Data processing and learning have become essential to the advancement of medicine, with pathology and lab medicine being no exception. Integrating scientific research with clinical informatics into clinical practice facilitates novel methodologies for patient care. Computational pathology is a burgeoning subspecialty in pathology that promises a better-integrated solution to histopathological images and clinical informatics. Deep-learning methods in computational pathology have demonstrated considerable advances in automated histopathological image analysis. However, convolutional neural networks (CNNs) face fundamental limitations when dealing with the significant morphological heterogeneity present in disease tissues. Conventional CNNs use fixed convolutional kernels, which restrict their effectiveness in adaptively extracting features from histopathological images that exhibit diverse pathological patterns, staining intensities, and tissue architecture. To address this substantial limitation, we present an optimized variant of Omni-Dimensional Dynamic Convolution (ODConv) networks for distinguishing diseased tissue from healthy tissue. Compared with prior dynamic convolution methods that attend to a single kernel dimension, ODConv applies multi-dimensional attention across spatial positions, input channels, output channels, and kernel candidates, enabling more flexible and adaptive feature extraction. We evaluated our approach on wheat-germ agglutinin-stained and hematoxylin and eosin-stained skeletal muscle images from multiple disease models, including G93A*SOD1 transgenic mice (amyotrophic lateral sclerosis) and Akita mice (Type I diabetes). ODConv, trained entirely from scratch without ImageNet pretraining, achieved competitive classification performance relative to seven fine-tuned pretrained architectures across both staining modalities, demonstrating the effectiveness of omni-dimensional dynamic kernels in learning discriminative morphological representations directly from domain data. The study reports strong statistical agreement metrics, proving effective class balance handling and stable decision boundaries. These findings confirm ODConv as a strong computational pathology framework that advances automated diagnosis of neurodegenerative and metabolic skeletal muscle disorders.

Accurate and early diagnosis of Alzheimer's disease (AD) remains a major clinical challenge, particularly in distinguishing mild cognitive impairment (MCI) from cognitively normal (CN) aging. Conventional approaches that rely solely on pre-trained 2D models often fail to capture the full spatial context of three-dimensional MRI volumes, as well as the temporal dependencies that exist across consecutive slices. In this study, we propose TGL-AD, a novel framework that integrates Vision Transformer (ViT) slice embeddings with temporal graph learning for subject-level AD classification. Standardized 3D MRI volumes were decomposed into 2D slices, encoded by a pre-trained ViT to generate 768-dimensional feature embeddings, and subsequently modeled as temporal graphs to preserve inter-slice continuity. Contextual information was transmitted across slices by graph neural networks (GNNs), and subject-level representations were generated for the final classification through global pooling. On the ADNI1 dataset, TGL-AD achieved an overall accuracy of 0.92 on the Complete 1Yr 1.5 T cohort and 0.98 on the Complete 3Yr 3 T cohort. For all diagnostic categories (AD, MCI, and CN), precision, recall, and F1-scores stayed consistently high across both groups. The macro-averaged and weighted-averaged F1-scores for the 1.5 T and 3 T data were 0.92 and 0.98, respectively. A comparative assessment against leading-edge architectures further confirms that TGL-AD surpasses CNN-based and transformer-based sequential baselines, attaining the highest recall (0.93 for 1.5 T and 0.98 for 3 T) and F1-score (0.92 for 1.5 T and 0.98 for 3 T). These findings show that the integration of transformer-based slice encoders and temporal graph modeling efficiently captures inter-slice dependencies and enhances classification performance across different acquisition settings.

The advancement of decision support systems for pathology and their implementation in clinical practice have been limited by the necessity for extensive, manually annotated datasets. Self-supervised learning (SSL) automates the extraction and interpretation of histopathological features from unannotated images, facilitating efficient model development without dependence on expert labeling. In this study, we introduce the SSL-HistoNet model that learns disease-relevant morphological representations from histopathological images through self-supervised learning. We applied it to WGA-stained skeletal muscle tissues from mouse models of amyotrophic lateral sclerosis (ALS) and Type I diabetes to explore its ability to capture pathological muscle phenotypes in an annotation-free setting. Following pretraining on unlabeled data, the SSL encoder was further integrated with an attention-guided classifier to evaluate its capacity to identify pathological muscle alterations. SSL-HistoNet achieved a precision of 0.98, a recall of 0.98, and an AUC of 0.98, demonstrating performance comparable to or outperforming state-of-the-art supervised models. Alongside high discriminative performance, exploratory feature analyses demonstrated consistent class-level changes in morphology-related patterns identified through representation learning. These findings highlight the capability of SSL-HistoNet as an annotation-free framework for outlining disease-specific tissue structures, reducing manual labeling demands and mitigating inter- and intra-observer variability in histological processes. Not applicable

BACKGROUND:Ganciclovir remains the primary therapeutic for cytomegalovirus (CMV) infections in early infancy, but its pharmacokinetics and dosing in very preterm infants with end-organ CMV disease have not been fully evaluated. METHODS:Premature infants with confirmed CMV infection and receiving ganciclovir as standard of care were enrolled into a pharmacokinetic (PK) sampling study. All infants were <32 weeks gestational age and >500 g at enrollment. Plasma for ganciclovir quantitation was collected at steady state at 0, 1, 2-3, 5-7, and 10-12 hours after the dose. Specimens were shipped and analyzed, and PK parameters were calculated in real time. Noncompartmental and modeling approaches were used for analysis. RESULTS:Eighteen infants were enrolled; their mean gestational age at delivery was 26.7 weeks, and their mean age and weight at enrollment were 42 days and 1519.0 g, respectively. PK assessments were completed in 17. The geometric mean dose and resulting 12-hour area under the curve were 5.19 mg/kg and 52.7 mg · h/L, respectively. A total of 85 ganciclovir concentration-time data points were available for modeling. A 1-compartment power covariate model with weight and serum creatinine on clearance and weight on distribution volume was used. Noncompartmental and modeled PK parameters were similar. CONCLUSIONS:These are the first intravenous ganciclovir population PK data with covariate assessments in premature infants being treated for CMV disease. Results suggest an intravenous dose of 5 mg/kg every 12 hours may be an appropriate starting regimen in of premature infants with congenital CMV. Additional data are needed in this and other populations to better define optimal ganciclovir exposure targets.

The progression of Alzheimer's disease (AD), a leading cause of dementia worldwide, is known for its variability and complexity, challenging the conventional methods of monitoring and predicting disease trajectories. This study introduces a semiparametric modeling approach to analyze longitudinal cognitive and imaging data. We studied two different outcome variables from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database: the Alzheimer's Disease Assessment Scale-Cognitive Subscale 13 (ADAS13) scores and ventricular volumes [Formula: see text]. Unlike traditional linear mixed effects models, semiparametric models do not assume a linear AD progression over time. Semiparametric models offer the advantage of capturing the non-linear features of AD progression, such as cognitive decline and neurodegeneration, represented by changes in ADAS13 scores and ventricular enlargement, respectively. By integrating regression splines and mixed modeling techniques, we provide a nuanced understanding of AD progression that captures the heterogeneity of disease trajectories. Our analysis reveals variations in the timing and degree of cognitive decline and neurodegeneration among AD patients, underlining the need for personalized approaches for monitoring and managing AD. This study's findings contribute to the modeling of AD progression and offer potential implications for interventions and prognostic assessments in clinical and research settings.

Objective Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that leads to cognitive decline and memory impairment, posing a public health concern in aging populations. Early and accurate detection of AD using non-invasive imaging biomarkers remains a critical clinical need for timely intervention and disease management. This study aimed to develop an advanced artificial intelligence (AI)-based diagnostic framework, ViTranZheimer, that leverages video vision transformers to analyze magnetic resonance imaging (MRI) and improve AD classification accuracy. Methods This study presents “ViTranZheimer,” an AD diagnosis approach that leverages video transformers to analyze MRI volumes. Our proposed deep learning framework aimed to improve the accuracy and sensitivity of AD diagnosis, thereby equipping clinicians with a tool for early detection and intervention. We exploited the temporal dependencies between slices by treating the MRI volumes as videos to capture intricate structural relationships. We evaluated ViTranZheimer on the publicly available Alzheimer’s Disease Neuroimaging Initiative: complete 3Yr 3T data collection, which includes 351 T1-weighted MRI scans categorized into normal controls (NC = 129), mild cognitive impairment (MCI = 145), and AD = 77 groups. Each MRI volume was preprocessed using spatial normalization and skull stripping, and modeled as a video sequence for input to a video vision transformer. The model was trained from scratch using 10-fold stratified cross-validation and optimized with the Adam optimizer over 500 epochs. Classification performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Statistical comparison was conducted using the Wilcoxon signed-rank test against 2 baseline models: a convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM) and vision transformer with bidirectional long short-term memory (ViT-BiLSTM). Results The proposed ViTranZheimer model achieved 98.6% accuracy in classifying NC, MCI, and AD cases, outperforming CNN-BiLSTM (96.5%) and ViT-BiLSTM (97.5%). It also attained superior precision, recall, F1-score (all 0.97), and an AUC of 0.99. Performance differences were statistically significant based on the Wilcoxon signed-rank test (P < 0.05). Conclusion ViTranZheimer demonstrated strong potential for accurate and early AD diagnosis using non-invasive MRI data. By leveraging video vision transformers, the model provides a promising tool for clinical decision support in neurodegenerative disease detection.

Abstract Background The most common cause of osteomyelitis and septic arthritis is Staphylococcus aureus. Vancomycin is a glycopeptide antibiotic used to treat proven or suspected methicillin-resistant S. aureus (MRSA). It is known to have serious adverse effects like nephrotoxicity and vancomycin infusion syndrome. Ceftaroline, a fifth-generation cephalosporin active against MRSA, is not approved by the Food and Drug Administration (FDA) for osteomyelitis or septic arthritis; but it is commonly used to treat bone and joint infections due to its range of activity and safety profile when compared to vancomycin.Table 1.Demographic, clinical and microbiological characteristics of patients treated with vancomycin, vancomycin followed by ceftaroline, and ceftaroline Methods This is a retrospective study of osteomyelitis and/or septic arthritis cases in children (0-18 years old) treated with Vancomycin and/or Ceftaroline between October 1st, 2019 to October 1st, 2023 admitted at Ochsner LSU Health Shreveport. Demographic data, pertinent medical history, days of antibiotic therapy, surgeries and microbiology results were collected. Complications during clinical course and treatment failure were reported.Table 2.Clinical outcomes of patients treated with vancomycin, vancomycin followed by ceftaroline, and ceftaroline.Fisher’s exact test was performed for all categorical variables. Results During the study period, 63 patients were admitted with osteomyelitis and/or septic arthritis and received either vancomycin (n=32), vancomycin followed by ceftaroline (n=21) or ceftaroline (n=10). Demographic, clinical, and microbiological data are presented in Table 1. Among treatment groups, one or more complications were reported per patient during admission. These included sepsis, multifocal disease, repeat imaging and additional surgeries. Treatment failure was defined as recrudescence, relapse, wound dehiscence, chronic osteomyelitis and non-union (Table 2). The vancomycin group had more treatment failures, with 9 patients (28%), when compared to 2 (20%) in the ceftaroline group and 1 (5%) in the group of vancomycin followed by ceftaroline. This difference was not statistically significant (p= 0.09) (Fig. 1). Side effects were only seen in the vancomycin group.Figure 1:Treatment failure per treatment group. Treatment failure was reported in 9 (28%) of 32 patients who received vancomycin alone, 2 (20%) of 10 patients on the ceftaroline group and 1 (5%) among 21 patients treated with vancomycin followed by ceftaroline. Fisher’s exact test was performed with a p value of 0.09. Conclusion This small retrospective study showed that children treated with vancomycin alone for bone and joint infections experienced more treatment failures. Side effects were only reported with vancomycin alone. Ceftaroline should be considered a safe alternative and promising empiric agent to treat osteomyelitis and septic arthritis in children. Disclosures John Vanchiere, MD, PhD, Biocryst: Advisor/Consultant|Biocryst: Grant/Research Support|Enanta: Grant/Research Support|GSK: Grant/Research Support|Merck: Grant/Research Support|Pfizer: Grant/Research Support|Tetraphase Pharmaceutical: Advisor/Consultant|Tetraphase Pharmaceutical: Grant/Research Support

CONTEXT:Metabolic dysfunction-associated steatotic liver disease (MASLD) is an umbrella term for simple hepatic steatosis and the more severe metabolic dysfunction-associated steatohepatitis. The current reliance on liver biopsy for diagnosis and a lack of validated biomarkers are major factors contributing to the overall burden of MASLD. OBJECTIVE:This study investigates the association between biomarkers and hepatic steatosis and stiffness measurements, measured by FibroScan®. METHODS:Data from the National Health and Nutritional Examination Survey (2017-2020) were collected for 15 560 patients. Propensity score matching balanced the data with a 1:1 case to control for age and sex allowing for preliminary trend assessment. Random Forest machine learning determined variable importance for the incorporation of key biomarkers (age, sex, race, BMI, HbA1c, plasma fasting glucose, insulin, total cholesterol, LDL-cholesterol, HDL-cholesterol, triglycerides, ALT, AST, ALP, albumin, GGT, LDH, iron, total bilirubin, total protein, uric acid, BUN, and hs-CRP) into logistic regression models predicting steatosis (MASLD indicated by a controlled attenuation parameter score of ≥238 dB/m) and stiffness (hepatic fibrosis indicated by a median liver stiffness ≥7 kPa). Sensitivity analysis using XGBoost and Recursive Feature Elimination was performed. RESULTS:The Random Forest models (the most accurate) predicted MASLD with 79.59% accuracy (P < .001) and specificity of 84.65% and predicted hepatic fibrosis with 86.07% accuracy (P < .001) and sensitivity of 98.01%. Both the steatosis and stiffness models identified statistically significant biomarkers, with age, BMI, and insulin appearing significant to both. CONCLUSION:These findings indicate that assessing a variety of biomarkers, across demographic, metabolic, lipid, and standard biochemistry categories, may provide valuable initial insights for diagnosing patients for MASLD and hepatic fibrosis.

Alzheimer's disease (AD) is a neurodegenerative disorder affecting millions worldwide, necessitating early and accurate diagnosis for optimal patient management. In recent years, advancements in deep learning have shown remarkable potential in medical image analysis. Methods In this study, we present "ViTranZheimer," an AD diagnosis approach which leverages video vision transformers to analyze 3D brain MRI data. By treating the 3D MRI volumes as videos, we exploit the temporal dependencies between slices to capture intricate structural relationships. The video vision transformer's self-attention mechanisms enable the model to learn long-range dependencies and identify subtle patterns that may indicate AD progression. Our proposed deep learning framework seeks to enhance the accuracy and sensitivity of AD diagnosis, empowering clinicians with a tool for early detection and intervention. We validate the performance of the video vision transformer using the ADNI dataset and conduct comparative analyses with other relevant models. Results The proposed ViTranZheimer model is compared with two hybrid models, CNN-BiLSTM and ViT-BiLSTM. CNN-BiLSTM is the combination of a convolutional neural network (CNN) and a bidirectional long-short-term memory network (BiLSTM), while ViT-BiLSTM is the combination of a vision transformer (ViT) with BiLSTM. The accuracy levels achieved in the ViTranZheimer, CNN-BiLSTM, and ViT-BiLSTM models are 98.6 demonstrated the highest accuracy at 98.6 evaluation metric, indicating its superior performance in this specific evaluation metric. Conclusion This research advances the understanding of applying deep learning techniques in neuroimaging and Alzheimer's disease research, paving the way for earlier and less invasive clinical diagnosis.

Wastewater has previously been used to monitor infectious diseases, drugs of misuse, and chemical exposures, including relating the prevalence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) to the population served. Most wastewater studies have used wastewater treatment plant (WWTP) sampling to assess county-level dynamics in SARS-CoV-2 prevalence. However, little is known regarding how viral prevalence and population coverage at WWTP sites influence predictions of county-level dynamics in SARS-CoV-2. Even less information is available from sampling at the level of individual neighborhoods. In this study, samples were collected during the Delta wave of the SARS-CoV-2 pandemic at two WWTPs and three neighborhoods in Shreveport, LA (total population of approximately 200,000 residents). The neighborhoods (10k-20k residents) and WWTPs (15 % versus 80 %) varied in the prevalence of the virus as well as the percent of the overall population that they covered. Grab samples were collected twice per month and normalized the data using pepper mild mottle virus (PMMoV) to correct for the size of the contributing population. Both treatment plants showed a significant correlation between SARS-CoV-2 levels in wastewater and the number of individual positive SARS-CoV-2 cases at the county level. The smaller plant, WWTP B, had a significantly larger viral prevalence per capita. The plant serving a larger population, WWTP A, was predictive of county positive SARS-CoV-2 cases up to 12 days in advance, whereas the smaller population covering plant, WWTP B, was only predictive out to 7 days. At the level of the neighborhood, the sampling site with the higher level of SARS-CoV-2 per capita showed the strongest relationship to both county cases and the earliest prediction of their increase. These findings suggest that the characteristics of wastewater sampling sites are major determinants of the public health information that can be derived from monitoring those sites.

Objective:Alzheimer's disease (AD) is a progressive neurodegenerative disorder that leads to cognitive decline and memory impairment, posing a public health concern in aging populations. Early and accurate detection of AD using non-invasive imaging biomarkers remains a critical clinical need for timely intervention and disease management. This study aims to develop an advanced artificial intelligence (AI)-based diagnostic framework, ViTranZheimer, that leverages video vision transformers to analyze magnetic resonance imaging (MRI) and improve the accuracy of AD classification. Methods:This study presents 'ViTranZheimer,' an AD diagnosis approach that leverages video transformers to analyze MRI volumes. Our proposed deep learning framework aims to improve the accuracy and sensitivity of AD diagnosis, equipping clinicians with a tool for early detection and intervention. We exploit the temporal dependencies between slices by treating the MRI volumes as videos to capture intricate structural relationships. We evaluated ViTranZheimer on the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI): Complete 3Yr 3T data collection, which includes 351 T1-weighted MRI scans categorized into normal controls (NC = 129), mild cognitive impairment (MCI = 145), and AD = 77 groups. Each MRI volume was preprocessed using spatial normalization and skull stripping, then modeled as a video sequence for input to a Video Vision Transformer (ViViT). The model was trained from scratch using 10-fold stratified cross-validation and optimized with the Adam optimizer over 500 epochs. Classification performance was evaluated using accuracy, precision, recall, F1-score, and area under the ROC curve (AUC). Statistical comparison was conducted using the Wilcoxon signed-rank test against two baseline models: a convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM), and a vision transformer with bidirectional long short-term memory (ViT-BiLSTM). Results:The proposed ViTranZheimer model achieved 98.6% accuracy in classifying NC, MCI, and AD cases, outperforming CNN-BiLSTM (96.5%) and ViT-BiLSTM (97.5%). It also attained superior precision, recall, F1-score (all 0.97), and an AUC of 0.99. Performance differences were statistically significant based on the Wilcoxon signed-rank test (P < 0.05). Conclusion:ViTranZheimer demonstrates strong potential for accurate and early Alzheimer's disease diagnosis using non-invasive MRI data. By leveraging video vision transformers, the model provides a promising tool for clinical decision support in neurodegenerative disease detection.

Alzheimer’s disease (AD), a neurodegenerative disease that mostly affects the elderly, slowly impairs memory, cognition, and daily tasks. AD has long been one of the most debilitating chronic neurological disorders, affecting mostly people over 65. In this study, we investigated the use of Vision Transformer (ViT) for Magnetic Resonance Image processing in the context of AD diagnosis. ViT was utilized to extract features from MRIs, map them to a feature sequence, perform sequence modeling to maintain interdependencies, and classify features using a time series transformer. The proposed model was evaluated using ADNI T1-weighted MRIs for binary and multiclass classification. Two data collections, Complete 1Yr 1.5T and Complete 3Yr 3T, from the ADNI database were used for training and testing. A random split approach was used, allocating 60% for training and 20% for testing and validation, resulting in sample sizes of (211, 70, 70) and (1378, 458, 458), respectively. The performance of our proposed model was compared to various deep learning models, including CNN with BiL-STM and ViT with Bi-LSTM. The suggested technique diagnoses AD with high accuracy (99.048% for binary and 99.014% for multiclass classification), precision, recall, and F-score. Our proposed method offers researchers an approach to more efficient early clinical diagnosis and interventions.

Methamphetamine is a growing health problem, as is mental health illness. However, no studies have investigated the combinatory effects of both diseases or characterized national trends over a period of time greater than 10 years. We evaluated US trends in mental health disorder-related hospital admissions (MHD-HAs) and compared them with those with concurrent methamphetamine use (MHD-HA-MUs), comparing the demographic characteristics from 2008 to 2020. Our findings reveal a significant increase in MHD-HA-MUs, increasing 10.5-fold, compared with a 1.4-fold increase in MHD-HAs. We also found a 1.53 times higher adjusted prevalence ratio of MHD-HA-MUs compared with MHD-HAs, even when adjusted for confounding factors. MHD-HA-MUs increased significantly among male patients (13-fold), non-Hispanic Black patients (39-fold), those aged 41-64 years (16-fold), and the South (24-fold). Overall, the data suggest that there are synergistic effects with methamphetamine use and mental health disorder, highlighting this patient group's unique needs, requiring distinct action.

Background Subjects with metabolic syndrome and obesity have higher levels of inflammation with depression of the vitamin D (VD) hydroxylase/metabolising genes (CYP2R1/CYP27A1/CYP27B1/VDR) required to convert VD consumed in the diet into 25(OH)VD. Compared with total 25(OH)VD levels, measurement of bioavailable 25(OH)VD is a better method to determine the beneficial effect of VD.Objective This study investigates whether cosupplementation with VD and L-cysteine (LC), which downregulates inflammation and upregulates VD-regulating genes, provides a better therapeutic benefit than supplementation with VD-alone in African Americans (AA).Methods AA participants (men/women, aged 18–65 years; n=165) were block randomised into one of four groups and received daily, oral supplementation for 6 months with placebo, LC (1000 mg/day), VD (2000 IU/day) or VD+LC. Fasting blood collected at the baseline and final visits was analysed for total, free and bioavailable 25(OH)VD along with insulin, VD-binding protein (VDBP), sex hormone-binding globulin (SHBG), free and total testosterone, and inflammatory marker levels. Studies were carried out in THP-1 monocytes to elucidate the direct effect of LC and testosterone on VD-regulating genes.Results Baseline data showed no differences in age, body mass index, calcium, liver or kidney function among the groups. Compared with levels in the group that received VD-alone supplementation, levels of neutrophil-to-lymphocyte ratio, C reactive protein, HOMA-IR, VDBP and HbA1c were significantly lower in the VD+LC group while the VD+LC group showed a significant increase in bioavailable 25(OH)VD in both sexes, total 25(OH)VD levels were significantly elevated in men but not in women treated with VD+LC. Blood levels of SHBG and free/total testosterone were elevated in the VD+LC group but not in the VD-alone group. LC and testosterone treatment significantly upregulated VD-metabolising genes (CYP2R1/CYP27A1/CYP27B1/VDR) and SHBG in THP-1 monocytes.Conclusions VD cosupplemented with LC upregulates circulating bioavailable 25(OH)VD and reduces inflammation. Total 25(OH)VD levels were higher in men but not in women in the VD+LC group. This pilot study suggests that compared with supplementation with VD-alone, VD+LC cosupplementation could be a better approach to raising the total 25(OH)VD in men and the bioavailable 25(OH)VD in both sexes and lowering the inflammatory risk in the AA population.Trial registration number NCT04939792.

Purpose:Alzheimer's disease (AD), a neurodegenerative disorder, is a condition that impairs cognition, memory, and behavior. Mild cognitive impairment (MCI), a transitional stage before AD, urgently needs the development of prediction models for conversion from MCI to AD. Method:This study used machine learning methods to predict whether MCI subjects would develop AD, highlighting the importance of biomarkers (biological indicators from neuroimaging, such as MRI and PET scans, and molecular assays from cerebrospinal fluid or blood) and non-biomarker features in AD research and clinical practice. These indicators aid in early diagnosis, disease monitoring, and the development of potential treatments for MCI subjects. Using baseline data, which includes measurements of different biomarkers, we predicted disease progression at the patient's last visit. The Shapley value explanation (SHAP) technique was used to identify key features for predicting patient progression. Results:The study used the ADNI database to evaluate the effectiveness of eight classification methods for predicting progression from MCI to AD. Four fundamental data sampling approaches were compared to balance the dataset and reduce overfitting. The SHAP technique improved the ability to identify biomarkers and non-biomarker features, enhancing the prediction of disease progression. NEAR-MISS was found to be the most advantageous sampling method, while XGBoost was found to be the superior classification method, offering enhanced accuracy and predictive power. Conclusion:The proposed SHAP for feature selection combined with XGBoost may provide improved predictive accuracy in diagnosing Alzheimer's patients.

Heart disease is the leading cause of death worldwide, and cardiac function as measured by ejection fraction (EF) is an important determinant of outcomes, making accurate measurement a critical parameter in PT evaluation. Echocardiograms are commonly used for measuring EF, but human interpretation has limitations in terms of intra- and inter-observer (or reader) variance. Deep learning (DL) has driven a resurgence in machine learning, leading to advancements in medical applications. We introduce the ViViEchoformer DL approach, which uses a video vision transformer to directly regress the left ventricular function (LVEF) from echocardiogram videos. The study used a dataset of 10,030 apical-4-chamber echocardiography videos from patients at Stanford University Hospital. The model accurately captures spatial information and preserves inter-frame relationships by extracting spatiotemporal tokens from video input, allowing for accurate, fully automatic EF predictions that aid human assessment and analysis. The ViViEchoformer's prediction of ejection fraction has a mean absolute error of 6.14%, a root mean squared error of 8.4%, a mean squared log error of 0.04, and an R^2 of 0.55. ViViEchoformer predicted heart failure with reduced ejection fraction (HFrEF) with an area under the curve of 0.83 and a classification accuracy of 87 using a standard threshold of less than 50% ejection fraction. Our video-based method provides precise left ventricular function quantification, offering a reliable alternative to human evaluation and establishing a fundamental basis for echocardiogram interpretation.