Volume 26

DOI:http://doi.org/10.65613/741826    Dr.Sophia Bertha        Professor, Ghent University Belgium Email: ：Sophia.Bertha@gmail.com Abstract: With the development of fintech and popularization of wealth management concepts, intelligent investment consultants have become important in the wealth management market, offering low – cost, efficient and personalized services. Traditional strategies rely on the “rational man” assumption, ignoring investors’ behavioral biases like loss aversion. Loss aversion, proposed in prospect theory, means investors feel more pain from losses than pleasure from equivalent gains. This bias leads to irrational decisions, affecting investment returns and service effectiveness. Therefore, exploring the optimization path of intelligent investment consultant strategies from the perspective of loss aversion is significant. This paper first combs related theories, analyzes the impact of loss aversion on decision – making and the defects of traditional strategies. Then, based on loss – aversion characteristics, it proposes targeted optimization schemes in investor portrait construction, asset allocation, risk control and investor education. Finally, it verifies the optimized strategy’s effectiveness through empirical analysis and gives relevant suggestions. The research shows that the optimized strategy can better adapt to investors’ behavior, reduce the negative impact of loss aversion, improve investment experience and returns, and enhance service competitiveness. Keywords: Loss Aversion; Intelligent Investment Consultant; Strategy Optimization; Prospect Theory; Asset Allocation 1. Introduction In recent years, driven by AI, big data, and cloud computing, the fintech industry has developed rapidly, and the wealth management market has entered a digital and intelligent era. Intelligent investment consultants, a new wealth management service model, integrate financial theory, algorithm models, and technology. They can generate personalized investment portfolios based on investors’ risk preferences, goals, and asset status, and adjust them with market changes[1]. Compared with traditional manual investment consultants, they have advantages like low threshold, low cost, high efficiency, and strong objectivity, and are widely recognized by investors. By 2025, China’s intelligent investment consultants’ asset management scale exceeded 500 billion yuan, and the number of users exceeded 100 million, showing strong momentum. However, as the market scale of intelligent investment consultants expands, problems have emerged. Traditional strategies are often based on classical financial theories assuming investors are rational. But in reality, investors are affected by behavioral biases, especially loss aversion. Kahneman and Tversky (1979) proposed the prospect theory, stating that loss aversion is common. The psychological utility loss from a loss is 2 – 2.5 times the utility gain from an equal gain. This makes investors over – emphasize loss risks and make irrational decisions, such as holding loss – making assets or selling profitable assets prematurely[2-4]. These behaviors reduce investors’ returns and the effectiveness of recommended portfolios, decreasing user trust and satisfaction. Currently, most research on intelligent investment consultants focuses on algorithm optimization, asset allocation efficiency, and service scope expansion. Few studies combine loss aversion for strategy optimization[5]. The mismatch between traditional strategies and investors’ behavioral characteristics (especially loss aversion) restricts the industry’s development. Therefore, it is necessary to study the impact of loss aversion on decision – making, find defects in traditional strategies, and propose targeted optimization schemes. This study starts from loss aversion to explore the strategy optimization path, which can enrich theories and guide the industry’s development, meet investors’ needs, and promote the healthy development of the wealth management market. 2. Theoretical Basis 2.1 Loss Aversion Theory Loss aversion, the core of prospect theory proposed by Kahneman and Tversky in 1979, is the psychological tendency where investors feel far more pain from losses than pleasure from equivalent gains. In prospect theory, they introduced the value function to describe the relationship between investors’ subjective value and gains/losses. The value function has three features: it uses a reference point as the origin, with gains and losses relative to it; it’s convex in the loss area and concave in the gain area, meaning investors are risk – averse in the gain area and risk – seeking in the loss area[6]; its slope is steeper in the loss area, showing losses have a greater impact on psychological utility. For example, losing 100 yuan causes much more pain than gaining 100 yuan, and investors usually need to gain 200 – 250 yuan to offset the pain of losing 100 yuan. Loss aversion is a common psychological phenomenon present in various investment scenarios, like in the stock market where investors often hold losing stocks for a long time and are unwilling to… Investors hold losing stocks to avoid “real” losses and sell profitable ones to lock in profits, resulting in “winning small and losing big”. In the fund market, investors panic and redeem when the net value falls, intensifying fluctuations, and redeem when it rises, missing appreciation opportunities. These are manifestations of loss aversion, affected by factors like psychological quality, investment experience, risk capacity, and market environment. Novice investors show more obvious loss aversion due to lack of experience and stronger fear of losses. Experienced investors can restrain it but can’t fully avoid its impact in extreme market fluctuations. Loss aversion affects investors’ decision – making in two ways: it makes them overly risk – averse, preferring low – risk, low – return assets and missing high – return opportunities; it also leads to irrational decisions like blind stop – loss and holding losses, reducing investment returns and even causing serious losses[7-9]. Therefore, understanding loss aversion’s characteristics and impact is the premise of optimizing the intelligent investment consultant strategy. 2.2 Intelligent Investment Consultant Intelligent investment consultant, or robo – advisor, is a financial service model using AI, big data, and algorithm models to collect and analyze investors’ information and offer personalized investment advice and asset allocation services. Its core is the algorithm model, including asset allocation, risk assessment, and market prediction models. The working process has four steps: first, collect investors’ information like risk preference, investment goal, etc.; second, assess investors’ risk – bearing capacity and needs via the risk assessment model; third, generate personalized investment portfolios with stocks, bonds, etc. according to the asset allocation model; fourth, adjust the portfolio dynamically based on market and investor needs to meet expected

DOI:http://doi.org/10.65613/742105   Elena Atanaskova-Petrov1, Associate Professor, PhD Elena Davitkovska1, Full Professor, PhD Aleksandra Angeleska1, Senior Research Associate, PhD Mirko Prodanov,Associate Professor, PhD Risto Uzunov1, Associate Professor, PhD Ss. Cyril and Methodius University in Skopje, Faculty of Veterinary Medicine – Skopje, Republic of North Macedonia Corresponding author: Risto Uzunov1, Associate professor, PhD Phone number: + 389 78 316 319; email: risteuzunov@fvm.ukim.edu.mk A short running title of maximum 4 words: AI in Small Animals Keywords: Artificial Intelligence, Small Animal Medicine, Predictive Modeling, Diagnostic Imaging, Veterinary Ethics.               THE ROLE OF ARTIFICIAL INTELLIGENCE IN SMALL ANIMAL VETERINARY MEDICINE: CURRENT APPLICATIONS AND FUTURE PERSPECTIVES Abstract Artificial Intelligence (AI) is increasingly being investigated as a tool to support diagnostics, clinical decision-making, and workflow optimization in small animal veterinary medicine. This narrative review critically summarizes current evidence on AI applications in companion animal healthcare, with a particular focus on diagnostic imaging, clinical pathology, predictive analytics, and clinical workflow optimization. Recent studies have demonstrated promising performance of deep learning models in diagnostic imaging, including automated vertebral heart scale assessment, while predictive models trained on electronic health records have identified cats at risk of chronic kidney disease up to two years before clinical diagnosis. Machine learning algorithms have also shown high diagnostic performance for canine hypoadrenocorticism, with reported sensitivity and specificity of 96.3% and 97.2%, respectively. In addition, AI-assisted clinical documentation using natural language processing and wearable sensor technologies has demonstrated potential to improve workflow efficiency and continuous patient monitoring, with selected validation studies reporting accuracies exceeding 99% for quantifying specific behaviours such as scratching. Despite these advances, current evidence remains limited by challenges related to algorithm interpretability, automation bias, heterogeneous datasets, and the absence of standardized regulatory frameworks for veterinary AI. Overall, available evidence suggests that AI represents a valuable adjunct to veterinary practice; however, its safe clinical implementation requires rigorous validation, appropriate regulatory oversight, and continued human supervision. Introduction Artificial intelligence (AI) is increasingly being explored as a tool to support data-driven diagnostics and clinical decision-making in veterinary medicine (1). Broadly defined, AI refers to computational systems designed to perform tasks that typically require human intelligence, such as visual perception, speech recognition, and complex decision-making (2,3). In the current veterinary landscape, AI has been proposed as one approach to help address modern challenges such as veterinary workforce burnout, the global shortage of diagnostic specialists, and the rising demand for high-throughput precision healthcare (3,4). To ensure scientific clarity, it is essential to distinguish between the various modalities of AI. Machine Learning (ML) is a subset of AI that employs statistical methods to enable computers to identify patterns and make decisions based on data without being explicitly programmed for specific tasks (2). Deep Learning (DL) represents a more advanced subset of ML that uses multilayer artificial neural networks to learn complex patterns from data; a prominent example in veterinary medicine is the use of Convolutional Neural Networks (CNNs) for diagnostic imaging to identify spatial hierarchies and extract features from medical images (5). Furthermore, Generative AI, such as Large Language Models (LLMs), focuses on creating new content based on trained datasets, though its clinical application requires caution due to the potential for “hallucinations” the generation of plausible but fabricated information (6,7). Similar structural vulnerabilities, including algorithm opacity and data fragmentation, have been highlighted as major integration barriers across broader food safety systems (8). AI applications in the veterinary field are generally categorized into clinical practice, biomedical research, public health, and administration (1). Within the clinical domain, published studies have demonstrated promising performance in diagnostic imaging, where DL models analyze radiographs, CT scans, and MRIs to detect abnormalities like fractures or cardiac enlargement (9). Additionally, AI-driven tools have been investigated for automated cell counting and parasite identification in veterinary clinical pathology (10,11). Beyond reactive diagnostics, predictive models are increasingly being investigated in internal medicine to forecast the risk of chronic conditions, such as feline chronic kidney disease or canine hypoadrenocorticism, before the onset of clinical symptoms (2,12). This review focuses specifically on the application of AI within small animal veterinary medicine. In many contemporary societies, the increasing “humanization” of companion animals has driven a demand for advanced digital health services that mirror human medical standards (13,14). Because companion animals cannot directly communicate subjective symptoms, AI-powered tools such as behavioral analysis and predictive risk modeling have the potential to provide objective data to improve patient outcomes (14,15). The objective of this narrative review is to critically summarize the current evidence regarding AI’s role in supporting diagnostics, patient care, and clinical workflow optimization in small animal practice while addressing the ethical and regulatory barriers to its adoption. Search Strategy and Selection Criteria This narrative review examines the current evidence regarding artificial intelligence (AI) applications in companion animal healthcare. To identify relevant literature, a structured literature search was conducted across major electronic databases, including PubMed, Google Scholar, and Web of Science, for studies published between 2016 and 2026. The search strategy utilized combinations of keywords including “artificial intelligence,” “machine learning,” “deep learning,” “small animal medicine,” “canine,” “feline,” “diagnostic imaging,” “predictive modeling,” and “veterinary ethics.” Selection criteria focused on original research, including retrospective studies and proof-of-concept investigations, to provide a critical appraisal of diagnostic performance and clinical utility. Priority was given to peer-reviewed original studies over secondary review articles to ensure the reliability of the synthesized evidence. Each cited study was critically evaluated based on its study design, sample size, reported diagnostic performance (including sensitivity and specificity where applicable), and methodological limitations.   Current Evidence in Small Animal Diagnostics The application of artificial intelligence (AI) and machine learning (ML) is being investigated as a tool to support diagnostic accuracy and reduce the subjectivity inherent in human clinical interpretation (14,15). While published studies have demonstrated that these systems can identify patterns in large datasets, it is important to note that much of the current evidence is based on retrospective investigations or proof-of-concept studies (9). Diagnostic Imaging and Cardiology In veterinary imaging, deep learning (DL) models, particularly Convolutional Neural

Zai Jhang1,a,Tie Xu2,b*   1School of Psychology,Jiangxi Normal University, Nanchang, 330022, Jiangxi, China 2School of Psychology,Jiangxi Normal University, Nanchang, 330022, Jiangxi, China aEmail: zaijhang@126.com bEmail: tiexu@jxnu.edu.cn Abstract：Bipolar disorder (BD) is a prevalent and chronic psychiatric disorder characterized by recurrent fluctuations of manic and depressive episodes, accompanied by persistent behavioral abnormalities, neurocognitive dysfunctions and social adaption disorders. Impulsive behaviors, cognitive function impairments and social function deficits are three core clinical manifestations that run through the whole course of BD, severely affecting patients’ disease prognosis, quality of life and social integration ability. This study aimed to explore the correlation mechanism among impulsive behaviors, cognitive function damage and social function deficits in BD patients, so as to provide theoretical support for clinical intervention, symptom improvement and functional rehabilitation of BD. A total of 220 patients diagnosed with BD in a tertiary psychiatric hospital from January 2023 to December 2024 were enrolled as the observation group, and 220 healthy volunteers with matched age, gender and educational level were recruited as the control group. All subjects were evaluated by Barratt Impulsiveness Scale (BIS-11), Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) and Social Disability Screening Schedule (SDSS). Statistical analysis was conducted to compare the differences of impulsivity level, cognitive function and social function between the two groups, and analyze the correlation and predictive effect among the three indicators in BD patients. The results showed that the total score and each dimension score of BIS-11 and SDSS in the observation group were significantly higher than those in the control group, while the total score and each sub-item score of RBANS were significantly lower than those in the control group (P<0.05). Correlation analysis indicated that the impulsivity level of BD patients was negatively correlated with cognitive function level, and positively correlated with social function deficit degree; cognitive function impairment was negatively correlated with social function ability (P<0.01). Regression analysis verified that impulsive behaviors and cognitive function impairment were independent predictive factors of social function deficits in BD patients. This study confirms that impulsive behaviors, cognitive impairments and social function deficits have significant interactive correlation in BD patients. Severe impulsive tendencies and progressive cognitive damage can jointly aggravate social functional disorders, which provides a new perspective for targeted clinical treatment and functional rehabilitation intervention of BD. Key words: Bipolar Disorder; Impulsive Behavior; Cognitive Impairment; Social Function Deficit; Correlation Analysis 1. Introduction 1.1 Research Background: Disease Burden and Functional Impairment of Bipolar Disorder Bipolar disorder is a severe mental disorder with high morbidity, high recurrence rate and high disability rate, ranking among the top causes of global mental disease-related disability. Epidemiological data show that the lifetime prevalence of BD in the general population is about 2.4% to 3.8%, and nearly 60% of patients will have recurrent episodes within 5 years after the first diagnosis. Different from single mood disorder, BD not only presents extreme emotional swings of mania and depression, but also accompanies multiple dimensional functional damage covering behavior, cognition and social interaction throughout the stable stage of the disease, which is the core cause of long-term social disability of patients. In recent years, with the continuous progress of psychiatric research, the clinical focus of BD has gradually shifted from single emotional symptom control to comprehensive functional rehabilitation, and the persistent subclinical functional impairment during the inter-episode stable period has become a research hotspot in the field of BD prognosis[1-3]. Impulsive behavior is one of the most prominent behavioral characteristics of BD patients. It refers to the unplanned, hasty and unregulated behavioral response without full rational thinking and risk assessment, which is extremely common in both manic episodes and stable periods of BD. Typical impulsive behaviors of BD patients include impulsive consumption, aggressive behavior, reckless driving, substance abuse and suicidal and self-injurious behaviors. Clinical studies have confirmed that the incidence of impulsive behaviors in BD patients is 3 to 5 times higher than that in healthy people, and severe impulsive behaviors are closely related to disease recurrence, adverse clinical events and poor long-term prognosis. Impulsive behavior is no longer regarded as a transient symptomatic performance of manic episodes, but a stable trait characteristic of BD patients, which runs through the whole disease course. Cognitive function impairment is another core residual symptom of BD, which exists stably in the remission stage of mood symptoms and cannot be completely improved by conventional mood-stabilizing treatment. The cognitive damage of BD mainly involves multiple core fields such as attention, memory, executive function, language comprehension and visual-spatial ability. A large number of neuropsychological studies have shown that even in the euthymic stage with normal emotional performance, BD patients still have persistent deficits in working memory, inhibitory control and decision-making ability. Cognitive dysfunction not only affects patients’ daily learning and work efficiency, but also restricts their ability of emotional regulation and behavioral control, becoming the internal neuropsychological basis of abnormal behavioral manifestations of BD[4-6]. Social function deficit is the ultimate disability manifestation of BD, which is characterized by the decline or loss of patients’ abilities in social communication, interpersonal interaction, family function, occupational performance and social role adaptation. Long-term follow-up studies have found that more than 70% of BD patients have different degrees of social adaption disorders after repeated disease episodes, and nearly 40% of patients cannot return to normal work and social life for a long time. Social functional disability is the key factor leading to the decline of patients’ quality of life and the increase of social medical burden, and improving social function has become the ultimate goal of clinical treatment and rehabilitation of BD. 1.2 Research Status: Independent Study Limitations of Three Core Symptoms At present, domestic and foreign scholars have carried out extensive research on impulsive behavior, cognitive impairment and social function deficit of BD respectively. In terms of impulsive behavior research, most studies focus on the correlation between impulsivity and disease episode type, suicidal behavior and substance abuse, confirming that high impulsivity is an important risk factor for adverse events of BD. In the field of cognitive function research,

DOI:http://doi.org/10.65613/741821 Xing Zhang1,a,Xu Liu2,b*   1School of Psychology, Jiangxi Normal University, Nanchang, 330022, Jiangxi, China 2School of Psychology,Jiangxi Normal University, Nanchang, 330022, Jiangxi, China aEmail: ilfzf@126.com bEmail: liuji-anping@jxnu.edu.cn Abstract：Sleep disorders have become a prevalent global health burden, characterized by abnormal sleep architecture and irregular sleep-wake cycles, which are closely intertwined with circadian rhythm dysfunction. Circadian rhythm disturbance, as a core pathological feature of sleep disorders, not only disrupts basic physiological homeostasis but also acts as a critical predisposing and perpetuating factor for emotional dysregulation, ultimately leading to the high comorbidity of anxiety and depression. Anxiety-depression comorbidity further exacerbates circadian misalignment and sleep deterioration, forming a self-reinforcing vicious cycle that severely impairs physical and mental health and social functioning. This study systematically explores the psychophysiological mechanisms linking circadian rhythm disturbances to anxiety-depression comorbidity in sleep disorder populations, from the perspectives of molecular genetics, neuroendocrine regulation, neural circuit dysfunction, immune-inflammatory imbalance, and psychological cognitive processing. By sorting out the bidirectional causal relationship and intermediate pathways among the three core variables, this paper clarifies the hierarchical and interactive mechanisms of physiological abnormality and psychological dysregulation. Three quantitative comparative tables are constructed to summarize core index differences, mechanism pathway correlations, and comorbidity risk factors. The findings aim to provide a theoretical basis for the precise intervention and clinical treatment of sleep disorder-related emotional comorbidities, and offer new ideas for breaking the pathological cycle of circadian disturbance, sleep dysfunction, and emotional disorders. Keywords: Sleep Disorders; Circadian Rhythm Disturbance; Anxiety-Depression Comorbidity; Psychophysiological Mechanism; Neural Regulation; Immune Homeostasis 1. Introduction 1.1 Epidemic Status of Sleep Disorders and Emotional Comorbidities With the acceleration of modern social rhythm and the diversification of lifestyle pressures, sleep disorders have evolved into one of the most common chronic health problems worldwide. Clinical epidemiological data show that more than 30% of the global population suffers from varying degrees of sleep dysfunction, including insomnia, sleep-wake phase disorder, irregular circadian sleep rhythm, and other subtypes, with a persistent upward trend in incidence year by year. Sleep is a basic physiological process essential for human physical recovery, neural repair, and emotional regulation[1-3]. Long-term abnormal sleep not only leads to daytime fatigue, cognitive decline, and physical dysfunction but also significantly increases the risk of mental and emotional disorders. Anxiety and depression are the most prevalent emotional comorbidities in patients with sleep disorders. Different from single anxiety or single depression, anxiety-depression comorbidity presents more severe clinical symptoms, longer disease course, higher recurrence rate, and poorer treatment prognosis. Clinical statistics indicate that over 60% of chronic insomnia patients have varying degrees of mixed anxiety and depressive symptoms, and nearly half of the patients with severe sleep-wake rhythm disorders eventually develop clinically diagnosed anxiety-depression comorbid disorders[4-6]. Compared with patients with simple sleep disorders or single emotional disorders, comorbid patients show more significant circadian rhythm disorders, more disordered physiological indicators, and more impaired psychological coping functions, forming a complex pathological interaction system. 1.2 Core Role of Circadian Rhythm in Sleep-Emotion Interaction Circadian rhythm is an endogenous 24-hour biological oscillation system formed by long-term biological evolution, which dominates the sleep-wake cycle, hormone secretion, neural activity, immune response, and cognitive emotional rhythm of the human body. The suprachiasmatic nucleus (SCN) of the hypothalamus is recognized as the core master clock of the human circadian system, which synchronizes peripheral tissue clocks through neural pathways and humoral regulation, maintaining the stability of the whole-body circadian homeostasis. Under normal physiological conditions, the circadian system coordinates with external environmental cues such as light and dark alternation, working and resting rules, to form a regular sleep-wake cycle and stable emotional diurnal variation[7]. Circadian rhythm disturbance is the key intermediate link connecting sleep disorders and anxiety-depression comorbidity. On the one hand, sleep disorders represented by insomnia and phase shift will directly disrupt the synchronization of the central circadian clock and peripheral clocks, leading to the disorder of core clock gene expression and abnormal rhythm of physiological indicators. On the other hand, circadian misalignment will further damage the neural circuits and endocrine pathways related to emotional regulation, reduce the body’s stress resistance and emotional regulation ability, and induce or aggravate anxiety and depressive symptoms. Existing studies have confirmed that circadian rhythm abnormality is not only a concomitant symptom of sleep and emotional disorders but also an independent risk factor for the occurrence and progression of comorbid diseases, which has a decisive impact on disease severity and prognosis[8-10]. 1.3 Research Significance and Framework of This Study At present, most existing studies focus on the simple correlation between sleep disorders and depression or sleep disorders and anxiety, while systematic elaboration on the psychophysiological mechanisms of circadian rhythm disorders participating in anxiety-depression comorbidity is insufficient. The interactive pathways of physiological regulation and psychological cognition in the comorbid process are still unclear, and there is a lack of standardized quantitative comparison of core pathological indicators. Based on the bidirectional interaction of sleep, circadian rhythm, and emotion, this study systematically analyzes the multi-dimensional psychophysiological mechanisms of circadian disturbance leading to anxiety-depression comorbidity in sleep disorder populations, sorts out the core pathways of genetic, neuroendocrine, neural circuit, immune, and psychological cognitive dysregulation, and constructs quantitative comparison tables of core indicators. The research results can make up for the deficiencies of existing theoretical research, provide targeted theoretical support for clinical precise intervention, and have important practical significance for improving the treatment effect of sleep and emotional comorbidities and reducing disease recurrence[11]. This study adopts a hierarchical and progressive research framework. First, it expounds the basic theoretical basis of circadian rhythm regulation and sleep-emotion interaction. Second, it analyzes the bidirectional causal relationship between circadian disturbance and anxiety-depression comorbidity. Third, it elaborates the core psychophysiological mechanisms from multiple dimensions. Fourth, it compares the differences of core indicators in different disease states through quantitative tables. Finally, it summarizes the pathological cycle and clinical enlightenment, realizing the organic combination of theoretical analysis and data verification. 2. Theoretical Basis of Circadian Rhythm Regulation and Sleep-Emotion Homeostasis 2.1 Composition and Regulatory Mechanism of Circadian Clock System The human circadian clock system is composed