Subjective Decisions Research Articles

The curriculum of English language teacher education in expanding circles: English teachers with the best teaching skills or the ones who are best English proficient?

Countries classified as expanding circles have endless worries about the qualities of Teacher Education products. This happened because such expanding circles can never give enough room for English learners to have real-life practices since English is not the lingua franca. Similarly, in Indonesia, the issue of highlighting the qualities of the products of Teacher Education has become an endless problem that never leaves a satisfactory solution. This issue might become a blip in a situation where a new curriculum will be implemented soon. Attempts have been made to increase qualified products of teacher education in Indonesia for years, yet the results are not better than expected. Six domains of content (i.e. theories of teaching, teaching skills, communication skills, subject matter knowledge, pedagogical reasoning and decision making, and context knowledge) presumably might have been used by Indonesian teacher education as the core knowledge base of Second Language Teacher Education (SLTE); however, since Indonesia has various geographical areas which implies various contexts of SLTE, these six domains of content might not be differently adopted in all parts of Indonesia. Highlighting how important all six content domains in the development of Indonesian SLTE are presumably led to how much attention should be paid to each domain. Reviewing these six domains of content, specifically, this article intends to analyze how those domains are synchronized in composing the core content of the English Department curriculum in teacher education. Are they all equally important?

Burden of proof regarding the existence of pre-existing debt in quasi-loan agreement - The subject decision: Supreme Court Decision, April 25, 2024, Decision 2022Da254024 -

Burden of proof regarding the existence of pre-existing debt in quasi-loan agreement - The subject decision: Supreme Court Decision, April 25, 2024, Decision 2022Da254024 -

Subjective Decisions About Medicines in a Time of Financial Distress: How AI and Mind Genomics Thinking Help to Clarify the Issues

The paper presents the results of a four-phase simulation of the response of ordinary people to the problems of affording the proper medicine in a time of financial hardship. Through AI (ChatGPT 3.5) and the emerging science of Mind Genomics, the paper generates a sense of the experience of financial hardship in a time of rising prices of drugs. Phase 1, the voice of the people, simulates interviews with ordinary people regarding their feelings and experiences. Phase 2, the town hall meeting, simulates the response of ordinary people to the presentation by drug company executives at a public meeting. Phase 3, the mind-set of pharmacists, presents the way pharmacists think about working with those customers who are facing financial hardships. Phase 4, questions and answers, shows how AI generates an instructional document about the multifaceted experience of individuals of lower income facing increasing cost of medicine. The four phases can be replicated and scaled across different aspects of medicine to provide a way by which to teach medical professionals about the inner experience of patients and customers.

The Clinical Status of Patients With Lumbar Spinal Stenosis Reflects Their Individual Decision to Undergo or Defer Lumbar Spinal Surgery.

To evaluate whether functional, clinical, and self-reported tests reflect lumbar spinal stenosis patients' decisions to undergo or defer surgery. Among 108 participants, 77 chose surgery (SG), and 31 opted to wait and see (WaSG) whether they got better spontaneously. Both groups were assessed at baseline (t0) and 3 months (t1), with additional self-reported measures at 6 (t2) and 12 months (t3). Key outcomes included corridor walk distance, chair sit-to-stand repetitions, grip strength, and various pain and disability indices. At baseline, SG reported higher leg pain (NPRS-leg: Δ = 1.66, P = 0.002) and poorer functional outcomes across multiple tests. By t1, both groups improved in disability, but SG showed greater reductions in the Oswestry Disability Index (Δ = 7.85, P = 0.001) and sustained improvements in leg pain at subsequent assessments. WaSG consistently engaged in more walking (mean Δ = 123.5 minutes, P < 0.001). Regression analyses indicated that surgery status, flexibility, and strength significantly predicted improvements in disability (adjusted R² = 0.296). Logistic regression identified predictors for surgery choice, including biological sex, leg pain intensity, walking performance, and weekly walking hours. Functional status, self-reported disability, and fear-avoidance beliefs in lumbar spinal stenosis patients reflect their subjective decision regarding surgery and highlight the importance of baseline leg pain, calf strength, walking-related parameters, and physical function in recovery. Observational prospective cohort.

The grey zone of taxonomy—The case of the Sikkim Myotis (Chiroptera: Vespertilionidae: Myotis sicarius), first recorded from Southeast Asia

Abstract In taxonomic works, the weight to be given to morphological, mitochondrial, or nuclear signals, and the assessment of differences as species or subspecies distinctions has also varied considerably over the past decades and is largely a subjective research decision. This apparent example of the “grey zone of taxonomy” underpins the need of critical studies of as many specimens as possible and of using both mitochondrial and nuclear genes in taxonomic-systematic studies, as phylogeny based on uniparentally inherited genes alone may not represent true evolutionary scenarios. Myotis sicarius, a species occurring thorough the Himalayan foothills was found for the first time out of South Asia, in North Vietnam. Analysis of topotypical and Vietnamese specimens revealed high mitochondrial heterogeneity – at the upper limit of the usual threshold of intraspecific difference – but only minute nuclear sequence and negligible morphological differences. Albeit the large geographic distance between the two records might suggest the existence of two putative reproductively isolated taxonomic units, based on the incongruent results we concluded that the split of geographic populations of M. sicarius into different taxa is unsupported. As a morphologically closely resembling species, we also reviewed the taxonomic status of the two morphological forms of M. annectans and synonymizing M. primula with M. annectans was also corroborated by our phylogenetic analyses.

Proximity Index Value for Supplier Selection Using Compromise Weighting of Stepwise Weight Assessment Ratio Analysis (SWARA) Analytical Hierarchy Process (AHP) and MEREC: A Case Study in Indonesian Leather Industry

Procurement of new raw materials is needed when product demand increases, and raw material suppliers must be determined to meet the company's needs. This research examines what criteria a company needs when selecting criteria using Delphi. The weighting of criteria cannot be separated from the element of the decision maker's subjectivity; therefore, it is necessary to compromise between subjective and objective criteria. Therefore, the study used The Method of Removal Effects of Criteria (objective weighting of criteria) and Stepwise Weight Assessment Ratio Analysis (subjective weighting of criteria) in weighting criteria. Then, considering the weight of the criteria, the Proximity Index Value (PIV) is used to evaluate and rate the suppliers. The offered methodology is applied to a real case study from a leather manufacturing company in Indonesia to verify its applicability with a sensitivity analysis performed on different scenarios. The findings indicated that the proposed model is dependable and that the rankings are resilient to fluctuations in the criterion weights.

Chasing net zero: critical uncertainties in coffee emissions calculations

Summary Net zero as a policy for reducing atmospheric carbon emissions is relatively straightforward; however, the implementation of that policy is not, particularly in difficult-to-measure sectors such as agriculture. As strategies to reduce emissions are explored, multiple uncertainties in measuring these emissions are confronted. In this paper, we use the example of a coffee supply chain in Peru to illustrate the magnitude of potential variability in emissions accounting results, which represent a necessary first step in moving towards net zero. We show that scope boundaries and emissions factors chosen for carbon calculations significantly alter emissions outcomes and can result in discrepancies of over 77 million kg CO2e when scaled to a medium-size coffee trader. Net zero targets and efforts to reduce emissions may be over- or understated depending on subjective decisions that cause significant differences in emissions results. Although framework guidance exists, it is apparent that a greater set of micro-level agreements is needed for calculating the emissions of lesser-studied sectors, such as agricultural supply chains. This process is imperative to focus efforts on reducing emissions and on moving from net zero as a mere policy to action and implementation.

Evaluating Remote Work Practices in the Public Sector: Insights from Saudi Arabian Employees

Remote work is a work pattern adopted in various organizations as an advancement of technology and an application of digital transformation. Remote work has many advantages that contribute to both employees and organizations. It allows flexibility and increases productivity besides many other benefits. However, remote work also has some challenges such as culture and reachability that need to be considered. Remote work is a significant change in employees’ pattern of work where they will have more autonomy and responsibility. Additionally, employees will be more reachable and they might work longer hours. Thus, all of this might contribute to substandard practices of remote work where its stereotype becomes negative. Literature has shown that some organizations have decided to return to office as a result of the substandard practices. Therefore, this research is motivated to understand the practices of remote work in Saudi Arabia’s public sector. This research found that the public sector relies heavily on technology. However, as a formal work pattern, only three organizations allow remote work. That said, employees become reachable more than ever when they are asked and contacted after working hours. This has resulted in a new finding that remote work might not be an official work pattern, but employees could work remotely after official working hours. This research has also found that the practices of remote work are substandard. Employees’ culture is behind and they misuse the concept of remote work. In addition, there is a lack of remote work policy which leaves a space for individuals and subjective decisions that might contribute negatively to remote work experience.

A systematic method to integrate co‐produced causal loop diagrams based on feedback stories

AbstractWithin participatory systems dynamics, more practitioners are compiling co‐produced causal loop diagrams (CLDs) to analyse and report workshop outputs. Though not formalized, existing documented techniques have been limited to analyses of representations in single‐group diagrams predicated on, at times, untraceable subjective judgements. This paper addresses the need for a systematic method to guide and justify the subjective decisions made in the integration process. We propose a multistep, three‐stage process that synthesizes feedback stories from representations in diagrams (i.e. what is represented) and transcripts of the participatory process (i.e. what is said). This approach enables practitioners to report the interpretive scheme through which qualitative data are analysed and, thus, support the subjective decisions they made during the integration process. Using a case study, we demonstrate the application of this method and its potential for narrowing the semantic distance between participants, practitioners and external audience for interpreting and analysing an integrated diagram. © 2024 The Author(s). System Dynamics Review published by John Wiley &amp; Sons Ltd on behalf of System Dynamics Society.

“How about you just ask?”: uplifting black adolescent girls’ reflections on educators’ decisions in the context of discipline disproportionality

ABSTRACT Educators’ subjective decisions regarding behaviors like dress code and defiance contribute to discipline disparities experienced by Black girls. However, Black adolescent girls’ voices on this issue remain largely unconsidered. To address this gap, we investigated their reflections on educators’ decision making concerning subjective behaviors and responses. We conducted a thematic analysis of quotes by Black US middle and high-school girls identified by coupling best practices for qualitative systematic reviews with a novel process to extract quotes in which Black adolescent girls specifically discussed discipline interactions (N = 41). Primarily, girls talked about discrimination and described educators’ failure to value their voices and experiences in their decision making. Notably, girls’ reflections were similar whether educators responded with a verbal reprimand or an office discipline referral. Students’ disengagement after these kinds of discipline interactions points to the importance of actively engaging Black girls in efforts to address disproportionality in school discipline.

Assessing metacognitive knowledge in subjective decisions: The knowledge of weights paradigm

Subjective, multi-attribute choice decisions – such as whom to marry or which college to attend – play a substantial role in decision makers’ long-term well-being. However, the metacognition literature lacks tools for assessing metacognitive capacities in subjective decisions. We present three studies in which we propose and validate the Knowledge of Weights (KoW) paradigm, a novel method for assessing metacognitive knowledge of attribute weights in subjective, multi-attribute choice decisions. In Study 1, we demonstrate the test-retest reliability of metrics generated by the KoW paradigm. In Study 2, we apply the KoW paradigm in four domains and show that it generates consistent results. In Study 3, we demonstrate that participants who perform better on the KoW paradigm make choices with which they are more satisfied, providing suggestive evidence of predictive validity. Use cases in cognitive psychology and beyond are discussed.

Stained glass ceilings: Gender and race in accounting academia in Brazil

AbstractBrazil is divided into five large regions marked by profound economic and social inequalities. Such vast differences can make people feel like “foreigners”, even though they live in the same country. Here, meritocracy is seen as the criterion for assessing and promoting people, which is conflicting given the absurdly unequal contexts in the country. This choice widens inequalities of gender, race and, above all, social class. Between 2000 and 2018, Brazil experienced profound social transformations. Female participation in the labor market grew, although there were still barriers to access and professional advancement for women, which were exacerbated in the case of black women. When it came to leadership positions, they were almost always blocked by processes which depended on subjective decisions from evaluators. These circumstances occur through daily confrontations with processes of sexualisation and racialisation. These transformations were followed in the most recent period by clear setbacks, deepened by the COVID‐19 pandemic and intense political polarization. A milestone in terms of Esperançar, a verb proposed by Paulo Freire (1992), were the 2022 presidential elections, understood as a process of re‐democratisation. The social achievements that have been maintained, however, are ‘advances’ that work differently when the diversity of the population and regional differences are taken into account. With this particular context in mind, the aim of this study is to investigate how the “glass ceiling” phenomenon has been present in the daily interactions and academic trajectory of black women in the accounting field. The question that underpinned this study was: how can the academic accounting environment, considering practice and discourse, boost or hinder the “glass ceiling” phenomenon in the professional career of black female academics? This is a qualitative study with a post‐structuralist approach, based on the adoption of auto‐ethnographic and oral history techniques. The evidence was built up through semi‐structured, in‐depth interviews with female academics who had graduated from postgraduate programmes. This corpus was analyzed from an interpretivist perspective and the findings reveal that the “glass ceiling” phenomenon is present in accounting academia in Brazil and is expressed in barriers specific to the field. Barriers are erected in processes of closure, blocking the path of black women who aim to succeed in prestigious academic spaces, regardless of their level of qualification. In this way, they are conceptualized as “stained glass ceilings”, because the barriers become visible and concrete in a country where racism is a structuring element of social relations.

The Digital Revolution in Medicine: Applications in Cardio-Oncology.

A critical evaluation of contemporary literature regarding the role of big data, artificial intelligence, and digital technologies in precision cardio-oncology care and survivorship, emphasizing innovative and groundbreaking endeavors. Artificial intelligence (AI) algorithm models can automate the risk assessment process and augment current subjective clinical decision tools. AI, particularly machine learning (ML), can identify medically significant patterns in large data sets. Machine learning in cardio-oncology care has great potential in screening, diagnosis, monitoring, and managing cancer therapy-related cardiovascular complications. To this end, large-scale imaging data and clinical information are being leveraged in training efficient AI algorithms that may lead to effective clinical tools for caring for this vulnerable population. Telemedicine may benefit cardio-oncology patients by enhancing healthcare delivery through lowering costs, improving quality, and personalizing care. Similarly, the utilization of wearable biosensors and mobile health technology for remote monitoring holds the potential to improve cardio-oncology outcomes through early intervention and deeper clinical insight. Investigations are ongoing regarding the application of digital health tools such as telemedicine and remote monitoring devices in enhancing the functional status and recovery of cancer patients, particularly those with limited access to centralized services, by increasing physical activity levels and providing access to rehabilitation services. In recent years, advances in cancer survival have increased the prevalence of patients experiencing cancer therapy-related cardiovascular complications. Traditional cardio-oncology risk categorization largely relies on basic clinical features and physician assessment, necessitating advancements in machine learning to create objective prediction models using diverse data sources. Healthcare disparities may be perpetuated through AI algorithms in digital health technologies. In turn, this may have a detrimental effect on minority populations by limiting resource allocation. Several AI-powered innovative health tools could be leveraged to bridge the digital divide and improve access to equitable care.

Automated geotechnical logging of core box images using machine learning

ABSTRACT Geotechnical characterization is contingent on reliable data to reduce uncertainty in the conditions of slope walls or underground workings. However, geotechnical data for greenfield and brownfield sites are often limited. The data that are available are often inconsistent and difficult to reliably use to inform the geotechnical domain model. SRK has developed machine learning workflows using deep learning for geotechnical classification of existing core box photographs to provide a reliable and objective data set that can be used to inform rock mass characterization and structural modeling. Conventional geotechnical parameters are often unsuitable for automation due to the reliance on subjective decisions by the logger for interval lengths or defining naturally open versus closed breaks. Three classification systems have been developed: the Core Damage Index (CDI), the Pseudo-RQD, and the Break Frequency. The CDI classifies discrete intervals within the photographs according to the average clast sizes relative to the core diameter to provide a high-resolution view of the variability of damage down a drill hole. Pseudo-RQD and Break Frequency are calculated by mapping the breaks and rubble zones observed on drill core images.

Clinical Significance of Combined Detection of CCL22 and IL-1 as Potential New Bronchial Inflammatory Mediators in Children's Asthma.

Severe asthma is a significant health burden because children with severe asthma are vulnerable to medication-related side effects, life-threatening deterioration, and impaired quality of life. However, there is a lack of data to elucidate the role of inflammatory variables in asthma. This study aimed to compare the levels of inflammatory factors in serum and sputum in children with acute and stable asthma to those in healthy children and the ability to predict clinical response to azithromycin therapy. This study recruited 95 individuals aged 1-3 years old and collected data from January 2018 to 2020. We examined serum and sputum inflammatory factors and constructed the least absolute shrinkage and selection operator (LASSO) model. Predictive models were constructed through multifactor logistic regression and presented in the form of column-line plots. The performance of the column-line diagrams was measured by subject work characteristics (ROC) curves, calibration plots, and decision curve analysis (DCA). Then, filter-paper samples were collected from 45 children with acute asthma who were randomly assigned to receive either azithromycin (10 mg/kg, n = 22) or placebo (n = 23). Pretreatment levels of immune mediators were then analyzed and compared with clinical response to azithromycin therapy. Of the 95 eligible participants, 21 (22.11%) were healthy controls, 29 (30.53%) had stable asthma, and 45 (47.37%) had acute asthma. The levels of interferon-γ (IFN-γ), tumor necrosis factor-a (TNF-α), chemokine CCL22 (CCL22), interleukin 12 (IL-12), chemokine CCL4 (CCL4), chemokine CCL2 (CCL2), and chemokine CCL13 (CCL13）were significantly higher in the acute asthma group than in the stable asthma group. A logistic regression analysis was performed using CCL22 and IL-1 as independent variables. Additionally, IFN-γ, TNF-α, IL-1, IL-13, and CCL22 were identified in the LASSO model. Finally, we found that CCL22 and IL-1 were more responsive in predicting the response to azithromycin treatment. Our results show that CCL22 and IL-1 are both representative markers during asthma symptom exacerbations and an immune mediator that can predict response to azithromycin therapy.

Symmetrical choices and biased confidence during uncertain personality trait judgments.

While great methodological strides have been made in the area of decision making research, decisions that rely on subjective stimuli, such as personality traits, still pose a challenge for researchers, partly because it is difficult to define a standard of accuracy for such choices-they lack a "ground truth". In studies on value-based decisions, this same problem has been circumvented by comparing uncertain subjective decisions against a separately assessed judgment of value-a "standard". Here we apply this method in a task of verbal personality trait judgment, and show how a separately assessed standard judgment can be used to precisely control stimulus presentation and analyze subjective personality choices via the method of reverse correlation. Per trial, a series of quasi-randomly sampled adjectives was shown, which participants categorized as more descriptive of either themselves of another person well known to them. Participants also indicated their confidence in the response. Each trial's difficulty was controlled based on the previously assessed standard judgment. Analysis of the behavioral data shows several decision-general properties during these personality judgments, such as symmetrical choices, steeper choice functions for confident trials, and a positive evidence bias during confidence judgment. We discuss how these findings can shed light on the cognitive processes involved in personality perception. The task and results together may help bridge the gap between research on complex, social forms of judgment and findings on more basic decision processes.

Algorithm aversion during disruptions: The case of safety stock

Algorithm aversion occurs when organizations or individuals reject optimal analytical decision support in favour of informal, subjective decisions. This phenomenon has been observed in many practical decision-making scenarios and is generally believed to negatively impact decision quality. However, its existence and effect in volatile supply chain environments has not been empirically tested in the literature. Safety stock buffering demand volatility is an important decision in supply chain management, making it an ideal lens to observe algorithm aversion. In this paper, we empirically investigate algorithm aversion behaviour in the context of safety stock settings. We collect data from a case retail company across a range of stockkeeping units (SKUs), encompassing both pre-disruption and post-disruption time stages with varying levels of volatility. We introduce a simulation model to determine whether algorithm aversion exists for safety stock decisions and to assess how algorithm adoption and adaptation affects performance. Our findings indicate that algorithm aversion occurs during supply chain disruptions, with algorithmic decisions significantly outperforming human judgment. Based on interview results and theories of information systems, we propose a theory to explain and generalize the above findings. This theory attributes algorithm aversion behaviour to reduced sense of fitness among algorithm users and lack of slack resources for both users and developers. It also offers insights into how the adoption and adaptation of algorithms influence decision performance during disruptive events.

Frugal engineering-inspired wearable augmented reality goggle system enables fluorescence-guided cancer surgery

Disparities in surgical outcomes often result from subjective decisions dictated by surgical training, experience, and available resources. To improve outcomes, surgeons have adopted advancements in robotics, endoscopy, and intra-operative imaging including fluorescence-guided surgery (FGS), which highlights tumors and anatomy in real-time. However, technical, economic, and logistic challenges hinder widespread adoption of FGS beyond high-resource centers. To overcome these impediments, we combined laser diodes, Raspberry Pi cameras and computers, off-the-shelf optical components, and 3D-printed parts to make a battery-powered, compact, dual white light and NIR imaging system that has comparable performance to existing bulkier, pricier, and wall-powered technologies. We combined these components with off-the-shelf augmented reality (AR) glasses to create a fully-wearable fluorescence imaging AR Raspberry Pi-based goggle system (FAR-Pi) and validated performance in a pre-clinical cancer surgery model. Novel device design ensures distance-independent coalignment between real and augmented views. As an open-source, affordable, and adaptable system, FAR-Pi is poised to democratize access to FGS and improve health outcomes worldwide.

Prediction of lymphovascular invasion in invasive breast cancer based on clinical-MRI radiomics features

ObjectiveWe aim to develop a predictive model for lymphovascular invasion (LVI) in patients with invasive breast cancer (IBC), using magnetic resonance imaging (MRI)-based radiomics features.MethodsA total of 204 patients with IBC admitted to our hospital were included in this retrospective study. The data was split into training and validation sets at a 7:3 ratio. Feature normalization was conducted, followed by feature selection using ANOVA, correlation analysis, and LASSO in the training set. The final step involved building a logistic regression model. The LVI prediction models were established by single sequence image and combined different sequence images as follows: A: prediction model based on the optimal sequence in the 7-phase enhanced MRI scans; B: prediction model based on the optimal sequences in the sequences T1WI, T2WI, and DWI; and C: the combined model based on the optimal sequences selected from A and B. Subjects' work characteristic curves (ROC) and decision curves (DCA) were plotted to determine the extent to which they predicted LVI performance in the training and validation sets. Simultaneously, nomogram models were constructed by integrating radiomics features and independent risk factors. In addition, an additional 16 patients from the center between January and August 2024 were collected as the Nomogram external validation set. The ROC and DCA were used to evaluate the performance of the model.ResultsIn the enhanced images, Model A built based on the enhanced 2-phase achieved the best average AUC, with a validation set of 0.764. Model B built based on the T2WI had better results, with a validation set of 0.693. Model C built by combining enhanced 2-phase and T2WI sequences had a mean AUC of 0.705 in the validation set. In addition, the tumor size, whether the tumor boundary was clear or not, and whether there was a coelom in the tumor tissue had a statistically significant effect on the LVI of IBC, and a clinical-radiomics nomogram was established. DCAs as well as Nomogram also indicate that Model A has good clinical utility. The AUC of the nomogram in the training set, internal validation set, and external validation set were 0.703, 0.615, and 0.609, respectively. The DCA also showed that the radiomics nomogram combined with clinical factors had good predictive ability for LVI.ConclusionIn IBC, MRI radiomics can serve as a noninvasive predictor of LVI. The clinical-MRI radiomics model, as an efficient visual prognostic tool, shows promise in forecasting LVI. This highlights the significant potential of pre-radiomics prediction in enhancing treatment strategies.

Leveraging Ensemble Models and Follow-up Data for Accurate Prediction of mRS Scores from Radiomic Features of DSC-PWI Images.

Predicting long-term clinical outcomes based on the early DSC PWI MRI scan is valuable for prognostication, resource management, clinical trials, and patient expectations. Current methods require subjective decisions about which imaging features to assess and may require time-consuming postprocessing. This study's goal was to predict multilabel 90-day modified Rankin Scale (mRS) score in acute ischemic stroke patients by combining ensemble models and different configurations of radiomic features generated from Dynamic susceptibility contrast perfusion-weighted imaging. In Follow-up studies, a total of 70 acute ischemic stroke (AIS) patients underwent magnetic resonance imaging within 24hours poststroke and had a follow-up scan. In the single study, 150 DSC PWI Image scans for AIS patients. The DRF are extracted from DSC-PWI Scans. Then Lasso algorithm is applied for feature selection, then new features are generated from initial and follow-up scans. Then we applied different ensemble models to classify between three classes normal outcome (0, 1 mRS score), moderate outcome (2,3,4 mRS score), and severe outcome (5,6 mRS score). ANOVA and post-hoc Tukey HSD tests confirmed significant differences in model style performance across various studies and classification techniques. Stacking models consistently on average outperformed others, achieving an Accuracy of 0.68 ± 0.15, Precision of 0.68 ± 0.17, Recall of 0.65 ± 0.14, and F1 score of 0.63 ± 0.15 in the follow-up time study. Techniques like Bo_Smote showed significantly higher recall and F1 scores, highlighting their robustness and effectiveness in handling imbalanced data. Ensemble models, particularly Bagging and Stacking, demonstrated superior performance, achieving nearly 0.93 in Accuracy, 0.95 in Precision, 0.94 in Recall, and 0.94 in F1 metrics in follow-up conditions, significantly outperforming single models. Ensemble models based on radiomics generated from combining Initial and follow-up scans can be used to predict multilabel 90-day stroke outcomes with reduced subjectivity and user burden.