Validation Dataset Research Articles

Advancements in Frank’s sign Identification using deep learning on 3D brain MRI

Frank’s sign (FS) is a diagnostic marker associated with aging and various health conditions. Despite its clinical significance, there lacks a standardized method for its identification. This study aimed to develop a deep learning model for automated FS detection in 3D facial images derived from MRI scans. Four deep learning architectures were evaluated for FS segmentation on a dataset of 400 brain MRI scans. The optimal model was subsequently validated on two external datasets, comprising 300 brain MRI scans each with varying FS presence. Dice similarity coefficient (DSC) and receiver operating characteristic (ROC) analysis were employed to assess model performance. The U-net architecture demonstrated superior performance in terms of accuracy and efficiency. On the validation datasets, the model achieved a DSC of 0.734, an intra-class correlation coefficient of 0.865, and an area under the ROC curve greater than 0.9 for FS detection. Additionally, the model identified optimal voxel thresholds for accurate FS classification, resulting in high sensitivity, specificity, and accuracy metrics. This study successfully developed a deep learning model for automated FS segmentation in MRI scans. This tool has the potential to enhance FS identification in clinical practice and contribute to further research on FS and its associated health implications.

An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs

PurposeDistal radius fractures (DRFs) are often initially assessed by junior doctors under time constraints, with limited supervision, risking significant consequences if missed. Convolutional Neural Networks (CNNs) can aid in diagnosing fractures. This study aims to internally and externally validate an open source algorithm for the detection and localization of DRFs.MethodsPatients from a level 1 trauma center from Adelaide, Australia that presented between 2016 and 2020 with wrist trauma were retrospectively included. Radiographs were reviewed confirming the presence or absence of a fracture, as well as annotating radius, ulna, and fracture location. An internal validation dataset from the same hospital was created. An external validation set was created with two other level 1 trauma centers, from Groningen and Rotterdam, the Netherlands. Three surgeons reviewed both sets for DRFs.ResultsThe algorithm was trained on 659 radiographs. The internal validation set included 190 patients, showing an accuracy of 87% and an AUC of 0.93 for DRF detection. The external validation set consisted of 188 patients, with an accuracy and AUC were 82% and 0.88 respectively. Radial and ulnar bone segmentation on the internal validation was excellent with an AP50 of 99 and 98, but moderate for fracture segmentation with an AP50 of 29. For external validation the AP50 was 92, 89 and 25 for radius, ulna, and fracture respectively.ConclusionThis open-source algorithm effectively detects DRFs with high accuracy and localizes them with moderate accuracy. It can assist clinicians in diagnosing suspected DRFs and is the first radiograph-based CNN externally validated on patients from multiple hospitals.

Mapping Pituitary Neuroendocrine Tumors: An Annotated MRI Dataset Profiling Tumor and Carotid Characteristics

Pituitary neuroendocrine tumors remain one of the most common intracranial tumors. While radiomic research related to pituitary tumors is progressing, public data sets for external validation remain scarce. We introduce an open dataset comprising high-resolution T1 contrast-enhanced MR scans of 136 patients with pituitary tumors, annotated for tumor segmentation and accompanied by clinical, radiological and pathological metadata. This diverse dataset captures variations in tumor size, location, and pathological activity, essential for understanding this complex condition. Expert annotations of both the tumor and adjacent carotid arteries ensure precise delineation, facilitating the development of automated segmentation algorithms. Our initiative addresses the need for standardized data in pituitary oncology, fosters collaboration and innovation, and enables the development and benchmarking of workflows that utilize pituitary radiomics for treatment planning and outcome prediction.

Derivation and validation of a clinical predictive model for longer duration diarrhea among pediatric patients in Kenya using machine learning algorithms

BackgroundDespite the adverse health outcomes associated with longer duration diarrhea (LDD), there are currently no clinical decision tools for timely identification and better management of children with increased risk. This study utilizes machine learning (ML) to derive and validate a predictive model for LDD among children presenting with diarrhea to health facilities.MethodsLDD was defined as a diarrhea episode lasting ≥ 7 days. We used 7 ML algorithms to build prognostic models for the prediction of LDD among children < 5 years using de-identified data from Vaccine Impact on Diarrhea in Africa study (N = 1,482) in model development and data from Enterics for Global Health Shigella study (N = 682) in temporal validation of the champion model. Features included demographic, medical history and clinical examination data collected at enrolment in both studies. We conducted split-sampling and employed K-fold cross-validation with over-sampling technique in the model development. Moreover, critical predictors of LDD and their impact on prediction were obtained using an explainable model agnostic approach. The champion model was determined based on the area under the curve (AUC) metric. Model calibrations were assessed using Brier, Spiegelhalter’s z-test and its accompanying p-value.ResultsThere was a significant difference in prevalence of LDD between the development and temporal validation cohorts (478 [32.3%] vs 69 [10.1%]; p < 0.001). The following variables were associated with LDD in decreasing order: pre-enrolment diarrhea days (55.1%), modified Vesikari score(18.2%), age group (10.7%), vomit days (8.8%), respiratory rate (6.5%), vomiting (6.4%), vomit frequency (6.2%), rotavirus vaccination (6.1%), skin pinch (2.4%) and stool frequency (2.4%). While all models showed good prediction capability, the random forest model achieved the best performance (AUC [95% Confidence Interval]: 83.0 [78.6–87.5] and 71.0 [62.5–79.4]) on the development and temporal validation datasets, respectively. While the random forest model showed slight deviations from perfect calibration, these deviations were not statistically significant (Brier score = 0.17, Spiegelhalter p-value = 0.219).ConclusionsOur study suggests ML derived algorithms could be used to rapidly identify children at increased risk of LDD. Integrating ML derived models into clinical decision-making may allow clinicians to target these children with closer observation and enhanced management.

A prognostic survival model based on endocrine-related gene expression in acute myelogenous leukemia.

Accurate prediction of survival in patients with acute myelogenous leukemia (AML) is challenging. Therefore, we developed a predictive survival model using endocrine-related gene expression to identify an endocrine signature for accurate stratification of AML prognosis. RNA matrices and clinical data for AML were downloaded from a training dataset (GEO) and two validation datasets (TCGA and TARGET). In relation to the survival outcome, a risk model was constructed by incorporating seven endocrine-related genes. The model exhibited favorable predictive efficacy in estimating 5-year survival rates, as demonstrated by both the training and validation cohorts. Multivariable analysis revealed that the endocrine signature demonstrated autonomous prognostic significance in the aforementioned cohorts. Prediction accuracy for 5-year overall survival increased using a nomogram combining endocrine risk score and classical prognostic factors compared with using classical prognostic factors alone. The model predictions were confirmed using AML cell lines. The endocrine-related prognostic model established in this study improves AML survival prediction accuracy.

Orbital-Radar v1.0.0: a tool to transform suborbital radar observations to synthetic EarthCARE cloud radar data

Abstract. The Earth Cloud, Aerosol and Radiation Explorer (EarthCARE) satellite developed by the European Space Agency (ESA) and the Japan Aerospace Exploration Agency (JAXA) launched in May 2024 carries a novel 94 GHz cloud profiling radar (CPR) with Doppler capability. This work describes the open-source instrument simulator Orbital-Radar, which transforms high-resolution radar data from field observations or forward simulations of numerical models to CPR primary measurements and uncertainties. The transformation accounts for sampling geometry and surface effects. We demonstrate Orbital-Radar's ability to provide realistic CPR views of typical cloud and precipitation scenes. The presented case studies show small-scale convection, marine stratus clouds, and Arctic mixed-phase cloud cases. These results provide valuable insights into the capabilities and challenges of the EarthCARE CPR mission and its advantages over the CloudSat CPR. Finally, Orbital-Radar allows for evaluating kilometre-scale numerical weather prediction models with EarthCARE CPR observations. So, Orbital-Radar can generate calibration and validation (Cal/Val) data sets already pre-launch. Nevertheless, an evaluation of synthetic CPR output data to accurate EarthCARE CPR data is missing.

Characterization of adrenal glands on computed tomography with a 3D V-Net-based model

ObjectivesTo evaluate the performance of a 3D V-Net-based segmentation model of adrenal lesions in characterizing adrenal glands as normal or abnormal.MethodsA total of 1086 CT image series with focal adrenal lesions were retrospectively collected, annotated, and used for the training of the adrenal lesion segmentation model. The dice similarity coefficient (DSC) of the test set was used to evaluate the segmentation performance. The other cohort, consisting of 959 patients with pathologically confirmed adrenal lesions (external validation dataset 1), was included for validation of the classification performance of this model. Then, another consecutive cohort of patients with a history of malignancy (N = 479) was used for validation in the screening population (external validation dataset 2). Parameters of sensitivity, accuracy, etc., were used, and the performance of the model was compared to the radiology report in these validation scenes.ResultsThe DSC of the test set of the segmentation model was 0.900 (0.810–0.965) (median (interquartile range)). The model showed sensitivities and accuracies of 99.7%, 98.3% and 87.2%, 62.2% in external validation datasets 1 and 2, respectively. It showed no significant difference comparing to radiology reports in external validation datasets 1 and lesion-containing groups of external validation datasets 2 (p = 1.000 and p > 0.05, respectively).ConclusionThe 3D V-Net-based segmentation model of adrenal lesions can be used for the binary classification of adrenal glands.Critical relevance statementA 3D V-Net-based segmentation model of adrenal lesions can be used for the detection of abnormalities of adrenal glands, with a high accuracy in the pre-surgical scene as well as a high sensitivity in the screening scene.Key PointsAdrenal lesions may be prone to inter-observer variability in routine diagnostic workflow.The study developed a 3D V-Net-based segmentation model of adrenal lesions with DSC 0.900 in the test set.The model showed high sensitivity and accuracy of abnormalities detection in different scenes.Graphical

The predictive value of the serum creatinine-to-albumin ratio (sCAR) and lactate dehydrogenase-to-albumin ratio (LAR) in sepsis-related persistent severe acute kidney injury

Background/objectivesSepsis-related acute kidney injury (SA-AKI) is a severe condition characterized by high mortality rates. The utility of the sCAR (secrum creatinine/albumin) and LAR (Lactate dehydrogenase/albumin) as diagnostic markers for persistent severe SA-AKI remains unclear.MethodsWe acquired training set data from the MIMIC-IV database and validation set data from the First Affiliated Hospital of Harbin Medical University. Logistic regression analysis was used to identify key predictors of persistent severe SA-AKI, considering factors such as sCAR, LAR, PAR (Platelet/albumin), BAR (BUN/albumin), and LAO (Lactic/albumin). Independent predictors, sCAR and LAR, were combined into a composite Log(sCAR)_Log(LAR) score, denoted as the Log(sCAR)_Log(LAR) score. Possible confounding factors were screened out by univariate logistic regression, and multivariable logistic regression was applied to evaluate the association of Log (sCAR) _Log (LAR) score with persistent severe sepsis and other secondary clinical outcomes. The ROC curve was utilized to obtain the best cutoff value of the Log(sCAR)_Log(LAR) score. The Kaplan–Meier curve was used to evaluate the prognosis predictive ability of the risk model.ResultsLogistic regression analysis indicated that sCAR and LAR independently predicted persistent severe SA-AKI. This led to the creation of Log(sCAR)_Log(LAR) score on the base of logarithms of sCAR and LAR. ROC curve analysis showed that the Log(sCAR)_Log(LAR) score was more effective in predicting persistent severe SA-AKI (AUC = 0.71) than Log(sCAR) (AUC = 0.69), Log(LAR) (AUC = 0.65), SOFA score (AUC = 0.66) and Δ Scr (AUC = 0.70). Multivariate regression identified that the SOFA score, PT, ΔScr, Tbil, chronic liver disease, and Vasopressor use as independent risk factors for persistent severe SA-AKI (P < 0.05). A basic clinical prediction model was created using these variables, and its predictive ability, recognition capability, and clinical utility improved with the inclusion of the Log(sCAR)_Log(LAR) score. The model's predictive ability for secondary outcomes, such as renal replacement therapy (RRT), also improved with the addition of the Log(sCAR)_Log(LAR) score. The sensitivity analysis further corroborated the stability of the Log(sCAR)_Log(LAR) score in predicting persistent severe SA-AKI and secondary outcomes, such as RRT.ConclusionsThe Log(sCAR)_Log(LAR) score effectively predicted persistent severe SA-AKI, potentially aiding intensive care physicians in risk assessment.

Equations for Estimating Resting Energy Expenditure in Patients on Peritoneal Dialysis

Abstract Background In peritoneal dialysis (PD) patients, determining energy expenditure is essential for recommending energy intake in nutrition management. Objective We aimed to develop and validate a resting energy expenditure (REE) equation for patients with PD and compare it to previously available REE equations in dialysis patients. Design This cross-sectional study enrolled 200 patients with PD from two hospitals in Beijing, China. Stepwise linear regression analysis was used to derive a new REE equation (eREE-PD) based on actual REE (aREE) measured using indirect calorimetry (IC) in the development dataset. The eREE-PD value was then validated with aREE in the validation dataset and compared with values from existing equations obtained in general populations and those developed for chronic kidney disease and dialysis patients, in terms of bias, precision, and accuracy. Results The bias, precision, and accuracy of the eREE-PD equation were significantly better than those of Harris-Benedict, WHO, and Schofield equations (P &amp;lt; 0.005) and comparable to Mifflin equation (P = 0.541 for bias, 0.988 for precision, and 0.359 for accuracy), with IC as reference method. Either bias, precision or accuracy of the eREE-PD were significantly better than eREE-V, eREE-Bscr and eREE-CFFM equations significantly (P &amp;lt; 0.005) and similar to eREE-CKD, eREE-Bcrp and eREE-Cweighht equations (P &amp;gt; 0.05 for bias, precision, and accuracy). The bias, precision, and accuracy of the eREE-PD equation were consistent across subgroups categorized by hs-CRP levels. Conclusion The eREE-PD equation, based on age, sex, and weight data, may serve as a reliable and practical tool for estimating REE in patients with PD, aiding in individualized nutritional management. However, external validation in other populations is required to confirm its generalizability beyond the studied cohort.

Effects of NK cell-related lncRNA on the immune microenvironment and molecular subtyping for pancreatic ductal adenocarcinoma

BackgroundPatients with pancreatic ductal adenocarcinoma (PDAC) face a highly unfavorable outcome and have a poor response to standard treatments. Immunotherapy, especially therapy based on natural killer (NK) cells, presents a promising avenue for the treatment of PDAC.AimsThis research endeavor seeks to formulate a predictive tool specifically designed for PDAC based on NK cell-related long non-coding RNA (lncRNA), revealing new molecular subtypes of PDAC to promote personalized and precision treatment.MethodsUtilizing the Tumor Immune Single-cell Hub 2 platform, we discovered genes associated with NK cells in PDAC. We employed the TCGA-PAAD dataset to ascertain the expression profiles of these NK cell-related genes and to screen for lncRNAs correlated with NK cells. Subsequently, we utilized Cox regression analysis for hazard ratios and LASSO regression analysis to identify three NK cell-related lncRNAs that were used to develop a prognostic assessment model. The forecasting accuracy of this model was appraised using the ROC curve and validated using a test set and the complete dataset.ResultsSuccessful construction of a prognostic model comprising three lncRNAs was achieved, demonstrating good predictive efficiency in the training set, validation dataset, and the entire dataset. NK cells display robust interactions with malignant cells, CD8 T cells, and fibroblasts in the PDAC tumor microenvironment and participate in the transport of various signaling molecules and following immune responses in PDAC. According to the expression patterns of NK cell-related lncRNA, we labeled PDAC patients as four molecular subtypes, exhibiting significant differences in immune cell infiltration, drug sensitivity, and other aspects.ConclusionThis study Uncovered the activity of NK cells within PDAC, proposed an NK cell-related lncRNA model, and delineated new molecular subtypes, thereby providing targets for personalized therapy.

The Future of Plant Health: Deep Learning Solutions

Plant diseases must be identified early to prevent crop losses, and agriculture is essential to maintaining food security. With the use of a deep learning model based on Convolutional Neural Networks (CNNs). This research aims to automate the process of detecting plant leaf diseases. To distinguish between healthy and unhealthy plant leaves, the suggested system makes use of image processing techniques. To increase the model's capacity for generalization, data augmentation methods including zooming, rescaling, and horizontal flipping are used. Using categorical cross-entropy as the loss function and Adam optimizer, the CNN model is trained on a dataset of plant leaf images. Findings show that the model performs well in situations involving the real-time detection of diseases, with high accuracy observed in both training and validation datasets.

Preliminary Development and Validation of Automated Nociception Recognition Using Computer Vision in Perioperative Patients.

Effective pain recognition and treatment in perioperative environments reduce length of stay and decrease risk of delirium and chronic pain. We sought to develop and validate preliminary computer vision-based approaches for nociception detection in hospitalized patients. Prospective observational cohort study using red-green-blue camera detection of perioperative patients. Adults (≥18 years) admitted for surgical procedures to the San Francisco Veterans Affairs Medical Center (SFVAMC) were included across 2 study phases: (1) algorithm development phase and (2) internal validation phase. Continuous recordings occurred perioperatively across any postoperative setting. We inputted facial images into convolutional neural networks using a pretrained backbone, to detect (1) critical care pain observation tool (CPOT) and (2) numerical rating scale (NRS). Outcomes were binary pain/no-pain. We performed external validation for CPOT and NRS classification on data from University of Northern British Columbia-McMaster University (UNBC) and Delaware Pain Database. Perturbation models were used for explainability. We included 130 patients for development, 77 patients for validation cohort and 25 patients from UNBC and 229 patients from Delaware datasets for external validation. Model area under the curve of the receiver operating characteristic for CPOT models were 0.71 (95% confidence interval [CI] 0.70, 0.74) on the development cohort, 0.91 (95% CI 0.90, 0.92) on the SFVAMC validation cohort, 0.91 (0.89, 0.93) on UNBC and 0.80 (95% CI 0.75, 0.85) on Delaware. NRS model had lower performance (AUC 0.58 [95% CI 0.55, 0.61]). Brier scores improved following calibration across multiple different techniques. Perturbation models for CPOT models revealed eyebrows, nose, lips, and foreheads were most important for model prediction. Automated nociception detection using computer vision alone is feasible but requires additional testing and validation given small datasets used. Future multicenter observational studies are required to better understand the potential for automated continuous assessments for nociception detection in hospitalized patients.

Extended Reconstructed Sea Surface Temperature Version 6 (ERSSTv6): Part II. Upgrades on Quality Control and Large-scale Filter

Abstract NOAA’s Extended Reconstructed Sea Surface Temperature (SST; ERSST) is a monthly 2° SST product starting from 1850. Our Part I study indicated that the performance scores of spatial correlation coefficient (SCC) and root-mean-square-difference (RMSD) dropped clearly after the mid-1970s in the analysis of ERSST with an artificial neural network (ANN) method. In this Part II study, we demonstrate that ERSST with the ANN method can further be improved progressively in the final ERSSTv6 by the following steps: 1) applying a nearest neighbor check (NNC) quality control algorithm on ship observations, 2) applying a large-scale (&gt;200km) filter (LS200) on SST super-observations, and 3) upgrading algorithms in proxy SST from ice concentration. These progressive improvements were assessed against validation and observation datasets. In comparison with ERSST with the ANN method alone, the quality of ERSSTv6 improves in the statistical metrics of SCC and RMSD by 2–11% and 0.01°–0.24°C, respectively, in the global oceans. In the ice-covered regions, SST bias and RMSD decrease by 0.67°C and 0.29°C, respectively.

A Multianalyte Machine Learning Model to Detect Wrong Blood in Complete Blood Count Tube Errors in a Pediatric Setting.

Multianalyte machine learning (ML) models can potentially identify previously undetectable wrong blood in tube (WBIT) errors, improving upon current single-analyte delta check methodology. However, WBIT detection model performance has not been assessed in a real-world, low-prevalence context. To estimate real-world positive predictive values, we propose a methodology to assess WBIT detection models by evaluating the impact of missing data and by using a "low prevalence" validation data set. We trained a range of model specifications using various predictors in a pediatric setting. We assessed the top-performing model on a modified, "low prevalence" validation data set across a range of probability thresholds. Model performance was also compared to a pre-positive patient identification (pre-PPID) dataset. An Extreme Gradient Boosting (XGBoost) model with minimal preprocessing performed the best for both complete blood count with differential white cell count (CBC with Diff) tests (accuracy 0.9715) and complete blood count without differential white cell count (CBC without Diff) tests (accuracy 0.9647). Assessment on a downsampled, "low prevalence" validation data set resulted in estimated positive predictive values ranging from 0.01 to 0.67 (CBC with Diff) and 0.01 to 0.75 (CBC without Diff), depending on the probability threshold chosen. A comparison of prospective performance to PPID data demonstrated a large decrease in estimated WBIT errors. We find that ML models can accurately predict WBITs in a primarily pediatric setting. Evaluating model performance across a range of probability thresholds minimizes the number of false positives while still providing added safety benefits. The decrease in estimated WBITS post-PPID implementation shows the potential safety benefits of a WBIT model for hospitals not using PPID when collecting laboratory specimens.

Generation of high-resolution MPRAGE-like images from 3D head MRI localizer (AutoAlign Head) images using a deep learning-based model.

Magnetization prepared rapid gradient echo (MPRAGE) is a useful three-dimensional (3D) T1-weighted sequence, but is not a priority in routine brain examinations. We hypothesized that converting 3D MRI localizer (AutoAlign Head) images to MPRAGE-like images with deep learning (DL) would be beneficial for diagnosing and researching dementia and neurodegenerative diseases. We aimed to establish and evaluate a DL-based model for generating MPRAGE-like images from MRI localizers. Brain MRI examinations including MPRAGE taken at a single institution for investigation of mild cognitive impairment, dementia and epilepsy between January 2020 and December 2022 were included retrospectively. Images taken in 2020 or 2021 were assigned to training and validation datasets, and images from 2022 were used for the test dataset. Using the training and validation set, we determined one model using visual evaluation by radiologists with reference to image quality metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). The test dataset was evaluated by visual assessment and quality metrics. Voxel-based morphometric analysis was also performed, and we evaluated Dice score and volume differences between generated and original images of major structures were calculated as absolute symmetrized percent change. Training, validation, and test datasets comprised 340 patients (mean age, 56.1 ± 24.4years; 195 women), 36 patients (67.3 ± 18.3years, 20 women), and 193 patients (59.5 ± 24.4years; 111 women), respectively. The test dataset showed: PSNR, 35.4 ± 4.91; SSIM, 0.871 ± 0.058; and LPIPS 0.045 ± 0.017. No overfitting was observed. Dice scores for the segmentation of main structures ranged from 0.788 (left amygdala) to 0.926 (left ventricle). Quadratic weighted Cohen kappa values of visual score for medial temporal lobe between original and generated images were 0.80-0.88. Images generated using our DL-based model can be used for post-processing and visual evaluation of medial temporal lobe atrophy.

Identification of biomarkers for knee osteoarthritis through clinical data and machine learning models

Knee osteoarthritis (KOA) represents a progressive degenerative disorder characterized by the gradual erosion of articular cartilage. This study aimed to develop and validate biomarker-based predictive models for KOA diagnosis using machine learning techniques. Clinical data from 2594 samples were obtained and stratified into training and validation datasets in a 7:3 ratio. Key clinical features were identified through differential analysis between KOA and control groups, combined with least absolute shrinkage and selection operator (LASSO) regression. The SHapley Additive Planning (SHAP) method was employed to rank feature importance quantitatively. Based on these rankings, predictive models were constructed using Logistic Regression (LR), Random Forest (RF), eXtreme Gradient Boosting (xGBoost), Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT) algorithms. Models were developed for subsets of variables, including the top 5, top 10, top 15, and all identified features. Receiver operating characteristic (ROC) curves were applied to compare diagnostic performance across models. Additionally, a risk stratification framework for KOA prediction was designed using recursive partitioning analysis (RPA). Using difference analysis and LASSO, 44 critical clinical features were identified. Among these, age, plasma prothrombin time, gender, body mass index (BMI), and prothrombin time and international normalized ratio (PTINR) emerged as the top five features, with SHAP values of 0.1990, 0.0981, 0.0471, 0.0433, and 0.0422, respectively. Machine learning analysis demonstrated that these variables provided robust diagnostic performance for KOA. In the training set, area under the curve (AUC) values for LR, RF, xGBoost, NB, SVM, and DT models were 0.947, 0.961, 0.892, 0.952, 0.885, and 0.779, respectively. Similarly, in the validation dataset, these models achieved AUC values of 0.961, 0.943, 0.789, 0.957, 0.824, and 0.76. Among them, RF consistently exhibited superior diagnostic accuracy for KOA. Additionally, RPA analysis indicated a higher prevalence of KOA among individuals aged 54 years and older. The integration of the top five clinical variables significantly enhanced the diagnostic accuracy for KOA, particularly when employing the RF model. Moreover, the RPA model offered valuable insights to assist clinicians in refining prognostic assessments and optimizing clinical decision-making processes.

Design of a Novel Fractional Whale Optimization-Enhanced Support Vector Regression (FWOA-SVR) Model for Accurate Solar Energy Forecasting

This study presents a novel Fractional Whale Optimization Algorithm-Enhanced Support Vector Regression (FWOA-SVR) framework for solar energy forecasting, addressing the limitations of traditional SVR in modeling complex relationships within data. The proposed framework incorporates fractional calculus in the Whale Optimization Algorithm (WOA) to improve the balance between exploration and exploitation during hyperparameter tuning. The FWOA-SVR model is comprehensively evaluated against traditional SVR, Long Short-Term Memory (LSTM), and Backpropagation Neural Network (BPNN) models using training, validation, and testing datasets. Experimental results show that FWOA-SVR achieves superior performance with the lowest MSE values (0.036311, 0.03942, and 0.03825), RMSE values (0.19213, 0.19856, and 0.19577), and the highest R2 values (0.96392, 0.96104, and 0.96192) for training, validation, and testing, respectively. These results highlight the significant improvements of FWOA-SVR in prediction accuracy and efficiency, surpassing benchmark models in capturing complex patterns within the data. The findings highlight the effectiveness of integrating fractional optimization techniques into machine learning frameworks for advancing solar energy forecasting solutions.

Predicting loss of independence among geriatric patients following gastrointestinal surgery

BackgroundWhile existing risk calculators focus on mortality and complications, elderly patients are concerned with how operations will affect their quality of life, especially their independence. We sought to develop a novel clinically relevant and easy-to-use score to predict elderly patients’ loss of independence after gastrointestinal surgery.MethodsThis retrospective cohort study included patients age ≥ 65 years enrolled in the American College of Surgeons National Surgical Quality Improvement Program database and Geriatric Pilot Project who underwent pancreatic, colorectal, or hepatic surgery (January 1, 2014- December 31, 2018). Primary outcome was loss of independence – discharge to facility other than home and decline in functional status. Patients from 2014 to 2017 comprised the training data set. A logistic regression (LR) model was generated using variables with p < 0.2 from the univariable analysis. The six factors most predictive of the outcome composed the short LR model and scoring system. The scoring system was validated with data from 2018.ResultsOf 6,510 operations, 841 patients (13%) lost independence. Training and validation datasets had 5,232 (80%) and 1,278 (20%) patients, respectively. The six most impactful factors in predicting loss of independence were age, preoperative mobility aid use, American Society of Anesthesiologists classification, preoperative albumin, non-elective surgery, and race (all OR > 1.83; p < 0.001). The odds ratio of each of these factors were used to create a sixteen-point scoring system. The scoring system demonstrated satisfactory discrimination and calibration across the training and validation datasets, with Receiver Operating Characteristic Area Under the Curve 0.78 in both and Hosmer-Lemeshow statistic of 0.16 and 0.34, respectively.ConclusionsThis novel scoring system predicts loss of independence for geriatric patients after gastrointestinal operations. Using readily available variables, this tool can be applied in the urgent setting and can contribute to elderly patients and their family discussions related to loss of independence prior to high-risk gastrointestinal operations. The applicability of this scoring tool to additional surgical sub-specialties and external validation should be explored in future studies.

OSBPL3 modulates the immunosuppressive microenvironment and predicts therapeutic outcomes in pancreatic cancer

BackgroundPancreatic cancer is characterized by a complex tumor microenvironment that hinders effective immunotherapy. Identifying key factors that regulate the immunosuppressive landscape is crucial for improving treatment strategies.MethodsWe constructed a prognostic and risk assessment model for pancreatic cancer using 101 machine learning algorithms, identifying OSBPL3 as a key gene associated with disease progression and prognosis. We integrated multi-dataset analyses, single-cell transcriptomic data, and functional experiments to explore the role of OSBPL3 in pancreatic cancer.ResultsOur risk prediction model, developed using machine learning algorithms, demonstrated high predictive accuracy across multiple datasets. Notably, the “rf” algorithm model showed an AUC of 1 in the training set and AUCs of 0.887 and 0.977 in two validation datasets. Ridge regression analysis identified OSBPL3 as a core prognostic feature gene. High OSBPL3 expression in pancreatic cancer samples was associated with immunosuppressive characteristics, including reduced CD8 + T cell infiltration and increased immunosuppressive cell populations such as Treg cells and M2 macrophages. Transcriptomic sequencing following OSBPL3 knockdown revealed enrichment of immune-related pathways, suggesting OSBPL3’s influence on the immune microenvironment. Single-cell analyses further confirmed OSBPL3’s role in shaping the immunosuppressive landscape by modulating Treg cells and M2 macrophages. Additionally, OSBPL3 expression was linked to resistance to immunotherapy, with high OSBPL3 expression associated with lower Immunophenoscore (IPS) scores, indicating poor responsiveness to immunotherapy.ConclusionsOur study reveals OSBPL3 as a critical regulator of the immunosuppressive microenvironment in pancreatic cancer and a potential therapeutic target. Targeting OSBPL3 may enhance the efficacy of immunotherapy and improve patient outcomes. Further research is warranted to explore OSBPL3 as a biomarker for predicting immunotherapy response and as a potential therapeutic target in combination with anti-PD1 therapy.

Deep learning model for identifying acute heart failure patients using electrocardiography in the emergency room.

Acute heart failure (AHF) poses significant diagnostic challenges in the emergency room (ER) because of its varied clinical presentation and limitations of traditional diagnostic methods. This study aimed to develop and evaluate a deep-learning model using electrocardiogram (ECG) data to enhance AHF identification in the ER. In this retrospective cohort study, we analyzed the ECG data of 19,285 patients who visited ERs of three hospitals between 2016 and 2020; 9,119 with available left ventricular ejection fraction and N-terminal prohormone of brain natriuretic peptide level data and who were diagnosed with AHF were included in the study. We extracted morphological and clinical parameters from ECG data to train and validate four machine learning models: baseline linear regression and more advanced models including XGBoost, Light GBM, and CatBoost. The CatBoost algorithm outperformed other models, showing superior area under the receiver operating characteristic and area under the precision-recall curve diagnostic accuracy across both internal (0.89 ± 0.01 and 0.89 ± 0.01) and external (0.90 and 0.89) validation datasets, respectively. The model demonstrated high accuracy, precision, recall, and f1 score, indicating robust performance in AHF identification. The developed machine learning model significantly enhanced AHF detection in the ER using conventional 12-lead ECGs combined with clinical data. These findings suggest that ECGs, a common tool in the ER, can effectively help screen for AHF.