IEEE Open J Eng Med Biol. 2024 Sep 9;6:41-53. doi: 10.1109/OJEMB.2024.3455801. eCollection 2025.

ABSTRACT

Infectious diseases are a major global public health concern. Precise modeling and prediction methods are essential to develop effective strategies for disease control. However, data imbalance and the presence of noise and intensity inhomogeneity make disease detection more challenging. Goal: In this article, a novel infectious disease pattern prediction system is proposed by integrating deterministic and stochastic model benefits with the benefits of the deep learning model. Results: The combined benefits yield improvement in the performance of solution prediction. Moreover, the objective is also to investigate the influence of time delay on infection rates and rates associated with vaccination. Conclusions: In this proposed framework, at first, the global stability at disease free equilibrium is effectively analysed using Routh-Haurwitz criteria and Lyapunov method, and the endemic equilibrium is analysed using non-linear Volterra integral equations in the infectious disease model. Unlike the existing model, emphasis is given to suggesting a model that is capable of investigating stability while considering the effect of vaccination and migration rate. Next, the influence of vaccination on the rate of infection is effectively predicted using an efficient deep learning model by employing the long-term dependencies in sequential data. Thus making the prediction more accurate.

PMID:39564557 | PMC:PMC11573407 | DOI:10.1109/OJEMB.2024.3455801

IEEE Open J Eng Med Biol. 2024 Sep 5;6:100-106. doi: 10.1109/OJEMB.2024.3454958. eCollection 2025.

ABSTRACT

Goal: This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. Methods: We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Results: Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Conclusions: Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.

PMID:39564554 | PMC:PMC11573408 | DOI:10.1109/OJEMB.2024.3454958

IEEE Open J Eng Med Biol. 2024 Sep 11;6:61-67. doi: 10.1109/OJEMB.2024.3459622. eCollection 2025.

ABSTRACT

Goal: Respiration-correlated cone-beam computed tomography (4D-CBCT) is an X-ray-based imaging modality that uses reconstruction algorithms to produce time-varying volumetric images of moving anatomy over a cycle of respiratory motion. The quality of the produced images is affected by the number of CBCT projections available for reconstruction. Interpolation techniques have been used to generate intermediary projections to be used, along with the original projections, for reconstruction. Transfer learning is a powerful approach that harnesses the ability to reuse pre-trained models in solving new problems. Methods: Several state-of-the-art pre-trained deep learning models, used for video frame interpolation, are utilized in this work to generate intermediary projections. Moreover, a novel regression predictive modeling approach is also proposed to achieve the same objective. Digital phantom and clinical datasets are used to evaluate the performance of the models. Results: The results show that the Real-Time Intermediate Flow Estimation (RIFE) algorithm outperforms the others in terms of the Structural Similarity Index Method (SSIM): 0.986 [Formula: see text] 0.010, Peak Signal to Noise Ratio (PSNR): 44.13 [Formula: see text] 2.76, and Mean Square Error (MSE): 18.86 [Formula: see text] 206.90 across all datasets. Moreover, the interpolated projections were used along with the original ones to reconstruct a 4D-CBCT image that was compared to that reconstructed from the original projections only. Conclusions: The reconstructed image using the proposed approach was found to minimize the streaking artifacts, thereby enhancing the image quality. This work demonstrates the advantage of using general-purpose transfer learning algorithms in 4D-CBCT image enhancement.

PMID:39564553 | PMC:PMC11573399 | DOI:10.1109/OJEMB.2024.3459622

Front Endocrinol (Lausanne). 2024 Nov 6;15:1395979. doi: 10.3389/fendo.2024.1395979. eCollection 2024.

ABSTRACT

BACKGROUND: Informative biomarkers play a vital role in guiding clinical decisions regarding management of cancers. We have previously demonstrated the potential of a deep convolutional neural network (CNN) for predicting cancer driver gene mutations from expert-curated histopathologic images in papillary thyroid carcinomas (PTCs). Recognizing the importance of whole slide image (WSI) analysis for clinical application, we aimed to develop an automated image preprocessing workflow that uses WSI inputs to categorize PTCs based on driver mutations.

METHODS: Histopathology slides from The Cancer Genome Atlas (TCGA) repository were utilized for diagnostic purposes. These slides underwent an automated tile extraction and preprocessing pipeline to ensure analysis-ready quality. Next, the extracted image tiles were utilized to train a deep learning CNN model, specifically Google's Inception v3, for the classification of PTCs. The model was trained to distinguish between different groups based on BRAFV600E or RAS mutations.

RESULTS: The newly developed pipeline performed equally well as the expert-curated image classifier. The best model achieved Area Under the Curve (AUC) values of 0.86 (ranging from 0.847 to 0.872) for validation and 0.865 (ranging from 0.854 to 0.876) for the final testing subsets. Notably, it accurately predicted 90% of tumors in the validation set and 84.2% in the final testing set. Furthermore, the performance of our new classifier showed a strong correlation with the expert-curated classifier (Spearman rho = 0.726, p = 5.28 e-08), and correlated with the molecular expression-based classifier, BRS (BRAF-RAS scores) (Spearman rho = 0.418, p = 1.92e-13).

CONCLUSIONS: Utilizing WSIs, we implemented an automated workflow with deep CNN model that accurately classifies driver mutations in PTCs.

PMID:39564124 | PMC:PMC11573888 | DOI:10.3389/fendo.2024.1395979

J Biomed Opt. 2024 Nov;29(11):116003. doi: 10.1117/1.JBO.29.11.116003. Epub 2024 Nov 19.

ABSTRACT

SIGNIFICANCE: Early detection of melanoma is crucial for improving patient outcomes, and dermoscopy is a critical tool for this purpose. However, hair presence in dermoscopic images can obscure important features, complicating the diagnostic process. Enhancing image clarity by removing hair without compromising lesion integrity can significantly aid dermatologists in accurate melanoma detection.

AIM: We aim to develop a novel synthetic hair dermoscopic image dataset and a deep learning model specifically designed for hair removal in melanoma dermoscopy images.

APPROACH: To address the challenge of hair in dermoscopic images, we created a comprehensive synthetic hair dataset that simulates various hair types and dimensions over melanoma lesions. We then designed a convolutional neural network (CNN)-based model that focuses on effective hair removal while preserving the integrity of the melanoma lesions.

RESULTS: The CNN-based model demonstrated significant improvements in the clarity and diagnostic utility of dermoscopic images. The enhanced images provided by our model offer a valuable tool for the dermatological community, aiding in more accurate and efficient melanoma detection.

CONCLUSIONS: The introduction of our synthetic hair dermoscopic image dataset and CNN-based model represents a significant advancement in medical image analysis for melanoma detection. By effectively removing hair from dermoscopic images while preserving lesion details, our approach enhances diagnostic accuracy and supports early melanoma detection efforts.

PMID:39564076 | PMC:PMC11575456 | DOI:10.1117/1.JBO.29.11.116003

Colomb Med (Cali). 2024 Jun 30;55(2):e2005944. doi: 10.25100/cm.v55i2.5944. eCollection 2024 Apr-Jun.

ABSTRACT

BACKGROUND: Morphological properties such as length and tortuosity of the large intestine segments play important roles, especially in interventional procedures like colonoscopy.

OBJECTIVE: Using computed tomography (CT) colonoscopy images, this study aimed to examine the morphological features of the colon's anatomical sections and investigate the relationship of these sections with each other or with age groups. The shapes of the transverse colon were analyzed using artificial intelligence.

METHODS: The study was conducted as a two- and three-dimensional examination of CT colonography images of people between 40 and 80 years old, which were obtained retrospectively. An artificial intelligence algorithm (YOLOv8) was used for shape detection on 3D colon images.

RESULTS: 160 people with a mean age of 89 men and 71 women included in the study were 57.79±8.55 and 56.55±6.60, respectively, and there was no statistically significant difference (p= 0.24). The total colon length was 166.11±25.07 cm for men and 158.73±21.92 cm for women, with no significant difference between groups (p=0.12). As a result of the training of the model Precision, Recall, and Mean Average Precision (mAP) were found to be 0.8578, 0.7940, and 0.9142, respectively.

CONCLUSION: The study highlights the importance of understanding the type and morphology of the large intestine for accurate interpretation of CT colonography results and effective clinical management of patients with suspected large intestine abnormalities. Furthermore, this study showed that 88.57% of the images in the test data set were detected correctly and that AI can play an important role in colon typing.

PMID:39564004 | PMC:PMC11573345 | DOI:10.25100/cm.v55i2.5944

Eur Heart J Digit Health. 2024 Aug 19;5(6):683-691. doi: 10.1093/ehjdh/ztae062. eCollection 2024 Nov.

ABSTRACT

AIMS: Although evaluation of left ventricular ejection fraction (LVEF) is crucial for deciding the rate control strategy in patients with atrial fibrillation (AF), real-time assessment of LVEF is limited in outpatient settings. We aimed to investigate the performance of artificial intelligence-based algorithms in predicting LV systolic dysfunction (LVSD) in patients with AF and rapid ventricular response (RVR).

METHODS AND RESULTS: This study is an external validation of a pre-existing deep learning algorithm based on residual neural network architecture. Data were obtained from a prospective cohort of AF with RVR at a single centre between 2018 and 2023. Primary outcome was the detection of LVSD, defined as a LVEF ≤ 40%, assessed using 12-lead electrocardiography (ECG). Secondary outcome involved predicting LVSD using 1-lead ECG (Lead I). Among 423 patients, 241 with available echocardiography data within 2 months were evaluated, of whom 54 (22.4%) were confirmed to have LVSD. Deep learning algorithm demonstrated fair performance in predicting LVSD [area under the curve (AUC) 0.78]. Negative predictive value for excluding LVSD was 0.88. Deep learning algorithm resulted competent performance in predicting LVSD compared with N-terminal prohormone of brain natriuretic peptide (AUC 0.78 vs. 0.70, P = 0.12). Predictive performance of the deep learning algorithm was lower in Lead I (AUC 0.68); however, negative predictive value remained consistent (0.88).

CONCLUSION: Deep learning algorithm demonstrated competent performance in predicting LVSD in patients with AF and RVR. In outpatient setting, use of artificial intelligence-based algorithm may facilitate prediction of LVSD and earlier choice of drug, enabling better symptom control in AF patients with RVR.

PMID:39563911 | PMC:PMC11570393 | DOI:10.1093/ehjdh/ztae062

J Forensic Sci. 2024 Nov 19. doi: 10.1111/1556-4029.15665. Online ahead of print.

ABSTRACT

Deepfake videos are growing progressively more competent because of the rapid advancements in artificial intelligence and deep learning technology. This has led to substantial problems around propaganda, privacy, and security. This research provides an analytically novel method for detecting deepfake videos using temporal discrepancies of the various statistical features of video at the pixel level, followed by a deep learning algorithm. To detect minute aberrations typical of deepfake manipulations, this study focuses on both spatial information inside individual frames and temporal correlations between subsequent frames. This study primarily provides a novel Euclidean distance variation probability score value for directly commenting on the authenticity of a deepfake video. Next, fine-tuning of InceptionResNetV2 with the addition of a dense layer is trained FaceForensics++ for deepfake detection. The proposed fine-tuned model outperforms the existing techniques as its testing accuracy on unseen data outperforms the existing methods. The propsd method achieved an accuracy of 99.80% for FF++ dataset and 97.60% accuracy for CelebDF dataset.

PMID:39562484 | DOI:10.1111/1556-4029.15665

Hum Brain Mapp. 2024 Dec 1;45(17):e26799. doi: 10.1002/hbm.26799.

ABSTRACT

Multimodal learning has emerged as a powerful technique that leverages diverse data sources to enhance learning and decision-making processes. Adapting this approach to analyzing data collected from different biological domains is intuitive, especially for studying neuropsychiatric disorders. A complex neuropsychiatric disorder like schizophrenia (SZ) can affect multiple aspects of the brain and biologies. These biological sources each present distinct yet correlated expressions of subjects' underlying physiological processes. Joint learning from these data sources can improve our understanding of the disorder. However, combining these biological sources is challenging for several reasons: (i) observations are domain specific, leading to data being represented in dissimilar subspaces, and (ii) fused data are often noisy and high-dimensional, making it challenging to identify relevant information. To address these challenges, we propose a multimodal artificial intelligence model with a novel fusion module inspired by a bottleneck attention module. We use deep neural networks to learn latent space representations of the input streams. Next, we introduce a two-dimensional (spatio-modality) attention module to regulate the intermediate fusion for SZ classification. We implement spatial attention via a dilated convolutional neural network that creates large receptive fields for extracting significant contextual patterns. The resulting joint learning framework maximizes complementarity allowing us to explore the correspondence among the modalities. We test our model on a multimodal imaging-genetic dataset and achieve an SZ prediction accuracy of 94.10% (p < .0001), outperforming state-of-the-art unimodal and multimodal models for the task. Moreover, the model provides inherent interpretability that helps identify concepts significant for the neural network's decision and explains the underlying physiopathology of the disorder. Results also show that functional connectivity among subcortical, sensorimotor, and cognitive control domains plays an important role in characterizing SZ. Analysis of the spatio-modality attention scores suggests that structural components like the supplementary motor area, caudate, and insula play a significant role in SZ. Biclustering the attention scores discover a multimodal cluster that includes genes CSMD1, ATK3, MOB4, and HSPE1, all of which have been identified as relevant to SZ. In summary, feature attribution appears to be especially useful for probing the transient and confined but decisive patterns of complex disorders, and it shows promise for extensive applicability in future studies.

PMID:39562310 | DOI:10.1002/hbm.26799

Eur J Surg Oncol. 2024 Nov 15:109463. doi: 10.1016/j.ejso.2024.109463. Online ahead of print.

ABSTRACT

BACKGROUND: Predicting pathological complete response (pCR) from pre or post-treatment features could be significant in improving the process of making clinical decisions and providing a more personalized treatment approach for better treatment outcomes. However, the lack of external validation of predictive models, missing in several published articles, is a major issue that can potentially limit the reliability and applicability of predictive models in clinical settings. Therefore, this systematic review described different externally validated methods of predicting response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients and how they could improve clinical decision-making.

METHOD: An extensive search for eligible articles was performed on PubMed, Cochrane, and Scopus between 2018 and 2023, using the keywords: (Response OR outcome) prediction AND (neoadjuvant OR chemoradiotherapy) treatment in 'locally advanced Rectal Cancer'.

INCLUSION CRITERIA: (i) Studies including patients diagnosed with LARC (T3/4 and N- or any T and N+) by pre-medical imaging and pathological examination or as stated by the author (ii) Standardized nCRT completed. (iii) Treatment with long or short course radiotherapy. (iv) Studies reporting on the prediction of response to nCRT with pathological complete response (pCR) as the primary outcome. (v) Studies reporting external validation results for response prediction. (vi) Regarding language restrictions, only articles in English were accepted.

EXCLUSION CRITERIA: (i) We excluded case report studies, conference abstracts, reviews, studies reporting patients with distant metastases at diagnosis. (ii) Studies reporting response prediction with only internally validated approaches.

DATA COLLECTION AND QUALITY ASSESSMENT: Three researchers (DC-D, FB, HT) independently reviewed and screened titles and abstracts of all articles retrieved after de-duplication. Possible disagreements were resolved through discussion among the three researchers. If necessary, three other researchers (LB, GC, MG) were consulted to make the final decision. The extraction of data was performed using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) template and quality assessment was done using the Prediction model Risk Of Bias Assessment Tool (PROBAST).

RESULTS: A total of 4547 records were identified from the three databases. After excluding 392 duplicate results, 4155 records underwent title and abstract screening. Three thousand and eight hundred articles were excluded after title and abstract screening and 355 articles were retrieved. Out of the 355 retrieved articles, 51 studies were assessed for eligibility. Nineteen reports were then excluded due to lack of reports on external validation, while 4 were excluded due to lack of evaluation of pCR as the primary outcome. Only Twenty-eight articles were eligible and included in this systematic review. In terms of quality assessment, 89 % of the models had low concerns in the participants domain, while 11 % had an unclear rating. 96 % of the models were of low concern in both the predictors and outcome domains. The overall rating showed high applicability potential of the models with 82 % showing low concern, while 18 % were deemed unclear.

CONCLUSION: Most of the external validated techniques showed promising performances and the potential to be applied in clinical settings, which is a crucial step towards evidence-based medicine. However, more studies focused on the external validations of these models in larger cohorts is necessary to ensure that they can reliably predict outcomes in diverse populations.

PMID:39562260 | DOI:10.1016/j.ejso.2024.109463

Brief Bioinform. 2024 Sep 23;25(6):bbae599. doi: 10.1093/bib/bbae599.

ABSTRACT

Rice consistently faces significant threats from biotic stresses, such as fungi, bacteria, pests, and viruses. Consequently, accurately and rapidly identifying previously unknown single-nucleotide polymorphisms (SNPs) in the rice genome is a critical challenge for rice research and the development of resistant varieties. However, the limited availability of high-quality rice genotype data has hindered this research. Deep learning has transformed biological research by facilitating the prediction and analysis of SNPs in biological sequence data. Convolutional neural networks are especially effective in extracting structural and local features from DNA sequences, leading to significant advancements in genomics. Nevertheless, the expanding catalog of genome-wide association studies provides valuable biological insights for rice research. Expanding on this idea, we introduce RiceSNP-BST, an automatic architecture search framework designed to predict SNPs associated with rice biotic stress traits (BST-associated SNPs) by integrating multidimensional features. Notably, the model successfully innovates the datasets, offering more precision than state-of-the-art methods while demonstrating good performance on an independent test set and cross-species datasets. Additionally, we extracted features from the original DNA sequences and employed causal inference to enhance the biological interpretability of the model. This study highlights the potential of RiceSNP-BST in advancing genome prediction in rice. Furthermore, a user-friendly web server for RiceSNP-BST (http://rice-snp-bst.aielab.cc) has been developed to support broader genome research.

PMID:39562160 | DOI:10.1093/bib/bbae599

Genome Res. 2024 Nov 19:gr.279694.124. doi: 10.1101/gr.279694.124. Online ahead of print.

ABSTRACT

Polygenic risk score (PRS) is a widely-used approach for predicting individuals' genetic risk of complex diseases, playing a pivotal role in advancing precision medicine. Traditional PRS methods, predominantly following a linear structure, often fall short in capturing the intricate relationships between genotype and phenotype. In this study, we present PRS-Net, an interpretable geometric deep learning-based framework that effectively models the nonlinearity of biological systems for enhanced disease prediction and biological discovery. PRS-Net begins by deconvoluting the genome-wide PRS at the single-gene resolution, and then explicitly encapsulates gene-gene interactions leveraging a graph neural network (GNN) for genetic risk prediction, enabling a systematic characterization of molecular interplay underpinning diseases. An attentive readout module is introduced to facilitate model interpretation. Extensive tests across multiple complex traits and diseases demonstrate the superior prediction performance of PRS-Net compared to conventional PRS methods. The interpretability of PRS-Net further enhances the identification of disease-relevant genes and gene programs. PRS-Net provides a potent tool for concurrent genetic risk prediction and biological discovery for complex diseases.

PMID:39562137 | DOI:10.1101/gr.279694.124

Am J Hum Genet. 2024 Nov 13:S0002-9297(24)00380-X. doi: 10.1016/j.ajhg.2024.10.011. Online ahead of print.

ABSTRACT

There has been considerable progress in building models to predict the effect of missense substitutions in protein-coding genes, fueled in large part by progress in applying deep learning methods to sequence data. These models have the potential to enable clinical variant annotation on a large scale and hence increase the impact of patient sequencing in guiding diagnosis and treatment. To realize this potential, it is essential to provide reliable assessments of model performance, scope of applicability, and robustness. As a response to this need, the ClinGen Sequence Variant Interpretation Working Group, Pejaver et al., recently proposed a strategy for validation and calibration of in-silico predictions in the context of guidelines for variant annotation. While this work marks an important step forward, the strategy presented still has important limitations. We propose core principles and recommendations to overcome these limitations that can enable both more reliable and more impactful use of variant effect prediction models in the future.

PMID:39561772 | DOI:10.1016/j.ajhg.2024.10.011

Talanta. 2024 Nov 8;284:127192. doi: 10.1016/j.talanta.2024.127192. Online ahead of print.

ABSTRACT

LIBS-based analysis has experienced an ever-increasing interest in recent years as a well-suited technique for chemical analysis tasks relying on elemental fingerprinting. This method stands out for its ability to offer rapid, simultaneous multi-element analysis with the advantage of portability. In the context of this research, our aim is to bridge the gap between the analysis of simulated and real data to better account for variations in plasma temperature and electron density, which are typically not considered in LIBS analysis. To achieve this, we employ two distinct methodologies, PLS and CNNs, to construct predictive models for predicting the concentration of the 24 elements within each LIBS spectrum. The initial phase of our investigation concentrates on the training and testing of these models using simulated LIBS data, with results evaluated through RMSEP values. The IQR and median RMSEP values for all the elements demonstrate that CNNs consistently achieved values below 0.01, while PLS results ranged from 0.01 to 0.05, highlighting the superior stability and predictive accuracy of CNNs model. In the next phase, we applied the pre-trained models to analyze the real LIBS spectra, consistently identifying Aluminum (Al), Iron (Fe), and Silicon (Si) as having the highest predicted concentrations. The overall predicted values were approximately 0.5 for Al, 0.6 for Si, and 0.04 for Fe. In the third phase, deliberate adjustments are made to the training parameters and architecture of the proposed CNNs model to force the network to emphasize specific elements, prioritizing them over other components present in each real LIBS spectrum. The generation of the three modified versions of the initially proposed CNNs allows us to explore the impact of regularization, sample weighting, and a customized loss function on prediction outcomes. Some elements emerge during the prediction phase, with Calcium (Ca), Magnesium (Mg), Zinc (Zn), Titanium (Ti), and Gallium (Ga) exhibiting more pronounced patterns.

PMID:39561618 | DOI:10.1016/j.talanta.2024.127192

Comput Biol Chem. 2024 Nov 15;113:108282. doi: 10.1016/j.compbiolchem.2024.108282. Online ahead of print.

ABSTRACT

Although bioinformatics-based methods accurately identify SEs (Super-enhancers), the results depend on feature design. It is foundational to representing biological sequences and automatically extracting their key features for improving SE identification. We propose a deep learning model MuSE (Multi-Feature Fusion for Super-Enhancer), based on multi-feature fusion. This model utilizes two encoding methods, one-hot and DNA2Vec, to signify DNA sequences. Specifically, one-hot encoding reflects single nucleotide information, while k-mer representations based on DNA2Vec capture both local sequence fragment information and global sequence characteristics. These types of feature vectors are conducted and combined by neural networks, which aim at SE prediction. To validate the effectiveness of MuSE, we design extensive experiments on human and mouse species datasets. Compared to baselines such as SENet, MuSE improves the prediction of F1 score to a maximum improvement exceeding 0.05 on mouse species. The k-mer representations based on DNA2Vec among the given features have the most important impact on predictions. This feature effectively captures context semantic knowledge and positional information of DNA sequences. However, its representation of the individuality of each species negatively affects MuSE's generalization ability. Nevertheless, the cross-species prediction results of MuSE improve again to reach an AUC of nearly 0.8, after removing this type of feature. Source codes are available at https://github.com/15831959673/MuSE.

PMID:39561516 | DOI:10.1016/j.compbiolchem.2024.108282

J Med Internet Res. 2024 Nov 19;26:e58892. doi: 10.2196/58892.

ABSTRACT

BACKGROUND: Current blood glucose monitoring (BGM) methods are often invasive and require repetitive pricking of a finger to obtain blood samples, predisposing individuals to pain, discomfort, and infection. Noninvasive blood glucose monitoring (NIBGM) is ideal for minimizing discomfort, reducing the risk of infection, and increasing convenience.

OBJECTIVE: This review aimed to map the use cases of artificial intelligence (AI) in NIBGM.

METHODS: A systematic scoping review was conducted according to the Arksey O'Malley five-step framework. Eight electronic databases (CINAHL, Embase, PubMed, Web of Science, Scopus, The Cochrane-Central Library, ACM Digital Library, and IEEE Xplore) were searched from inception until February 8, 2023. Study selection was conducted by 2 independent reviewers, descriptive analysis was conducted, and findings were presented narratively. Study characteristics (author, country, type of publication, study design, population characteristics, mean age, types of noninvasive techniques used, and application, as well as characteristics of the BGM systems) were extracted independently and cross-checked by 2 investigators. Methodological quality appraisal was conducted using the Checklist for assessment of medical AI.

RESULTS: A total of 33 papers were included, representing studies from Asia, the United States, Europe, the Middle East, and Africa published between 2005 and 2023. Most studies used optical techniques (n=19, 58%) to estimate blood glucose levels (n=27, 82%). Others used electrochemical sensors (n=4), imaging (n=2), mixed techniques (n=2), and tissue impedance (n=1). Accuracy ranged from 35.56% to 94.23% and Clarke error grid (A+B) ranged from 86.91% to 100%. The most popular machine learning algorithm used was random forest (n=10) and the most popular deep learning model was the artificial neural network (n=6). The mean overall checklist for assessment of medical AI score on the included papers was 33.5 (SD 3.09), suggesting an average of medium quality. The studies reviewed demonstrate that some AI techniques can accurately predict glucose levels from noninvasive sources while enhancing comfort and ease of use for patients. However, the overall range of accuracy was wide due to the heterogeneity of models and input data.

CONCLUSIONS: Efforts are needed to standardize and regulate the use of AI technologies in BGM, as well as develop consensus guidelines and protocols to ensure the quality and safety of AI-assisted monitoring systems. The use of AI for NIBGM is a promising area of research that has the potential to revolutionize diabetes management.

PMID:39561353 | DOI:10.2196/58892

JCO Clin Cancer Inform. 2024 Nov;8:e2400110. doi: 10.1200/CCI.24.00110. Epub 2024 Nov 19.

ABSTRACT

PURPOSE: Population-based cancer registries (PBCRs) collect data on all new cancer diagnoses in a defined population. Data are sourced from pathology reports, and the PBCRs rely on manual and rule-based solutions. This study presents a state-of-the-art natural language processing (NLP) pipeline, built by fine-tuning pretrained language models (LMs). The pipeline is deployed at the British Columbia Cancer Registry (BCCR) to detect reportable tumors from a population-based feed of electronic pathology.

METHODS: We fine-tune two publicly available LMs, GatorTron and BlueBERT, which are pretrained on clinical text. Fine-tuning is done using BCCR's pathology reports. For the final decision making, we combine both models' output using an OR approach. The fine-tuning data set consisted of 40,000 reports from the diagnosis year of 2021, and the test data sets consisted of 10,000 reports from the diagnosis year 2021, 20,000 reports from diagnosis year 2022, and 400 reports from diagnosis year 2023.

RESULTS: The retrospective evaluation of our proposed approach showed boosted reportable accuracy, maintaining the true reportable threshold of 98%.

CONCLUSION: Disadvantages of rule-based NLP in cancer surveillance include manual effort in rule design and sensitivity to language change. Deep learning approaches demonstrate superior performance in classification. PBCRs distinguish reportability status of incoming electronic cancer pathology reports. Deep learning methods provide significant advantages over rule-based NLP.

PMID:39561305 | DOI:10.1200/CCI.24.00110

Clin Cancer Res. 2024 Nov 19. doi: 10.1158/1078-0432.CCR-24-2599. Online ahead of print.

ABSTRACT

PURPOSE: Necrosis quantification in the neoadjuvant setting using pathology slide review is the most important validated prognostic marker in conventional osteosarcoma. Herein, we explored three deep learning strategies on histology samples to predict outcome for OSA in the neoadjuvant setting.

EXPERIMENTAL DESIGN: Our study relies on a training cohort from New York University (New York, NY) and an external cohort from Charles university (Prague, Czechia). We trained and validated the performance of a supervised approach that integrates neural network predictions of necrosis/tumor content, and compared predicted overall survival (OS) using Kaplan-Meier curves. Furthermore, we explored morphology-based supervised and self-supervised approaches to determine whether intrinsic histomorphological features could serve as a potential marker for OS in the setting of neoadjuvant.

RESULTS: Excellent correlation between the trained network and the pathologists was obtained for the quantification of necrosis content (R2=0.899, r=0.949, p < 0.0001). OS prediction cutoffs were consistent between pathologists and the neural network (22% and 30% of necrosis, respectively). Morphology-based supervised approach predicted OS with p-value=0.0028, HR=2.43 [1.10-5.38]. The self-supervised approach corroborated the findings with clusters enriched in necrosis, fibroblastic stroma, and osteoblastic morphology associating with better OS (lg2HR; -2.366; -1.164; -1.175; 95% CI=[-2.996; -0.514]). Viable/partially viable tumor and fat necrosis were associated with worse OS (lg2HR;1.287;0.822;0.828; 95% CI=[0.38-1.974]).

CONCLUSIONS: Neural networks can be used to automatically estimate the necrosis to tumor ratio, a quantitative metric predictive of survival. Furthermore, we identified alternate histomorphological biomarkers specific to the necrotic and tumor regions themselves which can be used as predictors.

PMID:39561274 | DOI:10.1158/1078-0432.CCR-24-2599

PLoS Comput Biol. 2024 Nov 19;20(11):e1012597. doi: 10.1371/journal.pcbi.1012597. Online ahead of print.

ABSTRACT

Predicting virus-host associations is essential to determine the specific host species that viruses interact with, and discover if new viruses infect humans and animals. Currently, the host of the majority of viruses is unknown, particularly in microbiomes. To address this challenge, we introduce EvoMIL, a deep learning method that predicts the host species for viruses from viral sequences only. It also identifies important viral proteins that significantly contribute to host prediction. The method combines a pre-trained large protein language model (ESM) and attention-based multiple instance learning to allow protein-orientated predictions. Our results show that protein embeddings capture stronger predictive signals than sequence composition features, including amino acids, physiochemical properties, and DNA k-mers. In multi-host prediction tasks, EvoMIL achieves median F1 score improvements of 10.8%, 16.2%, and 4.9% in prokaryotic hosts, and 1.7%, 6.6% and 11.5% in eukaryotic hosts. EvoMIL binary classifiers achieve impressive AUC over 0.95 for all prokaryotic hosts and range from roughly 0.8 to 0.9 for eukaryotic hosts. Furthermore, EvoMIL identifies important proteins in the prediction task. We found them capturing key functions in virus-host specificity.

PMID:39561204 | DOI:10.1371/journal.pcbi.1012597

PLoS One. 2024 Nov 19;19(11):e0313145. doi: 10.1371/journal.pone.0313145. eCollection 2024.

ABSTRACT

Ship detection over long distances is crucial for the visual perception of intelligent ships. Since traditional image processing-based methods are not robust, deep learning-based image recognition methods can automatically obtain the features of small ships. However, due to the limited pixels of ships over long distances, accurate features of such ships are difficult to obtain. To address this, a two-stage object detection method that combines the advantages of traditional and deep-learning methods is proposed. In the first stage, an object detection model for the sea-sky line (SSL) region is trained to select a potential region of ships. In the second stage, another object detection model for ships is trained using sliced patches containing ships. When testing, the SSL region is first detected using the trained 8th version of You Only Look Once (YOLOv8). Then, the SSL region detected is divided into several overlapping patches using the slicing technique, and another trained YOLOv8 is applied to detect ships. The experimental results showed that our method achieved 85% average precision when the intersection over union is 0.5 (AP50), and a detection speed of 75 ms per image with a pixel size of 1080×640. The code is available at https://github.com/gongyanfeng/PaperCode.

PMID:39561153 | DOI:10.1371/journal.pone.0313145