RESUMEN

Significance: Advancements in label-free microscopy could provide real-time, non-invasive imaging with unique sources of contrast and automated standardized analysis to characterize heterogeneous and dynamic biological processes. These tools would overcome challenges with widely used methods that are destructive (e.g., histology, flow cytometry) or lack cellular resolution (e.g., plate-based assays, whole animal bioluminescence imaging). Aim: This perspective aims to (1) justify the need for label-free microscopy to track heterogeneous cellular functions over time and space within unperturbed systems and (2) recommend improvements regarding instrumentation, image analysis, and image interpretation to address these needs. Approach: Three key research areas (cancer research, autoimmune disease, and tissue and cell engineering) are considered to support the need for label-free microscopy to characterize heterogeneity and dynamics within biological systems. Based on the strengths (e.g., multiple sources of molecular contrast, non-invasive monitoring) and weaknesses (e.g., imaging depth, image interpretation) of several label-free microscopy modalities, improvements for future imaging systems are recommended. Conclusion: Improvements in instrumentation including strategies that increase resolution and imaging speed, standardization and centralization of image analysis tools, and robust data validation and interpretation will expand the applications of label-free microscopy to study heterogeneous and dynamic biological systems.

Asunto(s)

RESUMEN

OpenPose-based motion analysis (OpenPose-MA), utilizing deep learning methods, has emerged as a compelling technique for estimating human motion. It addresses the drawbacks associated with conventional three-dimensional motion analysis (3D-MA) and human visual detection-based motion analysis (Human-MA), including costly equipment, time-consuming analysis, and restricted experimental settings. This study aims to assess the precision of OpenPose-MA in comparison to Human-MA, using 3D-MA as the reference standard. The study involved a cohort of 21 young and healthy adults. OpenPose-MA employed the OpenPose algorithm, a deep learning-based open-source two-dimensional (2D) pose estimation method. Human-MA was conducted by a skilled physiotherapist. The knee valgus angle during a drop vertical jump task was computed by OpenPose-MA and Human-MA using the same frontal-plane video image, with 3D-MA serving as the reference standard. Various metrics were utilized to assess the reproducibility, accuracy and similarity of the knee valgus angle between the different methods, including the intraclass correlation coefficient (ICC) (1, 3), mean absolute error (MAE), coefficient of multiple correlation (CMC) for waveform pattern similarity, and Pearson's correlation coefficients (OpenPose-MA vs. 3D-MA, Human-MA vs. 3D-MA). Unpaired t-tests were conducted to compare MAEs and CMCs between OpenPose-MA and Human-MA. The ICCs (1,3) for OpenPose-MA, Human-MA, and 3D-MA demonstrated excellent reproducibility in the DVJ trial. No significant difference between OpenPose-MA and Human-MA was observed in terms of the MAEs (OpenPose: 2.4° [95%CI: 1.9-3.0°], Human: 3.2° [95%CI: 2.1-4.4°]) or CMCs (OpenPose: 0.83 [range: 0.99-0.53], Human: 0.87 [range: 0.24-0.98]) of knee valgus angles. The Pearson's correlation coefficients of OpenPose-MA and Human-MA relative to that of 3D-MA were 0.97 and 0.98, respectively. This study demonstrated that OpenPose-MA achieved satisfactory reproducibility, accuracy and exhibited waveform similarity comparable to 3D-MA, similar to Human-MA. Both OpenPose-MA and Human-MA showed a strong correlation with 3D-MA in terms of knee valgus angle excursion.

Asunto(s)

RESUMEN

Background: Understanding interactions between multiple risk factors for shoulder and elbow injuries in Major League Baseball (MLB) pitchers is important to identify potential avenues by which risk can be reduced while minimizing impact on player performance. Purpose: To apply a novel game theory-based approach to develop a machine-learning model predictive of next-season shoulder and elbow injuries in MLB pitchers and use this model to understand interdependencies and interaction effects between the most important risk factors. Study Design: Case-control study; Level of evidence, 3. Methods: Pitcher demographics, workload measures, pitch-tracking metrics, and injury data between 2017 and 2022 were used to construct a database of MLB pitcher-years, where each item in the database corresponded to a pitcher's information and metrics for that year. An extreme gradient boosting machine-learning model was trained to predict next-season shoulder and elbow injuries utilizing Shapley additive explanation values to quantify feature importance as well as interdependencies and interaction effects between predictive variables. Results: A total of 3808 pitcher-years were included in this analysis; 606 (15.9%) of these involved a shoulder or elbow injury resulting in placement on the MLB injured list. Of the >65 candidate features (including workload, demographic, and pitch-tracking metrics), the most important contributors to predicting shoulder/elbow injury were increased: pitch velocity (all pitch types), utilization of sliders (SLs), fastball (FB) spin rate, FB horizontal movement, and player age. The strongest game theory interaction effects were that higher FB velocity did not alter a younger pitcher's predicted risk of shoulder/elbow injury versus older pitchers, risk of shoulder/elbow injury increased with the number of high-velocity pitches thrown (regardless of pitch type and in an additive fashion), and FB velocity <95 mph (<152.9 kph) demonstrated strong negative interaction effects with higher SL percentage, suggesting that the overall predicted risk of injury for pitchers throwing a high number of SLs could be attenuated by lower FB velocity. Conclusion: Pitch-tracking metrics were substantially more predictive of future injury than player demographics and workload metrics. There were many significant game theory interdependencies of injury risk. Notably, the increased risk of injury that was conferred by throwing with a high velocity was even further magnified if the pitchers were also older, threw a high percentage of SLs, and/or threw a greater number of pitches.

RESUMEN

Background: Imagination represents a pivotal capability of human intelligence. To develop human-like artificial intelligence, uncovering the computational architecture pertinent to imaginative capabilities through reverse engineering the brain's computational functions is essential. The existing Structure-Constrained Interface Decomposition (SCID) method, leverages the anatomical structure of the brain to extract computational architecture. However, its efficacy is limited to narrow brain regions, making it unsuitable for realizing the function of imagination, which involves diverse brain areas such as the neocortex, basal ganglia, thalamus, and hippocampus. Objective: In this study, we proposed the Function-Oriented SCID method, an advancement over the existing SCID method, comprising four steps designed for reverse engineering broader brain areas. This method was applied to the brain's imaginative capabilities to design a hypothetical computational architecture. The implementation began with defining the human imaginative ability that we aspire to simulate. Subsequently, six critical requirements necessary for actualizing the defined imagination were identified. Constraints were established considering the unique representational capacity and the singularity of the neocortex's modes, a distributed memory structure responsible for executing imaginative functions. In line with these constraints, we developed five distinct functions to fulfill the requirements. We allocated specific components for each function, followed by an architectural proposal aligning each component with a corresponding brain organ. Results: In the proposed architecture, the distributed memory component, associated with the neocortex, realizes the representation and execution function; the imaginary zone maker component, associated with the claustrum, accomplishes the dynamic-zone partitioning function; the routing conductor component, linked with the complex of thalamus and basal ganglia, performs the manipulation function; the mode memory component, related to the specific agranular neocortical area executes the mode maintenance function; and the recorder component, affiliated with the hippocampal formation, handles the history management function. Thus, we have provided a fundamental cognitive architecture of the brain that comprehensively covers the brain's imaginative capacities.

RESUMEN

High-resolution computed tomography (HRCT) is important for diagnosing interstitial lung disease (ILD) in inflammatory rheumatic disease (IRD) patients. However, visual ILD assessment via HRCT often has high inter-reader variability. Artificial intelligence (AI)-based techniques for quantitative image analysis promise more accurate diagnostic and prognostic information. This study evaluated the reliability of artificial intelligence-based quantification of pulmonary HRCT (AIqpHRCT) in IRD-ILD patients and verified IRD-ILD quantification using AIqpHRCT in the clinical setting. Reproducibility of AIqpHRCT was verified for each typical HRCT pattern (ground-glass opacity [GGO], non-specific interstitial pneumonia [NSIP], usual interstitial pneumonia [UIP], granuloma). Additional, 50 HRCT datasets from 50 IRD-ILD patients using AIqpHRCT were analysed and correlated with clinical data and pulmonary lung function parameters. AIqpHRCT presented 100% agreement (coefficient of variation = 0.00%, intraclass correlation coefficient = 1.000) regarding the detection of the different HRCT pattern. Furthermore, AIqpHRCT data showed an increase of ILD from 10.7 ± 28.3% (median = 1.3%) in GGO to 18.9 ± 12.4% (median = 18.0%) in UIP pattern. The extent of fibrosis negatively correlated with FVC (ρ=-0.501), TLC (ρ=-0.622), and DLCO (ρ=-0.693) (p < 0.001). GGO measured by AIqpHRCT also significant negatively correlated with DLCO (ρ=-0.699), TLC (ρ=-0.580) and FVC (ρ=-0.423). For the first time, the study demonstrates that AIpqHRCT provides a highly reliable method for quantifying lung parenchymal changes in HRCT images of IRD-ILD patients. Further, the AIqpHRCT method revealed significant correlations between the extent of ILD and lung function parameters. This highlights the potential of AIpqHRCT in enhancing the accuracy of ILD diagnosis and prognosis in clinical settings, ultimately improving patient management and outcomes.

RESUMEN

OBJECTIVE: To develop a deep learning algorithm for diagnosing lumbar central canal stenosis (LCCS) using abdominal CT (ACT) and lumbar spine CT (LCT). MATERIALS AND METHODS: This retrospective study involved 109 patients undergoing LCTs and ACTs between January 2014 and July 2021. The dural sac on CT images was manually segmented and classified as normal or stenosed (dural sac cross-sectional area ≥ 100 mm2 or < 100 mm2, respectively). A deep learning model based on U-Net architecture was developed to automatically segment the dural sac and classify the central canal stenosis. The classification performance of the model was compared on a testing set (990 images from 9 patients). The accuracy, sensitivity, and specificity of automatic segmentation were quantitatively evaluated by comparing its Dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC) with those of manual segmentation. RESULTS: In total, 990 CT images from nine patients (mean age ± standard deviation, 77 ± 7 years; six men) were evaluated. The algorithm achieved high segmentation performance with a DSC of 0.85 ± 0.10 and ICC of 0.82 (95% confidence interval [CI]: 0.80,0.85). The ICC between ACTs and LCTs on the deep learning algorithm was 0.89 (95%CI: 0.87,0.91). The accuracy of the algorithm in diagnosing LCCS with dichotomous classification was 84%(95%CI: 0.82,0.86). In dataset analysis, the accuracy of ACTs and LCTs was 85%(95%CI: 0.82,0.88) and 83%(95%CI: 0.79,0.86), respectively. The model showed better accuracy for ACT than LCT. CONCLUSION: The deep learning algorithm automatically diagnosed LCCS on LCTs and ACTs. ACT had a diagnostic performance for LCCS comparable to that of LCT.

RESUMEN

This paper presents the design and development of a coastal fisheries monitoring system that harnesses artificial intelligence technologies. Application of the system across the Pacific region promises to revolutionize coastal fisheries management. The program is built on a centralized, cloud-based monitoring system to automate data extraction and analysis processes. The system leverages YoloV4, OpenCV, and ResNet101 to extract information from images of fish and invertebrates collected as part of in-country monitoring programs overseen by national fisheries authorities. As of December 2023, the system has facilitated automated identification of over six hundred nearshore finfish species, and automated length and weight measurements of more than 80,000 specimens across the Pacific. The system integrates other key fisheries monitoring data such as catch rates, fishing locations and habitats, volumes, pricing, and market characteristics. The collection of these metrics supports much needed rapid fishery assessments. The system's co-development with national fisheries authorities and the geographic extent of its application enables capacity development and broader local inclusion of fishing communities in fisheries management. In doing so, the system empowers fishers to work with fisheries authorities to enable data-informed decision-making for more effective adaptive fisheries management. The system overcomes historically entrenched technical and financial barriers in fisheries management in many Pacific island communities.

Asunto(s)

RESUMEN

BACKGROUND: During the coronavirus disease of 2019 (COVID-19) pandemic, in-person interviews for the recruitment of family medicine residents shifted to online (virtual) interviews. The purpose of this study was twofold: (1) to gather the ideas about virtual interviews of family medicine applicants (interviewees), and faculty and staff who interviewed these applicants (interviewers), and (2) to describe interviewers' and interviewees' opinions of use of emerging technologies such as artificial intelligence (AI) and virtual reality (VR) in the recruitment process as well as during clinical practice. METHODS: This was a cross-sectional survey study. Participants were both interviewers and candidates who applied to the McGill University Family Medicine Residency Program for the 2020-2021 and 2021-2022 cycles. RESULTS: The study population was constituted by N = 132 applicants and N = 60 interviewers. The response rate was 91.7% (55/60) for interviewers and 43.2% (57/132) for interviewees. Both interviewers (43.7%) and interviewees (68.5%) were satisfied with connecting through virtual interviews. Interviewers (43.75%) and interviewees (55.5%) would prefer for both options to be available. Both interviewers (50%) and interviewees (72%) were interested in emerging technologies. Almost all interviewees (95.8%) were interested in learning about AI and VR and its application in clinical practice with the majority (60.8%) agreeing that it should be taught within medical training. CONCLUSION: Although experience of virtual interviewing during the COVID-19 pandemic has been positive for both interviewees and interviewers, the findings of this study suggest that it will be unlikely that virtual interviews completely replace in-person interviews for selecting candidates for family medicine residency programs in the long term as participants value aspects of in-person interviews and would want a choice in format. Since incoming family medicine physicians seem to be eager to learn and utilize emerging technologies such as AI and VR, educators and institutions should consider family physicians' needs due to the changing technological landscape in family medicine education.

Asunto(s)

RESUMEN

BACKGROUND: AI medical image analysis shows potential applications in research on premature aging and skin. The purpose of this study was to explore the mechanism of the Zuogui pill based on artificial intelligence medical image analysis on ovarian function enhancement and skin elasticity repair in rats with premature aging. MATERIALS AND METHODS: The premature aging rat model was established by using an experimental animal model. Then Zuogui pills were injected into the rats with premature aging, and the images were detected by an optical microscope. Then, through the analysis of artificial intelligence medical images, the image data is analyzed to evaluate the indicators of ovarian function. RESULTS: Through optical microscope image detection, we observed that the Zuogui pill played an active role in repairing ovarian tissue structure and increasing the number of follicles in mice, and Zuogui pill also significantly increased the level of progesterone in the blood of mice. CONCLUSION: Most of the ZGP-induced outcomes are significantly dose-dependent.

Asunto(s)

RESUMEN

Net radiation (Rn), a critical component in land surface energy cycling, is calculated as the difference between net shortwave radiation and longwave radiation at the Earth's surface and holds significant importance in crop models for precision agriculture management. In this study, we examined the performance of four machine learning models, including extreme learning machine (ELM), hybrid artificial neural networks with genetic algorithm models (GANN), generalized regression neural networks (GRNN), and random forests (RF), in estimating daily Rn at four representative sites across different climatic zones of China. The input variables included common meteorological factors such as minimum and maximum temperature, relative humidity, sunshine duration, and shortwave solar radiation. Model performance was assessed and compared using statistical parameters such as the correlation coefficient (R2), root mean square errors (RMSE), mean absolute errors (MAE), and Nash-Sutcliffe coefficient (NS). The results indicated that all models slightly underestimated actual Rn, with linear regression slopes ranging from 0.810 to 0.870 across different zones. The estimated Rn was found to be comparable to observed values in terms of data distribution characteristics. Among the models, the ELM and GANN demonstrated higher consistency with observed values, exhibiting R2 values ranging from 0.838 to 0.963 and 0.836 to 0.963, respectively, across varying climatic zones. These values surpassed those of the RF (0.809-0.959) and GRNN (0.812-0.949) models. Additionally, the ELM and GANN models showed smaller simulation errors in terms of RMSE, MAE, and NS across the four climatic zones compared to the RF and GRNN models. Overall, the ELM and GANN models outperformed the RF and GRNN models. Notably, the ELM model's faster computational speed makes it a strong recommendation for Rn estimates across different climatic zones of China.

RESUMEN

The programmed cell death protein 1 (PD-1, CD279) is an important therapeutic target in many oncological diseases. This checkpoint protein inhibits T lymphocytes from attacking other cells in the body and thus blocking it improves the clearance of tumor cells by the immune system. While there are already multiple FDA-approved anti-PD-1 antibodies, including nivolumab (Opdivo® from Bristol-Myers Squibb) and pembrolizumab (Keytruda® from Merck), there are ongoing efforts to discover new and improved checkpoint inhibitor therapeutics. In this study, we present multiple anti-PD-1 antibody fragments that were derived computationally using protein diffusion and evaluated through our scalable, in silico pipeline. Here we present nine synthetic Fv structures that are suitable for further empirical testing of their anti-PD-1 activity due to desirable predicted binding performance.

Asunto(s)

RESUMEN

This study aims to discuss the principles and pillars of robotic colorectal surgery training and share the training pathway at Portsmouth Hospitals University NHS Trust. A narrative review is presented to discuss all the relevant and critical steps in robotic surgical training. Robotic training requires a stepwise approach, including theoretical knowledge, case observation, simulation, dry lab, wet lab, tutored programs, proctoring (in person or telementoring), procedure-specific training, and follow-up. Portsmouth Colorectal has an established robotic training model with a safe stepwise approach that has been demonstrated through perioperative and oncological results. Robotic surgery training should enable a trainee to use the robotic platform safely and effectively, minimize errors, and enhance performance with improved outcomes. Portsmouth Colorectal has provided such a stepwise training program since 2015 and continues to promote and augment safe robotic training in its field. Safe and efficient training programs are essential to upholding the optimal standard of care.

RESUMEN

Inspired by advancements in natural language processing, we utilize self-supervised learning and an equivariant graph neural network to develop a unified platform for training generative models capable of generating inorganic crystal structures, as well as efficiently adapting to downstream tasks in material property prediction. To mitigate the challenge of evaluating the reliability of generated structures during training, we employ a generative adversarial network (GAN) with its discriminator being a cost-effective reliability evaluator, significantly enhancing model performance. We demonstrate the utility of our model in optimizing crystal structures under predefined conditions. Without external properties acquired experimentally or numerically, our model further displays its capability to help understand inorganic crystal formation by grouping chemically similar elements. This paper extends an invitation to further explore the scientific understanding of material structures through generative models, offering a fresh perspective on the scope and efficacy of machine learning in material science.

RESUMEN

Colorectal adenomas (CRAs) are potential precursor lesions to adenocarcinomas, currently classified by morphological features. We aimed to establish a molecular feature-based risk allocation framework toward improved patient stratification. Deep visual proteomics (DVP) is an approach that combines image-based artificial intelligence with automated microdissection and ultra-high sensitive mass spectrometry. Here, we used DVP on formalin-fixed, paraffin-embedded (FFPE) CRA tissues from nine male patients, immunohistologically stained for caudal-type homeobox 2 (CDX2), a protein implicated in colorectal cancer, enabling the characterization of cellular heterogeneity within distinct tissue regions and across patients. DVP identified DMBT1, MARCKS, and CD99 as protein markers linked to recurrence, suggesting their potential for risk assessment. It also detected a metabolic shift to anaerobic glycolysis in cells with high CDX2 expression. Our findings underscore the potential of spatial proteomics to refine early stage detection and contribute to personalized patient management strategies and provided novel insights into metabolic reprogramming.

RESUMEN

Background: Indocyanine green fluorescence angiography (ICGFA) is gaining popularity as an intraoperative tool to assess flap perfusion. However, it needs interpretation and there is concern regarding a potential for over-debridement with its use. Here we describe an artificial intelligence (AI) method that indicates the extent of flap trimming required. Methods: Operative ICGFA recordings from ten consenting patients undergoing flap reconstruction without subsequent partial/total necrosis as part of an approved prospective study (NCT04220242, Institutional Review Board Ref:1/378/2092), provided the training-testing datasets. Drawing from prior similar experience with ICGFA intestinal perfusion signal analysis, five fluorescence intensity and time-related features were analysed (MATLAB R2024a) from stabilised ICGFA imagery. Machine learning model training (with ten-fold cross-validation application) was grounded on the actual trimming by a consultant plastic surgeon (S.P.) experienced in ICGFA. MATLAB classification learner app was used to identify the most important feature and generate partial dependence plots for interpretability during training. Testing involved post-hoc application to unseen videos blinded to surgeon ICGFA interpretation. Results: Training:testing datasets comprised 7:3 ICGFA videos with 28 and 3 sampled lines respectively. Validation and testing accuracy were 99.9 % and 99.3 % respectively. Maximum fluorescence intensity identified as the most important predictive curve feature. Partial dependence plotting revealed a threshold of 22.1 grayscale units and regions with maximum intensity less then threshold being more likely to be predicted as "excise". Conclusion: The AI method proved discriminative regarding indicating whether to retain or excise peripheral flap portions. Additional prospective patients and expert references are needed to validate generalisability.

RESUMEN

Background and Aims: The utilization of artificial intelligence (AI) with computer-aided detection (CADe) has the potential to increase the adenoma detection rate (ADR) by up to 30% in expert settings and specialized centers. The impact of CADe on serrated polyp detection rates (SDR) and academic trainees ADR & SDR remains underexplored. We aim to investigate the effect of CADe on ADR and SDR at an academic center with various levels of providers' experience. Methods: A single-center retrospective analysis was conducted on asymptomatic patients between the ages of 45 and 75 who underwent screening colonoscopy. Colonoscopy reports were reviewed for 3 months prior to the introduction of GI Genius™ (Medtronic, USA) and 3 months after its implementation. The primary outcome was ADR and SDR with and without CADe. Results: Totally 658 colonoscopies were eligible for analysis. CADe resulted in statistically significant improvement in SDR from 8.92% to 14.1% (P = 0.037). The (ADR + SDR) with CADe and without CADe was 58% and 55.1%, respectively (P = 0.46). Average colonoscopy (CSC) withdrawal time was 17.33 min (SD 10) with the device compared with 17.35 min (SD 9) without the device (P = 0.98). Conclusion: In this study, GI Genius™ was associated with a statistically significant increase in SDR alone, but not in ADR or (ADR + SDR), likely secondary to the more elusive nature of serrated polyps compared to adenomatous polyps. The use of CADe did not affect withdrawal time.

RESUMEN

The recent advances in machine learning and deep learning algorithms, along with the advent of generative AI, have led AI to become the "new normal" in organizations. This trend has extended to CRM, resulting in the development of AI-enabled CRM systems, or AI-CRM. Despite the growing adoption of AI as part of competitive strategies, many firms report minimal or no positive effect of AI on performance. This study addresses the research questions: "What are the critical features of AI-CRM systems?" and "How do these features impact organizational competitive advantage?" To explore this, we aim to identify key characteristics of AI-CRM and assess their impact on organizational performance. In Study 1, we utilize BERTopic topic modeling to extract critical features of AI-CRM from user reviews. Study 2 employs PLS-SEM to examine how these features influence organizational competitive advantage. Study 1 reveals four main characteristics of AI-CRM (general, marketing, sales, and service/support), each comprising distinct features. Study 2 shows that these characteristics differentially impact CRM capability, significantly affecting performance and competitive advantage. The findings offer valuable insights for both theory and practice regarding the effective use of AI in organizations.

Asunto(s)

RESUMEN

Background: Large vision models (LVM) pretrained by large datasets have demonstrated their enormous capacity to understand visual patterns and capture semantic information from images. We proposed a novel method of knowledge domain adaptation with pretrained LVM for a low-cost artificial intelligence (AI) model to quantify the severity of SARS-CoV-2 pneumonia based on frontal chest X-ray (CXR) images. Methods: Our method used the pretrained LVMs as the primary feature extractor and self-supervised contrastive learning for domain adaptation. An encoder with a 2048-dimensional feature vector output was first trained by self-supervised learning for knowledge domain adaptation. Then a multi-layer perceptron (MLP) was trained for the final severity prediction. A dataset with 2599 CXR images was used for model training and evaluation. Results: The model based on the pretrained vision transformer (ViT) and self-supervised learning achieved the best performance in cross validation, with mean squared error (MSE) of 23.83 (95 % CI 22.67-25.00) and mean absolute error (MAE) of 3.64 (95 % CI 3.54-3.73). Its prediction correlation has the R 2 of 0.81 (95 % CI 0.79-0.82) and Spearman ρ of 0.80 (95 % CI 0.77-0.81), which are comparable to the current state-of-the-art (SOTA) methods trained by much larger CXR datasets. Conclusion: The proposed new method has achieved the SOTA performance to quantify the severity of SARS-CoV-2 pneumonia at a significantly lower cost. The method can be extended to other infectious disease detection or quantification to expedite the application of AI in medical research.

RESUMEN

In this paper, we present a comprehensive guide for implementing artificial intelligence (AI) techniques in traditional East Asian medicine (TEAM) research. We cover essential aspects of the AI model development pipeline, including research objective establishment, data collection and preprocessing, model selection, evaluation, and interpretation. The unique considerations in applying AI to TEAM datasets, such as data scarcity, imbalance, and model interpretability, are discussed. We provide practical tips and recommendations based on best practices and our own experience. The potential of large language models in TEAM research is also highlighted. Finally, we discuss the challenges and future directions of AI application in TEAM, emphasizing the need for standardized data collection and sharing platforms.