) as late recurrence mortality risk declined (8% to 1%), but almost half still received radiation (90% to 49%). Conclusions: Despite improvements in therapy, leukemia and lymphoma survivors are projected to experience CHC early onset and excess morbidity, underscoring the importance of prevention-focused survivorship care and continued efforts to develop more targeted therapies.

Estimating risk for pancreatic cancer among 9.4 million veterans in care.

10544 Background: Screening for pancreatic ductal adenocarcinoma (PDAC) has focused on individuals with a hereditary component, accounting for only 10% of PDAC events. Using the electronic health record, we developed a PDAC risk prediction model in a general population in the Veterans Health Administration (VA), the largest integrated health system in the US. Methods: We included all individuals from 2002- 2021 with ≥1 inpatient or outpatient VA encounter and recorded race, starting follow-up 1.5 years after first VA encounter. We excluded those who developed PDAC before start of follow-up. We used the multivariable Cox proportional hazards model in the derivation dataset (random 70% of cohort) to estimate the coefficients associated with each predictor for our outcome, time to PDAC (3 and 10 years), censoring at loss to follow-up or 12/31/2021. Candidate predictors included age, gender, race/ethnicity, sex, BMI, smoking status, alcohol use (alcohol use/related disorders and AUDIT-C), diabetes, pancreatitis, Hepatitis C, HIV, liver disease, cholecystectomy, pancreatic cysts, Charlson comorbidity index and common laboratory values. Selection of predictors was based on clinical reasoning, extent of missing values and model fit (Akaike Information Criterion and Harrell’s c–statistic). We evaluated model discrimination using c – statistic and model calibration comparing observed Kaplan – Meier estimated incidence vs. predicted risk score. Results: Among 9.4 million individuals, we observed 19,839 cases of PDAC within 10 years (6,022 cases within 3 years). Median baseline age was 58.5 years, 75.0% were White, and 16.3% were Black. Final predictors included age, gender, smoking, alcohol use (alcohol use/related disorders and AUDIT-C), BMI, diabetes, pancreatitis, pancreatic cyst, and history of cancer (Table, c-statistic in the derivation cohort 3 years: 0.79; 10 years: 0.77). Ten-year risk ranged maximally from 0-5.5%. Preliminary studies suggest labs do not clinically improve model performance. Conclusions: We developed a novel prediction model using available clinical data in a general population that identifies PDAC with high accuracy. Future work will try to identify additional predictors to improve the range of risk predicted. We will validate our findings in the testing set and in external cohorts. [Table: see text]

On the model uncertainties for the predicted muon content of extensive air showers

Motivated by the excess of the muon content of cosmic ray induced extensive air showers (EAS), relative to EAS modeling, observed by the Pierre Auger Observatory, and by the tension between Auger data and air shower simulations on the maximal muon production depth Xmaxμ, we investigate the possibility to modify the corresponding EAS simulation results, within the Standard Model of particle physics. We start by specifying the kinematic range for secondary hadron production, which is of relevance for such predictions. We further investigate the impact on the predicted EAS muon number and on Xmaxμ of various modifications of the treatment of hadronic interactions, in the framework of the QGSJET-III model, in particular the model calibration to accelerator data, the amount of the “glue” in the pion, and the energy dependence of the pion exchange process. None of the considered modifications of the model allowed us to enhance the EAS muon content by more than 10%. On the other hand, for the maximal muon production depth, some of the studied modifications of particle production give rise up to ∼10 g/cm2 larger Xmaxμ values, which increases the difference with Auger observations.

Rapid and non-destructive prediction of moisture content on intact gayo coffee beans using near infrared spectroscopy

Abstract Presented work explores the potential of Near-Infrared Spectroscopy (NIRS) as a rapid, non-destructive analytical method for predicting moisture content in intact Gayo coffee beans. The moisture content is an essential parameter affecting the quality, processing, and shelf life of coffee beans. While conventional moisture determination techniques involve invasive procedures and considerable time, NIRS emanates as an innovative technique offering non-invasive, swift analysis. Using a robust representative selection of Gayo coffee bean samples, we acquired numerous spectra and employed multivariate analysis to construct a calibration model correlating the spectral data with reference moisture values. The initial results exhibit a high correlation coefficient (r) of 0.93 and ratio prediction to deviation (RPD) index of 3, suggesting that the NIRS technique can effectively predict the moisture content within the beans. This research underpins the potential usage of NIRS which, if validated through further testing, could transform quality control operations in the coffee industry by offering a real-time, non-destructive approach for moisture content determination.

Strategies for multivariate characterization and classification of pulps and papers by near-infrared spectroscopy

BackgroundMultivariate calibration by Partial Least Squares (PLS) on near-infrared data has been applied successfully in several industrial sectors, including pulp and paper. The creation of multivariate calibration models relies on a set of well-characterised samples that cover the range of the intended application. However, sample sets that originate from an industrial process often show an uneven distribution of reference values. This can be addressed by curation of the reference data and the methodology for multivariate calibration. It needs to be better understood, how these approaches affect the quality and scope of the final model. ResultsWe describe the effect of log10 transformation of the reference values, regular PLS, robust PLS, the newly introduced bin PLS, and their combinations to select more evenly distributed reference values for the quantification of five pulp characteristics (kappa number, R18, R10, cuen viscosity, and brightness; 200 samples) by near-infrared spectroscopy. The quality of the models was assessed by root mean squared error of prediction, calibration range, and coverage of sample types. The best models yielded uncertainty levels equivalent to that of the reference measurement. The optimal approach depended on the investigated reference value. SignificanceRobust PLS commonly gives the model with the lowest error, but this usually comes at the cost of a notably reduced calibration range. The other approaches rarely impacted the calibration range. None of them stood out as superior; their performance depended on the calibrated parameter. It is therefore worthwhile to investigate various calibration options to obtain a model that matches the requirements of the application without compromising calibration range and sample coverage.

Comparative Study of Low Flow Frequency Analysis Using Bivariate Copula Model at Soyanggang Dam and Chungju Dam

A univariate analysis that relies solely on precipitation data in low flow frequency analysis is a technique to express meteorological drought, so it is limited to analyzing the characteristics of hydrological drought related to available water resources. In addition, if the data for the model calibration are insufficient, the uncertainty of a single variable limits the construction of a reliable model. To improve this problem, a frequency analysis was performed by constructing a bivariate copula model as a multivariate model with a high correlation between variables targeting reservoir inflows. The methodology utilizes the theory of runs to identify low flow events, establishing a threshold based on the mandatory regional water supply plan, and determining the low flow duration and cumulative water deficit. The Gumbel copula function, effective in capturing correlations between hydrological variables, was applied to derive a joint bivariate probability distribution, facilitating the calculation of combined low flow event return periods. This study compared low flow frequencies at Soyanggang dam (’74–’22) and Chungju dam (’86–‘22), which are in the same Han River basin but have different capacities and water demands, using a bivariate copula model. The top four extreme low flow events for the two adjacent dam basins did not occur in the same year and, in the years of the extreme low flow events at one of the two dam basins, there was an insignificant magnitude at the remaining dam basin. This result is noteworthy because it shows that the possibility of extreme low flow events appearing simultaneously in both watersheds is not as high as expected. The operational efficiency can be improved by setting the coordinated operation rules of the two reservoirs using the copula dependency structure.

A lightweight holographic imager for cloud microphysical studies from an untethered balloon

Abstract. We describe the construction and testing of an in situ cloud particle imager based on digital holography. The instrument was designed to be low cost and lightweight for vertical profiling of clouds with an untethered weather balloon. This capability is intended to address the lack of in situ cloud microphysical observations that are required for improving the understanding of cloud processes, calibration of climate and weather models, and validation of remote sensing observation methods. From a balloon sounding through multiple bands of cloud, we show that we can retrieve shape information and size distributions of the cloud particles as a function of altitude. Microphysical retrievals from an imaging satellite are compared to these in situ observations, and significant differences are identified, consistent with those identified in prior evaluation campaigns.

Vertical load distribution in precast hollow core floors: State of the art and future perspectives

AbstractPrecast prestressed hollow core (HC) floors are widely used in various applications within the construction sector. Such floors are usually designed as single, simply supported elements, although it is known that individual elements forming the floor interact with each other. This article presents the state of the art regarding load redistribution in HC floors in the light of experimental data, current analytical models and code provisions. While this phenomenon is widely known and recognized, only sparse, and often poorly documented experimental data are available, which represent the basis for the assessment and calibration of analytical models. Moreover, even though the available models and code provisions share similar assumptions, their outcomes are in some cases conflicting. Having recognized the existing knowledge gap, the authors outline future perspectives for the development of consistent analytical and numerical approaches supplemented by new experimental data.

POE-Based Error Modeling and Multiple Plane Constraint-Based Parameter Identification for the Kinematic Calibration of a 4-UPS/SPR Parallel External Fixator

Limb deformity is a common complaint in orthopedic surgery. Currently, gradual treatment using parallel external fixator (PEF) has become the preferred option for deformity correction. As the key medical apparatus with the special application properties of temporary assembly and direct utilization, the geometric errors generated during the manufacturing and assembly process of the PEF contribute to the post-correction residual and iatrogenic deformities. However, considering the complexity of clinical scenarios, there is a lack of an applicable solution to reduce the effect of the above error source of PEF. To overcome these problems, taking a 4-UPS/SPR PEF as the research object, this paper proposes a novel kinematic calibration method. First, the error model with the features of completeness, continuity, and minimality is first established based on the product of exponentials (POE) formula. Then, the identifiability analysis is conducted to eliminate the redundant error parameters and ensure the stability and accuracy of the iterative calculation in the process of parameter identification. Furthermore, a multiple plane constraint (MPC)-based parameter identification approach is introduced to the calibration task of the PEF to effectively reduce the difficulty of the pose information measurement in the current cost-effective constraint calibration method. Finally, the simulation and prototype experiments validate that the proposed calibration method (i.e., the combination of the POE-based error model and the MPC-based parameter identification approach) can accomplish the calibration tasks in clinical applications and meet the cost-effectiveness and efficiency requirements.

A modified linear-elastic model for calibration of resonant column devices accommodating drive system compliance

Measurements of small-strain shear modulus of soils and rocks using the resonant column apparatus are highly dependent on accurate physical characterisation of the apparatus's drive components. This is typically achieved via a calibration exercise, yet it is widely reported that existing interpretation methods yield physical properties which vary with frequency, complicating subsequent interpretation of test data. Previous research has indicated that much of this apparent frequency dependency occurs due to compliance of the drive system. In this study the linear elastic model of the resonant column apparatus is adapted to include a new drive stiffness parameter, supported by finite element analysis of the drive system. A novel calibration method is presented based on this drive compliance model. Thirteen calibration bars and three added masses are used to conduct an extensive calibration exercise for both a Hardin- and Stokoe-type resonant column apparatus. The novel calibration method is compared with three existing methods in the literature. Limitations of the four methods are identified and discussed. The drive compliance model and its associated calibration method is shown to be a robust means of characterising the apparatus behaviour whilst successfully eliminating frequency-dependency of the calibration parameters. The model is valid where total system damping is small and is particularly valuable when testing stiff specimens where common apparatus assumptions may not apply.

Performance Evaluation of AquaCrop Model of Tomato under Stage Wise Deficit Drip Irrigation at Southern Ethiopia

Crop modeling is a powerful tool for predicting yield and water productivity. The aim of the study was to calibrate and validate the AquaCrop model for tomato under staged deficit drip irrigation in Ethiopia. The AquaCrop model was calibrated and validated by using the observed data of canopy cover, biomass, dry yield, and soil water content. The results showed that the model was accurate in predicting canopy cover, biomass, and dry yield under different water levels. The overall performance in simulating canopy cover of AquaCrop, biomass, and soil water content showed a good match between measured and simulated data. The calibration results indicated good performance on canopy cover with 0.96 ≤ r ≤ 1.00, 2.9% ≤ RMSE ≤ 8.0%, 7.5% ≤ CV (RMSE) ≤ 21.1%, 0.91 ≤ EF ≤ 0.99, and 0.98 ≤ d ≤ 1.00. On biomass, the model calibration values were 0.99 ≤ r ≤ 1.00, 0.3 t/ha ≤ RMSE ≤ 0.8 t/ha, 8.3% ≤ CV (RMSE) ≤ 25.2%, 0.92 ≤ EF ≤ 0.99, and 0.98 ≤ d ≤ 1.00. Soil water content displayed poor performance on calibration, with performance values of 0.54 ≤ r ≤ 0.82, 3.6 mm ≤ RMSE ≤ 24.4 mm, 1.30% ≤ CV (RMSE) ≤ 9.00%, −4.18 ≤ EF ≤ 0.00, and 0.66 ≤ d ≤ 0.81. The validation results demonstrated that the model performed well on canopy cover with 0.96 ≤ r ≤ 1.00, 3.1% ≤ RMSE ≤ 7.7%, 8.2% ≤ CV (RMSE) ≤ 20.8%, EF ≥ 0.91, and d ≥ 0.9. The model validation correctly predicted biomass with r ≥ 0.98, 0.3 t/ha ≤ RMSE ≤ 0.7 t/ha, 8.9% ≤ CV (RMSE) ≤ 21.8%, EF ≥ 0.94, and d ≥ 0.98. The model validation poorly performed in forecasting soil water content, 0.20 ≤ r ≤ 0.80, 10.2 t/ha ≤ RMSE ≤ 24.0 t/ha, 3.5% ≤ CV (RMSE) ≤ 9.0%, −22.76 ≤ EF ≤ 0.63, and 0.40 ≤ d ≤ 0.87. The AquaCrop model is easy to use, requires less input data, and has high simulation accuracy, making it a useful tool for predicting crop yields and water productivity under staged deficit irrigation in areas with limited data.

Use of Constant-Analyte Samples in Updating Quantitative Near-Infrared Calibration Models for Physiological Levels of Glucose

Updating procedures were investigated for multivariate calibration models for physiological levels of glucose in aqueous samples based on near-infrared spectroscopy. The methodology evaluated used samples with constant glucose concentrations collected on the prediction day to augment previously collected calibration spectra for the purpose of computing an updated model for use only on that day. Models were based on partial-least squares (PLS) regression in conjunction with spectral preprocessing using direct orthogonal signal correction (DOSC). The use of constant-analyte samples allowed the procedure to be compatible with samples collected at the beginning of a chemical reaction or from a fasting patient in a blood glucose monitoring application. The methodology was tested with nine sets of prediction spectra collected from 368 to 617 days after the collection of the calibration data. The updated PLS models based on four augmented samples exhibited an approximately 50% improvement in prediction accuracy relative to models that were based solely on the original calibration data. The use of DOSC in conjunction with updating was found to be beneficial overall, but only led on average to less than 10% improvement in prediction performance.

Rapid quality assessment and traceability of ginger powder from Northeast India and Indian market based on near infrared spectroscopic fingerprinting.

Ginger (Zingiber officinale Rosc.) varies widely due to varying concentrations of phytochemicals and geographical origin. Rapid non-invasive quality and traceability assessment techniques ensure a sustainable value chain. The objective of this study is the development of suitable machine learning models to estimate the concentration of 6-gingerol and check traceability based on the spectral fingerprints of dried ginger samples collected from Northeast India and the Indian market using near-infrared spectrometry. Samples from the market and Northeast India underwent High Performance Liquid Chromatographic analysis for 6-gingerol content estimation. Near infrared (NIR) Spectrometer acquired spectral data. Quality prediction utilized partial least square regression (PLSR), while fingerprint-based traceability identification employed principal component analysis and t-distributed stochastic neighbor embedding (t-SNE). Model performance was assessed using RMSE and R2 values across selective wavelengths and spectral fingerprints. The standard normal variate pretreated spectral data over the wavelength region of 1,100-1,250 nm and 1,325-1,550 nm showed the optimal calibration model with root mean square error of calibration and R2 C (coefficient of determination for calibration) values of 0.87 and 0.897 respectively. A lower value (0.24) of root mean square error of prediction and a higher value (0.973) of R2 P (coefficient of determination for prediction) indicated the effectiveness of the developed model. t-SNE performed better clustering of samples based on geographical location, which was independent of gingerol content. The developed NIR spectroscopic model for Indian ginger samples predicts the 6-gingerol content and provides geographical traceability-based identification to ensure a sustainable value chain, which can promote efficiency, cost-effectiveness, consumer confidence, sustainable sourcing, traceability, and data-driven decision-making.

Prediction model for asymptomatic carotid atherosclerosis using retinal microvascular intelligent analysis: A retrospective study

ImportanceEarly detection and timely diagnosis of asymptomatic carotid atherosclerosis significantly assist in the prevention of ischemic stroke for them. ObjectiveThis observational study aimed to develop and validate a novel prediction model to assist in the early diagnosis of carotid atherosclerosis based on new characteristic variables screened by retinal microvascular intelligence analysis. Main Outcome(s) and Method (s)The least absolute shrinkage and selection operator (LASSO) combined with 10-fold cross-validation were screened for characteristic variables, and nomograms were plotted to demonstrate the prediction model. Receiver operating characteristic (ROC) curves and area under the curve (AUC), calibration plots and brier score (BS), and decision curve analysis (DCA) were used to evaluate the risk model's discrimination, calibration, and clinical applicability. ResultsAge, gender, diabetes mellitus (DM), drinking history, vascular branching angle, mean vascular diameter within 0.5–1.0 papillary diameter (PD), curvature tortuosity arteriole in the inferior region of the optic disc, and vascular density in the nasal region of the optic disc were identified as characteristic variables for carotid atherosclerosis with retinal microvascular intelligence analysis. The predictive nomogram model presented good discrimination with AUCs of 0.790 (0.774–0.806), and the calibration curve displayed high consistency between predicted and actual probability. The DCA demonstrated that this nomogram model led to net benefits in a threshold probability range of 20 %–94 % and could be adapted for clinical decision-making. The results of the 100-bootstrap resampling strategy for internal validation also show that the risk model is well discriminated with an AUC of 0.789 and excellent calibration. External validation showed good discrimination with AUCs of 0.703 (0.627 - 0.779) and good calibration, the risk threshold is 10 %–92 % in terms of DCA. Conclusions and RelevanceThe novel prediction model based on retinal microvascular intelligence analysis constructed in this study could be effective prognoses for predicting the risk of asymptomatic carotid atherosclerosis in a Chinese screening population.