Literature Watch

Learning Transversus Abdominis Activation in Older Adults with Chronic Low Back Pain Using an Ultrasound-Based Wearable: A Randomized Controlled Pilot Study

Deep learning - Thu, 2025-01-23 06:00

J Funct Morphol Kinesiol. 2025 Jan 1;10(1):14. doi: 10.3390/jfmk10010014.

ABSTRACT

Background/Objectives: Chronic low back pain (CLBP) is prevalent among older adults and leads to significant functional limitations and reduced quality of life. Segmental stabilization exercises (SSEs) are commonly used to treat CLBP, but the selective activation of deep abdominal muscles during these exercises can be challenging for patients. To support muscle activation, physiotherapists use biofeedback methods such as palpation and ultrasound imaging. This randomized controlled pilot study aimed to compare the effectiveness of these two biofeedback techniques in older adults with CLBP. Methods: A total of 24 participants aged 65 years or older with CLBP were randomly assigned to one of two groups: one group performed self-palpation biofeedback, while the other group used real-time ultrasound imaging to visualize abdominal muscle activation. Muscle activation and thickness were continuously tracked using a semi-automated algorithm. The preferential activation ratio (PAR) was calculated to measure muscle activation, and statistical comparisons between groups were made using ANOVA. Results: Both groups achieved positive PAR values during all repetitions of the abdominal-draw-in maneuver (ADIM) and abdominal bracing (AB). Statistical analysis revealed no significant differences between the groups in terms of PAR during ADIM (F(2, 42) = 0.548, p = 0.58, partial η2 = 0.025) or AB (F(2, 36) = 0.812, p = 0.45, partial η2 = 0.043). Both groups reported high levels of exercise enjoyment and low task load. Conclusions: In conclusion, both palpation and ultrasound biofeedback appear to be effective for guiding older adults with CLBP during SSE. Larger studies are needed to confirm these results and examine the long-term effectiveness of these biofeedback methods.

PMID:39846655 | DOI:10.3390/jfmk10010014

Categories: Literature Watch

High-throughput markerless pose estimation and home-cage activity analysis of tree shrew using deep learning

Deep learning - Thu, 2025-01-23 06:00

Animal Model Exp Med. 2025 Jan 23. doi: 10.1002/ame2.12530. Online ahead of print.

ABSTRACT

BACKGROUND: Quantifying the rich home-cage activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models. However, due to the lack of effective behavioral methods, most efforts on tree shrew behavior are limited to simple measures, resulting in the loss of much behavioral information.

METHODS: To address this issue, we present a deep learning (DL) approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews, including drinking, eating, resting, and staying in the dark house, etc. RESULTS: This high-throughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period. Additionally, we demonstrated an innovative system with reliable apparatus, paradigms, and analysis methods for investigating food grasping behavior. The median duration for each bout of grasping was 0.20 s.

CONCLUSION: This study provides an efficient tool for quantifying and understand tree shrews' natural behaviors.

PMID:39846430 | DOI:10.1002/ame2.12530

Categories: Literature Watch

SpaGraphCCI: Spatial cell-cell communication inference through GAT-based co-convolutional feature integration

Deep learning - Thu, 2025-01-23 06:00

IET Syst Biol. 2025 Jan-Dec;19(1):e70000. doi: 10.1049/syb2.70000.

ABSTRACT

Spatially resolved transcriptomics technologies potentially provide the extra spatial position information and tissue image to better infer spatial cell-cell interactions (CCIs) in processes such as tissue homeostasis, development, and disease progression. However, methods for effectively integrating spatial multimodal data to infer CCIs are still lacking. Here, the authors propose a deep learning method for integrating features through co-convolution, called SpaGraphCCI, to effectively integrate data from different modalities of SRT by projecting gene expression and image feature into a low-dimensional space. SpaGraphCCI can achieve significant performance on datasets from multiple platforms including single-cell resolution datasets (AUC reaches 0.860-0.907) and spot resolution datasets (AUC ranges from 0.880 to 0.965). SpaGraphCCI shows better performance by comparing with the existing deep learning-based spatial cell communication inference methods. SpaGraphCCI is robust to high noise and can effectively improve the inference of CCIs. We test on a human breast cancer dataset and show that SpaGraphCCI can not only identify proximal cell communication but also infer new distal interactions. In summary, SpaGraphCCI provides a practical tool that enables researchers to decipher spatially resolved cell-cell communication based on spatial transcriptome data.

PMID:39846423 | DOI:10.1049/syb2.70000

Categories: Literature Watch

Novel Integration of Spatial and Single-Cell Omics Data Sets Enables Deeper Insights into IPF Pathogenesis

Idiopathic Pulmonary Fibrosis - Thu, 2025-01-23 06:00

Proteomes. 2025 Jan 13;13(1):3. doi: 10.3390/proteomes13010003.

ABSTRACT

Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease characterized by repetitive alveolar injuries with excessive deposition of extracellular matrix (ECM) proteins. A crucial need in understanding IPF pathogenesis is identifying cell types associated with histopathological regions, particularly local fibrosis centers known as fibroblast foci. To address this, we integrated published spatial transcriptomics and single-cell RNA sequencing (scRNA-seq) transcriptomics and adopted the Query method and the Overlap method to determine cell type enrichments in histopathological regions. Distinct fibroblast cell types are highly associated with fibroblast foci, and transitional alveolar type 2 and aberrant KRT5-/KRT17+ (KRT: keratin) epithelial cells are associated with morphologically normal alveoli in human IPF lungs. Furthermore, we employed laser capture microdissection-directed mass spectrometry to profile proteins. By comparing with another published similar dataset, common differentially expressed proteins and enriched pathways related to ECM structure organization and collagen processing were identified in fibroblast foci. Importantly, cell type enrichment results from innovative spatial proteomics and scRNA-seq data integration accord with those from spatial transcriptomics and scRNA-seq data integration, supporting the capability and versatility of the entire approach. In summary, we integrated spatial multi-omics with scRNA-seq data to identify disease-associated cell types and potential targets for novel therapies in IPF intervention. The approach can be further applied to other disease areas characterized by spatial heterogeneity.

PMID:39846634 | DOI:10.3390/proteomes13010003

Categories: Literature Watch

EXO<sup>TLR1/2-STING</sup>: A Dual-Mechanism Stimulator of Interferon Genes Activator for Cancer Immunotherapy

Systems Biology - Thu, 2025-01-23 06:00

ACS Nano. 2025 Jan 23. doi: 10.1021/acsnano.4c18056. Online ahead of print.

ABSTRACT

As natural agonists of the stimulator of interferon genes (STING) protein, cyclic dinucleotides (CDNs) can activate the STING pathway, leading to the expression of type I interferons and various cytokines. Efficient activation of the STING pathway in antigen-presenting cells (APCs) and tumor cells is crucial for antitumor immune response. Tumor-derived exosomes can be effectively internalized by APCs and tumor cells and have excellent potential to deliver CDNs to the cytoplasm of APCs and tumor cells. Here, we leverage tumor exosomes as a delivery platform, designing an EXOTLR1/2-STING loaded with CDNs. To achieve efficient loading of CDNs onto exosomes, we chemically conjugated CDNs with Pam3CSK4, a compound featuring multiple fatty acid chains, resulting in Pam3CSK4-CDGSF. Utilizing the high lipophilicity of Pam3CSK4, Pam3CSK4-CDGSF could be efficiently loaded onto the exosomes through simple incubation. Moreover, as an agonist for Toll-like receptor 1/2, Pam3CSK4 also exhibits robust immunological synergistic effects in conjunction with CDNs. EXOTLR1/2-STING effectively induced the activation of APCs and triggered tumor cell death, producing a favorable antitumor therapeutic effect. It also demonstrated significant synergistic effects with immune checkpoint therapies.

PMID:39846950 | DOI:10.1021/acsnano.4c18056

Categories: Literature Watch

Gut phages and their interactions with bacterial and mammalian hosts

Systems Biology - Thu, 2025-01-23 06:00

J Bacteriol. 2025 Jan 23:e0042824. doi: 10.1128/jb.00428-24. Online ahead of print.

ABSTRACT

The mammalian gut microbiome is a dense and diverse community of microorganisms that reside in the distal gastrointestinal tract. In recent decades, the bacterial members of the gut microbiome have been the subject of intense research. Less well studied is the large community of bacteriophages that reside in the gut, which number in the billions of viral particles per gram of feces, and consist of considerable unknown viral "dark matter." This community of gut-residing bacteriophages, called the gut "phageome," plays a central role in the gut microbiome through predation and transformation of native gut bacteria, and through interactions with their mammalian hosts. In this review, we will summarize what is known about the composition and origins of the gut phageome, as well as its role in microbiome homeostasis and host health. Furthermore, we will outline the interactions of gut phages with their bacterial and mammalian hosts, and plot a course for the mechanistic study of these systems.

PMID:39846747 | DOI:10.1128/jb.00428-24

Categories: Literature Watch

In-line prediction of viability and viable cell density through machine learning-based soft sensor modeling and an integrated systems approach: An industrially relevant PAT case study

Systems Biology - Thu, 2025-01-23 06:00

Biotechnol Prog. 2025 Jan 23:e3520. doi: 10.1002/btpr.3520. Online ahead of print.

ABSTRACT

The biopharmaceutical industry is shifting toward employing digital analytical tools for improved understanding of systems biology data and production of quality products. The implementation of these technologies can streamline the manufacturing process by enabling faster responses, reducing manual measurements, and building continuous and automated capabilities. This study discusses the use of soft sensor models for prediction of viability and viable cell density (VCD) in CHO cell culture processes by using in-line optical density and permittivity sensors. A significant innovation of this study is the development of a simplified empirical model and adoption of an integrated systems approach for in-line viability prediction. The initial evaluation of this viability model demonstrated promising accuracy with 96% of the residuals within a ±5% error limit and a Final Day mean absolute percentage error of ≤5% across various scales and process conditions. This model was integrated with a VCD prediction model utilizing Gaussian Process Regressor with Matern Kernel (nu = 0.5), selected from over a hundred advanced machine learning techniques. This VCD prediction model had an R2 of 0.92 with 89% predictions within ±10% error and significantly outperformed the commonly used partial least squares regression models. The results validated the use of these models for real-time in-line prediction of viability and VCD and highlighted the potential to substantially reduce reliance on labor-intensive discrete offline measurements. The integration of these innovative technologies aligns with regulatory guidelines and establishes a foundation for further advancements in the biomanufacturing industry, promising improved process control, efficiency, and compliance with quality standards.

PMID:39846513 | DOI:10.1002/btpr.3520

Categories: Literature Watch

Drug safety and mandatory reporting

Drug-induced Adverse Events - Thu, 2025-01-23 06:00

Schmerz. 2025 Jan 23. doi: 10.1007/s00482-024-00857-3. Online ahead of print.

ABSTRACT

The spontaneous reporting system for cases of suspected side effects is a central instrument for detecting possible side effects after a pharmaceutical preparation has received marketing authorization. It provides important information (signals) on the occurrence of rare, previously unknown side effects, on increases in the frequency of known side effects that may also be due to quality defects, or on changes in the type or severity of known side effects. In recent decades, this system has made a significant contribution to the identification of drug-related risks that only arise upon widespread use following approval and to the introduction of appropriate measures to minimize risk.

PMID:39847136 | DOI:10.1007/s00482-024-00857-3

Categories: Literature Watch

Imaging paediatric bone marrow in immunocompromised patients

Drug-induced Adverse Events - Thu, 2025-01-23 06:00

Pediatr Radiol. 2025 Jan 23. doi: 10.1007/s00247-024-06153-7. Online ahead of print.

ABSTRACT

The bone marrow of immunocompromised patients may exhibit abnormalities due to the underlying disease, adverse treatment effects, and/or complications arising from either source. Such complexity poses a significant diagnostic challenge, particularly in children. Magnetic resonance imaging (MRI) is the modality of choice when evaluating bone marrow in these patients. The high soft tissue contrast of MRI studies allows for detailed evaluation of bone marrow composition, including fat content, cellularity, and vascularisation. During the early years of life, bone marrow undergoes physiological maturation manifesting as a wide range of MRI findings. Understanding the most common MRI features during this phase of development is essential. However, it is equally critical to recognise physiological variations that can mimic pathological changes, as distinguishing between variations and truly pathological abnormalities is crucial for accurate diagnosis and management. This article reviews normal bone marrow and its variations during childhood, as well as the most common alterations presenting in immunocompromised patients.

PMID:39847093 | DOI:10.1007/s00247-024-06153-7

Categories: Literature Watch

Exploring the shared mechanism of fatigue between systemic lupus erythematosus and myalgic encephalomyelitis/chronic fatigue syndrome: monocytic dysregulation and drug repurposing

Drug Repositioning - Thu, 2025-01-23 06:00

Front Immunol. 2025 Jan 7;15:1440922. doi: 10.3389/fimmu.2024.1440922. eCollection 2024.

ABSTRACT

BACKGROUND: SLE and ME/CFS both present significant fatigue and share immune dysregulation. The mechanisms underlying fatigue in these disorders remain unclear, and there are no standardized treatments. This study aims to explore shared mechanisms and predict potential therapeutic drugs for fatigue in SLE and ME/CFS.

METHODS: Genes associated with SLE and ME/CFS were collected from disease target and clinical sample databases to identify overlapping genes. Bioinformatics analyses, including GO, KEGG, PPI network construction, and key target identification, were performed. ROC curve and correlation analysis of key targets, along with single-cell clustering, were conducted to validate their expression in different cell types. Additionally, an inflammation model was established using THP-1 cells to simulate monocyte activation in both diseases in vitro, and RT-qPCR was used to validate the expression of the key targets. A TF-mRNA-miRNA co-regulatory network was constructed, followed by drug prediction and molecular docking.

RESULTS: Fifty-eight overlapping genes were identified, mainly involved in innate immunity and inflammation. Five key targets were identified (IL1β, CCL2, TLR2, STAT1, IFIH1). Single-cell sequencing revealed that monocytes are enriched with these targets. RT-qPCR confirmed significant upregulation of these targets in the model group. A co-regulatory network was constructed, and ten potential drugs, including suloctidil, N-Acetyl-L-cysteine, simvastatin, ACMC-20mvek, and camptothecin, were predicted. Simvastatin and camptothecin showed high affinity for the key targets.

CONCLUSION: SLE and ME/CFS share immune and inflammatory pathways. The identified key targets are predominantly enriched in monocytes at the single-cell level, suggesting that classical monocytes may be crucial in linking inflammation and fatigue. RT-qPCR confirmed upregulation in activated monocytes. The TF-mRNA-miRNA network provides a foundation for future research, and drug prediction suggests N-Acetyl-L-cysteine and camptothecin as potential therapies.

PMID:39845969 | PMC:PMC11752880 | DOI:10.3389/fimmu.2024.1440922

Categories: Literature Watch

Effect of long and short half-life PDE5 inhibitors on HbA1c levels: a systematic review and meta-analysis

Drug Repositioning - Thu, 2025-01-23 06:00

EClinicalMedicine. 2024 Dec 31;80:103035. doi: 10.1016/j.eclinm.2024.103035. eCollection 2025 Feb.

ABSTRACT

BACKGROUND: Phosphodiesterase 5 (PDE5) inhibitors, owing to their mechanism of action, have been gaining recognition as a potential case of drug repurposing and combination therapy for diabetes treatment. We aimed to examine the effect of long and short half-life PDE5 inhibitors have on Haemoglobin A1c (HbA1c) levels.

METHODS: A systematic review and meta-analysis was conducted of randomised controlled trials (RCTs) in people with elevated HbA1c (>6%) to assess mean difference in HbA1c levels from baseline versus controls after any PDE5 inhibitor intervention of ≥4 weeks, excluding multiple interventions. Cochrane CENTRAL, PMC Medline, ClinicalTrials.gov, and WHO ICTRP were searched without language restrictions up to September 30, 2024. Summary data from published data were extracted. PRISMA and Cochrane guidelines used to extract and assess data using a random-effects meta-analysis. This study is registered with the Research Registry, reviewregistry1733.

FINDINGS: Among 1096 studies identified, in analysis of 13 studies with 1083 baseline patients, long half-life PDE5 inhibitors (tadalafil, PF-00489791) had decreases in HbA1c while short half-life PDE5 inhibitors (sildenafil, avanafil) had no change. Five (38.5%) studies had a low risk of bias, and eight (61.5%) had some concerns. Long half-life inhibitors had significant mean decrease of -0.40% ([-0.66, -0.14], p = 0.002, I2 = 82%, 7.70% baseline HbA1c). Short half-life inhibitors had insignificant mean difference of +0.08% ([-0.16, 0.33], p = 0.51, I2 = 40%, 7.73% baseline HbA1c). In ≥8-week trials with participants with type 2 diabetes (T2D) and mean HbA1c ≥ 6.5%, long half-life inhibitors had significant mean decrease of -0.50% ([-0.83, -0.17], I2 = 88%, p = 0.003); short half-life inhibitors had significant mean increase of +0.36% ([0.03, 0.68], I2 = 3%, p = 0.03).

INTERPRETATION: At the well-controlled HbA1c of the participants, previous literature shows current diabetes treatments have similar HbA1c decreases, so the HbA1c mean difference of long half-life PDE5 inhibitors may indeed be clinically relevant. This suggests future investigation into PDE5 inhibitors as part of combination therapy or as therapy for high HbA1c individuals is needed, especially because of variable risk of biases, homogeneity, and sample sizes in our study.

FUNDING: None.

PMID:39844934 | PMC:PMC11751502 | DOI:10.1016/j.eclinm.2024.103035

Categories: Literature Watch

Joint embedding-classifier learning for interpretable collaborative filtering

Drug Repositioning - Thu, 2025-01-23 06:00

BMC Bioinformatics. 2025 Jan 22;26(1):26. doi: 10.1186/s12859-024-06026-8.

ABSTRACT

BACKGROUND: Interpretability is a topical question in recommender systems, especially in healthcare applications. An interpretable classifier quantifies the importance of each input feature for the predicted item-user association in a non-ambiguous fashion.

RESULTS: We introduce the novel Joint Embedding Learning-classifier for improved Interpretability (JELI). By combining the training of a structured collaborative-filtering classifier and an embedding learning task, JELI predicts new user-item associations based on jointly learned item and user embeddings while providing feature-wise importance scores. Therefore, JELI flexibly allows the introduction of priors on the connections between users, items, and features. In particular, JELI simultaneously (a) learns feature, item, and user embeddings; (b) predicts new item-user associations; (c) provides importance scores for each feature. Moreover, JELI instantiates a generic approach to training recommender systems by encoding generic graph-regularization constraints.

CONCLUSIONS: First, we show that the joint training approach yields a gain in the predictive power of the downstream classifier. Second, JELI can recover feature-association dependencies. Finally, JELI induces a restriction in the number of parameters compared to baselines in synthetic and drug-repurposing data sets.

PMID:39844056 | DOI:10.1186/s12859-024-06026-8

Categories: Literature Watch

Infarct core segmentation using U-Net in CT perfusion imaging: a feasibility study

Deep learning - Thu, 2025-01-23 06:00

Acta Radiol. 2025 Jan 23:2841851241305736. doi: 10.1177/02841851241305736. Online ahead of print.

ABSTRACT

BACKGROUND: The wide variability in thresholds on computed tomography (CT) perfusion parametric maps has led to controversy in the stroke imaging community about the most accurate measurement of core infarction.

PURPOSE: To investigate the feasibility of using U-Net to perform infarct core segmentation in CT perfusion imaging.

MATERIAL AND METHODS: CT perfusion parametric maps were the input of U-Net, while the ground truth segmentation was determined based on diffusion-weighted imaging (DWI). The dataset used in this study was from the ISLES2018 challenge, which contains 63 acute stroke patients receiving CT perfusion imaging and DWI within 8 h of stroke onset. The segmentation accuracy of model outputs was assessed by calculating Dice similarity coefficient (DSC), sensitivity, and intersection over union (IoU).

RESULTS: The highest DSC was observed in U-Net taking mean transit time (MTT) or time-to-maximum (Tmax) as input. Meanwhile, the highest sensitivity and IoU were observed in U-Net taking Tmax as input. A DSC in the range of 0.2-0.4 was found in U-Net taking Tmax as input when the infarct area contains < 1000 pixels. A DSC of 0.4-0.6 was found in U-Net taking Tmax as input when the infarct area contains 1000-1999 pixels. A DSC value of 0.6-0.8 was found in U-Net taking Tmax as input when the infarct area contains ≥ 2000 pixels.

CONCLUSION: Our model achieved good performance for infarct area containing ≥ 2000 pixels, so it may assist in identifying patients who are contraindicated for intravenous thrombolysis.

PMID:39846186 | DOI:10.1177/02841851241305736

Categories: Literature Watch

Artificial Intelligence-Based Detection and Numbering of Dental Implants on Panoramic Radiographs

Deep learning - Thu, 2025-01-23 06:00

Clin Implant Dent Relat Res. 2025 Feb;27(1):e70000. doi: 10.1111/cid.70000.

ABSTRACT

OBJECTIVES: This study aimed to develop an artificial intelligence (AI)-based deep learning model for the detection and numbering of dental implants in panoramic radiographs. The novelty of this model lies in its ability to both detect and number implants, offering improvements in clinical decision support for dental implantology.

MATERIALS AND METHODS: A retrospective dataset of 32 585 panoramic radiographs, collected from patients at Sivas Cumhuriyet University between 2014 and 2024, was utilized. Two deep-learning models were trained using the YOLOv8 algorithm. The first model classified the regions of the jaw to number the teeth and identify implant regions, while the second model performed implant segmentation. Performance metrics including precision, recall, and F1-score were used to evaluate the model's effectiveness.

RESULTS: The implant segmentation model achieved a precision of 91.4%, recall of 90.5%, and an F1-score of 93.1%. For the implant-numbering task, precision ranged from 0.94 to 0.981, recall from 0.895 to 0.956, and F1-scores from 0.917 to 0.966 across various jaw regions. The analysis revealed that implants were most frequently located in the maxillary posterior region.

CONCLUSIONS: The AI model demonstrated high accuracy in detecting and numbering dental implants in panoramic radiographs. This technology offers the potential to reduce clinicians' workload and improve diagnostic accuracy in dental implantology. Further validation across more diverse datasets is recommended to enhance its clinical applicability.

CLINICAL RELEVANCE: This AI model could revolutionize dental implant detection and classification, providing fast, objective analyses to support clinical decision-making in dental practices.

PMID:39846131 | DOI:10.1111/cid.70000

Categories: Literature Watch

Dissecting AlphaFold2's capabilities with limited sequence information

Deep learning - Thu, 2025-01-23 06:00

Bioinform Adv. 2024 Nov 25;5(1):vbae187. doi: 10.1093/bioadv/vbae187. eCollection 2025.

ABSTRACT

SUMMARY: Protein structure prediction aims to infer a protein's three-dimensional (3D) structure from its amino acid sequence. Protein structure is pivotal for elucidating protein functions, interactions, and driving biotechnological innovation. The deep learning model AlphaFold2, has revolutionized this field by leveraging phylogenetic information from multiple sequence alignments (MSAs) to achieve remarkable accuracy in protein structure prediction. However, a key question remains: how well does AlphaFold2 understand protein structures? This study investigates AlphaFold2's capabilities when relying primarily on high-quality template structures, without the additional information provided by MSAs. By designing experiments that probe local and global structural understanding, we aimed to dissect its dependence on specific features and its ability to handle missing information. Our findings revealed AlphaFold2's reliance on sterically valid C β for correctly interpreting structural templates. Additionally, we observed its remarkable ability to recover 3D structures from certain perturbations and the negligible impact of the previous structure in recycling. Collectively, these results support the hypothesis that AlphaFold2 has learned an accurate biophysical energy function. However, this function seems most effective for local interactions. Our work advances understanding of how deep learning models predict protein structures and provides guidance for researchers aiming to overcome limitations in these models.

AVAILABILITY AND IMPLEMENTATION: Data and implementation are available at https://github.com/ibmm-unibe-ch/template-analysis.

PMID:39846081 | PMC:PMC11751578 | DOI:10.1093/bioadv/vbae187

Categories: Literature Watch

CardiacField: computational echocardiography for automated heart function estimation using two-dimensional echocardiography probes

Deep learning - Thu, 2025-01-23 06:00

Eur Heart J Digit Health. 2024 Sep 24;6(1):137-146. doi: 10.1093/ehjdh/ztae072. eCollection 2025 Jan.

ABSTRACT

AIMS: Accurate heart function estimation is vital for detecting and monitoring cardiovascular diseases. While two-dimensional echocardiography (2DE) is widely accessible and used, it requires specialized training, is prone to inter-observer variability, and lacks comprehensive three-dimensional (3D) information. We introduce CardiacField, a computational echocardiography system using a 2DE probe for precise, automated left ventricular (LV) and right ventricular (RV) ejection fraction (EF) estimations, which is especially easy to use for non-cardiovascular healthcare practitioners. We assess the system's usability among novice users and evaluate its performance against expert interpretations and advanced deep learning (DL) tools.

METHODS AND RESULTS: We developed an implicit neural representation network to reconstruct a 3D cardiac volume from sequential multi-view 2DE images, followed by automatic segmentation of LV and RV areas to calculate volume sizes and EF values. Our study involved 127 patients to assess EF estimation accuracy against expert readings and two-dimensional (2D) video-based DL models. A subset of 56 patients was utilized to evaluate image quality and 3D accuracy and another 50 to test usability by novice users and across various ultrasound machines. CardiacField generated a 3D heart from 2D echocardiograms with <2 min processing time. The LVEF predicted by our method had a mean absolute error (MAE) of 2.48 % , while the RVEF had an MAE of 2.65 % .

CONCLUSION: Employing a straightforward apical ring scan with a cost-effective 2DE probe, our method achieves a level of EF accuracy for assessing LV and RV function that is comparable to that of three-dimensional echocardiography probes.

PMID:39846074 | PMC:PMC11750196 | DOI:10.1093/ehjdh/ztae072

Categories: Literature Watch

Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis

Deep learning - Thu, 2025-01-23 06:00

Eur Heart J Digit Health. 2024 Oct 27;6(1):7-22. doi: 10.1093/ehjdh/ztae080. eCollection 2025 Jan.

ABSTRACT

Cardiovascular disease (CVD) remains a major cause of mortality in the UK, prompting the need for improved risk predictive models for primary prevention. Machine learning (ML) models utilizing electronic health records (EHRs) offer potential enhancements over traditional risk scores like QRISK3 and ASCVD. To systematically evaluate and compare the efficacy of ML models against conventional CVD risk prediction algorithms using EHR data for medium to long-term (5-10 years) CVD risk prediction. A systematic review and random-effect meta-analysis were conducted according to preferred reporting items for systematic reviews and meta-analyses guidelines, assessing studies from 2010 to 2024. We retrieved 32 ML models and 26 conventional statistical models from 20 selected studies, focusing on performance metrics such as area under the curve (AUC) and heterogeneity across models. ML models, particularly random forest and deep learning, demonstrated superior performance, with the highest recorded pooled AUCs of 0.865 (95% CI: 0.812-0.917) and 0.847 (95% CI: 0.766-0.927), respectively. These significantly outperformed the conventional risk score of 0.765 (95% CI: 0.734-0.796). However, significant heterogeneity (I² > 99%) and potential publication bias were noted across the studies. While ML models show enhanced calibration for CVD risk, substantial variability and methodological concerns limit their current clinical applicability. Future research should address these issues by enhancing methodological transparency and standardization to improve the reliability and utility of these models in clinical settings. This study highlights the advanced capabilities of ML models in CVD risk prediction and emphasizes the need for rigorous validation to facilitate their integration into clinical practice.

PMID:39846062 | PMC:PMC11750195 | DOI:10.1093/ehjdh/ztae080

Categories: Literature Watch

A 3D decoupling Alzheimer's disease prediction network based on structural MRI

Deep learning - Thu, 2025-01-23 06:00

Health Inf Sci Syst. 2025 Jan 17;13(1):17. doi: 10.1007/s13755-024-00333-3. eCollection 2025 Dec.

ABSTRACT

PURPOSE: This paper aims to develop a three-dimensional (3D) Alzheimer's disease (AD) prediction method, thereby bettering current predictive methods, which struggle to fully harness the potential of structural magnetic resonance imaging (sMRI) data.

METHODS: Traditional convolutional neural networks encounter pressing difficulties in accurately focusing on the AD lesion structure. To address this issue, a 3D decoupling, self-attention network for AD prediction is proposed. Firstly, a multi-scale decoupling block is designed to enhance the network's ability to extract fine-grained features by segregating convolutional channels. Subsequently, a self-attention block is constructed to extract and adaptively fuse features from three directions (sagittal, coronal and axial), so that more attention is geared towards brain lesion areas. Finally, a clustering loss function is introduced and combined with the cross-entropy loss to form a joint loss function for enhancing the network's ability to discriminate between different sample types.

RESULTS: The accuracy of our model is 0.985 for the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and 0.963 for the Australian Imaging, Biomarker & Lifestyle (AIBL) dataset, both of which are higher than the classification accuracy of similar tasks in this category. This demonstrates that our model can accurately distinguish between normal control (NC) and Alzheimer's Disease (AD), as well as between stable mild cognitive impairment (sMCI) and progressive mild cognitive impairment (pMCI).

CONCLUSION: The proposed AD prediction network exhibits competitive performance when compared with state-of-the-art methods. The proposed model successfully addresses the challenges of dealing with 3D sMRI image data and the limitations stemming from inadequate information in 2D sections, advancing the utility of predictive methods for AD diagnosis and treatment.

PMID:39846055 | PMC:PMC11748674 | DOI:10.1007/s13755-024-00333-3

Categories: Literature Watch

Artificial Intelligence in Pediatric Epilepsy Detection: Balancing Effectiveness With Ethical Considerations for Welfare

Deep learning - Thu, 2025-01-23 06:00

Health Sci Rep. 2025 Jan 22;8(1):e70372. doi: 10.1002/hsr2.70372. eCollection 2025 Jan.

ABSTRACT

BACKGROUND AND AIM: Epilepsy is a major neurological challenge, especially for pediatric populations. It profoundly impacts both developmental progress and quality of life in affected children. With the advent of artificial intelligence (AI), there's a growing interest in leveraging its capabilities to improve the diagnosis and management of pediatric epilepsy. This review aims to assess the effectiveness of AI in pediatric epilepsy detection while considering the ethical implications surrounding its implementation.

METHODOLOGY: A comprehensive systematic review was conducted across multiple databases including PubMed, EMBASE, Google Scholar, Scopus, and Medline. Search terms encompassed "pediatric epilepsy," "artificial intelligence," "machine learning," "ethical considerations," and "data security." Publications from the past decade were scrutinized for methodological rigor, with a focus on studies evaluating AI's efficacy in pediatric epilepsy detection and management.

RESULTS: AI systems have demonstrated strong potential in diagnosing and monitoring pediatric epilepsy, often matching clinical accuracy. For example, AI-driven decision support achieved 93.4% accuracy in diagnosis, closely aligning with expert assessments. Specific methods, like EEG-based AI for detecting interictal discharges, showed high specificity (93.33%-96.67%) and sensitivity (76.67%-93.33%), while neuroimaging approaches using rs-fMRI and DTI reached up to 97.5% accuracy in identifying microstructural abnormalities. Deep learning models, such as CNN-LSTM, have also enhanced seizure detection from video by capturing subtle movement and expression cues. Non-EEG sensor-based methods effectively identified nocturnal seizures, offering promising support for pediatric care. However, ethical considerations around privacy, data security, and model bias remain crucial for responsible AI integration.

CONCLUSION: While AI holds immense potential to enhance pediatric epilepsy management, ethical considerations surrounding transparency, fairness, and data security must be rigorously addressed. Collaborative efforts among stakeholders are imperative to navigate these ethical challenges effectively, ensuring responsible AI integration and optimizing patient outcomes in pediatric epilepsy care.

PMID:39846037 | PMC:PMC11751886 | DOI:10.1002/hsr2.70372

Categories: Literature Watch

Enhancing semantic segmentation for autonomous vehicle scene understanding in indian context using modified CANet model

Deep learning - Thu, 2025-01-23 06:00

MethodsX. 2024 Dec 21;14:103131. doi: 10.1016/j.mex.2024.103131. eCollection 2025 Jun.

ABSTRACT

Recent advancements in artificial intelligence (AI) have increased interest in intelligent transportation systems, particularly autonomous vehicles. Safe navigation in traffic-heavy environments requires accurate road scene segmentation, yet traditional computer vision methods struggle with complex scenarios. This study emphasizes the role of deep learning in improving semantic segmentation using datasets like the Indian Driving Dataset (IDD), which presents unique challenges in chaotic road conditions. We propose a modified CANet that incorporates U-Net and LinkNet elements, focusing on accuracy, efficiency, and resilience. The CANet features an encoder-decoder architecture and a Multiscale Context Module (MCM) with three parallel branches to capture contextual information at multiple scales. Our experiments show that the proposed model achieves a mean Intersection over Union (mIoU) value of 0.7053, surpassing state-of-the-art models in efficiency and performance. Here we demonstrate:•Traditional computer vision methods struggle with complex driving scenarios, but deep learning based semantic segmentation methods show promising results.•Modified CANet, incorporating U-Net and LinkNet elements is proposed for semantic segmentation of unstructured driving scenarios.•The CANet structure consists of an encoder-decoder architecture and a Multiscale Context Module (MCM) with three parallel branches to capture contextual information at multiple scales.

PMID:39846010 | PMC:PMC11751566 | DOI:10.1016/j.mex.2024.103131

Categories: Literature Watch

Pages

Subscribe to Anil Jegga aggregator - Literature Watch