Frontiers in Artificial Intelligence最新文献

The use of Financial Technology (Fintech) has been proposed as a promising way to bridge the gender gap, both financially and socially. However, there is evidence that Fintech is far from achieving this objective, and that women's perceptions of Fintech usages are not clear. Therefore, the main objective of the this study is to segment women's perceptions toward Fintech tools and interpret these segments using machine learning methods. Two primary segments of women were produced, namely a "Fintech-friendly" group and a "Fintech-sceptical" group. The importance and reasonings behind the aforementioned segmentation are then examined. The most prominent factors affecting a woman being in the "Fintech-friendly" group are the perceived benefits of Fintech tools compared to the traditional ones, such as ease of usage, time-space convenience, and its advantageous nature. Finally, for Fintech stakeholders, implications for usability, ease, Fintech education, and tailored experiences may be advantageous approaches.

The ability to accurately predict the yields of different crop genotypes in response to weather variability is crucial for developing climate resilient crop cultivars. Genotype-environment interactions introduce large variations in crop-climate responses, and are hard to factor in to breeding programs. Data-driven approaches, particularly those based on machine learning, can help guide breeding efforts by factoring in genotype-environment interactions when making yield predictions. Using a new yield dataset containing 93,028 records of soybean hybrids across 159 locations, 28 states, and 13 years, with 5,838 distinct genotypes and daily weather data over a 214-day growing season, we developed two convolutional neural network (CNN) models: one that integrates CNN and fully-connected neural networks (CNN model), and another that incorporates a long short-term memory (LSTM) layer after the CNN component (CNN-LSTM model). By applying the Generalized Ensemble Method (GEM), we combined the CNN-based models and optimized their weights to improve overall predictive performance. The dataset provided unique genotype information on seeds, enabling an investigation into the potential of planting different genotypes based on weather variables. We employed the proposed GEM model to identify the best-performing genotypes across various locations and weather conditions, making yield predictions for all potential genotypes in each specific setting. To assess the performance of the GEM model, we evaluated it on unseen genotype-location combinations, simulating real-world scenarios where new genotypes are introduced. By combining the base models, the GEM ensemble approach provided much better prediction accuracy compared to using the CNN-LSTM model alone and slightly better accuracy than the CNN model, as measured by both RMSE and MAE on the validation and test sets. The proposed data-driven approach can be valuable for genotype selection in scenarios with limited testing years. In addition, we explored the impact of incorporating state-level soil data alongside the weather, location, genotype and year variables. Due to data constraints, including the absence of latitude and longitude details, we used uniform soil variables for all locations within the same state. This limitation restricted our spatial information to state-level knowledge. Our findings suggested that integrating state-level soil variables did not substantially enhance the predictive capabilities of the models. We also performed a feature importance analysis using RMSE change to identify crucial predictors. Location showed the highest RMSE change, followed by genotype and year. Among weather variables, maximum direct normal irradiance (MDNI) and average precipitation (AP) displayed higher RMSE changes, indicating their importance.

The COVID-19 pandemic marked a before and after in the business world, causing a growing demand for applications that streamline operations, reduce delivery times and costs, and improve the quality of products. In this context, artificial intelligence (AI) has taken a relevant role in improving these processes, since it incorporates mathematical models that allow analyzing the logical structure of the systems to detect and reduce errors or failures in real-time. This study aimed to determine the most relevant aspects to be considered for detecting software defects using AI. The methodology used was qualitative, with an exploratory, descriptive, and non-experimental approach. The technique involved a documentary review of 79 bibliometric references. The most relevant finding was the use of regression testing techniques and automated log files, in machine learning (ML) and robotic process automation (RPA) environments. These techniques help reduce the time required to identify failures, thereby enhancing efficiency and effectiveness in the lifecycle of applications. In conclusion, companies that incorporate AI algorithms will be able to include an agile model in their lifecycle, as they will reduce the rate of failures, errors, and breakdowns allowing cost savings, and ensuring quality.

In response to the increasing significance of artificial intelligence (AI) in healthcare, there has been increased attention - including a Presidential executive order to create an AI Safety Institute - to the potential threats posed by AI. While much attention has been given to the conventional risks AI poses to cybersecurity, and critical infrastructure, here we provide an overview of some unique challenges of AI for the medical community. Above and beyond obvious concerns about vetting algorithms that impact patient care, there are additional subtle yet equally important things to consider: the potential harm AI poses to its own integrity and the broader medical information ecosystem. Recognizing the role of healthcare professionals as both consumers and contributors to AI training data, this article advocates for a proactive approach in understanding and shaping the data that underpins AI systems, emphasizing the need for informed engagement to maximize the benefits of AI while mitigating the risks.

Introduction: This research aims to explore the growing field of frugal innovation within the business environment, particularly its intersection with sustainability and artificial intelligence.

Methods: Through a comprehensive literature review, the study analyzes key research trends and methodologies from 420 scholarly articles published between 2012 and August 2024. A bibliometric review traces the evolution of frugal innovation, while a content analysis provides insights into its practical applications across various industries, especially in resource-constrained settings.

Results: The findings highlight the significant role of frugal innovation in addressing global challenges, such as reducing environmental impact and promoting social inclusion, especially through the adoption of cleaner technologies and socially responsible business practices. The study also emphasizes the transformative potential of AI in enhancing the scalability and efficiency of frugal solutions.

Discussion: This research contributes to the ongoing conversation on sustainable development by identifying knowledge gaps and proposing future strategies for leveraging frugal innovation to drive inclusive growth. The implications of this research are valuable for academics, practitioners, and policymakers aiming to foster sustainable innovation in diverse socio-economic contexts.

We study a contextual bandit setting where the agent has access to causal side information, in addition to the ability to perform multiple targeted experiments corresponding to potentially different context-action pairs-simultaneously in one-shot within a budget. This new formalism provides a natural model for several real-world scenarios where parallel targeted experiments can be conducted and where some domain knowledge of causal relationships is available. We propose a new algorithm that utilizes a novel entropy-like measure that we introduce. We perform several experiments, both using purely synthetic data and using a real-world dataset. In addition, we study sensitivity of our algorithm's performance to various aspects of the problem setting. The results show that our algorithm performs better than baselines in all of the experiments. We also show that the algorithm is sound; that is, as budget increases, the learned policy eventually converges to an optimal policy. Further, we theoretically bound our algorithm's regret under additional assumptions. Finally, we provide ways to achieve two popular notions of fairness, namely counterfactual fairness and demographic parity, with our algorithm.

Introduction: It is not uncommon to repurpose administrative food data to create food environment datasets in the health department and research settings; however, the available administrative data are rarely categorized in a way that supports meaningful insight or action, and ground-truthing or manually reviewing an entire city or neighborhood is rate-limiting to essential operations and analysis. We show that such categorizations should be viewed as a classification problem well addressed by recent advances in natural language processing and deep learning-with the advent of large language models (LLMs).

Methods: To demonstrate how to automate the process of categorizing food stores, we use the foundation model BERT to give a first approximation to such categorizations: a best guess by store name. First, 10 food retail classes were developed to comprehensively categorize food store types from a public health perspective.

Results: Based on this rubric, the model was tuned and evaluated (F1_micro = 0.710, F1_macro = 0.709) on an extensive storefront directory of New York City. Second, the model was applied to infer insights from a large, unlabeled dataset using store names alone, aiming to replicate known temporospatial patterns. Finally, a complimentary application of the model as a data quality enhancement tool was demonstrated on a secondary, pre-labeled restaurant dataset.

Discussion: This novel application of an LLM to the enumeration of the food environment allowed for marked gains in efficiency compared to manual, in-person methods, addressing a known challenge to research and operations in a local health department.

Objectives: Endometrial carcinosarcoma is a rare, aggressive high-grade endometrial cancer, accounting for about 5% of all uterine cancers and 15% of deaths from uterine cancers. The treatment can be complex, and the prognosis is poor. Its increasing incidence underscores the urgent requirement for personalized approaches in managing such challenging diseases.

Method: In this work, we designed an explainable machine learning approach to predict recurrence-free survival in patients affected by endometrial carcinosarcoma. For this purpose, we exploited the predictive power of clinical and histopathological data, as well as chemotherapy and surgical information collected for a cohort of 80 patients monitored over time. Among these patients, 32.5% have experienced the appearance of a recurrence.

Results: The designed model was able to well describe the observed sequence of events, providing a reliable ranking of the survival times based on the individual risk scores, and achieving a C-index equals to 70.00% (95% CI, 59.38-84.74).

Conclusion: Accordingly, machine learning methods could support clinicians in discriminating between endometrial carcinosarcoma patients at low-risk or high-risk of recurrence, in a non-invasive and inexpensive way. To the best of our knowledge, this is the first study proposing a preliminary approach addressing this task.

Diagnostic errors pose a significant public health challenge, affecting nearly 800,000 Americans annually, with even higher rates globally. In the ICU, these errors are particularly prevalent, leading to substantial morbidity and mortality. The clinical reasoning process aims to reduce diagnostic uncertainty and establish a plausible differential diagnosis but is often hindered by cognitive load, patient complexity, and clinician burnout. These factors contribute to cognitive biases that compromise diagnostic accuracy. Emerging technologies like large language models (LLMs) offer potential solutions to enhance clinical reasoning and improve diagnostic precision. In this perspective article, we explore the roles of LLMs, such as GPT-4, in addressing diagnostic challenges in critical care settings through a case study of a critically ill patient managed with LLM assistance.