Model Of Stage Research Articles

All Together and Separately: Learning to Learn in the Studio

AbstractThis study aims to develop learning to learn and self‐learning in the architectural design studio. The study considers that one of the ways in which the architectural design studio can be resistant to environmental conditions is to be aware of and manage the way the architecture student learns. The main theme of the methodological approach is learning how to learn, and its experients are first‐year architecture students. The method consists of design research and a questionnaire. Design research is configured as a two‐stage pedagogical approach: The first phase consists of an abstraction practice and results in a physical model. The second stage includes a single‐function small‐scale design task and imposes the use of design knowledge obtained from the physical model in the first stage as a mandatory condition. The study concluded in three basic positions: The first is that the first‐grade architecture student establishes the relationality of comprehending–understanding–making sense of self‐learning and learning mode. Second, the student has become a direct active learner, and finally, a way of making use of the built environment as an educational object has been discovered. Broadly, the study has enabled the students to become aware of self‐learning. Improving such a learning culture in architectural education can provide a way to prepare for an uncertain future.

New subgenera of Ellipteroides Becker (Tipuloidea: Limoniidae) and their phylogenetic implications

A new subgenus of Ellipteroides—Jantares subgen. nov.—is reported from Eocene Baltic amber with one new species Ellipteroides (Jantares) hansi sp. nov. This new subgenus is easily distinguishable from the other subgenera by a male terminalia with interbases very long, a simplified gonostylus, wing venation by the combination of a closed discal cell and m-cu placed at Mb. After numerous comparisons of the morphological characteristics of subgenera of the genus Ellipteroides, we defined this species in a new subgenus. The newly described species herein is the second evidence on the occurrence of Ellipteroides in the fossil record. The new discovery adds to the knowledge of the crane flies’ history evolution, especially its Eocene stage and new view on phylogeny within the genus Ellipteroides. A phylogenetic analysis was carried out and we propose a new classification within the genus Ellipteroides. This system adds a new subgenera E. (Afroellipteroides) subgen. nov., E. (Iberiopteroides) subgen. nov., E. (Photogonomyia) subgen. nov., and new combinations intendent to correct morphological inconsistencies in the current taxonomy of the group. The results of the analysis are important for understanding phylogenetic relationships within the genus, but also for determining the model of various stages of evolution of Limoniidae using the fossil records of the family.

Prediction of relapse-free survival in stage III gastric cancer patients treated with postoperative adjuvant chemotherapy: Random survival forest analysis from the START-2 trial.

446 Background: The START-2 trial demonstrated that docetaxel plus S-1 (DS) was superior to S-1 alone (S-1) in terms of recurrence-free survival (RFS) and overall survival (OS) as the adjuvant chemotherapy for stage III gastric cancer (GC) patients (pts) (J Clin Oncol 2019, Gastric Cancer 2022). We conducted the START-2 AR study as a retrospective analysis using data from the START-2 trial to develop a prognostic model for stage III GC pts treated with postoperative chemotherapy. Methods: Among 912 pts in the START-2 trial, 599 pts signed the consent form to participate in the START-2 AR study. There were 542 pts (265 pts in DS group and 277 pts in S-1 group) without missing values of prognostic candidates. Pts were randomly divided into a training set and a validation set with a ratio of 7:3. Prognostic model for RFS was developed using random survival forest (RSF) with the training set. The RSF model was applied to the validation set to assess its performance, evaluated using Harrell's C-index. We calculated tertiles of risk scores from the RSF model to divide the training set into low-, middle-, and high-risk subgroups. These cut-off values were used to classify the validation set. A Cox proportional hazard model was applied to compare the prognosis among the risk groups. Results: There were no statistically significant differences in patient characteristicsbetween the 599 pts in the START-2 AR study and the 912 pts in the STRAT-2 trial. RFS was comparable between the two groups. The RSF model for the training set (n = 380) yielded a C-index of 0.873, identifying the number of metastatic lymph nodes, serum albumin, CEA, tumor diameter, the primary tumor location, platelet count, age as prognostic factors in order of importance. In the validation set (n = 162), the C-index was 0.648. Both the low-risk group (n = 35) (hazard ratio [HR]: 0.34, 95% confidence interval [CI]: 0.17 – 0.68, p < 0.01) and the middle-risk group (n = 74) (HR: 0.55, 95% CI: 0.33 – 0.89, p = 0.02) in the validation set had significantly better RFS compared to the high-risk group (n = 53). Among the 76 pts in the low-risk group treated with DS, 44 were categorized into the low-risk group when assuming they had been treated with S-1 alone. The analysis of 599 pts after multiple imputation yielded results consistent with those from the complete data. Conclusions: We developed the RSF-based predictive model for stage III GC pts, which demonstrated good performance. The number of metastatic lymph modes was identified as the most important prognostic factor. Risk stratification based on this model effectively differentiated prognostic outcomes. Future external validation of the model is required. Clinical trial information: UMIN000011438.

Prognostic Models From Transcriptomic Signatures of the Tumor Microenvironment and Cell Cycle in Stage III Colon Cancer From PETACC-8 and IDEA-France Trials.

The objective of this work was to establish prognostic models in stage III colon cancer (CC) on the basis of transcriptomic signatures of the tumor microenvironment (TME) and cell cycle from the PETACC-8 (training set) and IDEA-France (validation set) trials. 3'RNA sequencing was performed in 1,733 patients from the PETACC-8 trial and 1,248 patients from the IDEA-France trial. Four transcriptomic signatures were analyzed: T-cell and macrophage M2 signatures, the expression of CXCL13, and a score on the basis of the Oncotype DX CC Recurrence Score using the same formula from the stromal score and the cell cycle score. The Immune Proliferative Stromal (IPS) score was defined as the number of dichotomized signatures that fall under the category of a dismal prognosis (from 0 to 4). Time to recurrence (TTR) was defined as the time from the date of random assignment to local and/or metastatic relapse and/or death because of CC, whichever occurs first. High Oncotype-like and M2 scores and low CXCL13 expression and T-cell score were associated with a shorter TTR. A multivariable model including these signatures and all known prognostic factors applied to the IDEA-France cohort by obtaining a value of this model for each patient showed TTR significantly different depending on the quartile of this value and a 3-year rate of patients without recurrence ranging from 56% for the lowest quartile to 89% for the highest quartile (P < .0001). The IPS score was significantly associated with TTR in multivariable analysis. Using transcriptomic data of patients with stage III CC from two large-scale adjuvant trials, a prognostic model on the basis of signatures of the TME and the cell cycle provides important information in addition to known prognostic factors for patient stratification on risk of recurrence.

Semi-Supervised Medical Image Segmentation Based on Frequency Domain Aware Stable Consistency Regularization.

With the advancement of deep learning models nowadays, they have successfully applied in the semi-supervised medical image segmentation where there are few annotated medical images and a large number of unlabeled ones. A representative approach in this regard is the semi-supervised method based on consistency regularization, which improves model training by imposing consistency constraints (perturbations) on unlabeled data. However, the perturbations in this kind of methods are often artificially designed, which may introduce biases unfavorable to the model learning in the handling of medical image segmentation. On the other hand, the majority of such methods often overlook the supervision in the Encoder stage of training and primarily focus on the outcomes in the later stages, potentially leading to chaotic learning in the initial phase and subsequently impacting the learning process of the model in the later stages. At the meanwhile, they miss the intrinsic spatial-frequency information of the images. Therefore, in this study, we propose a new semi-supervised medical image segmentation approach based on frequency domain aware stable consistency regularization. Specifically, to avoid the bias introduced by artificially setting perturbations, we first utilize the inherent frequency domain information of images, including both high and low frequencies, as the consistency constraint. Secondly, we incorporate supervision in the Encoder stage of model training to ensure that the model does not fail to learn due to the disruption of the original feature space caused by strong augmentation. Finally, extensive experimentation validates the effectiveness of our semi-supervised approach.

Development of a multi-laboratory integrated predictive model for silicosis utilizing machine learning: a retrospective case-control study.

Due to the high global prevalence of silicosis and the ongoing challenges in its diagnosis, this pilot study aims to screen biomarkers from routine blood parameters and develop a multi-biomarker model for its early detection. A case-control study was conducted to screen biomarkers for the diagnosis of silicosis using LASSO regression, SVM and RF. A sample of 612 subjects (half cases and half controls) were randomly divided into training and test groups in a 2:1 ratio. Logistic regression analysis and receiver operating characteristic (ROC) curves were used to construct a multiple biomarker-based model for the diagnosis of silicosis, which was applied to both the training and the testing datasets. The training cohort revealed significant statistical differences (P < 0.05) in multiple hematologic parameters between silicosis patients and healthy individuals. Based on machine learning, eight silicosis biomarkers were screened and identified from routine blood cell, biochemical and coagulation parameters. D-dimer (DD), Albumin/Globulin (A/G), lactate dehydrogenase (LDH) and white blood cells (WBC) were selected for constructing the logistic regression model for silicosis diagnostics. This model had a satisfactory performance in the training cohort with an area under the ROC curve (AUC) of 0.982, a diagnostic sensitivity of 95.4%, and a specificity of 92.2%. In addition, the model had a prediction accuracy of 0.936 with an AUC of 0.979 in the independent test cohort. Moreover, the diagnostic accuracies of the logistic model in silicosis stages 1, 2, and 3 were 88.0, 95.4, and 94.3% with an AUC of 0.968, 0.983, and 0.990 for silicosis, respectively. A diagnostic model based on DD, A/G, LDH and WBC is successfully proposed for silicosis diagnostics. It is cheap, sensitive, specific, and preliminarily offers a potential strategy for the large-scale screening of silicosis.

The Dutch Early-Stage Melanoma (D-ESMEL) study: a discovery set and validation cohort to predict the absolute risk of distant metastases in stage I/II cutaneous melanoma.

Early-stage cutaneous melanoma patients generally have a favorable prognosis, yet a significant proportion of metastatic melanoma cases arise from this group, highlighting the need for improved risk stratification using novel prognostic biomarkers. The Dutch Early-Stage Melanoma (D-ESMEL) study introduces a robust, population-based methodology to develop an absolute risk prediction model for stage I/II melanoma, incorporating clinical, imaging, and multi-omics data to identify patients at increased risk for distant metastases. Utilizing the Netherlands Cancer Registry and Dutch Nationwide Pathology Databank, we collected primary tumor samples from early-stage melanoma patients, with and without distant metastases during follow-up. Our study design includes a discovery set of metastatic cases and matched controls to identify novel prognostic factors, followed by a validation cohort using a nested case-control design to validate these factors and to build a risk prediction model. Tissue sections underwent Hematoxylin & Eosin (H&E) staining, RNA sequencing (RNAseq), DNA sequencing (DNAseq), immunohistochemistry (IHC), and multiplex immunofluorescence (MxIF).The discovery set included 442 primary melanoma samples (221 case-control sets), with 46% stage I and 54% stage II melanomas. The median time to distant metastasis was 3.4years, while controls had a median follow-up time of 9.8years. The validation cohort included 154 cases and 154 controls from a random population-based selection of 5,815 patients. Our approach enabled the collection of a large number of early-stage melanoma samples from population-based databases with extensive follow-up and a sufficient number of metastatic events. This methodology in prognostic cancer research holds the potential to impact clinical decision-making through absolute risk prediction.

MIASS: A multi-interactive attention model for sleep staging via EEG and EOG signals

Sleep staging is essential for sleep analysis. Recent studies have attempted to integrate multi-modal signals such as electroencephalogram (EEG) and electrooculogram (EOG) to enhance model sensitivity. However, these attempts still face limitations in effectively fusing multi-modal signals, particularly in capturing both global and fine-grained interaction information in sleep epochs simultaneously. To address this, we propose a multi-interactive model (MIASS) that integrates two core modules, the global information interaction (GII) module and the fine-grained information interaction (FII) module. The GII module can effectively capture the global correlation paradigm in EEG and EOG at the epoch level by combining the global channel and spatial attentions with a residual network. The FII module explores the fine-grained correlation paradigm between small EEG and EOG segments within epochs using the cross-attention mechanism to achieve more fine-grained interaction information. The combination of these modules increased the accuracy of the model up to 89.2%, 86.6% and 89.7% on the SleepEDF-20, SleepEDF-78 and SHHS datasets, respectively, which outperforms the comparison models by 0.2–5.7%. The ablation study confirmed the benefits of integrating global and fine-grained correlation paradigms to enhance sleep staging performance, and the model input study demonstrated that MIASS maintains good performance under various input conditions.

An analytical placement algorithm with looking-ahead routing topology optimization

Placement is a critical step in the modern VLSI design flow, as it dramatically determines the performance of circuit designs. Most placement algorithms estimate the design performance with a half-perimeter wirelength (HPWL) and target it as their optimization objective. The wirelength model used by these algorithms limits their ability to optimize the internal routing topology, which can lead to discrepancies between estimates and the actual routing wirelength. This paper proposes an analytical placement algorithm to optimize the internal routing topology. We first introduce a differential wirelength model in the global placement stage based on an ideal routing topology RSMT. Through screening and tracing various segments, this model can generate meaningful gradients for interior points during gradient computation. Then, after global placement, we propose a cell refinement algorithm and further optimize the routing wirelength with swift density control. Experiments on ICCAD2015 benchmarks show that our algorithm can achieve a 3% improvement in routing wirelength, 0.8% in HPWL, and 23.8% in TNS compared with the state-of-the-art analytical placer. On industrial benchmarks, our algorithm can also achieve a 10.6% improvement in routing wirelength, 27.3% in WNS, and 34.4% in TNS.

Development of a Prognostic Model for Stage IV Colorectal Cancer Using Metastatic Patterns.

Metastatic patterns are the most convenient and common prediction models for the prognosis of patients with stage IV colorectal cancer. However, current prediction models do not include the severity of metastases in organs and exclude certain types of metastatic patterns. The aim of this study was to develop a prediction model that included several metastatic organs as well as the severity of liver and lung metastases, based on the Japanese Classification of Colorectal, Appendiceal, and Anal Carcinoma: the 3rd English Edition. We performed a state-wide cohort study and developed a prediction model using Cox proportional hazard regression analysis, utilizing data on patients with stage IV colorectal cancer in hospital-based cancer registries of all nine designated cancer hospitals across Fukushima Prefecture, Japan. The study included 1,230 patients with stage IV colorectal cancer. The prediction score consisted of the severity of liver and lung metastases, peritoneal dissemination, non-regional lymph node metastases, and other organ metastases (scale: 0-9 on a 10-point scale; divided into a 2-point scale, grade: I-V). The study found that the model had good discrimination properties, with a Harrell's concordance index of 0.64 (95% confidence interval: 0.62-0.66), and the grade was an independent prognostic factor [hazard ratio (HR)=1.83; 95% confidence interval=1.68-2.00; p<0.001]. We created a practical prediction model for stage IV colorectal cancer that can be applied at the time of diagnosis, using only metastatic patterns. Further external validation studies are required to ensure the accuracy of this model.

Knowledge Reasoning- and Progressive Distillation-Integrated Detection of Electrical Construction Violations.

To address the difficulty in detecting workers' violation behaviors in electric power construction scenarios, this paper proposes an innovative method that integrates knowledge reasoning and progressive multi-level distillation techniques. First, standards, norms, and guidelines in the field of electric power construction are collected to build a comprehensive knowledge graph, aiming to provide accurate knowledge representation and normative analysis. Then, the knowledge graph is combined with the object-detection model in the form of triplets, where detected objects and their interactions are represented as subject-predicate-object relationship. These triplets are embedded into the model using an adaptive connection network, which dynamically weights the relevance of external knowledge to enhance detection accuracy. Furthermore, to enhance the model's performance, the paper designs a progressive multi-level distillation strategy. On one hand, knowledge transfer is conducted at the object level, region level, and global level, significantly reducing the loss of contextual information during distillation. On the other hand, two teacher models of different scales are introduced, employing a two-stage distillation strategy where the advanced teacher guides the primary teacher in the first stage, and the primary teacher subsequently distills this knowledge to the student model in the second stage, effectively bridging the scale differences between the teacher and student models. Experimental results demonstrate that under the proposed method, the model size is reduced from 14.5 MB to 3.8 MB, and the floating-point operations (FLOPs) are reduced from 15.8 GFLOPs to 5.9 GFLOPs. Despite these optimizations, the AP50 reaches 92.4%, showing a 1.8% improvement compared to the original model. These results highlight the method's effectiveness in accurately detecting workers' violation behaviors, providing a quantitative basis for its superiority and offering a novel approach for safety management and monitoring at construction sites.

Role of Artificial Intelligence in MRI-Based Rectal Cancer Staging: A Systematic Review.

Several studies explored the application of artificial intelligence (AI) in magnetic resonance imaging (MRI)-based rectal cancer (RC) staging, but a comprehensive evaluation remains lacking. This systematic review aims to review the performance of AI models in MRI-based RC staging. PubMed and Embase were searched from the inception of the database till October 2024 without any language and year restrictions. The prospective or retrospective studies evaluating AI models (including machine learning (ML) and deep learning (DL)) for diagnostic performance in MRI-based RC staging compared with any comparator were included in this review. The performance metrics were considered as outcomes.Two independent reviewers were involved in the study selection and data extraction to limit bias; any disagreements were resolved through mutual consensus or discussion with a third reviewer. A total of 716 records were identified from the databases. Out of these, 14 studies (1.95%) were finally included in this review. These studies werepublished between 2019 and 2024. Various MRI technologies were adapted by the studies and multiple AI models were developed. DL was the most common. The MRI images including T1-weighted images (14.28%), T2-weighted images (85.71%), diffusion-weighted images (42.85%), or the combination of these from different landscapes and systems were used to develop the AI models. The models were built using various techniques, mainly DL such as conventional neural network (28.57%), DL reconstruction (14.28%), Weakly supervISed model DevelOpment fraMework (7.12%), deep neural network (7.12%), Faster region-based CNN (7.12%), ResNet, DL-based clinical-radiomics nomogram (7.12%),LASSO (7.12%), and random forest classifier (7.12%). All the models that used single-type images or combined imaging modalities showed a better performance than manual assessment in terms of higher accuracy, sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and area under the curve with a score of >0.75. This is considered to be a good performance. The current study indicates that MRI-based AI models for RC staging show great promise with a high performance.

The influence of agricultural trade liberalization on agricultural total factor productivity growth: Empirical evidence from ASEAN countries

Agriculture is a way of life in the ASEAN region due to the fact that eight out of ASEAN member states rely on agriculture for food and income. Therefore, the present study empirically explores the impact of agricultural trade liberalization on agricultural total factor productivity (ATFP) growth in ASEAN countries using panel data from 2002–2021. By deploying the data envelopment analysis-Malmquist productivity index (DEA-Malmquist) approach in the first stage and the pooled mean group (PMG) panel autoregressive distributed lag (ARDL) model in the second stage, the findings reveal that ATFP in the ASEAN countries demonstrated moderate growth over the study period, with an average mean value of 1.028. This signifies that the average growth in ATFP in the region was 2.8% across the countries and over a period of time. This suggests that the ASEAN countries have become increasingly dependent on technological innovation in their agricultural sectors in recent years. Agricultural trade liberalization positively contributed to ATFP growth in the short term, whereas the impact was not statistically significant in the long term. These consequences are highly significant and should not be disregarded since trade liberalization plays a crucial role in determining agricultural competitiveness.

Modelling human brain development and disease with organoids.

Organoids are systems derived from pluripotent stem cells at the interface between traditional monolayer cultures and in vivo animal models. The structural and functional characteristics of organoids enable the modelling of early stages of brain development in a physiologically relevant 3D environment. Moreover, organoids constitute a tool with which to analyse how individual genetic variation contributes to the susceptibility and progression of neurodevelopmental disorders. This Roadmap article describes the features of brain organoids, focusing on the neocortex, and their advantages and limitations - in comparison with other model systems - for the study of brain development, evolution and disease. We highlight avenues for enhancing the physiological relevance of brain organoids by integrating bioengineering techniques and unbiased high-throughput analyses, and discuss future applications. As organoids advance in mimicking human brain functions, we address the ethical and societal implications of this technology.

LPSGM: A Unified Flexible Large PSG Model for Sleep Staging and Mental Disorder Diagnosis.

We present the Large PSG Model (LPSGM), a unified and flexible framework for sleep staging and disease diagnosis using polysomnography (PSG) data. LPSGM is designed to address the challenges of cross-center generalization in sleep staging and to enable fine-tuning for downstream disease diagnosis tasks. LPSGM introduces a unified training framework for heterogeneous datasets and allows flexible channel input adjustments during inference. The model is first trained on 220,500 hours whole-night PSG from 16 public datasets, achieving robust sleep staging performance. It is then fine-tuned on target center data for various disease classification tasks, including narcolepsy diagnosis, anxiety and depression detection, and the classification of healthy versus depressed individuals. LPSGM outperforms baseline models on both sleep staging and disease diagnosis tasks. Our results demonstrate that LPSGM not only enhances sleep staging accuracy but also improves the diagnosis of sleep-related and psychiatric disorders, showing promise for clinical applications in sleep medicine and psychiatry.

Development of proactive care model for patients with chronic kidney disease stage 4–5 to clinical outcomes and quality of life: an action research

ABSTRACT Background Patients with chronic kidney disease often struggle to control clinical symptoms and need help from the healthcare team. This study aimed to develop a proactive care model for stage 4–5 chronic kidney disease patients and investigate its effectiveness on their clinical outcomes and quality of life in Thailand. Methods The study was a comprehensive, collaborative effort conducted in North Thailand involving a multidisciplinary team of healthcare professionals. This team, which included physicians, professional nurses, pharmacists, and nutritionists from the Chronic Kidney Disease Clinic at a secondary hospital, worked together to develop and implement a proactive care model for stage 4–5 chronic kidney disease patients. The research instruments used were a proactive care model for CKD stages 4–5 patients, the clinical outcomes assessment form, and the Kidney Disease Quality of Life Short Form. Quantitative data were analyzed using descriptive statistics, Chi-Square, and dependent t-tests, while qualitative data were analyzed using content analysis. Results The proactive care model for patients with chronic kidney disease stage 4–5 consists of 1) a multidisciplinary team providing chronic kidney disease standards, 2) providing knowledge and counseling for behavior change, and 3) supporting self-management of patients with chronic kidney disease. After the experiment, mean systolic blood pressure, diastolic blood pressure, and mean potassium were significantly lower than before, and Hematocrit significantly increased. In contrast, glomerular rate, fasting blood sugar, and hemoglobin A1C did not change after the intervention compared to before (p > .05). After the experiment, patients’ overall quality of life significantly increased. Conclusions This study demonstrated that the proactive care model for Chronic Kidney Disease stage 4–5 patients significantly improved clinical outcomes and profoundly impacted quality of life. Therefore, all components of the proactive care model should be applied, including working as a multidisciplinary team and helping patients adjust their behaviors and manage their health.

The fibrosis investigating navigator in diabetes (FIND): A tool to predict liver fibrosis risk in subjects with diabetes.

Type 2 diabetes increases the risk of cirrhosis and liver cancer. Noninvasive and early assessment of liver fibrosis is essential. We aimed to develop a score to aid in the initial assessment of liver fibrosis in the diabetic population. A fibrosis investigating navigator in diabetes (FIND) score was developed and validated in the NHANES dataset (2017-2020). Fibrosis was defined as a liver stiffness measurement (LSM) ≥8.0 kPa. The diagnostic accuracies of FIB-4, NFS, LiverRisk, steatosis-associated fibrosis estimator (SAFE) and metabolic dysfunction-associated fibrosis (MAF-5) were compared. FIND was also externally validated in various liver diseases via biopsy as a reference in an Asian centre between 2016 and 2020. Finally, we examined the prognostic implications of the FIND index utilizing data from the UK Biobank cohort (2006-2010). The FIND score model yielded an AUROC of 0.781 for the prediction of an LSM ≥8 kPa in the validation set, which was consistently greater than that of other available models (all p < 0.05). In the whole NHANES dataset, the 85% sensitivity cut-off of 0.16 corresponded to a NPV of 91.9%, whereas the 85% specificity cut-off of 0.31 corresponded to a PPV of 50.6%. FIND displayed overall accuracies similar to those of the other models in staging fibrosis stages, with biopsy used as a reference. In the UK Biobank cohort, FIND >0.31 was associated with an increased risk of all-cause and liver-related mortality in the diabetic population in adjusted models (HR, 1.75; 95% CI, 1.62-1.89; HR, 23.59; 95% CI, 13.67-40.69). In diabetes patients, the novel FIND score performs well in identifying subjects at risk of liver fibrosis and predicting all-cause and liver-related mortality.

Clinical Reasoning and Knowledge Assessment of Rheumatology Residents Compared to AI Models: A Pilot Study.

Background: The integration of artificial intelligence (AI) in medicine has progressed from rule-based systems to advanced models and is showing potential in clinical decision-making. In this study, the psychological impact of AI collaboration in clinical practice is assessed, highlighting its role as a support tool for medical residents. This study aimed to compare clinical decision-making approaches of junior rheumatology residents with both trained and untrained AI models in clinical reasoning, pre-diagnosis, first-line, and second-line management stages. Methods: Ten junior rheumatology residents and two GPT-4 models (trained and untrained) responded to 10 clinical cases, encompassing diagnostic and treatment challenges in inflammatory arthritis. The cases were evaluated using the Revised-IDEA (R-IDEA) scoring system and additional case management metrics. In addition to scoring clinical case performance, residents' attitudes toward AI integration in clinical practice were assessed through a structured questionnaire, focusing on perceptions of AI's potential after reviewing the trained GPT-4's answers. Results: Trained GPT-4 outperformed residents across all stages, achieving significantly higher median R-IDEA scores and superior performance in pre-diagnosis, first-line, and second-line management phases. Residents expressed a positive attitude toward AI integration, with 60% favoring AI as a supportive tool in clinical practice, anticipating benefits in competence, fatigue, and burnout. Conclusions: Trained GPT-4 models outperform junior residents in clinical reasoning and management of rheumatology cases. Residents' positive attitudes toward AI suggest its potential as a supportive tool to enhance confidence and reduce uncertainty in clinical practice. Trained GPT-4 may be used as a supplementary tool during the early years of residency.

Balancing mitigation strategies for viral outbreaks.

Control and prevention strategies are indispensable tools for managing the spread of infectious diseases. This paper examined biological models for the post-vaccination stage of a viral outbreak that integrate two important mitigation tools: social distancing, aimed at reducing the disease transmission rate, and vaccination, which boosts the immune system. Five different scenarios of epidemic progression were considered: (ⅰ) the "no control" scenario, reflecting the natural evolution of a disease without any safety measures in place, (ⅱ) the "reconstructed" scenario, representing real-world data and interventions, (ⅲ) the "social distancing control" scenario covering a broad set of behavioral changes, (ⅳ) the "vaccine control" scenario demonstrating the impact of vaccination on epidemic spread, and (ⅴ) the "both controls concurrently" scenario incorporating social distancing and vaccine controls simultaneously. By comparing these scenarios, we provided a comprehensive analysis of various intervention strategies, offering valuable insights into disease dynamics. Our innovative approach to modeling the cost of control gave rise to a robust computational algorithm for solving optimal control problems associated with different public health regulations. Numerical results were supported by real data for the Delta variant of the COVID-19 pandemic in the United States.

Liver fibrosis classification on trichrome histology slides using weakly supervised learning in children and young adults.

Traditional liver fibrosis staging via percutaneous biopsy suffers from sampling bias and variable inter-pathologist agreement, highlighting the need for more objective techniques. Deep learning models for disease staging from medical images have shown potential to decrease diagnostic variability, with recent weakly supervised learning strategies showing promising results even with limited manual annotation. To study the clustering-constrained attention multiple instance learning (CLAM) approach for staging liver fibrosis on trichrome whole slide images (WSIs) of children and young adults. This is an ethics board approved retrospective study utilizing 217 trichrome WSI from pediatric liver biopsies for model development and testing. Two pediatric pathologists scored WSI using two liver fibrosis staging systems, METAVIR and Ishak. Cases were then secondarily categorized into either high- or low-stage liver fibrosis and used for model development. The CLAM pipeline was used to develop binary classification models for histological liver fibrosis. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, and Cohen's Kappa. The CLAM models showed strong diagnostic performance, with sensitivities up to 0.76 and AUCs up to 0.92 for distinguishing low- and high-stage fibrosis. The agreement between model predictions and average pathologist scores was moderate to substantial (Kappa: 0.57-0.69), whereas pathologist agreement on the METAVIR and Ishak scoring systems was only fair (Kappa: 0.39-0.46). CLAM pipeline showed promise in detecting features important for differentiating low- and high-stage fibrosis from trichrome WSI based on the results, offering a promising objective method for liver fibrosis detection in children and young adults.