Human-centric and semantics-based explainable event detection: a survey

The rapid proliferation of artificial intelligence (AI) technologies across various industries and decision-making processes has undeniably transformed the way of approaching complex problems and tasks. AI systems have proven their prowess in areas such as healthcare, finance, and autonomous systems, revolutionizing how decisions are made. Nevertheless, this proliferation of AI has raised critical concerns regarding the transparency, accountability, and fairness of these systems, as many of the state-of-the-art AI models often resemble complex black boxes. These intricate models, particularly deep learning neural networks, harbor non-linear relationships that are difficult for human users to decipher, thereby raising concerns about bias, fairness, and overall trustworthiness in AI-driven decisions. The urgency of this issue is underscored by the realization that AI should not merely be accurate; it should also be interpretable. Explainable AI (XAI) has emerged as a vital field of research, emphasizing the development of models and techniques that render AI systems comprehensible and transparent in their decision-making processes. This paper investigates into the relevance and significance of XAI across various domains, including healthcare, finance, and autonomous systems, where the ability to understand the rationale behind AI decisions is paramount. In healthcare, where AI assists in diagnosis and treatment, the interpretability of AI models is crucial for clinicians to make informed decisions. In finance, applications like credit scoring and investment analysis demand transparent AI to ensure fairness and accountability. In the realm of autonomous systems, transparency is indispensable to guarantee safety and compliance with regulations. Moreover, government agencies in areas such as law enforcement and social services require interpretable AI to maintain ethical standards and accountability. This paper also highlights the diverse array of research efforts in the XAI domain, spanning from model-specific interpretability methods to more general approaches aimed at unveiling complex AI models. Interpretable models like decision trees and rule-based systems have gained attention for their inherent transparency, while integrating explanation layers into deep neural networks strives to balance accuracy with interpretability. The study emphasizes the significance of this burgeoning field in bridging the gap between AI's advanced capabilities and human users' need for comprehensible AI systems. It seeks to contribute to this field by exploring the design, development, and practical applications of interpretable AI models and techniques, with the ultimate goal of enhancing the trust and understanding of AI-driven decisions.

The use of artificial intelligence (AI) systems is significantly increased in the past few years. AI system is expected to provide accurate predictions and it is also crucial that the decisions made by the AI systems are humanly interpretable i.e. anyone must be able to understand and comprehend the results produced by the AI system. AI systems are being implemented even for simple decision support and are easily accessible to the common man on the tip of their fingers. The increase in usage of AI has come with its own limitation, i.e. its interpretability. This work contributes towards the use of explainability methods such as local interpretable model-agnostic explanations (LIME) to interpret the results of various black box models. The conclusion is that, the bidirectional long short-term memory (LSTM) model is superior for sentiment analysis. The operations of a random forest classifier, a black box model, using explainable artificial intelligence (XAI) techniques like LIME is used in this work. The features used by the random forest model for classification are not entirely correct. The use of LIME made this possible. The proposed model can be used to enhance performance, which raises the trustworthiness and legitimacy of AI systems.

Artificial Intelligence: The Future of Maxillofacial Prognosis and Diagnosis?

Artificial Intelligence (AI) is changing the way healthcare, finance & law enforcement work by making them more efficient & creative and making it easier to make these decisions based on their information. As AI models become more complicated, their decision-making processes become less clear, which hurts trust, accountability & ethical use. Explainable AI (XAI) has come up to help with these problems by making AI systems easier to understand and more open, which helps people understand why certain actions were taken. XAI makes AI's decision-making processes easier to understand by employing these approaches including feature significance analysis, model-agnostic methodologies, interpretable models & visualization tools. These methods make sure that important tasks like medical diagnosis, approving loans & finding bias in law enforcement algorithms are all accurate, fair & easy to understand. XAI gives consumers clear, useful information that helps them make informed decisions with confidence, even if they aren't tech-savvy.  This research looks at the main ideas of XAI, including its most important methods, uses & the problems it has to solve to live up to its potential. XAI builds trust in AI systems by making AI models easier to understand. This leads to more widespread use & more responsibility in important areas. As AI becomes better, it will be important to explain things in order to deal with moral difficulties, reduce bias & make sure that people follow the rules. This will help people utilize AI technology in a more responsible & sustainable way

The framework of Input and Output Privacy aids in conceptualization of data privacy protections, providing considerations for situations where multiple parties are collaborating in a compute system (Input Privacy) as well as considerations when releasing data from a compute process (Output Privacy). Similar frameworks for conceptualization of privacy protections at a systems design level are lacking within the Artificial Intelligence space, which can lead to mischaracterizations and incorrect implementations of privacy protections. In this paper, we apply the Input and Output Privacy framework to Artificial Intelligence (AI) systems, establishing parallels between traditional data systems and newer AI systems to help privacy professionals and AI developers and deployers conceptualize and determine the places in those systems where privacy protections have the greatest effect. We discuss why the Input and Output Privacy framework is useful when evaluating privacy protections for AI systems, examine the similarities and differences of Input and Output privacy between traditional data systems and AI systems, and provide considerations on how to protect Input and Output Privacy for systems utilizing AI models. This framework offers developers and deployers of AI systems common ground for conceptualizing where and how privacy protections can be applied in their systems and for minimizing risk of misaligned implementations of privacy protection.

Adversarial attacks on artificial intelligence (AI) systems have become a growing concern in the field of cybersecurity. Such attacks are based on minor alterations in the input data that may mislead AI models and make wrong judgments, which is a serious threat to many industries, which use AI technologies, including autonomous vehicles, healthcare, and finance. The growing complexities in such attacks bring out weak points to AI systems, which poses threat to their integrity, safety and reliability. This study examines adversarial attacks and how such attacks are made and their effect on AI-based systems. The research looks at different defence strategies and their contributions towards curbing such threats. The research mentions the main issues of detecting and defending against adversarial attacks through an in-depth analysis of real-life case studies and the necessity to harness the issue with enhanced security precautions. The approach is a synthesis of case studies, simulations, and metrics of evaluation in order to understand the susceptibility of AI models. Significant details of the research include the ever-increasing mounting sophistication of attacks and the dire necessity of sturdy defense measures to secure the AI systems.

Understanding of artificial intelligence (AI) systems becomes more important as their use cases in real-world applications growth. Today’s AI systems are increasingly complex and ubiquitous. They will be responsible for making decisions that directly affect individuals. Explainable AI can potentially help by explaining actions, decisions and behaviours of AI systems to users. Our approach is to provide a tool with an interactive user interface in 3D. The tool visualizes deep learning network layers and allows interactive exploration on different levels of detail. The visualization then improves transparency and opacity of AI systems for experts and non-experts.

Artificial intelligence (AI) systems are increasingly being used in consumer as well and business applications. Companies are using them, Governments are using them, public security, medical researchers, you and I – everybody seems to be somehow touched. As it becomes more advanced and ubiquitous in our lives, it is critical that AI developers and users understand the ethical implications and challenges posed by this powerful technology. This paper explores the key ethical skills and considerations that are essential for navigating the new world of AI. Artificial Intelligence (AI) presents significant ethical dimensions across various sectors, including research, business, and daily life. It is important to appreciate the major ethical dimensions of AI and how they impact AI systems. Policies and guidelines needs to be laid out for development and usage of such systems. Automated Decisions/Responsibility: No matter how intelligent a AI system might perceived to be, it is always prone to making errors. So, AI system that make automated decisions will always be dangerous. Therefore, it is important to ensure that there is always "human intervention" or "human review" for outcomes/decisions made by AI systems. Determining accountability for AI-generated actions or content remains a significant challenge, emphasizing the need for ethical governance frameworks. There has to be human accountability.Fairness/Bias: AI systems can perpetuate existing biases present in training data, leading to discriminatory outcomes.Transparency: The opaque nature of many AI algorithms complicates accountability, making it difficult to understand decision-making processes.Privacy: AI's capability to process vast datasets can infringe on individual privacy rights, necessitating stringent data protection measuresHuman Dignity: The risk of AI-generated content resembling existing works raises ethical issues regarding originality and authorship.

Real-World Surveillance of FDA-Cleared Artificial Intelligence Models: Rationale and Logistics.

Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study

Although the categorization of ultrasound using the Breast Imaging Reporting and Data System (BI-RADS) has become widespread worldwide, the problem of inter-observer variability remains. To maintain uniformity in diagnostic accuracy, we have developed a novel artificial intelligence (AI) system in which AI can distinguish whether a static image obtained using a breast ultrasound represents BI-RADS3 or lower, or BI-RADS4a or higher, to determine the medical management that should be performed on a patient whose breast ultrasound shows abnormalities. To establish and validate the AI system, a training dataset consisting of 4,028 images containing 5,014 lesions and a test dataset consisting of 3,166 images containing 3,656 lesions were collected and annotated. We selected a setting that maximized the area under the curve (AUC) and minimized the difference in sensitivity and specificity by adjusting the internal parameters of the AI system, achieving an AUC, sensitivity, and specificity of 0.95, 90.0%, and 88.5%, respectively. Furthermore, based on 30 images extracted from the test data, the diagnostic accuracy of 20 clinicians and the AI system was compared, and the AI system was found to be significantly superior to the clinicians (McNemar test, p < 0.001). Then, we conducted a trial to introduce the system for use in clinical practice. Physicians reviewed the images and determined whether they were BI-RADS3 or lower, or BI-RADS4a or higher. Next, the classification was performed again for the same images concerning the AI diagnosis. At this time, the initial judgment was allowed to be overturned. We checked whether there was any difference in the diagnostic accuracy, sensitivity, and specificity before and after reviewing to the AI diagnosis. Reviews by 24 physicians were evaluated: 4 Japanese Breast Cancer Society breast specialists, 5 non-specialists and physicians with experience treating more than 40 cases of breast cancer, and 15 non-specialists and physicians with no experience treating more than 40 cases of breast cancer. The average rate of accuracy before confirming the AI diagnosis increased to 73.1% after confirming the AI diagnosis (p=0.00548), compared to 69.3% on average before the AI diagnosis. Compared to practice experience, the accuracy increased from an average of 77.1% to 79.6% for the 9 physicians who were breast specialists or who had treated 40 or more cases of breast cancer. For the 15 physicians with less than 40 breast cancer cases, the average rate of accuracy increased from 64.7% to 69.2%. Furthermore, sensitivity increased significantly to an average of 99.7% after reviewing of the AI diagnosis from an average of 88.8% prior to reviewing the AI-diagnosis.(p< 0.01). Specificity increased from an average of 62.4% to 63.8% (p=0.433) after reviewing AI diagnosis. We showed that our AI system, when applied to clinical practice and used by physicians, contributes to the improvement of diagnostic accuracy. Our results indicated that our AI diagnostic system was sufficiently accurate to be used in the clinical practice. Citation Format: Erina Odani, Tetsu Hayashida, masayuki kikuchi, Aiko Nagayama, tomoko seki, maiko takahashi, Akiko Matsumoto, Takeshi Murata, Rurina Watanuki, Takamichi Yokoe, Ayako Nakashoji, Hinako Maeda, Tatsuya Onishi, Sota Asaga, Takashi Hojo, Hiromitsu Jinno, Keiichi Sotome, Akira Matsui, Akihiko Suto, Shigeru Imoto, Yuko Kitagawa. Establishment of the breast ultrasound support system using deep-learning system [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P1-05-06.

We discuss how over the last 30 to 50 years, Artificial Intelligence (AI)\nsystems that focused only on data have been handicapped, and how knowledge has\nbeen critical in developing smarter, intelligent, and more effective systems.\nIn fact, the vast progress in AI can be viewed in terms of the three waves of\nAI as identified by DARPA. During the first wave, handcrafted knowledge has\nbeen at the center-piece, while during the second wave, the data-driven\napproaches supplanted knowledge. Now we see a strong role and resurgence of\nknowledge fueling major breakthroughs in the third wave of AI underpinning\nfuture intelligent systems as they attempt human-like decision making, and seek\nto become trusted assistants and companions for humans. We find a wider\navailability of knowledge created from diverse sources, using manual to\nautomated means both by repurposing as well as by extraction. Using knowledge\nwith statistical learning is becoming increasingly indispensable to help make\nAI systems more transparent and auditable. We will draw a parallel with the\nrole of knowledge and experience in human intelligence based on cognitive\nscience, and discuss emerging neuro-symbolic or hybrid AI systems in which\nknowledge is the critical enabler for combining capabilities of the\ndata-intensive statistical AI systems with those of symbolic AI systems,\nresulting in more capable AI systems that support more human-like intelligence.\n

Artificial intelligence (AI) systems powered by large language models have become increasingly prevalent in modern society, enabling a wide range of applications through natural language interaction. As AI agents proliferate in our daily lives, their generic and uniform expressiveness presents a significant limitation to their appeal and adoption. Personality expression represents a key prerequisite for creating more human-like and distinctive AI systems. We show that AI models can express deterministic and consistent personalities when instructed using established psychological frameworks, with varying degrees of accuracy depending on model capabilities. We find that more advanced models like GPT-4o and o1 demonstrate the highest accuracy in expressing specified personalities across both Big Five and Myers-Briggs assessments, and further analysis suggests that personality expression emerges from a combination of intelligence and reasoning capabilities. Our results reveal that personality expression operates through holistic reasoning rather than question-by-question optimization, with response-scale metrics showing higher variance than test-scale metrics. Furthermore, we find that model fine-tuning affects communication style independently of personality expression accuracy. These findings establish a foundation for creating AI agents with diverse and consistent personalities, which could significantly enhance human-AI interaction across applications from education to healthcare, while additionally enabling a broader range of more unique AI agents. The ability to quantitatively assess and implement personality expression in AI systems opens new avenues for research into more relatable, trustworthy, and ethically designed AI.

Background: The topic of artificial Intelligence and its application in medicine has gained tremendous popularity, coinciding with advances in its technology. Breast cancer treatments vary, with surgery being one of them. In this review, we aim to evaluate artificial Intelligence’s ability to predict surgical outcomes, complications, and survival rates after breast cancer surgery by analyzing original research conducted over the last 5 years. Materials and Methods: A PubMed search was conducted by two authors from January 1, 2020, to April 13, 2025, using the keywords "Artificial Intelligence" and "Breast Surgery". After elimination, 14 of the 215 articles were full-text screened, and nine original articles were selected for inclusion in our review. Discussion: Artificial intelligence models and systems have had a significant impact on the medical field, and breast cancer surgery is no exception. Several original research studies have explored AI's ability to predict surgical outcomes and postoperative results. In this review, we focus on the postoperative aspects of breast cancer surgery and its application of artificial intelligence. Of the nine articles included in this paper, all reported multiple statistically significant results (p <0.05). Although no prospective research directly compares artificial intelligence with practicing physicians, artificial intelligence’s ability to accurately predict surgical outcomes, complications, and survival has shown higher accuracy and c-index than commonly used prediction methods, as reported in multiple studies. Conclusion: Artificial Intelligence can be a valuable asset in helping surgeons and medical doctors worldwide predict prognosis with improved systems and accuracy rates, even surpassing those of currently used conservative systems. There is a lack of information on PubMed regarding the comparison of these two aspects, particularly with larger sample sizes. More research should be conducted on this topic, particularly in comparing Artificial Intelligence systems and models with current systems and evaluation methods.

BackgroundThe surgical difficulty of laparoscopic cholecystectomy (LC) for acute cholecystitis (AC) and the risk of bile duct injury (BDI) depend on the degree of fibrosis and scarring caused by inflammation; therefore, understanding these intraoperative findings is crucial to preventing BDI. Scarring makes it particularly difficult to perform safely and increases the BDI risk. This study aimed to develop an artificial intelligence (AI) system to indicate intraoperative findings of scarring in LC for AC.Materials and methodsAn AI system was developed to detect scarred areas using an algorithm for semantic segmentation based on deep learning. The training dataset consisted of 2025 images extracted from LC videos of 21 cases with AC. External evaluation committees (EEC) evaluated the AI system on 20 cases of untrained data from other centers. EECs evaluated the accuracy in identifying the scarred area and the usefulness of the AI system, which were assessed based on annotation and a 5-point Likert-scale questionnaire.ResultsThe average DICE coefficient for scarred areas between AI detection and EEC annotation was 0.612. The EEC’s average detection accuracy on the Likert scale was 3.98 ± 0.76. AI systems were rated as relatively useful for both clinical and educational applications.ConclusionWe developed an AI system to detect scarred areas in LC for AC. Since scarring increases the surgical difficulty, this AI system has the potential to reduce BDI.