Standard Labeling Research Articles

Thoughts From the Front Lines: Canadian Perspectives in Adopting and Implementing Recommended Clinical Labels in Preschool Speech-Language Pathology.

Previous literature has proposed barriers to speech-language pathologists (SLPs) using standard clinical labels; however, the perspectives of SLPs have been studied to a lesser extent. This quality improvement project reports on SLPs' perceived barriers and facilitators to using currently recommended clinical labels for preschool communication disorders and identifies next steps to support implementation in one preschool communicative health system. This project aimed to establish the consistent use of clinical labels in one large Canadian preschool speech and language program. After completing a web-based training and a 3-month trial period, 387 SLPs completed an exit survey to share their perceived barriers and facilitators to label use. Qualitative survey data were analyzed using a hybrid codebook inductive/deductive thematic analysis approach. Six themes were identified, which aligned with the diffusion of innovations theory. SLPs identified several facilitators and barriers to using the recommended clinical labels within each theme. Major facilitators included improved communication, better caregiver understanding of children's communication, positive feedback from caregivers, SLPs' increased confidence in sharing labels, and improved access to services for children. Major barriers related to additional time required to share labels, SLPs' perceptions of caregivers' values, SLPs' views surrounding the recommended labels, lack of comfort using some labels, and limited opportunity to practice label use or observe successful label use by others. Contextual barriers continue to impact SLPs' use of the recommended clinical labels. Ongoing collaboration with SLPs and caregivers will be critical for supporting implementation. Further research examining SLPs' perspectives across other clinical settings and geographic areas is needed. https://doi.org/10.23641/asha.27296970.

Machine learning approaches toward an understanding of acute kidney injury: current trends and future directions.

Acute kidney injury (AKI) is a significant health challenge associated with adverse patient outcomes and substantial economic burdens. Many authors have sought to prevent and predict AKI. Here, we comprehensively review recent advances in the use of artificial intelligence (AI) to predict AKI, and the associated challenges. Although AI may detect AKI early and predict prognosis, integration of AI-based systems into clinical practice remains challenging. It is difficult to identify AKI patients using retrospective data; information preprocessing and the limitations of existing models pose problems. It is essential to embrace standardized labeling criteria and to form international multi-institutional collaborations that foster high-quality data collection. Additionally, existing constraints on the deployment of evolving AI technologies in real-world healthcare settings and enhancement of the reliabilities of AI outputs are crucial. Such efforts will improve the clinical applicability, performance, and reliability of AKI Clinical Support Systems, ultimately enhancing patient prognoses.

Zr-MOF-based substrate with inherent internal standards facilitates reliable SERS analysis of sulfonamide antibiotics

A multifunctional structure comprising gold nanoparticles immobilized within a zirconium-based metal-organic framework (AuNPs/Zr-MOF) was systematically designed. With the capabilities of analyte enrichment, Raman signal enhancement and internal standard calibration, the as-prepared AuNPs/Zr-MOF substrates demonstrate the outstanding SERS sensing performance toward the representative sulfonamide antibiotics (SAs), sulfadiazine, sulfamerazine, sulfamethazine and sulfaquinoxaline. For the first time, these four SAs are detected by SERS in real honey samples at levels of 2.8 ∼ 5.2 ng·g−1 within 10 min. The extensive π-bond conjugated system of Zr-MOF significantly enhances the concentration of SAs through π-π interactions. The entrapped SAs are adsorbed perpendicularly onto the surface of Au via coordinated interactions between Au and two oxygen atoms, or between Au and the terminal amino group. To achieve reliable quantitative analysis, the inherent vibration of the Zr-MOF structure was used as an internal standard label. Combined with a simple clean-up protocol, the established SERE sensing method is superior to conventional methods in terms of time, while achieving the impressive sensitivity. This study presents a robust SERS-based approach for the rapid detection and monitoring of multiple analytes.

A Labeling Intercomparison of Retrogressive Thaw Slumps by a Diverse Group of Domain Experts

ABSTRACTDeep‐learning (DL) models have become increasingly beneficial for the detection of retrogressive thaw slumps (RTS) in the permafrost domain. However, comparing accuracy metrics is challenging due to unstandardized labeling guidelines. To address this, we conducted an experiment with 12 international domain experts from a broad range of scientific backgrounds. Using 3 m PlanetScope multispectral imagery, they digitized RTS footprints in two sites. We evaluated label uncertainty by comparing manually outlined RTS labels using Intersection‐over‐Union (IoU) and F1 metrics. At the Canadian Peel Plateau site, we see good agreement, particularly in the active parts of RTS. Differences were observed in the interpretation of the debris tongue and the stable vegetated sections of RTS. At the Russian Bykovsky site, we observed a larger mismatch. Here, the same differences were documented, but several participants mistakenly identified non‐RTS features. This emphasizes the importance of site‐specific knowledge for reliable label creation. The experiment highlights the need for standardized labeling procedures and definition of their scientific purpose. The most similar expert labels outperformed the accuracy metrics reported in the literature, highlighting human labeling capabilities with proper training, site knowledge, and clear guidelines. These findings lay the groundwork for DL‐based RTS monitoring in the pan‐Arctic.

The effects and mechanism of discounting unit price

PurposeSupermarket promotions typically use a standard label, which displays the regular price, discounted price and discounted unit price. Visits to supermarkets across multiple countries found that none used a price label that also contains the regular (i.e. pre-discounted) unit price. This study aims to investigate the effectiveness of a dual unit-price label that includes the regular unit price as a reference price, and what underpins its efficacy in enhancing promotion attractiveness.Design/methodology/approachThe authors executed four studies, supported by three supplemental studies. Study 1 established external validity through a natural instore experiment. Studies 2 and 3 tested the dual unit-price label with different pack sizes and assortment sizes, respectively. Finally, Study 4 tested the underpinning mechanism of the efficacy of the dual unit-price label.FindingsIn Study 1, daily sales records over four weeks showed that dual unit-price label promotions had larger sales volume than standard-label promotions. Study 2 showed a larger pack size, a heuristic cue for greater economy and increased preference for dual unit-price label promotions. Study 3 similarly found that the dual unit-price label was preferred more as cognitive load was increased by assortment size. Finally, Study 4 demonstrated the dual processing of the dual unit-price label, using a conscious preference measure (information provided) and an unconscious implicit attitude test.Research limitations/implicationsUnit-price research has mainly considered a cognitive process. The authors demonstrated the importance of considering a heuristic process.Practical implicationsSupermarkets can use this simple and yet effective tool to improve promotion effectiveness.Originality/valueThis study demonstrates that the dual unit-price label is a new and easy tool to enhance sales promotions, which academic research and managerial practice had never considered previously.

Review of Plastic Waste Recycling: Advances, Challenges, and Future Perspectives

Plastic waste recycling is pivotal for sustainable waste management, offering solutions to mitigate environmental impacts and conserve resources. This thesis reviews technological advancements, challenges, and future prospects in recycling various plastic types. It begins with an overview of plastic pollution’s global impact and the imperative to manage plastic waste responsibly amidst rising production. Recycling processes are explored, detailing collection, sorting, cleaning, and reshaping methods that extend plastic life cycles while reducing energy consumption and greenhouse gas emissions. The review highlights challenges such as plastic type variability, recycling infrastructure limitations, and market demand discrepancies, affecting recycling effectiveness. Technological advances, including mechanical and chemical recycling innovations, are analyzed for their potential to improve plastic recycling rates. Economic and environmental implications underscore the benefits of effective recycling, contributing to a circular economy and minimizing landfill waste. Future directions advocate for enhanced recycling technologies, standardized labeling, and policy interventions like extended producer responsibility schemes. By addressing these facets, stakeholders can collaboratively advance sustainable plastic waste management globally, fostering a future where environmental stewardship aligns with economic viability.

Deep Learning for Automated Classification of Hip Hardware on Radiographs.

To develop a deep learning model for automated classification of orthopedic hardware on pelvic and hip radiographs, which can be clinically implemented to decrease radiologist workload and improve consistency among radiology reports. Pelvic and hip radiographs from 4279 studies in 1073 patients were retrospectively obtained and reviewed by musculoskeletal radiologists. Two convolutional neural networks, EfficientNet-B4 and NFNet-F3, were trained to perform the image classification task into the following most represented categories: no hardware, total hip arthroplasty(THA), hemiarthroplasty, intramedullary nail, femoral neck cannulated screws, dynamic hip screw, lateral blade/plate, THA with additional femoral fixation, and post-infectious hip. Model performance was assessed on an independent test set of 851 studies from 262 patients and compared to individual performance of five subspecialty-trained radiologists using leave-one-out analysis against an aggregate gold standard label. For multiclass classification, the area under the receiver operating characteristic curve (AUC) for NFNet-F3 was 0.99 or greater for all classes, and EfficientNet-B4 0.99 or greater for all classes except post-infectious hip, with an AUC of 0.97. When compared with human observers, models achieved an accuracy of 97%, which is non-inferior to four out of five radiologists and outperformed one radiologist. Cohen's kappa coefficient for both models ranged from 0.96 to 0.97, indicating excellent inter-reader agreement. A deep learning model can be used to classify a range of orthopedic hip hardware with high accuracy and comparable performance to subspecialty-trained radiologists.

Bootstrapping public entities. Domain-specific NER for public speakers

ABSTRACT Named Entity Recognition (NER) is a supervised machine learning task that finds various applications in automated content analysis, as the identification of entities is vital for understanding public discourse. However, sometimes the standard NER labels are not specific enough for a given domain. We introduce Public Entity Recognition (PER). PER is a domain-specific version of NER, that is trained for five entity types that are common to public discourse: politicians, parties, authorities, media, and journalists. PER can be used for pre-processing documents, in a pipeline with other classifiers or directly for analyzing information in texts. The taxonomy for PER is taken from the database of (German) public speakers and aims at low-threshold integration into computational social science research. We experiment with different training settings, involving weakly supervised training and training on manually annotated data. We evaluate multilingual transformer models of different sizes against rule-based entity matching and find that the models do not only outperform the baseline but also reach competitive absolute scores of around .8 and higher in F1. We further test for generalization and domain adaptation. We show that with only around 100–150 additional sentences, the model can be adapted to new languages.

An Efficient and Versatile Variational Method for High-Dimensional Data Classification

High-dimensional data classification is a fundamental task in machine learning and imaging science. In this paper, we propose an efficient and versatile multi-class semi-supervised classification method for classifying high-dimensional data and unstructured point clouds. To begin with, a warm initialization is generated by using a fuzzy classification method such as the standard support vector machine or random labeling. Then an unconstraint convex variational model is proposed to purify and smooth the initialization, followed by a step which is to project the smoothed partition obtained previously to a binary partition. These steps can be repeated, with the latest result as a new initialization, to keep improving the classification quality. We show that the convex model of the smoothing step has a unique solution and can be solved by a specifically designed primal–dual algorithm whose convergence is guaranteed. We test our method and compare it with the state-of-the-art methods on several benchmark data sets. Thorough experimental results demonstrate that our method is superior in both the classification accuracy and computation speed for high-dimensional data and point clouds.

Optimal Large Language Model Characteristics to Balance Accuracy and Energy Use for Sustainable Medical Applications.

Background Large language models (LLMs) for medical applications use unknown amounts of energy, which contribute to the overall carbon footprint of the health care system. Purpose To investigate the tradeoffs between accuracy and energy use when using different LLM types and sizes for medical applications. Materials and Methods This retrospective study evaluated five different billion (B)-parameter sizes of two open-source LLMs (Meta's Llama 2, a general-purpose model, and LMSYS Org's Vicuna 1.5, a specialized fine-tuned model) using chest radiograph reports from the National Library of Medicine's Indiana University Chest X-ray Collection. Reports with missing demographic information and missing or blank files were excluded. Models were run on local compute clusters with visual computing graphic processing units. A single-task prompt explained clinical terminology and instructed each model to confirm the presence or absence of each of the 13 CheXpert disease labels. Energy use (in kilowatt-hours) was measured using an open-source tool. Accuracy was assessed with 13 CheXpert reference standard labels for diagnostic findings on chest radiographs, where overall accuracy was the mean of individual accuracies of all 13 labels. Efficiency ratios (accuracy per kilowatt-hour) were calculated for each model type and size. Results A total of 3665 chest radiograph reports were evaluated. The Vicuna 1.5 7B and 13B models had higher efficiency ratios (737.28 and 331.40, respectively) and higher overall labeling accuracy (93.83% [3438.69 of 3665 reports] and 93.65% [3432.38 of 3665 reports], respectively) than that of the Llama 2 models (7B: efficiency ratio of 13.39, accuracy of 7.91% [289.76 of 3665 reports]; 13B: efficiency ratio of 40.90, accuracy of 74.08% [2715.15 of 3665 reports]; 70B: efficiency ratio of 22.30, accuracy of 92.70% [3397.38 of 3665 reports]). Vicuna 1.5 7B had the highest efficiency ratio (737.28 vs 13.39 for Llama 2 7B). The larger Llama 2 70B model used more than seven times the energy of its 7B counterpart (4.16 kWh vs 0.59 kWh) with low overall accuracy, resulting in an efficiency ratio of only 22.30. Conclusion Smaller fine-tuned LLMs were more sustainable than larger general-purpose LLMs, using less energy without compromising accuracy, highlighting the importance of LLM selection for medical applications. © RSNA, 2024 Supplemental material is available for this article.

Semi-supervised Double Deep Learning Temporal Risk Prediction (SeDDLeR) with Electronic Health Records

Background:Risk prediction plays a crucial role in planning for prevention, monitoring, and treatment. Electronic Health Records (EHRs) offer an expansive repository of temporal medical data encompassing both risk factors and outcome indicators essential for effective risk prediction. However, challenges emerge due to the lack of readily available gold-standard outcomes and the complex effects of various risk factors. Compounding these challenges are the false positives in diagnosis codes, and formidable task of pinpointing the onset timing in annotations. Objective:We develop a Semi-supervised Double Deep Learning Temporal Risk Prediction (SeDDLeR) algorithm based on extensive unlabeled longitudinal Electronic Health Records (EHR) data augmented by a limited set of gold standard labels on the binary status information indicating whether the clinical event of interest occurred during the follow-up period. Methods:The SeDDLeR algorithm calculates an individualized risk of developing future clinical events over time using each patient’s baseline EHR features via the following steps: (1) construction of an initial EHR-derived surrogate as a proxy for the onset status; (2) deep learning calibration of the surrogate along gold-standard onset status; and (3) semi-supervised deep learning for risk prediction combining calibrated surrogates and gold-standard onset status. To account for missing onset time and heterogeneous follow-up, we introduce temporal kernel weighting. We devise a Gated Recurrent Units (GRUs) module to capture temporal characteristics. We subsequently assess our proposed SeDDLeR method in simulation studies and apply the method to the Massachusetts General Brigham (MGB) Biobank to predict type 2 diabetes (T2D) risk. Results:SeDDLeR outperforms benchmark risk prediction methods, including Semi-parametric Transformation Model (STM) and DeepHit, with consistently best accuracy across experiments. SeDDLeR achieved the best C-statistics ( 0.815, SE 0.023; vs STM +.084, SE 0.030, P-value .004; vs DeepHit +.055, SE 0.027, P-value .024) and best average time-specific AUC (0.778, SE 0.022; vs STM + 0.059, SE 0.039, P-value .067; vs DeepHit + 0.168, SE 0.032, P-value <0.001) in the MGB T2D study. Conclusion:SeDDLeR can train robust risk prediction models in both real-world EHR and synthetic datasets with minimal requirements of labeling event times. It holds the potential to be incorporated for future clinical trial recruitment or clinical decision-making.

Automatic generation of architecture drawings from point clouds

AbstractTraditional methods for producing architectural drawings require extensive manual labor. This paper proposes an automated method for generating a comprehensive set of three‐view drawings, including the standardized labeling of doors and annotation of dimensions and areas. The output drawings are software‐readable and editable, and the method is applicable to intricate structures with non‐orthogonal or curved walls. To fully validate the accuracy of the proposed method, two distinct building scenarios were selected for experimentation.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis.

Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality. This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data. In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips. Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance. Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

Weakly Supervised Deep Learning in Radiology.

Deep learning (DL) is currently the standard artificial intelligence tool for computer-based image analysis in radiology. Traditionally, DL models have been trained with strongly supervised learning methods. These methods depend on reference standard labels, typically applied manually by experts. In contrast, weakly supervised learning is more scalable. Weak supervision comprises situations in which only a portion of the data are labeled (incomplete supervision), labels refer to a whole region or case as opposed to a precisely delineated image region (inexact supervision), or labels contain errors (inaccurate supervision). In many applications, weak labels are sufficient to train useful models. Thus, weakly supervised learning can unlock a large amount of otherwise unusable data for training DL models. One example of this is using large language models to automatically extract weak labels from free-text radiology reports. Here, we outline the key concepts in weakly supervised learning and provide an overview of applications in radiologic image analysis. With more fundamental and clinical translational work, weakly supervised learning could facilitate the uptake of DL in radiology and research workflows by enabling large-scale image analysis and advancing the development of new DL-based biomarkers.

On-slide clearing and imaging of 100-µm-thick histological sections using ethyl cinnamate and epifluorescence.

Thick histological samples are difficult to image without proper tissue clearing methods. Among these methods ethyl cinnamate (ECi)-based clearing preserves antigenicity and is compatible with immunofluorescent labeling. In contrast to many other clearing protocols, ECi-based clearing is fast and is done as a final step after standard immunofluorescent labeling protocols.

An efficient, amine-specific iTRAQ labeling method improves the peptide and protein identification rates

Isotope tags for relative and absolute quantification (iTRAQ) are among the most widely used proteomics quantification techniques. These tags can be rapidly coupled to the primary amines of proteins/peptides through chemical reactions under mild conditions, making this technique universally applicable to any kind of sample. However, iTRAQ reagents also partially react with the hydroxyl groups of serine, threonine and tyrosine residues, particularly when these residues coexist with a histidine residue in the same peptide. This overlabeling of peptides causes systematic biases and significantly compromises protein/peptide identification rates. In this study, we report a novel iTRAQ labeling method that overcomes the detrimental overlabeling while providing high amine labeling efficiency. The impacts of reaction temperature, reactant concentrations, reaction time, buffer compositions, and pH on iTRAQ labeling performance were investigated in-depth. In a comparison experiment between our method and the standard labeling method provided by the iTRAQ manufacturer, our method reduced the number of overlabeled peptides by 55-fold while achieving comparable amine labeling efficiency. This improvement allowed our method to eliminates the systematic bias against histidyl- and hydroxyl-containing peptides, and more importantly, enabled the identification of 23.9% more peptides and 9.8% more proteins. SignificanceIn addition to amines, the hydroxyl groups in serine, threonine, and tyrosine residues can also partially labeled by iTRAQ reagents, which leads to systematic biases and significantly compromises the analytical sensitivity. To address this issue, we developed a novel iTRAQ labeling method that overcomes the detrimental overlabeling while providing high labeling efficiency of amines. When benchmarking our method against the standard method provided by the reagent manufacturer, our method achieved comparable labeling efficiency but reduced the overlabeled species by 55-fold. This significant improvement eliminated the systematic biases, and more importantly, enabled the identification of 23.9% more peptides and 9.8% more proteins, demonstrating its superior performance and potential to enhance proteome quantification using iTRAQ labeling.

Automatic standard plane and diagnostic usability classification in obstetric ultrasounds

ObjectiveThis study introduces an innovative end-to-end deep learning pipeline designed to automatically classify and order fetal ultrasound standard planes in alignment with the guidelines of the Canadian Association of Radiologists, while also assessing the diagnostic usability of each view. The primary objective is to address the manual and cumbersome challenges that interpreting radiologists encounter in the existing obstetric ultrasound workflow. MethodsWe compiled a diverse dataset, comprising 33,561 de-identified two-dimensional obstetrical ultrasound images acquired from January 1, 2010, to June 1, 2020. This dataset was categorized into 19 distinct classes associated with standard planes and further partitioned into training, validation, and testing subsets via a 60:20:20 stratified split. The standard plane and diagnostic usability networks are founded on a convolutional neural network framework and employ the benefits of transfer learning. ResultsThe standard plane classification network demonstrated promising results by achieving 99.4 % and 98.7 % for accuracy and F1 score, respectively. Subsequently, the diagnostic usability network demonstrated strong performance, registering 80 % accuracy and an 82 % F1 score. Notably, this study is the first to investigate whether deep learning methods can surpass sonographers in the standard plane labeling task, with some instances revealing the algorithm's capacity to rectify sonographer mislabeled planes. ConclusionThe results highlight the algorithm's potential to be integrated into a clinical setting by serving as a reliable assistive tool, alleviating the cognitive workload faced by radiologists and enhancing efficiency and diagnostic outcomes in the current obstetric ultrasound process.

ASC4FIRST, a pivotal phase 3 study of asciminib (ASC) vs investigator-selected tyrosine kinase inhibitors (IS TKIs) in newly diagnosed patients (pts) with chronic myeloid leukemia (CML): Primary results.

LBA6500 Background: We present primary results from ASC4FIRST (NCT04971226), the first study in CML comparing all current standard-of-care frontline TKIs with a novel agent, ASC, in newly diagnosed pts. ASC Specifically Targets the ABL Myristoyl Pocket (STAMP). Methods: Adults with CML were randomly assigned 1:1 to receive ASC 80 mg once daily or an IS TKI at standard label doses, stratified by ELTS risk category and prerandomization selected (PRS) TKI (imatinib [IMA] or second-generation [2G] TKIs), which was selected by investigators before randomization, accounting for pt preference. Pts diagnosed within 3 mo before enrollment with no prior treatment (Tx) except IMA/2G TKIs for ≤2 wk prior to randomization were eligible. Primary objectives were to demonstrate superior major molecular response (MMR) rate at wk 48 with ASC vs IS TKI and ASC vs IS TKI within the stratum of pts with IMA as PRS TKI (ASCIMA vs IS TKIIMA). The study is positive if either objective is met. Comparing MMR rate of ASC vs IS TKI at wk 48 within the stratum of pts with 2G TKIs as PRS TKI (ASC2G vs IS TKI2G) was an unpowered secondary objective. Results: Pts received ASC (n=201: ASCIMA, n=101; ASC2G, n=100) or IS TKI (n=204: IS TKIIMA, n=102; IS TKI2G, n=102 [nilotinib, 48%; dasatinib, 41%; bosutinib, 11%]). Median follow-up was 16.3 and 15.7 mo for ASC and IS TKI, respectively (cutoff: Nov 28, 2023). At cutoff, Tx was ongoing in 86%, 62%, and 75% of pts on ASC, IMA, and 2G TKIs, respectively, with pts most commonly discontinuing due to unsatisfactory therapeutic effect (6%, 21%, 10%) (Tx failure per ELN2020 [5%, 16%, 8%], MMR loss [0.5%, 0%, 0%], physician decision [0.5%, 5%, 2%]) and adverse events (AEs) (5%, 11%, 10%). MMR rate at wk 48 (per ITT) was superior with ASC (67.7%) vs IS TKI (49.0%) and with ASCIMA (69.3%) vs IS TKIIMA (40.2%), meeting both primary objectives with high statistical significance; rate difference was 18.9% [95% CI, 9.6%-28.2%] and 29.6% [95% CI, 16.9%-42.2%], respectively, both with adjusted 1-sided P&lt;.001. MMR rate at wk 48 was higher with ASC2G vs IS TKI2G (66.0% vs 57.8%). BCR::ABL1IS ≤1% rate at wk 48 was 87% with ASC vs 73% with IS TKI and 84% with ASCIMA vs 62% with IS TKIIMA. At wk 48, MR4 and MR4.5 rates were higher with ASC vs IS TKI (39% vs 21%; 17% vs 9%), ASCIMA vs IS TKIIMA (43% vs 15%; 18% vs 5%), and ASC2G vs IS TKI2G (35% vs 26%; 16% vs 13%). ASC had markedly favorable safety and tolerability vs IMA and 2G TKIs, with less grade ≥3 AEs (38%, 44%, 55%), half the rate of AEs leading to Tx discontinuation (5%, 11%, 10%), and less dose adjustments/interruptions to manage AEs (30%, 39%, 53%). Rate of arterial occlusive events was 1%, 0%, and 2%, respectively. Conclusions: ASC is the only agent to show a statistically significant superior efficacy and excellent safety and tolerability vs all current standard-of-care frontline Tx, with potential to be the therapy of choice for CML. Clinical trial information: NCT04971226 .

Dual-stream mutually adaptive quality assessment for authentic distortion image

To address semantic misperception caused by distortion and accurately simulate human perceptual processes, this study proposed a method that utilised dual-stream mutually adaptive feature mapping. To extract complementary features, a dual-stream unsupervised method was used during the training phase. One stream was responsible for the extraction of low-level and global features, whereas the other was dedicated to extracting high-level semantic and positional features. Following the freezing of feature extraction network weights, we proposed a structure that used standard deviation labels to predict the quality distribution. The experimental results obtained from 10 published image quality databases demonstrated the superiority of the proposed algorithm. The algorithm outperformed the majority of mainstream methods when evaluated on authentic distortion databases and exhibited competitive performance on synthetic distortion databases.

Identifying multidisciplinary problems from scientific publications based on a text generation method

Abstract Purpose A text generation based multidisciplinary problem identification method is proposed, which does not rely on a large amount of data annotation. Design/methodology/approach The proposed method first identifies the research objective types and disciplinary labels of papers using a text classification technique; second, it generates abstractive titles for each paper based on abstract and research objective types using a generative pre-trained language model; third, it extracts problem phrases from generated titles according to regular expression rules; fourth, it creates problem relation networks and identifies the same problems by exploiting a weighted community detection algorithm; finally, it identifies multidisciplinary problems based on the disciplinary labels of papers. Findings Experiments in the “Carbon Peaking and Carbon Neutrality” field show that the proposed method can effectively identify multidisciplinary research problems. The disciplinary distribution of the identified problems is consistent with our understanding of multidisciplinary collaboration in the field. Research limitations It is necessary to use the proposed method in other multidisciplinary fields to validate its effectiveness. Practical implications Multidisciplinary problem identification helps to gather multidisciplinary forces to solve complex real-world problems for the governments, fund valuable multidisciplinary problems for research management authorities, and borrow ideas from other disciplines for researchers. Originality/value This approach proposes a novel multidisciplinary problem identification method based on text generation, which identifies multidisciplinary problems based on generative abstractive titles of papers without data annotation required by standard sequence labeling techniques.