PLoS One. 2024 May 31;19(5):e0304069. doi: 10.1371/journal.pone.0304069. eCollection 2024.

ABSTRACT

Deep learning has achieved immense success in computer vision and has the potential to help physicians analyze visual content for disease and other abnormalities. However, the current state of deep learning is very much a black box, making medical professionals skeptical about integrating these methods into clinical practice. Several methods have been proposed to shed some light on these black boxes, but there is no consensus on the opinion of medical doctors that will consume these explanations. This paper presents a study asking medical professionals about their opinion of current state-of-the-art explainable artificial intelligence methods when applied to a gastrointestinal disease detection use case. We compare two different categories of explanation methods, intrinsic and extrinsic, and gauge their opinion of the current value of these explanations. The results indicate that intrinsic explanations are preferred and that physicians see value in the explanations. Based on the feedback collected in our study, future explanations of medical deep neural networks can be tailored to the needs and expectations of doctors. Hopefully, this will contribute to solving the issue of black box medical systems and lead to successful implementation of this powerful technology in the clinic.

PMID:38820304 | DOI:10.1371/journal.pone.0304069

Med Phys. 2024 May 31. doi: 10.1002/mp.17235. Online ahead of print.

ABSTRACT

BACKGROUND: Stereotactic body radiotherapy (SBRT) is a well-established treatment modality for liver metastases in patients unsuitable for surgery. Both CT and MRI are useful during treatment planning for accurate target delineation and to reduce potential organs-at-risk (OAR) toxicity from radiation. MRI-CT deformable image registration (DIR) is required to propagate the contours defined on high-contrast MRI to CT images. An accurate DIR method could lead to more precisely defined treatment volumes and superior OAR sparing on the treatment plan. Therefore, it is beneficial to develop an accurate MRI-CT DIR for liver SBRT.

PURPOSE: To create a new deep learning model that can estimate the deformation vector field (DVF) for directly registering abdominal MRI-CT images.

METHODS: The proposed method assumed a diffeomorphic deformation. By using topology-preserved deformation features extracted from the probabilistic diffeomorphic registration model, abdominal motion can be accurately obtained and utilized for DVF estimation. The model integrated Swin transformers, which have demonstrated superior performance in motion tracking, into the convolutional neural network (CNN) for deformation feature extraction. The model was optimized using a cross-modality image similarity loss and a surface matching loss. To compute the image loss, a modality-independent neighborhood descriptor (MIND) was used between the deformed MRI and CT images. The surface matching loss was determined by measuring the distance between the warped coordinates of the surfaces of contoured structures on the MRI and CT images. To evaluate the performance of the model, a retrospective study was carried out on a group of 50 liver cases that underwent rigid registration of MRI and CT scans. The deformed MRI image was assessed against the CT image using the target registration error (TRE), Dice similarity coefficient (DSC), and mean surface distance (MSD) between the deformed contours of the MRI image and manual contours of the CT image.

RESULTS: When compared to only rigid registration, DIR with the proposed method resulted in an increase of the mean DSC values of the liver and portal vein from 0.850 ± 0.102 and 0.628 ± 0.129 to 0.903 ± 0.044 and 0.763 ± 0.073, a decrease of the mean MSD of the liver from 7.216 ± 4.513 mm to 3.232 ± 1.483 mm, and a decrease of the TRE from 26.238 ± 2.769 mm to 8.492 ± 1.058 mm.

CONCLUSION: The proposed DIR method based on a diffeomorphic transformer provides an effective and efficient way to generate an accurate DVF from an MRI-CT image pair of the abdomen. It could be utilized in the current treatment planning workflow for liver SBRT.

PMID:38820286 | DOI:10.1002/mp.17235

J Sep Sci. 2024 Jun;47(11):e2400051. doi: 10.1002/jssc.202400051.

ABSTRACT

While automated peak detection functionalities are available in commercially accessible software, achieving optimal true positive rates frequently necessitates visual inspection and manual adjustments. In the initial phase of this study, hetero-variants (glycoforms) of a monoclonal antibody were distinguished using liquid chromatography-mass spectrometry, revealing discernible peaks at the intact level. To comprehensively identify each peak (hetero-variant) in the intact-level analysis, a deep learning approach utilizing convolutional neural networks (CNNs) was employed in the subsequent phase of the study. In the current case study, utilizing conventional software for peak identification, five peaks were detected using a 0.5 threshold, whereas seven peaks were identified using the CNN model. The model exhibited strong performance with a probability area under the curve (AUC) of 0.9949, surpassing that of partial least squares discriminant analysis (PLS-DA) (probability AUC of 0.8041), and locally weighted regression (LWR) (probability AUC of 0.6885) on the data acquired during experimentation in real-time. The AUC of the receiver operating characteristic curve also illustrated the superior performance of the CNN over PLS-DA and LWR.

PMID:38819868 | DOI:10.1002/jssc.202400051

Int J Cardiovasc Imaging. 2022 May;38(5):915-917. doi: 10.1007/s10554-022-02621-z.

NO ABSTRACT

PMID:38819731 | DOI:10.1007/s10554-022-02621-z

Rev Sci Instrum. 2024 May 1;95(5):055005. doi: 10.1063/5.0194437.

ABSTRACT

Aiming at the problem that the cement production process is inherently affected by uncertainty, time delay, and strong coupling among variables, this paper proposed a novel soft sensor of free calcium oxide in a cement clinker. The model utilizes a dual-parallel integrated structure with an optimized integration of one-dimensional convolutional neural networks, long and short-term memory networks, graphical neural networks, and extreme gradient boosting. The proposed model can mitigate the risks associated with overfitting while incorporating the strengths of each individual model and excels in extracting both local and global features as well as temporal and spatial characteristics from the original time series data, ensuring its stability. The experimental results demonstrate that this dual-parallel integrated model exhibits superior robustness, predictive accuracy, and generalization capabilities when compared to single models or enhancements made to other deep learning algorithms.

PMID:38819257 | DOI:10.1063/5.0194437

Kaohsiung J Med Sci. 2024 May 31. doi: 10.1002/kjm2.12850. Online ahead of print.

ABSTRACT

Liver fibrosis is a pathological condition characterized by the abnormal proliferation of liver tissue, subsequently able to progress to cirrhosis or possibly hepatocellular carcinoma. The development of artificial intelligence and deep learning have begun to play a significant role in fibrosis detection. This study aimed to develop SMART AI-PATHO, a fully automated assessment method combining quantification of histopathological architectural features, to analyze steatosis and fibrosis in nonalcoholic fatty liver disease (NAFLD) core biopsies and employ Metavir fibrosis staging as standard references and fat assessment grading measurement for comparison with the pathologist interpretations. There were 146 participants enrolled in our study. The correlation of Metavir scoring system interpretation between pathologists and SMART AI-PATHO was significantly correlated (Agreement = 68%, Kappa = 0.59, p-value <0.001), which subgroup analysis of significant fibrosis (Metavir score F2-F4) and nonsignificant fibrosis (Metavir score F0-F1) demonstrated substantial correlated results (agreement = 80%, kappa = 0.61, p-value <0.001), corresponding with the correlation of advanced fibrosis (Metavir score F3-F4) and nonadvanced fibrosis groups (Metavir score F0-F2), (agreement = 89%, kappa = 0.74, p-value <0.001). SMART AI-PATHO, the first pivotal artificially intelligent diagnostic tool for the color-based NAFLD hepatic tissue staging in Thailand, demonstrated satisfactory performance as a pathologist to provide liver fibrosis scoring and steatosis grading. In the future, developing AI algorithms and reliable testing on a larger scale may increase accuracy and contribute to telemedicine consultations for general pathologists in clinical practice.

PMID:38819013 | DOI:10.1002/kjm2.12850

Anal Chem. 2024 May 31. doi: 10.1021/acs.analchem.4c01314. Online ahead of print.

ABSTRACT

Inaccurate or cumbersome clinical pathogen diagnosis between Gram-positive bacteria (G+) and Gram-negative (G-) bacteria lead to delayed clinical therapeutic interventions. Microelectrode-based electrochemical sensors exhibit the significant advantages of rapid response and minimal sample consumption, but the loading capacity and discrimination precision are weak. Herein, we develop reversible fusion-fission MXene-based fiber microelectrodes for G+/G- bacteria analysis. During the fissuring process, the spatial utilization, loading capacity, sensitivity, and selectivity of microelectrodes were maximized, and polymyxin B and vancomycin were assembled for G+/G- identification. The surface-tension-driven reversible fusion facilitated its reusability. A deep learning model was further applied for the electrochemical impedance spectroscopy (EIS) identification in diverse ratio concentrations of G+ and G- of (1:100-100:1) with higher accuracy (>93%) and gave predictable detection results for unknown samples. Meanwhile, the as-proposed sensing platform reached higher sensitivity toward E. coli (24.3 CFU/mL) and S. aureus (37.2 CFU/mL) in 20 min. The as-proposed platform provides valuable insights for bacterium discrimination and quantification.

PMID:38818541 | DOI:10.1021/acs.analchem.4c01314

Front Physiol. 2024 May 7;15:1331852. doi: 10.3389/fphys.2024.1331852. eCollection 2024.

ABSTRACT

Cardiac arrhythmias cause depolarization waves to conduct unevenly on the myocardial surface, potentially delaying local components with respect to a previous beat when stimulated at faster frequencies. Despite the diagnostic value of localizing the distinct local electrocardiogram (EGM) components for identifying regions with decrement-evoked potentials (DEEPs), current software solutions do not perform automatic signal quantification. Electrophysiologists must manually measure distances on the EGM signals to assess the existence of DEEPs during pacing or extra-stimuli protocols. In this work, we present a deep learning (DL)-based algorithm to identify decrement in atrial components (measured in the coronary sinus) with respect to their ventricular counterparts from EGM signals, for disambiguating between accessory pathways (APs) and atrioventricular re-entrant tachycardias (AVRTs). Several U-Net and W-Net neural networks with different configurations were trained on a private dataset of signals from the coronary sinus (312 EGM recordings from 77 patients who underwent AP or AVRT ablation). A second, separate dataset was annotated for clinical validation, with clinical labels associated to EGM fragments in which decremental conduction was elucidated. To alleviate data scarcity, a synthetic data augmentation method was developed for generating EGM recordings. Moreover, two novel loss functions were developed to minimize false negatives and delineation errors. Finally, the addition of self-attention mechanisms and their effect on model performance was explored. The best performing model was a W-Net model with 6 levels, optimized solely with the Dice loss. The model obtained precisions of 91.28%, 77.78% and of 100.0%, and recalls of 94.86%, 95.25% and 100.0% for localizing local field, far field activations, and extra-stimuli, respectively. The clinical validation model demonstrated good overall agreement with respect to the evaluation of decremental properties. When compared to the criteria of electrophysiologists, the automatic exclusion step reached a sensitivity of 87.06% and a specificity of 97.03%. Out of the non-excluded signals, a sensitivity of 96.77% and a specificity of 95.24% was obtained for classifying them into decremental and non-decremental potentials. Current results show great promise while being, to the best of our knowledge, the first tool in the literature allowing the delineation of all local components present in an EGM recording. This is of capital importance at advancing processing for cardiac electrophysiological procedures and reducing intervention times, as many diagnosis procedures are performed by comparing segments or late potentials in subsequent cardiac cycles.

PMID:38818521 | PMC:PMC11138951 | DOI:10.3389/fphys.2024.1331852

Heliyon. 2024 May 16;10(10):e31255. doi: 10.1016/j.heliyon.2024.e31255. eCollection 2024 May 30.

ABSTRACT

Urinary tract infection (UTI) is one of the most common infectious diseases among children, but there is controversy regarding the use of preventive antibiotics for children first diagnosed with febrile pyelonephritis. To the best of our knowledge, no studies have addressed this issue by the deep learning technology. Therefore, in the current study, we conducted a study using Tc99m-DMSA renal static imaging data to investigate the need for preventive antibiotics on children first diagnosed with febrile pyelonephritis under 2 years old. The self-collected dataset comprised 64 children who did not require preventive antibiotic treatments and 112 children who did. Using several classic deep learning models, we verified that it is feasible to screen whether the first diagnosed children with febrile pyelonephritis require preventive antibacterial therapy, achieving a graded diagnosis. With the AlexNet model, we obtained accuracy of 84.05%, sensitivity of 81.71% and specificity of 86.70%, respectively. The experimental results indicate that deep learning technology could provide a new avenue to implement computer-assisted decision support for the diagnosis of the febrile pyelonephritis.

PMID:38818202 | PMC:PMC11137416 | DOI:10.1016/j.heliyon.2024.e31255

Heliyon. 2024 May 18;10(10):e31485. doi: 10.1016/j.heliyon.2024.e31485. eCollection 2024 May 30.

ABSTRACT

Emotion recognition technology through EEG signal analysis is currently a fundamental concept in artificial intelligence. This recognition has major practical implications in emotional health care, human-computer interaction, and so on. This paper provides a comprehensive study of different methods for extracting electroencephalography (EEG) features for emotion recognition from four different perspectives, including time domain features, frequency domain features, time-frequency features, and nonlinear features. We summarize the current pattern recognition methods adopted in most related works, and with the rapid development of deep learning (DL) attracting the attention of researchers in this field, we pay more attention to deep learning-based studies and analyse the characteristics, advantages, disadvantages, and applicable scenarios. Finally, the current challenges and future development directions in this field were summarized. This paper can help novice researchers in this field gain a systematic understanding of the current status of emotion recognition research based on EEG signals and provide ideas for subsequent related research.

PMID:38818173 | PMC:PMC11137547 | DOI:10.1016/j.heliyon.2024.e31485

Heliyon. 2024 May 18;10(10):e31539. doi: 10.1016/j.heliyon.2024.e31539. eCollection 2024 May 30.

ABSTRACT

More accurate sun position estimation could transform the design and operation of solar power systems, weather forecasting services, and outdoor augmented reality systems. Although several image-based approaches to sun position estimation have been proposed, their performance is significantly affected by momentary disruptions in cloud cover because they use only a single image as input. This study proposes a deep learning-based sun position estimation system that leverages spatial, temporal, and geometric features to accurately regress sun positions even when the sun is partially or entirely occluded. In the proposed approach, spatial features are extracted from an input image sequence by applying a separate Resnet-based convolution network to each frame. To ensure that the temporal changes in the brightness distribution across frames are considered, the spatial features are concatenated and passed on to a stack of LSTM layers prior to regressing the final sun position. The proposed network is also trained with elliptical (geometric) constraints to ensure that predicted sun positions are consistent with the natural elliptical path of the sun in the sky. The proposed approach's performance was evaluated on the Sirta and Laval datasets along with a custom dataset, and an R2 Score of 0.98 was achieved, which is at least 0.1 higher than that of previous approaches. The proposed approach is capable of identifying the position of the sun even when occluded and was employed in a novel sky imaging system consisting of only a camera and fisheye lens in place of a complex array of sensors.

PMID:38818140 | PMC:PMC11137535 | DOI:10.1016/j.heliyon.2024.e31539

Comput Struct Biotechnol J. 2024 May 16;23:2122-2131. doi: 10.1016/j.csbj.2024.05.023. eCollection 2024 Dec.

ABSTRACT

B-cell epitope identification plays a vital role in the development of vaccines, therapies, and diagnostic tools. Currently, molecular docking tools in B-cell epitope prediction are heavily influenced by empirical parameters and require significant computational resources, rendering a great challenge to meet large-scale prediction demands. When predicting epitopes from antigen-antibody complex, current artificial intelligence algorithms cannot accurately implement the prediction due to insufficient protein feature representations, indicating novel algorithm is desperately needed for efficient protein information extraction. In this paper, we introduce a multimodal model called WUREN (Whole-modal Union Representation for Epitope predictioN), which effectively combines sequence, graph, and structural features. It achieved AUC-PR scores of 0.213 and 0.193 on the solved structures and AlphaFold-generated structures, respectively, for the independent test proteins selected from DiscoTope3 benchmark. Our findings indicate that WUREN is an efficient feature extraction model for protein complexes, with the generalizable application potential in the development of protein-based drugs. Moreover, the streamlined framework of WUREN could be readily extended to model similar biomolecules, such as nucleic acids, carbohydrates, and lipids.

PMID:38817963 | PMC:PMC11137340 | DOI:10.1016/j.csbj.2024.05.023

Plant Phenomics. 2024 May 30;6:0189. doi: 10.34133/plantphenomics.0189. eCollection 2024.

ABSTRACT

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

PMID:38817960 | PMC:PMC11136674 | DOI:10.34133/plantphenomics.0189

J Cancer. 2024 Apr 23;15(11):3350-3361. doi: 10.7150/jca.94759. eCollection 2024.

ABSTRACT

This study has used machine learning algorithms to develop a predictive model for differentiating between dermoscopic images of basal cell carcinoma (BCC) and actinic keratosis (AK). We compiled a total of 904 dermoscopic images from two sources - the public dataset (HAM10000) and our proprietary dataset from the First Affiliated Hospital of Dalian Medical University (DAYISET 1) - and subsequently categorised these images into four distinct cohorts. The study developed a deep learning model for quantitative analysis of image features and integrated 15 machine learning algorithms, generating 207 algorithmic combinations through random combinations and cross-validation. The final predictive model, formed by integrating XGBoost with Lasso regression, exhibited effective performance in the differential diagnosis of BCC and AK. The model demonstrated high sensitivity in the training set and maintained stable performance in three validation sets. The area under the curve (AUC) value reached 1.000 in the training set and an average of 0.695 in the validation sets. The study concludes that the constructed discriminative diagnostic model based on machine learning algorithms has excellent predictive capabilities that could enhance clinical decision-making efficiency, reduce unnecessary biopsies, and provide valuable guidance for further treatment.

PMID:38817855 | PMC:PMC11134443 | DOI:10.7150/jca.94759

Digit Health. 2024 May 28;10:20552076241258757. doi: 10.1177/20552076241258757. eCollection 2024 Jan-Dec.

ABSTRACT

The development of artificial intelligence (AI) has revolutionised the medical system, empowering healthcare professionals to analyse complex nonlinear big data and identify hidden patterns, facilitating well-informed decisions. Over the last decade, there has been a notable trend of research in AI, machine learning (ML), and their associated algorithms in health and medical systems. These approaches have transformed the healthcare system, enhancing efficiency, accuracy, personalised treatment, and decision-making. Recognising the importance and growing trend of research in the topic area, this paper presents a bibliometric analysis of AI in health and medical systems. The paper utilises the Web of Science (WoS) Core Collection database, considering documents published in the topic area for the last four decades. A total of 64,063 papers were identified from 1983 to 2022. The paper evaluates the bibliometric data from various perspectives, such as annual papers published, annual citations, highly cited papers, and most productive institutions, and countries. The paper visualises the relationship among various scientific actors by presenting bibliographic coupling and co-occurrences of the author's keywords. The analysis indicates that the field began its significant growth in the late 1970s and early 1980s, with significant growth since 2019. The most influential institutions are in the USA and China. The study also reveals that the scientific community's top keywords include 'ML', 'Deep Learning', and 'Artificial Intelligence'.

PMID:38817839 | PMC:PMC11138196 | DOI:10.1177/20552076241258757

J Med Imaging (Bellingham). 2024 May;11(3):034502. doi: 10.1117/1.JMI.11.3.034502. Epub 2024 May 29.

ABSTRACT

PURPOSE: Evaluation of lung fissure integrity is required to determine whether emphysema patients have complete fissures and are candidates for endobronchial valve (EBV) therapy. We propose a deep learning (DL) approach to segment fissures using a three-dimensional patch-based convolutional neural network (CNN) and quantitatively assess fissure integrity on CT to evaluate it in subjects with severe emphysema.

APPROACH: From an anonymized image database of patients with severe emphysema, 129 CT scans were used. Lung lobe segmentations were performed to identify lobar regions, and the boundaries among these regions were used to construct approximate interlobar regions of interest (ROIs). The interlobar ROIs were annotated by expert image analysts to identify voxels where the fissure was present and create a reference ROI that excluded non-fissure voxels (where the fissure is incomplete). A CNN configured by nnU-Net was trained using 86 CT scans and their corresponding reference ROIs to segment the ROIs of left oblique fissure (LOF), right oblique fissure (ROF), and right horizontal fissure (RHF). For an independent test set of 43 cases, fissure integrity was quantified by mapping the segmented fissure ROI along the interlobar ROI. A fissure integrity score (FIS) was then calculated as the percentage of labeled fissure voxels divided by total voxels in the interlobar ROI. Predicted FIS (p-FIS) was quantified from the CNN output, and statistical analyses were performed comparing p-FIS and reference FIS (r-FIS).

RESULTS: The absolute percent error mean (±SD) between r-FIS and p-FIS for the test set was 4.0% (±4.1%), 6.0% (±9.3%), and 12.2% (±12.5%) for the LOF, ROF, and RHF, respectively.

CONCLUSIONS: A DL approach was developed to segment lung fissures on CT images and accurately quantify FIS. It has potential to assist in the identification of emphysema patients who would benefit from EBV treatment.

PMID:38817711 | PMC:PMC11135203 | DOI:10.1117/1.JMI.11.3.034502

J Neurol. 2024 May 31. doi: 10.1007/s00415-024-12354-9. Online ahead of print.

ABSTRACT

Essential tremor (ET) stands as the most prevalent movement disorder, characterized by rhythmic and involuntary shaking of body parts. Achieving an accurate and comprehensive assessment of tremor severity is crucial for effectively diagnosing and managing ET. Traditional methods rely on clinical observation and rating scales, which may introduce subjective biases and hinder continuous evaluation of disease progression. Recent research has explored new approaches to quantifying ET. A promising method involves the use of intelligent devices to facilitate objective and quantitative measurements. These devices include inertial measurement units, electromyography, video equipment, and electronic handwriting boards, and more. Their deployment enables real-time monitoring of human activity data, featuring portability and efficiency. This capability allows for more extensive research in this field and supports the shift from in-lab/clinic to in-home monitoring of ET symptoms. Therefore, this review provides an in-depth analysis of the application, current development, potential characteristics, and roles of intelligent devices in assessing ET.

PMID:38816480 | DOI:10.1007/s00415-024-12354-9

Sci Rep. 2024 May 30;14(1):12468. doi: 10.1038/s41598-024-61557-7.

ABSTRACT

Post-traumatic stress disorder (PTSD) lacks clear biomarkers in clinical practice. Language as a potential diagnostic biomarker for PTSD is investigated in this study. We analyze an original cohort of 148 individuals exposed to the November 13, 2015, terrorist attacks in Paris. The interviews, conducted 5-11 months after the event, include individuals from similar socioeconomic backgrounds exposed to the same incident, responding to identical questions and using uniform PTSD measures. Using this dataset to collect nuanced insights that might be clinically relevant, we propose a three-step interdisciplinary methodology that integrates expertise from psychiatry, linguistics, and the Natural Language Processing (NLP) community to examine the relationship between language and PTSD. The first step assesses a clinical psychiatrist's ability to diagnose PTSD using interview transcription alone. The second step uses statistical analysis and machine learning models to create language features based on psycholinguistic hypotheses and evaluate their predictive strength. The third step is the application of a hypothesis-free deep learning approach to the classification of PTSD in our cohort. Results show that the clinical psychiatrist achieved a diagnosis of PTSD with an AUC of 0.72. This is comparable to a gold standard questionnaire (Area Under Curve (AUC) ≈ 0.80). The machine learning model achieved a diagnostic AUC of 0.69. The deep learning approach achieved an AUC of 0.64. An examination of model error informs our discussion. Importantly, the study controls for confounding factors, establishes associations between language and DSM-5 subsymptoms, and integrates automated methods with qualitative analysis. This study provides a direct and methodologically robust description of the relationship between PTSD and language. Our work lays the groundwork for advancing early and accurate diagnosis and using linguistic markers to assess the effectiveness of pharmacological treatments and psychotherapies.

PMID:38816468 | DOI:10.1038/s41598-024-61557-7

BMJ Health Care Inform. 2024 May 30;31(1):e100971. doi: 10.1136/bmjhci-2023-100971.

ABSTRACT

Computerised decision support (CDS) tools enabled by artificial intelligence (AI) seek to enhance accuracy and efficiency of clinician decision-making at the point of care. Statistical models developed using machine learning (ML) underpin most current tools. However, despite thousands of models and hundreds of regulator-approved tools internationally, large-scale uptake into routine clinical practice has proved elusive. While underdeveloped system readiness and investment in AI/ML within Australia and perhaps other countries are impediments, clinician ambivalence towards adopting these tools at scale could be a major inhibitor. We propose a set of principles and several strategic enablers for obtaining broad clinician acceptance of AI/ML-enabled CDS tools.

PMID:38816209 | DOI:10.1136/bmjhci-2023-100971

Magn Reson Imaging. 2024 May 28:S0730-725X(24)00162-0. doi: 10.1016/j.mri.2024.05.012. Online ahead of print.

ABSTRACT

OBJECTIVES: To evaluate the performance of the multimodal model, termed variable Vision Transformer (vViT), in the task of predicting isocitrate dehydrogenase (IDH) status among adult patients with diffuse glioma.

MATERIALS AND METHODS: vViT was designed to predict IDH status using patient characteristics (sex and age), radiomic features, and contrast-enhanced T1-weighted images (CE-T1WI). Radiomic features were extracted from each enhancing tumor (ET), necrotic tumor core (NCR), and peritumoral edematous/infiltrated tissue (ED). CE-T1WI were split into four images and input to vViT. In the training, internal test, and external test, 271 patients with 1070 images (535 IDH wildtype, 535 IDH mutant), 35 patients with 194 images (97 IDH wildtype, 97 IDH mutant), and 291 patients with 872 images (436 IDH wildtype, 436 IDH mutant) were analyzed, respectively. Metrics including accuracy and AUC-ROC were calculated for the internal and external test datasets. Permutation importance analysis combined with the Mann-Whitney U test was performed to compare inputs.

RESULTS: For the internal test dataset, vViT correctly predicted IDH status for all patients. For the external test dataset, an accuracy of 0.935 (95% confidence interval; 0.913-0.945) and AUC-ROC of 0.887 (0.798-0.956) were obtained. For both internal and external test datasets, CE-T1WI ET radiomic features and patient characteristics had higher importance than other inputs (p < 0.05).

CONCLUSIONS: The vViT has the potential to be a competent model in predicting IDH status among adult patients with diffuse glioma. Our results indicate that age, sex, and CE-T1WI ET radiomic features have key information in estimating IDH status.

PMID:38815636 | DOI:10.1016/j.mri.2024.05.012