Biomedicines. 2025 Apr 13;13(4):951. doi: 10.3390/biomedicines13040951.

ABSTRACT

Cancer remains one of the leading causes of mortality worldwide, driving the need for innovative approaches in research and treatment. Artificial intelligence (AI) has emerged as a powerful tool in oncology, with the potential to revolutionize cancer diagnosis, treatment, and management. This paper reviews recent advancements in AI applications within cancer research, focusing on early detection through computer-aided diagnosis, personalized treatment strategies, and drug discovery. We survey AI-enhanced diagnostic applications and explore AI techniques such as deep learning, as well as the integration of AI with nanomedicine and immunotherapy for cancer care. Comparative analyses of AI-based models versus traditional diagnostic methods are presented, highlighting AI's superior potential. Additionally, we discuss the importance of integrating social determinants of health to optimize cancer care. Despite these advancements, challenges such as data quality, algorithmic biases, and clinical validation remain, limiting widespread adoption. The review concludes with a discussion of the future directions of AI in oncology, emphasizing its potential to reshape cancer care by enhancing diagnosis, personalizing treatments and targeted therapies, and ultimately improving patient outcomes.

PMID:40299653 | DOI:10.3390/biomedicines13040951

Pac Symp Biocomput. 2025;30:675-689. doi: 10.1142/9789819807024_0048.

ABSTRACT

Alzheimer's disease (AD) is a neurocognitive disorder that deteriorates memory and impairs cognitive functions. Mild Cognitive Impairment (MCI) is generally considered as an intermediate phase between normal cognitive aging and more severe conditions such as AD. Although not all individuals with MCI will develop AD, they are at an increased risk of developing AD. Diagnosing AD once strong symptoms are already present is of limited value, as AD leads to irreversible cognitive decline and brain damage. Thus, it is crucial to develop methods for the early prediction of AD in individuals with MCI. Recurrent Neural Networks (RNN)-based methods have been effectively used to predict the progression from MCI to AD by analyzing electronic health records (EHR). However, despite their widespread use, existing RNN-based tools may introduce increased model complexity and often face difficulties in capturing long-term dependencies. In this study, we introduced a novel Dynamic deep learning model for Early Prediction of AD (DyEPAD) to predict MCI subjects' progression to AD utilizing EHR data. In the first phase of DyEPAD, embeddings for each time step or visit are captured through Graph Convolutional Networks (GCN) and aggregation functions. In the final phase, DyEPAD employs tensor algebraic operations for frequency domain analysis of these embeddings, capturing the full scope of evolutionary patterns across all time steps. Our experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and National Alzheimer's Coordinating Center (NACC) datasets demonstrate that our proposed model outperforms or is in par with the state-of-the-art and baseline methods.

PMID:40299624 | DOI:10.1142/9789819807024_0048

Pac Symp Biocomput. 2025;30:565-579. doi: 10.1142/9789819807024_0040.

ABSTRACT

Precision medicine significantly enhances patients prognosis, offering personalized treatments. Particularly for metastatic cancer, incorporating primary tumor location into the diagnostic process greatly improves survival rates. However, traditional methods rely on human expertise, requiring substantial time and financial resources. To address this challenge, Machine Learning (ML) and Deep Learning (DL) have proven particularly effective. Yet, their application to medical data, especially genomic data, must consider and encompass privacy due to the highly sensitive nature of data. In this paper, we propose OGHE, a convolutional neural network-based approach for privacy-preserving cancer classification designed to exploit spatial patterns in genomic data, while maintaining confidentiality by means of Homomorphic Encryption (HE). This encryption scheme allows the processing directly on encrypted data, guaranteeing its confidentiality during the entire computation. The design of OGHE is specific for privacy-preserving applications, taking into account HE limitations from the outset, and introducing an efficient packing mechanism to minimize the computational overhead introduced by HE. Additionally, OGHE relies on a novel feature selection method, VarScout, designed to extract the most significant features through clustering and occurrence analysis, while preserving inherent spatial patterns. Coupled with VarScout, OGHE has been compared with existing privacy-preserving solutions for encrypted cancer classification on the iDash 2020 dataset, demonstrating their effectiveness in providing accurate privacy-preserving cancer classification, and reducing latency thanks to our packing mechanism. The code is released to the scientific community.

PMID:40299616 | DOI:10.1142/9789819807024_0040

Pac Symp Biocomput. 2025;30:167-184. doi: 10.1142/9789819807024_0013.

ABSTRACT

Accurate prediction of suicide risk is crucial for identifying patients with elevated risk burden, helping ensure these patients receive targeted care. The US Department of Veteran Affairs' suicide prediction model primarily leverages structured electronic health records (EHR) data. This approach largely overlooks unstructured EHR, a data format that could be utilized to enhance predictive accuracy. This study aims to enhance suicide risk models' predictive accuracy by developing a model that incorporates both structured EHR predictors and semantic NLP-derived variables from unstructured EHR. XGBoost models were fit to predict suicide risk- the interactions identified by the model were extracted using SHAP, validated using logistic regression models, added to a ridge regression model, which was subsequently compared to a ridge regression approach without the use of interactions. By introducing a selection parameter, α, to balance the influence of structured (α=1) and unstructured (α=0) data, we found that intermediate α values achieved optimal performance across various risk strata, improved model performance of the ridge regression approach and uncovered significant cross-modal interactions between psychosocial constructs and patient characteristics. These interactions highlight how psychosocial risk factors are influenced by individual patient contexts, potentially informing improved risk prediction methods and personalized interventions. Our findings underscore the importance of incorporating nuanced narrative data into predictive models and set the stage for future research that will expand the use of advanced machine learning techniques, including deep learning, to further refine suicide risk prediction methods.

PMID:40299589 | DOI:10.1142/9789819807024_0013

JMIR AI. 2025 Apr 29;4:e76150. doi: 10.2196/76150.

ABSTRACT

[This corrects the article DOI: 10.2196/67239.].

PMID:40299541 | DOI:10.2196/76150

Biomedicines. 2025 Mar 31;13(4):836. doi: 10.3390/biomedicines13040836.

ABSTRACT

Pancreatic cancer is one of the most lethal neoplasms. Despite considerable research conducted in recent decades, not much has been achieved to improve its survival rate. That may stem from the lack of effective screening strategies in increased pancreatic cancer risk groups. One population that may be appropriate for screening is new-onset diabetes (NOD) patients. Such a conclusion stems from the fact that pancreatic cancer can cause diabetes several months before diagnosis. The most widely used screening tool for this population, the ENDPAC (Enriching New-Onset Diabetes for Pancreatic Cancer) model, has not achieved satisfactory results in validation trials. This provoked the first attempts at using artificial intelligence (AI) to create larger, multi-parameter models that could better identify the at-risk population, which would be suitable for screening. The results shown by the authors of these trials seem promising. Nonetheless, the number of publications is limited, and the downfalls of using AI are not well highlighted. This narrative review presents a summary of previous publications, recent advancements and feasible solutions for effective screening of patients with NOD for pancreatic cancer.

PMID:40299428 | DOI:10.3390/biomedicines13040836

Biomedicines. 2025 Apr 1;13(4):846. doi: 10.3390/biomedicines13040846.

ABSTRACT

Improved image quality, better scanners, innovative software technologies, enhanced computational power, superior network connectivity, and the ease of virtual image reproduction and distribution are driving the potential use of digital pathology for diagnosis and education. Although relatively common in clinical oncology, its application in liver pathology is under development. Digital pathology and improving subjective histologic scoring systems could be essential in managing obesity-associated steatotic liver disease. The increasing use of digital pathology in analyzing liver specimens is particularly intriguing as it may offer a more detailed view of liver biology and eliminate the incomplete measurement of treatment responses in clinical trials. The objective and automated quantification of histological results may help establish standardized diagnosis, treatment, and assessment protocols, providing a foundation for personalized patient care. Our experience with artificial intelligence (AI)-based software enhances reproducibility and accuracy, enabling continuous scoring and detecting subtle changes that indicate disease progression or regression. Ongoing validation highlights the need for collaboration between pathologists and AI developers. Concurrently, automated image analysis can address issues related to the historical failure of clinical trials stemming from challenges in histologic assessment. We discuss how these novel tools can be incorporated into liver research and complement post-diagnosis scenarios where quantification is necessary, thus clarifying the evolving role of digital pathology in the field.

PMID:40299404 | DOI:10.3390/biomedicines13040846

Int J Comput Assist Radiol Surg. 2025 Apr 29. doi: 10.1007/s11548-025-03369-2. Online ahead of print.

ABSTRACT

PURPOSE: Automated localization of critical anatomical structures in endoscopic pituitary surgery is crucial for enhancing patient safety and surgical outcomes. While deep learning models have shown promise in this task, their predictions often suffer from frame-to-frame inconsistency. This study addresses this issue by proposing ConsisTNet, a novel spatio-temporal model designed to improve prediction stability.

METHODS: ConsisTNet leverages spatio-temporal features extracted from consecutive frames to provide both temporally and spatially consistent predictions, addressing the limitations of single-frame approaches. We employ a semi-supervised strategy, utilizing ground-truth label tracking for pseudo-label generation through label propagation. Consistency is assessed by comparing predictions across consecutive frames using predicted label tracking. The model is optimized and accelerated using TensorRT for real-time intraoperative guidance.

RESULTS: Compared to previous state-of-the-art models, ConsisTNet significantly improves prediction consistency across video frames while maintaining high accuracy in segmentation and landmark detection. Specifically, segmentation consistency is improved by 4.56 and 9.45% in IoU for the two segmentation regions, and landmark detection consistency is enhanced with a 43.86% reduction in mean distance error. The accelerated model achieves an inference speed of 202 frames per second (FPS) with 16-bit floating point (FP16) precision, enabling real-time intraoperative guidance.

CONCLUSION: ConsisTNet demonstrates significant improvements in spatio-temporal consistency of anatomical localization during endoscopic pituitary surgery, providing more stable and reliable real-time surgical assistance.

PMID:40299263 | DOI:10.1007/s11548-025-03369-2

Nanomicro Lett. 2025 Apr 29;17(1):241. doi: 10.1007/s40820-025-01757-6.

ABSTRACT

Bimodal pressure sensors capable of simultaneously detecting static and dynamic forces are essential to medical detection and bio-robotics. However, conventional pressure sensors typically integrate multiple operating mechanisms to achieve bimodal detection, leading to complex device architectures and challenges in signal decoupling. In this work, we address these limitations by leveraging the unique piezotronic effect of Y-ion-doped ZnO to develop a bimodal piezotronic sensor (BPS) with a simplified structure and enhanced sensitivity. Through a combination of finite element simulations and experimental validation, we demonstrate that the BPS can effectively monitor both dynamic and static forces, achieving an on/off ratio of 1029, a gauge factor of 23,439 and a static force response duration of up to 600 s, significantly outperforming the performance of conventional piezoelectric sensors. As a proof-of-concept, the BPS demonstrates the continuous monitoring of Achilles tendon behavior under mixed dynamic and static loading conditions. Aided by deep learning algorithms, the system achieves 96% accuracy in identifying Achilles tendon movement patterns, thus enabling warnings for dangerous movements. This work provides a viable strategy for bimodal force monitoring, highlighting its potential in wearable electronics.

PMID:40299192 | DOI:10.1007/s40820-025-01757-6

Eur Radiol Exp. 2025 Apr 29;9(1):44. doi: 10.1186/s41747-025-00584-z.

ABSTRACT

BACKGROUND: T2-weighted images are a critical component of prostate magnetic resonance imaging (MRI), and it would be useful to automatically assess image quality (IQ) on a patient-specific basis without radiologist oversight.

METHODS: This retrospective study comprised 1,412 axial T2-weighted prostate scans. Four experienced uroradiologists graded IQ using a 0-to-3 scale (0 = uninterpretable; 1 = marginally interpretable; 2 = adequately diagnostic; 3 = more than adequately diagnostic), binarized into nondiagnostic (IQ0 or IQ1), requiring rescanning, and diagnostic (IQ2 or IQ3), not requiring rescanning. The deep learning (DL) model was trained on 1,006 scans; 203 other scans were used for validation of multiple convolutional neural networks; the remaining 203 exams were used as a test set. 3D-DenseNet_169 was chosen among 11 models based on multiple evaluation criteria. The rescan predictions were compared to the number of rescans performed on a subset of 174 exams.

RESULTS: The model accurately predicts radiologist IQ scores (Cohen κ = 0.658), similar to the human inter-rater reliability (κ = 0.688-0.791). The model also predicts rescanning necessity similarly to radiologists: model κ = 0.537; reviewer κ = 0.577-0.703. The rescan model prediction area under the curve was 0.867.

CONCLUSION: The DL model showed a strong ability to differentiate diagnostic from nondiagnostic axial T2-weighted prostate images, accurately mimicking expert radiologists' IQ scores. Using the model, the clinical unnecessary rescan rate could be reduced from over 50% to less than 30%.

RELEVANCE STATEMENT: DL assessment of T2-weighted prostate MRI scans can accurately assess IQ, determining the need to repeat inadequate scans as well as avoiding repeat scans of those with adequate diagnostic quality, resulting in reduced unnecessary rescanning.

KEY POINTS: Artificial intelligence assessment of prostate MRI T2-weighted image quality can improve exam time management. The model showed over 75% accuracy in assessing prostate MRI T2-weighted image quality. Expert radiologists have a substantial agreement in evaluating prostate MRI T2-weighted image quality.

PMID:40299162 | DOI:10.1186/s41747-025-00584-z

Anal Chem. 2025 Apr 29. doi: 10.1021/acs.analchem.5c00306. Online ahead of print.

ABSTRACT

Cell-cell interactions are crucial for understanding various physiological and pathological processes, yet conventional population-level methods fail to disclose the heterogeneity at a single-cell resolution. Single-cell coculture systems that isolate and cultivate single-cell pairs can help reveal heterogeneous interactions between different types of individual cells. However, precise and high-throughput pairing of individual cells for long-term coculture remains challenging. Meanwhile, tools for analyzing single-cell data sets have lagged due to the increased data throughput. Herein, we report a deep learning-assisted high-throughput addressable single-cell coculture system (DL-HASCCS), enabling fast pairing of individual heterogeneous cells and quantitative analysis of single-cell interactions in a high-throughput manner by integrating high-throughput single-cell cocultivation and automated data processing. By analyzing the interaction between single breast cancer cells and single endothelial cells under normal and chemotherapy conditions, the effect of cell-cell interactions on cell proliferation and migration is revealed at the single-cell level, providing valuable insights into cellular heterogeneity.

PMID:40298933 | DOI:10.1021/acs.analchem.5c00306

Adv Sci (Weinh). 2025 Apr 29:e2501750. doi: 10.1002/advs.202501750. Online ahead of print.

ABSTRACT

Despite being a serious health condition that significantly increases cardiovascular and metabolic disease risks, sleep apnea syndrome (SAS) remains largely underdiagnosed. While polysomnography (PSG) remains the gold standard for diagnosis, its clinical application is limited by high costs, complex setup requirements, and sleep quality interference. Although wearable devices using photoplethysmography (PPG) have shown promise in SAS detection, their continuous operation demands substantial power consumption, hindering long-term monitoring capabilities. Here, a dual-modal wearable system is presented integrating a piezoelectric nanogenerator (PENG) and PPG sensor with a biomimetic fingertip structure for SAS detection. A two-stage detection strategy is adopted where the self-powered PENG performs continuous preliminary screening, activating the PPG sensor only when suspicious events are detected. Combined with a Vision Transformer-based deep learning model, the high-accuracy configuration achieves 99.59% accuracy, while the low-power two-stage approach maintained 94.95% accuracy. This dual-modal wearable pulse detection system provides a practical solution for long-term SAS monitoring, overcoming the limitations of traditional PSG while maintaining high detection accuracy. The system's versatility in both home and clinical settings offers the potential for improving early detection rates and treatment outcomes for SAS patients.

PMID:40298874 | DOI:10.1002/advs.202501750

Radiology. 2025 Apr;315(1):e242570. doi: 10.1148/radiol.242570.

ABSTRACT

Background Precise assessment of myocardial ischemia burden and cardiovascular risk stratification based on dynamic CT myocardial perfusion imaging (MPI) is lacking. Purpose To develop and validate a deep learning (DL) model for automated quantification of myocardial blood flow (MBF) and ischemic myocardial volume (IMV) percentage and to explore the prognostic value for major adverse cardiovascular events (MACE). Materials and Methods This multicenter study comprised three cohorts of patients with clinically indicated CT MPI and coronary CT angiography (CCTA). Cohorts 1 and 2 were retrospective cohorts (May 2021 to June 2023 and January 2018 to December 2022, respectively). Cohort 3 was prospectively included (November 2016 to December 2021). The DL model was developed in cohort 1 (training set: 211 patients, validation set: 57 patients, test set: 90 patients). The diagnostic performance of MBF derived from the DL model (MBFDL) for myocardial ischemia was evaluated in cohort 2 based on the area under the receiver operating characteristic curve (AUC). The prognostic value of the DL model-derived IMV percentage was assessed in cohort 3 using multivariable Cox regression analyses. Results Across three cohorts, 1108 patients (mean age: 61 years ± 12 [SD]; 667 men) were included. MBFDL showed excellent agreement with manual measurements in the test set (segment-level intraclass correlation coefficient = 0.928; 95% CI: 0.921, 0.935). MBFDL showed higher diagnostic performance (vessel-based AUC: 0.97) over CT-derived fractional flow reserve (FFR) (vessel-based AUC: 0.87; P = .006) and CCTA-derived diameter stenosis (vessel-based AUC: 0.79; P < .001) for hemodynamically significant lesions, compared with invasive FFR. Over a mean follow-up of 39 months, MACE occurred in 94 (14.2%) of 660 patients. IMV percentage was an independent predictor of MACE (hazard ratio = 1.12, P = .003), with incremental prognostic value (C index: 0.86; 95% CI: 0.84, 0.88) over conventional risk factors and CCTA parameters (C index: 0.84; 95% CI: 0.82, 0.86; P = .02). Conclusion A DL model enabled automated CT MBF quantification and accurate diagnosis of myocardial ischemia. DL model-derived IMV percentage was an independent predictor of MACE and mildly improved cardiovascular risk stratification. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Zhu and Xu in this issue.

PMID:40298595 | DOI:10.1148/radiol.242570

Anal Chem. 2025 Apr 29. doi: 10.1021/acs.analchem.4c06014. Online ahead of print.

ABSTRACT

The efficiency and resolution of dispersive spectrometers play crucial roles in optical spectroscopy. Achieving optimal analytical performance in optical spectroscopy requires striking a delicate balance between employing a narrow spectrometer input slit to enhance spectral resolution while sacrificing throughput or utilizing a wider slit to increase throughput at the expense of resolution. Here, we introduce a spectrometer slit empowered by a deep learning model SlitNET. We trained a neural network to reconstruct synthetic Raman spectra with enhanced resolution from low-resolution inputs. Subsequently, we performed transfer learning from synthetic data to experimental Raman data of materials. By fine-tuning the model with experimental data, we recovered high-resolution Raman spectra. This enhancement enabled us to distinguish between materials that were previously indistinguishable when using a wide slit. SlitNET achieved a resolution enhancement equivalent to employing a 10 μm slit size but with a physical input slit of 100 μm. This, in turn, enables us to simultaneously achieve high throughput and resolution, thereby enhancing the analytic sensitivity and specificity in optical spectroscopy. The incorporation of deep learning into spectrometers highlights the convergence of photonic instrumentation and artificial intelligence, offering improved measurement accuracy across various optical spectroscopy applications.

PMID:40298458 | DOI:10.1021/acs.analchem.4c06014

Res Sq [Preprint]. 2025 Apr 7:rs.3.rs-6149503. doi: 10.21203/rs.3.rs-6149503/v1.

ABSTRACT

Recently, topological deep learning (TDL), which integrates algebraic topology with deep neural networks, has achieved tremendous success in processing point-cloud data, emerging as a promising paradigm in data science. However, TDL has not been developed for data on differentiable manifolds, including images, due to the challenges posed by differential topology. We address this challenge by introducing manifold topological deep learning (MTDL) for the first time. To highlight the power of Hodge theory rooted in differential topology, we consider a simple convolutional neural network (CNN) in MTDL. In this novel framework, original images are represented as smooth manifolds with vector fields that are decomposed into three orthogonal components based on Hodge theory. These components are then concatenated to form an input image for the CNN architecture. The performance of MTDL is evaluated using the MedMNIST v2 benchmark database, which comprises 717,287 biomedical images from eleven 2D and six 3D datasets. MTDL significantly outperforms other competing methods, extending TDL to a wide range of data on smooth manifolds.

PMID:40297704 | PMC:PMC12036455 | DOI:10.21203/rs.3.rs-6149503/v1

Head Neck Tumor Segm MR Guid Appl (2024). 2025;15273:99-111. doi: 10.1007/978-3-031-83274-1_7. Epub 2025 Mar 3.

ABSTRACT

Accurate segmentation of gross tumor volume (GTV) is essential for effective MRI-guided adaptive radiotherapy (MRgART) in head and neck cancer. However, manual segmentation of the GTV over the course of therapy is time-consuming and prone to interobserver variability. Deep learning (DL) has the potential to overcome these challenges by automatically delineating GTVs. In this study, our team, UW LAIR, tackled the challenges of both pre-radiotherapy (pre-RT) (Task 1) and mid-radiotherapy (mid-RT) (Task 2) tumor volume segmentation. To this end, we developed a series of DL models for longitudinal GTV segmentation. The backbone of our models for both tasks was SegResNet with deep supervision. For Task 1, we trained the model using a combined dataset of pre-RT and mid-RT MRI data, which resulted in the improved aggregated Dice similarity coefficient (DSCagg) on a hold-out internal testing set compared to models trained solely on pre-RT MRI data. In Task 2, we introduced mask-aware attention modules, enabling pre-RT GTV masks to influence intermediate features learned from mid-RT data. This attention-based approach yielded slight improvements over the baseline method, which concatenated mid-RT MRI with pre-RT GTV masks as input. In the final testing phase, the ensemble of 10 pre-RT segmentation models achieved an average DSCagg of 0.794, with 0.745 for primary GTV (GTVp) and 0.844 for metastatic lymph nodes (GTVn) in Task 1. For Task 2, the ensemble of 10 mid-RT segmentation models attained an average DSCagg of 0.733, with 0.607 for GTVp and 0.859 for GTVn, leading us to achieve 1st place. In summary, we presented a collection of DL models that could facilitate GTV segmentation in MRgART, offering the potential to streamline radiation oncology workflows.

PMID:40297614 | PMC:PMC12036643 | DOI:10.1007/978-3-031-83274-1_7

medRxiv [Preprint]. 2025 Apr 11:2025.04.08.25325262. doi: 10.1101/2025.04.08.25325262.

ABSTRACT

Late-onset Tay-Sachs (LOTS) disease and late-onset Sandhoff disease (LOSD) have long been considered indistinguishable due to similar clinical presentations and shared biochemical deficits. However, recent magnetic resonance imaging (MRI) studies have shown distinct cerebellar atrophy associated with LOTS. In this study, we furthered this investigation to determine if the cerebellar atrophy is globally uniform or preferentially targets certain cerebellar regions. We utilized DeepCERES , a deep learning cerebellar specific segmentation and cortical thickness pipeline to analyze differences between LOTS (n=20), LOSD (n=5), and neurotypical controls (n=1038). LOTS had smaller volumes of the whole cerebellum as well as cerebellar lobules IV, V, VI, VIIB, VIIIA, VIIIB, IX, and both Crus I and II compared to both LOSD and neurotypical controls. LOTS patients also had smaller cortical thickness of cerebellar lobules V, VI, VIIB, VIIIA, VIIIB, and both Crus I and II compared to both LOSD and neurotypical controls. Cerebellar functional and lesion localization studies have implicated lobules V and VI in speech articulation and execution while lobules VI, Crus I, VIIA, among others, have been implicated in a variety of behaviors and neuropsychiatric symptoms. Our observations provide a possible anatomical substrate to the higher prevalence of dysarthria and psychosis in our LOTS but not LOSD patients. Future studies are needed for direct comparisons considering phenotypic aspects such as age of symptom onset, presence and severity of dysarthria and ataxia, full characterization of neuropsychiatric profiles, molecular pathology and biochemical differences to fully understand the dichotomy observed in these two diseases.

PMID:40297453 | PMC:PMC12036421 | DOI:10.1101/2025.04.08.25325262

medRxiv [Preprint]. 2025 Apr 7:2025.04.06.25325337. doi: 10.1101/2025.04.06.25325337.

ABSTRACT

Alzheimer's disease (AD) and AD-related dementias (ADRD) exhibit heterogeneous progression rates, with rapid progression (RP) posing significant challenges for timely intervention and treatment. The increasingly available patient-centered electronic health records (EHRs) have made it possible to develop advanced machine learning models for risk prediction of disease progression by leveraging comprehensive clinical, demographic, and laboratory data. In this study, we propose AutoRADP, an interpretable autoencoder-based framework that predicts rapid AD/ADRD progression using both structured and unstructured EHR data from UFHealth. AutoRADP incorporates a rule-based natural language processing method to extract critical cognitive assessments from clinical notes, combined with feature selection techniques to identify essential structured EHR features. To address the data imbalance issue, we implement a hybrid sampling strategy that combines similarity-based and clustering-based upsampling. Additionally, by utilizing SHapley Additive exPlanations (SHAP) values, we provide interpretable predictions, shedding light on the key factors driving the rapid progression of AD/ADRD. We demonstrate that AutoRADP outperforms existing methods, highlighting the potential of our framework to advance precision medicine by enabling accurate and interpretable predictions of rapid AD/ADRD progression, and thereby supporting improved clinical decision-making and personalized interventions.

PMID:40297450 | PMC:PMC12036374 | DOI:10.1101/2025.04.06.25325337

medRxiv [Preprint]. 2025 Apr 8:2025.04.07.25325386. doi: 10.1101/2025.04.07.25325386.

ABSTRACT

Alzheimer's disease (AD), particularly late-onset AD, stands as the most prevalent neurodegenerative disorder globally. Owing to its substantial heritability, genetic studies have emerged as indispensable for elucidating genes and biological pathways driving AD onset and progression. However, genetic and molecular mechanisms underlying AD remain poorly defined, largely due to the pronounced heterogeneity of AD and the intricate interactions among AD genetic factors. Notably, approximately 90% of AD-associated genetic variants reside in intronic and intergenic regions, yet their functional significance has remained largely uncharacterized. To address this challenge, we developed a deep learning framework combining bulk and single-cell epigenomic data to evaluate the regulatory potential (i.e., silencing and activating strength) of noncoding AD variants in the dorsolateral prefrontal cortex (DLPFCs) and its major cell types. This model identified 1,457 silencer and 3,084 enhancer AD-associated variants in the DLPFC and binned them into silencer variants only (SL), enhancer variants only (EN), or both variant types (ENSL) classes. Each class exerts distinct cellular and molecular influences on AD pathogenesis. EN loci predominantly regulate housekeeping metabolic processes, whereas SL loci (including the genes MS4A6A , TREM2 , USP6NL , HLA-D ) are selectively linked to immune responses. Notably, 71% of these genes are significantly upregulated in AD and pro-inflammation-stimulated microglia. Furthermore, genes associated with SL loci are, in neuronal cells, often responsive to glutamate receptor antagonists (e.g, NBQX) and anti-inflammatory perturbagens (such as D-64131), the compound classes known for reducing the AD risk. ENSL loci, in contrast, are uniquely implicated in memory maintenance, neurofibrillary tangle assembly, and are also shared by other neurological disorders such as Parkinson's disease and schizophrenia. Key genes in this class of loci, such as MAPT , CR1/2 , and CLU , are frequently upregulated in AD subtypes with hyperphosphorylated tau aggregates. Critically, our model can accurately predict the impact of regulatory variants, with an average Pearson correlation coefficient of 0.54 and a directional concordance rate of 70% between our predictions and experimental outcomes. This model identified rs636317 as a causal AD variant in the MS4A locus, distinguishing it from the 7bp-away allele-neutral variant rs636341. Similarly, rs7922621 was prioritized over its 54-bp-away allele-neutral rs7901634 in the TSPAN14 locus. Additional causal variants include rs6701713 in the CR1 locus, and rs28834970 and rs755951 in the PTK2B locus. Collectively, this work advances our understanding of the regulatory landscape of AD-associated genetic variants, providing a framework to explore their functional roles in the pathogenesis of this complex disease.

PMID:40297423 | PMC:PMC12036408 | DOI:10.1101/2025.04.07.25325386

Digit Health. 2025 Apr 15;11:20552076251335542. doi: 10.1177/20552076251335542. eCollection 2025 Jan-Dec.

ABSTRACT

BACKGROUND: In modern workplaces, emotional well-being significantly impacts productivity, interpersonal relationships, and organizational stability. This study introduced an innovative facial-based emotion recognition system aimed at the real-time monitoring and management of employee emotional states.

METHODS: Utilizing the RetinaFace model for facial detection, the Dlib algorithm for feature extraction, and VGG16 for micro-expression classification, the system constructed a 10-dimensional emotion feature vector. Emotional anomalies were identified using the K-Nearest Neighbors algorithm and assessed with a 3σ-based risk evaluation method.

RESULTS: The system achieved high accuracy in emotion classification, as demonstrated by an empirical analysis, where VGG16 outperformed MobileNet and ResNet50 in key metrics such as accuracy, precision, and recall. Data augmentation techniques were employed to enhance the performance of the micro-expression classification model.

CONCLUSION: These techniques improved the across diverse emotional expressions, resulting in more accurate and robust emotion recognition. When deployed in a corporate environment, the system successfully monitored employees' emotional trends, identified potential risks, and provided actionable insights into early intervention. This study contributes to advancing corporate mental health management and lays the foundation for scalable emotion-based support systems in organizational settings.

PMID:40297378 | PMC:PMC12035250 | DOI:10.1177/20552076251335542