Int J Comput Assist Radiol Surg. 2024 May 5. doi: 10.1007/s11548-024-03119-w. Online ahead of print.

ABSTRACT

PURPOSE: Deep learning-based analysis of micro-ultrasound images to detect cancerous lesions is a promising tool for improving prostate cancer (PCa) diagnosis. An ideal model should confidently identify cancer while responding with appropriate uncertainty when presented with out-of-distribution inputs that arise during deployment due to imaging artifacts and the biological heterogeneity of patients and prostatic tissue.

METHODS: Using micro-ultrasound data from 693 patients across 5 clinical centers who underwent micro-ultrasound guided prostate biopsy, we train and evaluate convolutional neural network models for PCa detection. To improve robustness to out-of-distribution inputs, we employ and comprehensively benchmark several state-of-the-art uncertainty estimation methods.

RESULTS: PCa detection models achieve performance scores up to 76 % average AUROC with a 10-fold cross validation setup. Models with uncertainty estimation obtain expected calibration error scores as low as 2 % , indicating that confident predictions are very likely to be correct. Visualizations of the model output demonstrate that the model correctly identifies healthy versus malignant tissue.

CONCLUSION: Deep learning models have been developed to confidently detect PCa lesions from micro-ultrasound. The performance of these models, determined from a large and diverse dataset, is competitive with visual analysis of magnetic resonance imaging, the clinical benchmark to identify PCa lesions for targeted biopsy. Deep learning with micro-ultrasound should be further studied as an avenue for targeted prostate biopsy.

PMID:38704793 | DOI:10.1007/s11548-024-03119-w

Ann Nucl Med. 2024 May 5. doi: 10.1007/s12149-024-01936-2. Online ahead of print.

ABSTRACT

OBJECTIVE: To investigate the prognostic value of 18F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.

METHODS: We retrospectively analyzed the pre-treatment 18F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (n = 166) and digital (n = 51) PET cohorts. 18F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.

RESULTS: In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUVmax, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319, p < 0.001) and digital PET cohorts (HR = 1.284, p = 0.001). Our model provided incremental prognostic value to staging status (c-indices = 0.738 vs. 0.558 and 0.662 vs. 0.598 in the analog and digital PET cohorts, respectively). Our model also demonstrated a significant prognostic value for overall survival (HR = 1.198, p < 0.001, c-index = 0.708 and HR = 1.256, p = 0.021, c-index = 0.664 in the analog and digital PET cohorts, respectively).

CONCLUSIONS: Combining 18F-FDG PET-based intensity, volumetric features, and DL with clinical variables may improve the survival stratification in patients with advanced EGFR-mutated lung adenocarcinoma receiving TKI treatment. Implementing the prediction model across different generations of PET scanners may be feasible and facilitate tailored therapeutic strategies for these patients.

PMID:38704786 | DOI:10.1007/s12149-024-01936-2

Brief Bioinform. 2024 Mar 27;25(3):bbae192. doi: 10.1093/bib/bbae192.

ABSTRACT

Computational analysis of fluorescent timelapse microscopy images at the single-cell level is a powerful approach to study cellular changes that dictate important cell fate decisions. Core to this approach is the need to generate reliable cell segmentations and classifications necessary for accurate quantitative analysis. Deep learning-based convolutional neural networks (CNNs) have emerged as a promising solution to these challenges. However, current CNNs are prone to produce noisy cell segmentations and classifications, which is a significant barrier to constructing accurate single-cell lineages. To address this, we developed a novel algorithm called Single Cell Track (SC-Track), which employs a hierarchical probabilistic cache cascade model based on biological observations of cell division and movement dynamics. Our results show that SC-Track performs better than a panel of publicly available cell trackers on a diverse set of cell segmentation types. This cell-tracking performance was achieved without any parameter adjustments, making SC-Track an excellent generalized algorithm that can maintain robust cell-tracking performance in varying cell segmentation qualities, cell morphological appearances and imaging conditions. Furthermore, SC-Track is equipped with a cell class correction function to improve the accuracy of cell classifications in multiclass cell segmentation time series. These features together make SC-Track a robust cell-tracking algorithm that works well with noisy cell instance segmentation and classification predictions from CNNs to generate accurate single-cell lineages and classifications.

PMID:38704671 | DOI:10.1093/bib/bbae192

Int J Surg. 2024 May 3. doi: 10.1097/JS9.0000000000001510. Online ahead of print.

NO ABSTRACT

PMID:38704627 | DOI:10.1097/JS9.0000000000001510

Chemosphere. 2024 May 2:142223. doi: 10.1016/j.chemosphere.2024.142223. Online ahead of print.

ABSTRACT

Antibiotic resistance (AR) is considered one of the greatest global threats in the current century, which can only be overcome if all interconnected areas of humans, animals and the environment are taken into account as part of the One Health concept proposed by the World Health Organization (WHO). Water and wastewater are among the most important environmental media of AR sources, where the phenomena are generally non-linear. Therefore, the aim of this study was to investigate the application of machine learning-based methods (MLMs) to solve AR-induced problems in water and wastewater. For this purpose, most relevant databases were searched in the period between 1987 and 2023 to systematically analyze and categorize the applications. Accordingly, the results showed that out of 12 applications, 11 (91.6%) were for shallow learning and 1 (8.3%) for deep learning. In shallow learning category, n = 6, 50% of the applications were regression and n = 4, 33.3% were classification, mainly using artificial neural networks, decision trees and Bayesian methods for the following objectives: Predicting the survival of antibiotic-resistant bacteria (ARB), determining the order of influencing parameters on AR-based scores, and identifying the major sources of antibiotic resistance genes (ARGs). In addition, only one study (8.3%) was found for clustering and no study for association. Surprisingly, deep learning had been used in only one study (8.3%) to predict ARGs sequences. Therefore, working on the knowledge gaps of AR, especially using clustering, association and deep learning methods, would be a promising option to analyze more aspects of the related problems. However, there is still a long way to go to consider and apply MLMs as unique approaches to study different aspects of AR in water and wastewater.

PMID:38704045 | DOI:10.1016/j.chemosphere.2024.142223

Mod Pathol. 2024 May 2:100508. doi: 10.1016/j.modpat.2024.100508. Online ahead of print.

ABSTRACT

Image based deep learning models are used to extract new information from standard H&E pathology slides, however, biological interpretation of the features detected by artificial intelligence (AI) remains a challenge. High-grade serous ovarian carcinoma (HGSC) is characterized by aggressive behavior and chemotherapy resistance, but also by striking variability in outcome. Our understanding of this disease is limited, partly due to considerable tumor heterogeneity. We previously trained an AI model to identify HGSC tumor regions that are highly associated with outcome status but are indistinguishable by conventional morphologic methods. Here we applied spatial transcriptomics to further profile the AI-identified tumor regions in 16 patients (8 per outcome group) and identify molecular features related to disease outcome in patients who underwent primary debulking surgery and platinum-based chemotherapy. We examined FFPE tissue from 1) regions identified by the AI model as highly associated with short or extended chemotherapy response, and 2) background tumor regions (not identified by the AI model as highly associated with outcome status) from the same tumors. We show that the transcriptomic profiles of AI-identified regions are more distinct than background regions from the same tumors, are superior in predicting outcome, and differ in several pathways including those associated with chemoresistance in HGSC. Further, we find that poor outcome and good outcome regions are enriched by different tumor subpopulations, suggesting distinctive interaction patterns. In summary, our work presents proof of concept that AI-guided spatial transcriptomic analysis improves recognition of biologic features relevant to patient outcome.

PMID:38704029 | DOI:10.1016/j.modpat.2024.100508

Am J Ophthalmol. 2024 May 2:S0002-9394(24)00199-5. doi: 10.1016/j.ajo.2024.04.030. Online ahead of print.

ABSTRACT

PURPOSE: To develop deep learning (DL) algorithm to detect glaucoma progression using optical coherence tomography (OCT) images, in the absence of a reference standard.

DESIGN: Retrospective cohort study.

METHODS: Glaucomatous and healthy eyes with ≥5 reliable peripapillary OCT (Spectralis, Heidelberg Engineering) circle scans were included. A weakly supervised time-series learning model, called Noise Positive-Unlabeled (Noise-PU) DL was developed to classify whether sequences of OCT B-scans showed glaucoma progression. The model used two learning schemes, one to identify age-related changes by differentiating test sequences from glaucoma vs. healthy eyes, and the other to identify test-retest variability based on scrambled OCTs of glaucoma eyes. Both models' bases were convolutional neural networks (CNN) and long short-term memory (LSTM) networks which were combined to form a CNN-LSTM model. Model features were combined and jointly trained to identify glaucoma progression, accounting for age-related loss. The DL model's outcomes were compared with ordinary least squares (OLS) regression of retinal nerve fiber layer (RNFL) thickness over time, matched for specificity. The hit ratio was used as a proxy for sensitivity.

RESULTS: 8,785 follow-up sequences of 5 consecutive OCT tests from 3253 eyes (1859 subjects) were included in the study. Mean follow-up time was 3.5±1.6 years. In the test sample, the hit ratios of the DL and OLS methods were 0.498 (95%CI:0.470-0.526) and 0.284 (95%CI:0.258-0.309) respectively (P<0.001) when the specificities were equalized to 95%.

CONCLUSION: A DL model was able to identify longitudinal glaucomatous structural changes in OCT B-scans using a surrogate reference standard for progression.

PMID:38703802 | DOI:10.1016/j.ajo.2024.04.030

BMC Bioinformatics. 2024 May 4;25(1):176. doi: 10.1186/s12859-024-05771-0.

ABSTRACT

BACKGROUND: Protein residue-residue distance maps are used for remote homology detection, protein information estimation, and protein structure research. However, existing prediction approaches are time-consuming, and hundreds of millions of proteins are discovered each year, necessitating the development of a rapid and reliable prediction method for protein residue-residue distances. Moreover, because many proteins lack known homologous sequences, a waiting-free and alignment-free deep learning method is needed.

RESULT: In this study, we propose a learning framework named FreeProtMap. In terms of protein representation processing, the proposed group pooling in FreeProtMap effectively mitigates issues arising from high-dimensional sparseness in protein representation. In terms of model structure, we have made several careful designs. Firstly, it is designed based on the locality of protein structures and triangular inequality distance constraints to improve prediction accuracy. Secondly, inference speed is improved by using additive attention and lightweight design. Besides, the generalization ability is improved by using bottlenecks and a neural network block named local microformer. As a result, FreeProtMap can predict protein residue-residue distances in tens of milliseconds and has higher precision than the best structure prediction method.

CONCLUSION: Several groups of comparative experiments and ablation experiments verify the effectiveness of the designs. The results demonstrate that FreeProtMap significantly outperforms other state-of-the-art methods in accurate protein residue-residue distance prediction, which is beneficial for lots of protein research works. It is worth mentioning that we could scan all proteins discovered each year based on FreeProtMap to find structurally similar proteins in a short time because the fact that the structure similarity calculation method based on distance maps is much less time-consuming than algorithms based on 3D structures.

PMID:38704533 | DOI:10.1186/s12859-024-05771-0

BMC Bioinformatics. 2024 May 4;25(1):177. doi: 10.1186/s12859-024-05763-0.

ABSTRACT

BACKGROUND: Hepatitis B virus (HBV) integrates into human chromosomes and can lead to genomic instability and hepatocarcinogenesis. Current tools for HBV integration site detection lack accuracy and stability.

RESULTS: This study proposes a deep learning-based method, named ViroISDC, for detecting integration sites. ViroISDC generates corresponding grammar rules and encodes the characteristics of the language data to predict integration sites accurately. Compared with Lumpy, Pindel, Seeksv, and SurVirus, ViroISDC exhibits better overall performance and is less sensitive to sequencing depth and integration sequence length, displaying good reliability, stability, and generality. Further downstream analysis of integrated sites detected by ViroISDC reveals the integration patterns and features of HBV. It is observed that HBV integration exhibits specific chromosomal preferences and tends to integrate into cancerous tissue. Moreover, HBV integration frequency was higher in males than females, and high-frequency integration sites were more likely to be present on hepatocarcinogenesis- and anti-cancer-related genes, validating the reliability of the ViroISDC.

CONCLUSIONS: ViroISDC pipeline exhibits superior precision, stability, and reliability across various datasets when compared to similar software. It is invaluable in exploring HBV infection in the human body, holding significant implications for the diagnosis, treatment, and prognosis assessment of HCC.

PMID:38704528 | DOI:10.1186/s12859-024-05763-0

Probiotics Antimicrob Proteins. 2024 May 4. doi: 10.1007/s12602-024-10261-z. Online ahead of print.

ABSTRACT

The main issue with clinical infections is multidrug resistance to traditional antibiotics. As they are essential to innate immunity, shielding hosts from pathogenic microbes, traditional herbal remedies are an excellent supplier of antimicrobial peptides (AMPs), vital parts of defensive systems. Nevertheless, little is known about the bioactive peptide components of most ethnobotanical species. Our goal in this study was to find new, likely AMPs from Portulaca oleracea (P. oleracea) using in silico studies. The P. oleracea transcriptome was gained from Sequence Read Archive (SRA) and quality controlled, then adapters and other low-quality reads were trimmed. Afterward, de novo assembled and translated open reading frames (ORFs) were determined. Next, the ORFs were filtered based on AMP physiochemical criteria and deep learning methods. Finally, the five selected putative AMPs docked with E. coli and S. aureus membranes that showed penetration in bilayers. In this step, PO2 was chosen as a candidate AMP to analyze with molecular dynamics (MD) simulations. Our data demonstrated that PO2 is more stable in E. coli than in S. aureus. Moreover, these predicted AMPs can be good candidates for in vitro and in vivo analysis.

PMID:38704476 | DOI:10.1007/s12602-024-10261-z

NPJ Digit Med. 2024 May 4;7(1):115. doi: 10.1038/s41746-024-01119-3.

ABSTRACT

Spectral-domain optical coherence tomography (SDOCT) is the gold standard of imaging the eye in clinics. Penetration depth with such devices is, however, limited and visualization of the choroid, which is essential for diagnosing chorioretinal disease, remains limited. Whereas swept-source OCT (SSOCT) devices allow for visualization of the choroid these instruments are expensive and availability in praxis is limited. We present an artificial intelligence (AI)-based solution to enhance the visualization of the choroid in OCT scans and allow for quantitative measurements of choroidal metrics using generative deep learning (DL). Synthetically enhanced SDOCT B-scans with improved choroidal visibility were generated, leveraging matching images to learn deep anatomical features during the training. Using a single-center tertiary eye care institution cohort comprising a total of 362 SDOCT-SSOCT paired subjects, we trained our model with 150,784 images from 410 healthy, 192 glaucoma, and 133 diabetic retinopathy eyes. An independent external test dataset of 37,376 images from 146 eyes was deployed to assess the authenticity and quality of the synthetically enhanced SDOCT images. Experts' ability to differentiate real versus synthetic images was poor (47.5% accuracy). Measurements of choroidal thickness, area, volume, and vascularity index, from the reference SSOCT and synthetically enhanced SDOCT, showed high Pearson's correlations of 0.97 [95% CI: 0.96-0.98], 0.97 [0.95-0.98], 0.95 [0.92-0.98], and 0.87 [0.83-0.91], with intra-class correlation values of 0.99 [0.98-0.99], 0.98 [0.98-0.99], and 0.95 [0.96-0.98], 0.93 [0.91-0.95], respectively. Thus, our DL generative model successfully generated realistic enhanced SDOCT data that is indistinguishable from SSOCT images providing improved visualization of the choroid. This technology enabled accurate measurements of choroidal metrics previously limited by the imaging depth constraints of SDOCT. The findings open new possibilities for utilizing affordable SDOCT devices in studying the choroid in both healthy and pathological conditions.

PMID:38704440 | DOI:10.1038/s41746-024-01119-3

Sci Rep. 2024 May 4;14(1):10262. doi: 10.1038/s41598-024-61106-2.

ABSTRACT

As sustainability emerges as a crucial factor in the development of modern enterprises, integrating environmental, social, and governance (ESG) information into financial assessments has become essential. ESG indicators serve as important metrics in evaluating a company's sustainable practices and governance effectiveness, influencing investor trust and future growth potential, ultimately affecting stock prices. This study proposes an innovative approach that combines ESG sentiment index extracted from news with technical indicators to predict the S&P 500 index. By utilizing a deep learning model and exploring optimal window sizes, the study explores the best model through mean absolute percentage error (MAPE) as an evaluation metric. Additionally, an ablation test clarifies the influence of ESG and its causality with the S&P 500 index. The experimental results demonstrate improved predictive accuracy when considering ESG sentiment compared to relying solely on technical indicators or historical data. This comprehensive methodology enhances the advantage of stock price prediction by integrating technical indicators, which consider short-term fluctuations, with ESG information, providing long-term effects. Furthermore, it offers valuable insights for investors and financial market experts, validating the necessity to consider ESG for financial assets and introducing a new perspective to develop investment strategies and decision-making processes.

PMID:38704434 | DOI:10.1038/s41598-024-61106-2

Sci Rep. 2024 May 4;14(1):10280. doi: 10.1038/s41598-024-59846-2.

ABSTRACT

In modern healthcare, integrating Artificial Intelligence (AI) and Internet of Medical Things (IoMT) is highly beneficial and has made it possible to effectively control disease using networks of interconnected sensors worn by individuals. The purpose of this work is to develop an AI-IoMT framework for identifying several of chronic diseases form the patients' medical record. For that, the Deep Auto-Optimized Collaborative Learning (DACL) Model, a brand-new AI-IoMT framework, has been developed for rapid diagnosis of chronic diseases like heart disease, diabetes, and stroke. Then, a Deep Auto-Encoder Model (DAEM) is used in the proposed framework to formulate the imputed and preprocessed data by determining the fields of characteristics or information that are lacking. To speed up classification training and testing, the Golden Flower Search (GFS) approach is then utilized to choose the best features from the imputed data. In addition, the cutting-edge Collaborative Bias Integrated GAN (ColBGaN) model has been created for precisely recognizing and classifying the types of chronic diseases from the medical records of patients. The loss function is optimally estimated during classification using the Water Drop Optimization (WDO) technique, reducing the classifier's error rate. Using some of the well-known benchmarking datasets and performance measures, the proposed DACL's effectiveness and efficiency in identifying diseases is evaluated and compared.

PMID:38704423 | DOI:10.1038/s41598-024-59846-2

Nat Commun. 2024 May 4;15(1):3768. doi: 10.1038/s41467-024-48171-x.

ABSTRACT

Accurate intraoperative differentiation of primary central nervous system lymphoma (PCNSL) remains pivotal in guiding neurosurgical decisions. However, distinguishing PCNSL from other lesions, notably glioma, through frozen sections challenges pathologists. Here we sought to develop and validate a deep learning model capable of precisely distinguishing PCNSL from non-PCNSL lesions, especially glioma, using hematoxylin and eosin (H&E)-stained frozen whole-slide images. Also, we compared its performance against pathologists of varying expertise. Additionally, a human-machine fusion approach integrated both model and pathologic diagnostics. In external cohorts, LGNet achieved AUROCs of 0.965 and 0.972 in distinguishing PCNSL from glioma and AUROCs of 0.981 and 0.993 in differentiating PCNSL from non-PCNSL lesions. Outperforming several pathologists, LGNet significantly improved diagnostic performance, further augmented to some extent by fusion approach. LGNet's proficiency in frozen section analysis and its synergy with pathologists indicate its valuable role in intraoperative diagnosis, particularly in discriminating PCNSL from glioma, alongside other lesions.

PMID:38704409 | DOI:10.1038/s41467-024-48171-x

Sci Rep. 2024 May 5;14(1):10300. doi: 10.1038/s41598-024-60798-w.

ABSTRACT

This paper proposes an innovative global solution which is a pioneering work applying automated machine learning algorithms to remarkable precision sparse underwater direction-of-arrival (DOA) estimation that views the subaquatic sparse-sampling DOA estimation problem as a classification prediction task. The proposed solution, termed automated multi-layer perceptron discriminative neural network (AutoMPDNN), is built upon a Bayesian optimization framework. AutoMPDNN transforms sparsely sampled time-domain signals into the complex domain, preserving essential components in a one-source single-snapshot scenario. Leveraging Bayesian optimization principles, the algorithm embeds necessary hyperparameters into the loss function, effectively defining it as a maximum likelihood problem using the upper confidence bound function and incorporating sparse signal features. We also explore the model space architecture and introduce variants of AutoMPDNN, denoted as AutoMPDNNs_ln (n = 2,3,4). Through a series of plane wave simulation experiments, it is demonstrated that AutoMPDNN achieves the highest prediction performance for one-source single-snapshot scenarios compared to classical DOA estimation algorithms that incorporate sparse representation approaches, as well as contemporary deep learning DOA methods under varying conditions.

PMID:38704397 | DOI:10.1038/s41598-024-60798-w

J Cell Mol Med. 2024 May;28(9):e18296. doi: 10.1111/jcmm.18296.

ABSTRACT

We investigated subarachnoid haemorrhage (SAH) macrophage subpopulations and identified relevant key genes for improving diagnostic and therapeutic strategies. SAH rat models were established, and brain tissue samples underwent single-cell transcriptome sequencing and bulk RNA-seq. Using single-cell data, distinct macrophage subpopulations, including a unique SAH subset, were identified. The hdWGCNA method revealed 160 key macrophage-related genes. Univariate analysis and lasso regression selected 10 genes for constructing a diagnostic model. Machine learning algorithms facilitated model development. Cellular infiltration was assessed using the MCPcounter algorithm, and a heatmap integrated cell abundance and gene expression. A 3 × 3 convolutional neural network created an additional diagnostic model, while molecular docking identified potential drugs. The diagnostic model based on the 10 selected genes achieved excellent performance, with an AUC of 1 in both training and validation datasets. The heatmap, combining cell abundance and gene expression, provided insights into SAH cellular composition. The convolutional neural network model exhibited a sensitivity and specificity of 1 in both datasets. Additionally, CD14, GPNMB, SPP1 and PRDX5 were specifically expressed in SAH-associated macrophages, highlighting its potential as a therapeutic target. Network pharmacology analysis identified some targeting drugs for SAH treatment. Our study characterised SAH macrophage subpopulations and identified key associated genes. We developed a robust diagnostic model and recognised CD14, GPNMB, SPP1 and PRDX5 as potential therapeutic targets. Further experiments and clinical investigations are needed to validate these findings and explore the clinical implications of targets in SAH treatment.

PMID:38702954 | DOI:10.1111/jcmm.18296

Methods. 2024 May 1:S1046-2023(24)00110-5. doi: 10.1016/j.ymeth.2024.04.020. Online ahead of print.

ABSTRACT

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

PMID:38702021 | DOI:10.1016/j.ymeth.2024.04.020

Anal Chem. 2024 May 3. doi: 10.1021/acs.analchem.4c01845. Online ahead of print.

ABSTRACT

Microorganism are ubiquitous and intimately connected with human health and disease management. The accurate and fast identification of pathogenic microorganisms is especially important for diagnosing infections. Herein, three tetraphenylethylene derivatives (S-TDs: TBN, TPN, and TPI) featuring different cationic groups, charge numbers, emission wavelengths, and hydrophobicities were successfully synthesized. Benefiting from distinct cell wall binding properties, S-TDs were collectively utilized to create a sensor array capable of imaging various microorganisms through their characteristic fluorescent signatures. Furthermore, the interaction mechanism between S-TDs and different microorganisms was explored by calculating the binding energy between S-TDs and cell membrane/wall constituents, including phospholipid bilayer and peptidoglycan. Using a combination of the fluorescence sensor array and a deep learning model of residual network (ResNet), readily differentiation of Gram-negative bacteria (G-), Gram-positive bacteria (G+), fungi, and their mixtures was achieved. Specifically, by extensive training of two ResNet models with large quantities of images data from 14 kinds of microorganism stained with S-TDs, identification of microorganism was achieved at high-level accuracy: over 92.8% for both Gram species and antibiotic-resistant species, with 90.35% accuracy for the detection of mixed microorganism in infected wound. This novel method provides a rapid and accurate method for microbial classification, potentially aiding in the diagnosis and treatment of infectious diseases.

PMID:38702857 | DOI:10.1021/acs.analchem.4c01845

J Transl Med. 2024 Apr 30;22(1):411. doi: 10.1186/s12967-024-05067-0.

ABSTRACT

Upon a diagnosis, the clinical team faces two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions. However, individuals do not consistently demonstrate the reported response from relevant clinical trials. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies with the changes in their condition. In practice, the drug and the dose selection depend significantly on the medical protocol and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data and Artificial Intelligence (AI) approaches have emerged as excellent decision-making tools, but multiple challenges limit their application. AI is a rapidly evolving and dynamic field with the potential to revolutionize various aspects of human life. AI has become increasingly crucial in drug discovery and development. AI enhances decision-making across different disciplines, such as medicinal chemistry, molecular and cell biology, pharmacology, pathology, and clinical practice. In addition to these, AI contributes to patient population selection and stratification. The need for AI in healthcare is evident as it aids in enhancing data accuracy and ensuring the quality care necessary for effective patient treatment. AI is pivotal in improving success rates in clinical practice. The increasing significance of AI in drug discovery, development, and clinical trials is underscored by many scientific publications. Despite the numerous advantages of AI, such as enhancing and advancing Precision Medicine (PM) and remote patient monitoring, unlocking its full potential in healthcare requires addressing fundamental concerns. These concerns include data quality, the lack of well-annotated large datasets, data privacy and safety issues, biases in AI algorithms, legal and ethical challenges, and obstacles related to cost and implementation. Nevertheless, integrating AI in clinical medicine will improve diagnostic accuracy and treatment outcomes, contribute to more efficient healthcare delivery, reduce costs, and facilitate better patient experiences, making healthcare more sustainable. This article reviews AI applications in drug development and clinical practice, making healthcare more sustainable, and highlights concerns and limitations in applying AI.

PMID:38702711 | DOI:10.1186/s12967-024-05067-0

BMC Med Inform Decis Mak. 2024 May 3;24(1):117. doi: 10.1186/s12911-024-02514-2.

ABSTRACT

BACKGROUND: Irregular time series (ITS) are common in healthcare as patient data is recorded in an electronic health record (EHR) system as per clinical guidelines/requirements but not for research and depends on a patient's health status. Due to irregularity, it is challenging to develop machine learning techniques to uncover vast intelligence hidden in EHR big data, without losing performance on downstream patient outcome prediction tasks.

METHODS: In this paper, we propose Perceiver, a cross-attention-based transformer variant that is computationally efficient and can handle long sequences of time series in healthcare. We further develop continuous patient state attention models, using Perceiver and transformer to deal with ITS in EHR. The continuous patient state models utilise neural ordinary differential equations to learn patient health dynamics, i.e., patient health trajectory from observed irregular time steps, which enables them to sample patient state at any time.

RESULTS: The proposed models' performance on in-hospital mortality prediction task on PhysioNet-2012 challenge and MIMIC-III datasets is examined. Perceiver model either outperforms or performs at par with baselines, and reduces computations by about nine times when compared to the transformer model, with no significant loss of performance. Experiments to examine irregularity in healthcare reveal that continuous patient state models outperform baselines. Moreover, the predictive uncertainty of the model is used to refer extremely uncertain cases to clinicians, which enhances the model's performance. Code is publicly available and verified at https://codeocean.com/capsule/4587224 .

CONCLUSIONS: Perceiver presents a computationally efficient potential alternative for processing long sequences of time series in healthcare, and the continuous patient state attention models outperform the traditional and advanced techniques to handle irregularity in the time series. Moreover, the predictive uncertainty of the model helps in the development of transparent and trustworthy systems, which can be utilised as per the availability of clinicians.

PMID:38702692 | DOI:10.1186/s12911-024-02514-2