Optimizing Psychopharmacotherapy Using Personality Biomarkers: A Seven-Factor Model Perspective

3056 Background: Non-small-cell carcinoma (NCSLC) is the most common type of early lung cancer. Early detection of NSCLC is still a diagnostic challenge. Current clinical management of patients with pulmonary nodule is inefficient and may lead to misclassification, thus increasing healthcare expenses. Further, a few previous studies showed liquid biopsy and artificial intelligence (AI) platform on computed tomography (CT) imaging contributes to early NSCLC detection. Still, there is something lacking in a precise and authorized lung nodule classifier to minimize discomfort of patients. This study aims to evaluate the possibility and effectiveness of combining circulating genetically abnormal cells (CACs) with an AI platform on CT imaging to improve the diagnostic route for NSCLC. Methods: A prospective cohort of 101 in-patients was enrolled from Sep. 1, 2020 to Jan. 15, 2021, with non-calcified pulmonary nodules, ranging from 0.5 to 3 cm in diameter, indicated by CT. The participants' pulmonary nodules will be assessed by two evaluation tools: CAC detection on full blood and AI platform on CT imaging. The diagnostic performances of the two tools were evaluated in a blinded validation study respectively and combined in an open-label retrospective analysis. Results: 68 of enrolled patients were confirmed as NSCLC by pathology. The diagnostic performance of CACs for NSCLC detection was 80.9% for sensitivity and 87.3% for positive predictive value (PPV) while overall accuracy reaches 79.2%. AI platform showed a slight disadvantage as 78.6% for PPV and 73.5% for accuracy. 9 false-negative patients on CAC results could be reversed with a combination of AI platform on CT imaging, while sensitivity rises to 94.1%. However, of 33 benign nodules patients, 8 wrong diagnoses by CAC detection could decrease to 2 when combined with the results from the AI platform, which may avoid unnecessary biopsies. Conclusions: Coupling CAC with an AI platform on CT imaging could be a useful strategy to improve the diagnostic route for NSCLC and avoid unnecessary biopsies.[Table: see text]

ABSTRACTAcademic SummaryBy integrating artificial intelligence (AI) platforms into their processes, firms aim to enhance their strategic capabilities and gain a competitive advantage. This study investigates the impact of such platforms on value generation within solution‐based strategies, proposing two connected mechanisms. First, AI platforms foster collaborative value systems between firms and value‐chain agents across the stages of the solution delivery process (i.e., problem identification, solution development, and solution implementation). Second, such cooperation could foster the development of situating capabilities (i.e., grounding, bounding, and recasting), which are conceptually linked to the mitigation of situated agency constraints that stifle value creation within productive systems. These relationships underscore the value generation potential of AI platforms for solution providers, extending the premise of situated AI capabilities to the organizational and inter‐organizational level. Data collected from 570 Spanish manufacturing firms in 2023 reveals that firms utilizing AI platforms exhibit greater cooperative and situating capability‐building behavior during the problem identification and solution implementation stages. However, no significant association is found between AI platforms and the more creative stage of solution development. The study provides novel insights into the interplay between AI platforms, user cooperation, situated agency, and strategic capabilities as drivers of value generation and advancement of the AI‐dominated paradigm. Theoretical and practical implications are discussed.Managerial SummaryThis study highlights the strategic role of AI platforms in enhancing collaboration between manufacturers and solution seekers throughout the solution delivery process. AI technologies facilitate collective learning, adaptation, and knowledge sharing, particularly during the diagnostic and implementation stages, where real‐time data processing and predictive analytics help tailor solutions to user‐specific challenges. This more effective coordination is essential for mitigating agency problems that arise due to asymmetric information or misaligned objectives within complex solution systems. However, the findings reveal that AI's influence is limited in the co‐creation of solution design and development, which relies heavily on human insight, creativity, and contextual judgment. Managers should therefore not view AI as a substitute for human input, but rather as a complementary tool that enhances efficacy and integration. For firms seeking to strengthen their solution‐oriented strategies, the key takeaway is that maintaining a balanced approach—combining AI‐enabled collaboration with human ingenuity—will improve solution outcomes and sustain competitive advantage in markets increasingly shaped by personalization and customer‐specific problem solving.

Background Atrial fibrillation (AF) is commonly reported in the general population and is associated with significant mortality and morbidity. While easy to use smartphone-based portable devices exist to record 1-lead ECG, the ability of commercially available software to automatically detect AF using those devices remains limited with poor positive predictive value (PPV). Purpose We aimed to conduct an external validation of an existing cloud-based deep learning platform for the automatic detection of AF in a large cohort of patients with 1-lead ECG records. Methods 8,528 patients with 1-lead 30 seconds ECGs from an handheld device originating from a Cardiology Challenge were included in this study. Ground truth for the presence or absence of AF was obtained from the challenge labeling process including both a benchmark algorithm and manual labeling by experts. The could-based Artificial Intelligence (AI) platform, whose deep learning algorithms were not trained with ECGs recorded by this type of handheld devices, was used to automatically detect cardiac arrhythmias including AF. Additional reading was conducted by a cardiology experts committee to review false positive (FP) and false negative (FN) cases. Performance metrics including sensitivity, specificity, accuracy, F1-score, PPV, and negative predictive value (NPV) for AF classification were computed considering AI’s AF detection with standalone cloud-based AI software as a medical device (SaMD) versus challenge expert labeling or additional expert committee labeling. Results The AI platform achieved an accuracy of 96.1% and 96.4%, a sensitivity of 83.3% and 84.2%, a specificity of 97.3% and 97.6%, and a F1-score of 79.0% and 80.9%, when considering the initial challenge labels and additional expert review as the ground truth, respectively (Table 1, Figure 1). PPV was reported as 75.2% and 78.0% and NPV as 98.4% and 98.4%, largely exceeding previously reported metrics using commercial software to detect AF from same 1-lead ECG records. In addition to AF, the AI platform automatically detected other arrhythmias present on those ECG records such as different types of premature ventricular complexes (PVCs) or premature atrial complexes (PACs) along with 1-degree atrioventricular block. Conclusion The results of this external validation indicate that the existing AI platform could achieve cardiologist-level accuracy in detecting AF from 1-lead ECG records. Single-channel portable ECG devices coupled with cloud-based and device agnostic deep learning platforms are therefore promising tools for AF screening. Such an AI platform could facilitate and standardize remote AF. It has the potential to improve accuracy in non-cardiology expert healthcare professional interpretation and trigger further tests for effective patient management. Further health economic and outcomes research is necessary to evaluate the impact on healthcare providers and payers of the presented AI solution.Table 1:AI platform AF classification Figure 1:AI classification of ECGs

Deep learning-based platform performs high detection sensitivity of intracranial aneurysms in 3D brain TOF-MRA: An external clinical validation study

BackgroundThere has been a resurgence of Artificial Intelligence (AI) on a global scale in recent times, resulting in the development of cutting-edge AI solutions within hospitals. However, this has also led to the creation of isolated AI solutions that are not integrated into clinical IT. To tackle this issue, a clinical Artificial Intelligence (AI) platform that handles the entire development cycle of clinical AI models and is integrated into clinical IT is required. This research investigates the integration of a clinical AI platform into the clinical IT infrastructure. This is demonstrated by outlining the stages of the AI model development cycle within the clinical IT infrastructure, illustrating the interaction between different IT system landscapes within the hospital with BPMN diagrams.MethodsInitially, a thorough analysis of the requirements is conducted to refine the necessary aspects of the clinical AI platform with consideration of the individual aspects of clinical IT. Subsequently, processes representing the entire development cycle of an AI model are identified. To facilitate the architecture of the AI platform, BPMN diagrams of all the identified processes are created. Clinical use cases are used to evaluate the processes using the FEDS framework.ResultsOur BPMN process diagrams cover the entire development cycle of a clinical AI model within the clinical IT. The processes involved are Data Selection, Data Annotation, On-site Training and Testing, and Inference, with distinctions between (Semi-Automated) Batch Inference and Real-Time Inference. Three clinical use cases were assessed to evaluate the processes and demonstrate that this approach covers a wide range of clinical AI use cases.ConclusionsThe evaluations were executed successfully, which indicate the comprehensive nature of our approach. The results have shown that different clinical AI use cases are covered by the BPMN diagrams. Our clinical AI platform is ideally suited for the local development of AI models within clinical IT. This approach provides a basis for further developments, e.g., enabling the training and deployment of an AI model across multiple sites or the integration of security- and privacy-related aspects.

The issues investigated in this research include the accuracy of artificial intelligence (AI) scoring of essay answers, the challenges of validity and fairness in automated scoring, as well as potential biases in the algorithms used, and how these affect academic assessment results compared to human scoring. The method used in this study consists of several systematic steps. First, data was collected by asking relevant questions to an artificial intelligence (AI) platform. After that, the questions are inputted into AI platforms such as Copilot, Gemini, and Blackbox AI. Next, the resulting answers are analyzed using machine learning algorithms and natural language processing (NLP) to ensure the quality and depth of analysis. The answer results are then tested to evaluate their accuracy and relevance to the context of the question asked. the analysis results are visualized in the form of graphs or tables. this research shows that artificial intelligence (AI) has great potential in the automated assessment of essay answers. The results showed that Copilot got the highest score of 63.4%, Gemini 50.5% and Blackbox.AI 56.9%. However, the answer accuracy results between each AI Platform are still below 70%, meaning that the answers from the AI platform are still far from expectations. The next research recommendation is to retest the AI Platform using other methods to get accurate and consistent results.

Deep Learning-Based Cataract Detection and Grading from Slit-Lamp and Retro-Illumination Photographs: Model Development and Validation Study.

Artificial Intelligence Platforms – A New Research Agenda for Digital Platform Economy

BackgroundSimulation-based learning (SBL) has become standard practice in educating health care professionals to apply their knowledge and skills in patient care. While SBL has demonstrated its value in education, many educators find the process of developing new, unique scenarios to be time-intensive, creating limits to the variety of issues students may experience within educational settings. Generative artificial intelligence (AI) platforms, such as ChatGPT (OpenAI), have emerged as a potential tool for developing simulation case studies more efficiently, though little is known about the performance of AI in generating high-quality case studies for interprofessional education.ObjectiveThis study aimed to generate geriatric case scenarios across 5 AI platforms by a transdisciplinary team and systematically evaluate them for quality, accuracy, and bias.MethodsTen geriatric case studies were generated using the same prompt from 5 different generative AI platforms (N=50): ChatGPT, Claude (Anthropic AI), Copilot (Microsoft), Gemini (Google), and Grok (xAI). An evaluation tool was developed to collect evaluative data to assess the content and quality of each case, sociodemographic data of the featured patient, the appropriateness of each case for interprofessional education, and potential bias. Case quality was evaluated using the Simulation Scenario Evaluation Tool (SSET). Each case was evaluated by 3 team members who had experience in SBL education. Assessment scores were averaged, and qualitative responses were extracted to triangulate patterns found in the quantitative data.ResultsWhile each AI platform was able to generate 10 unique case studies, the quality of studies varied within and across platforms. Generally, evaluators felt that the content in the cases was accurate, though some cases were not realistic. Some patient populations and common conditions among older adults were underrepresented or absent across the cases. All cases were set within traditional health care settings (eg, hospitals and routine medical visits). No cases featured home-based care. Based on the average SSET scores, reviewers assessed ChatGPT to be the highest overall performer (mean 3.27, SD 0.45, 95% CI 2.95-3.59) while Grok received the lowest scores (mean 1.61, SD 1.26, 95% CI 0.71-2.51). Platforms performed best at generating learning objectives (mean 3.35, SD 1.08, 95% CI 3.04-3.65) and lowest on their ability to describe supplies and materials that may be available in hypothetical scenarios (mean 1.27, SD 0.84, 95% CI 1.03-1.51).ConclusionsThis study is the first to systematically evaluate and compare multiple generative AI platforms for case study generation using a validated assessment tool (SSET) and provides evidence-based guidance on selecting and using AI tools effectively. The findings offer practical direction for educators navigating available generative AI tools to enhance training for health care professionals, including specific strategies for prompt engineering that can improve the quality of SBL resources in interprofessional education. These insights enable educators to leverage AI capabilities while maintaining pedagogical rigor.

Deep Learning-Based Cataract Detection and Grading from Slit-Lamp and Retro-Illumination Photographs: Model Development and Validation Study

Health information is highly accessible with the prominence of artificial intelligence (AI) platforms, such as Chat Generative Pre-Trained Transformer (ChatGPT). Within the context of human immunodeficiency virus (HIV), it is paramount to understand and evaluate the information being provided by AI platforms concerning the safety, side effects, and efficacy of medications to prevent and treat HIV. Prompts (n = 38) requesting information regarding HIV medication use for prevention and treatment were inputted into three AI-based Large Language Models (LLMs; ChatGPT 3.5, ChatGPT 4.0, Google Bard [now Gemini]) and one chatbot (HIV.gov Chatbot) on four consecutive weeks. Outputs (n = 608) were recorded verbatim, weekly by platform. Qualitative analyses using a conventional content analysis coding approach examined key themes in responses; response comprehensiveness was rated via the number of themes represented in a response. Core themes emerged across prompts. A recommendation to speak with a medical professional for further information was the most common theme across platforms. Organ/bone side effects were the most prevalent side effect. Responses pointed to medication efficacy to prevent and treat HIV. ChatGPT 4.0 provided the most comprehensive responses across platforms, while the HIV.gov Chatbot gave the least comprehensive information. Health information on HIV medication safety, side effects, and efficacy is widely available using AI platforms. Results indicate that AI responses typically included recommendations to consult a medical professional to personalize care. The efficacy of medications was never questioned across AI platforms. Future research directions for AI use within the context of HIV prevention and care are provided.

Modern artificial intelligence (AI) platforms have a significant impact on education, they are becoming a full-fledged professional activity tool capable of optimizing learning processes and educational administration. The introduction of AI in the field of education is aimed at improving efficiency, personalizing approaches and automating routine tasks. The subject of this study is the use of AI platforms in education, their impact on the quality of services provided and the effectiveness of educational processes in the context of platform integration. In the educational field, AI platforms are being considered, including adaptive learning platforms Knewton, DreamBox Learning, Civitas Learning, IBM Watson Education, proctoring platforms ProctorU, ExamSoft, Turnitin writing quality control platforms, Grammarly, Edsight and Automated Essay Scoring creative work assessment platforms. As part of the research, data from an online survey of Russian experts representing universities from 8 federal districts and having experience working with these AI platforms is being processed. A comparative analysis method is used that identifies common and distinctive features of AI platforms based on special criteria, the integral assessment of which underlies the ranking of platforms. The scientific novelty of this study lies in a comprehensive analysis of the use of AI platforms in such a socially significant field as education. Unlike the systemic approaches of S.M. Kashchuk or B. Omodan, the study covers special issues of automated decision-making and evaluation of its effectiveness in real conditions. An important contribution of this study is the analysis of the mechanisms of AI adaptation to the individual needs of users, which is a key factor in the successful platform integration of these technologies. An expert survey based on the analysis of such special criteria as adaptability, interactivity, functionality, efficiency, accessibility, integration and innovation on a scale of "low -moderate – medium – high" allows for an integrated multi-criteria assessment of platforms based on the totality of all criteria, to build a platform rating, to identify the most promising AI platforms (in terms of interactivity and innovation – DreamBox Learning, in terms of adaptability and functionality – Knewton), as well as identify ways to overcome their limitations.

This research analyzes the use of AI (Artificial Intelligence) platform as a learning media for Mathematics and Natural Sciences Education students at Palangka Raya University. As technology develops, AI is often used in higher education as a system that mimics human intelligence. Various AI platforms have diverse functions that support student learning activities. The research method used descriptive qualitative with data collection through questionnaires on Google Form. The results show that students actively use AI, with ChatGPT being the most frequently used. AI makes it easier for students to obtain information quickly, makes the learning process more effective, and learning more interesting. However, there are risks of AI dependency and data inaccuracy. This research also describes the utilization of AI to contribute to improving the quality of learning for MIPA Education students at Palangka Raya University.

OBJECTIVE: This study aims to assess the accuracy and clinical utility of artificial intelligence (AI) platforms in responding to questions related to penile fracture, a rare but urgent urological emergency. MATERIAL and METHODS: Twenty-five questions addressing key clinical aspects of penile fracture were submitted to four AI platforms: ChatGPT, Copilot, Gemini, and Perplexity. Two expert urologists evaluated each response across five domains –relevance, clarity, structure, utility, and factual accuracy– using a 5-point Likert scale. Inter-rater reliability was assessed using the intraclass correlation coefficient (ICC), and statistical comparisons were made using one-way ANOVA and Tukey’s post-hoc tests. RESULTS: Copilot and ChatGPT scored highest overall, with mean scores of 4.90 and 4.89 respectively, while Perplexity scored significantly lower (4.68; p <0.001). Copilot also achieved the highest ratings in clarity and factual accuracy. Inter-rater reliability was high, and dimensional analysis confirmed the consistent superiority of Copilot and ChatGPT in clinical relevance and clarity. CONCLUSION: While AI platforms –especially Copilot and ChatGPT– show promise in generating medically relevant content about penile fracture, limitations in factual accuracy and clinical specificity remain. Caution is advised in using these tools in urgent care settings without professional oversight. Keywords: artificial intelligence, clinical accuracy, emergency medicine, large language models, penile fracture, urology

Background: The introduction of direct oral anticoagulants (DOACs), while reducing the need for monitoring, have also placed pressure on patients to self-manage. Suboptimal adherence goes undetected as routine laboratory tests are not reliable indicators of adherence, placing patients at increased risk of stroke and bleeding.