The Extent to Which Artificial Intelligence Can Help Fulfill Metastatic Breast Cancer Patient Healthcare Needs: A Mixed-Methods Study

Current Oncology, Journal Year: 2025, Volume and Issue: 32(3), P. 145 - 145

Published: March 2, 2025

The Artificial Intelligence Patient Librarian (AIPL) was designed to meet the psychosocial and supportive care needs of Metastatic Breast Cancer (MBC) patients with HR+/HER2− subtypes. AIPL provides conversational patient education, answers user questions, offers tailored online resource recommendations. This study, conducted in three phases, assessed AIPL’s impact on patients’ ability manage their advanced disease. In Phase 1, educational content adapted for chatbot delivery, over 100 credible resources were annotated using a Convolutional Neural Network (CNN) drive 2 involved 42 participants who completed pre- post-surveys after two weeks. surveys measured activation Activation Measure (PAM) tool evaluated experience System Usability Scale (SUS). 3 included focus groups explore experiences depth. Of participants, 36 10 participating groups. Most aged 40–64. PAM scores showed no significant differences between pre-survey (mean = 59.33, SD 5.19) post-survey 59.22, 6.16), while SUS indicated good usability. Thematic analysis revealed four key themes: basic wellness health guidance, limited support managing relationships, condition-specific medical information, is unable offer hope patients. Despite showing PAM, possibly due high baseline activation, demonstrated usability met information needs, particularly newly diagnosed MBC Future iterations will incorporate large language model (LLM) provide more comprehensive personalized assistance.

Language: Английский

---

Sentiment Analysis of Short Texts Using SVMs and VSMs-Based Multiclass Semantic Classification

Applied Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(1)

Published: March 14, 2024

In our approach, a hybrid machine learning model is proposed which uses Enhanced Vector Space Model (EVSM) along with Hybrid Support Machine (HSVM) classifier. Initially the social media-based information retrieved using (EVSM). EVSMs are employed in order to characterize text content by mapping them into high-dimensional vector spaces, capturing relationships between words and their contextual meanings. Rigorous feature selection methods designate texts for review, multiclass semantic classification algorithm, specifically HSVM classifier, utilized categorization. Decision tree algorithm used SVM refine process. To enhance sentiment analysis accuracy, dictionaries not only presented but also extended through expansion of Stanford's GloVE tool. precision, work introduces weight-enhancing processing renowned weights. Sentiments classified positive, negative, neutral categories. Notably, achieved results demonstrate improved attributed incorporation an emotional enhancement factor determining weights leveraging word availability. The accuracy obtained be 92.78% 91.33% positive rate 97.32% negative rate.

Language: Английский

---

AI based medical imagery diagnosis for COVID-19 disease examination and remedy

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 10, 2025

Abstract COVID-19, caused by the SARS-CoV-2 coronavirus, has spread to more than 200 countries, affecting millions, costing billions, and claiming nearly 2 million lives since late 2019. This highly contagious disease can easily overwhelm healthcare systems if not managed promptly. The current diagnostic method, Molecular diagnosis, is slow low sensitivity. CXR, an initial imaging tool, provides rapid results, but less sensitive compared CT scans. article focuses on using AI for two main objectives: classifying severity of COVID-19 determining appropriate treatment. Highlights key factors in diagnosis treatment addressing questions such as: 1. For innate immunity important or acquired immunity? 2. Is disorder Acute Respiratory Distress Syndrome(ARDS)? 3. cross mortality due aging dangerous COVID-19? 4. a seasonal deficiency vitamin D winter? 5. it better treat as epidemic pandemic?

Language: Английский

---

Multimodal marvels of deep learning in medical diagnosis using image, speech, and text: A comprehensive review of COVID-19 detection

AI Open, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

The Future of Virology Diagnostics Using Wearable Devices Driven by Artificial Intelligence

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 473 - 504

Published: Jan. 10, 2025

The utilization of the wearable devices (WDs) that are enhanced by artificial intelligence (AI) can have a notable potential in healthcare. This chapter aimed to provide an overview applications AI-driven WDs enhancing early detection and management virus infections. First, we presented examples highlight capabilities very monitoring infections such as COVID-19. In addition, provided on utility machine learning algorithms analyze large data for signs We also overviewed enable real-time surveillance effective outbreak management. showed how this be achieved via collection analysis diverse WDs' across various populations. Finally, discussed challenges ethical issues comes with virology diagnostics, including concerns about privacy security well issue equitable access.

Language: Английский

---

Advancements and challenges in CT image segmentation for COVID-19 diagnosis through augmented and virtual Reality: A systematic review and future perspectives

Journal of Radiation Research and Applied Sciences, Journal Year: 2025, Volume and Issue: 18(2), P. 101374 - 101374

Published: March 23, 2025

Language: Английский

---

Use machine learning to predict bone metastasis of esophageal cancer: A population-based study

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: April 1, 2025

Objective The objective of this study is to develop a machine learning (ML)-based predictive model for bone metastasis (BM) in esophageal cancer (EC) patients. Methods This utilized data from the Surveillance, Epidemiology, and End Results database spanning 2010 2020 analyze EC A total 21,032 confirmed cases were included study. Through univariate multivariate logistic regression (LR) analysis, 10 indicators associated with risk BM identified. These factors incorporated into seven different ML classifiers establish models. performance these models was assessed compared using various metrics including area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F-score, precision, decision analysis. Factors such as age, gender, histological type, T stage, N surgical intervention, chemotherapy, presence brain, lung, liver metastases identified independent Among developed, based on LR algorithm demonstrated excellent internal validation set. AUC, specificity 0.831, 0.721, 0.787, 0.717, respectively. Conclusion We have successfully developed an online calculator utilizing assist clinicians accurately assessing patients EC. tool demonstrates high accuracy thereby enhancing development personalized treatment plans.

Language: Английский

---

Using an app for COVID-19 contact tracing costs less per person traced than manual tracing: microcosting analysis of a randomised trial in Cameroon

BMJ Public Health, Journal Year: 2025, Volume and Issue: 2(Suppl 1), P. e001064 - e001064

Published: Jan. 1, 2025

Introduction SARS-CoV-2 contact tracing in Cameroon has been done manually using paper forms and phone calls. However, there were reports of inaccurate details, resulting delays identifying testing contacts. A recently introduced digital contact-tracing module the Mamal Pro app automatically sends SMS messages to notify all reported contacts district unit. We assessed total costs, cost per reached, tested found SARS-CoV-2-positive for both manual (standard care, SOC) app-based (intervention, ITV) approaches. Methods cluster randomised trial comparing SOC ITV was implemented across eight health districts between October 2022 March 2023. The calculated by dividing each approach number SARS-CoV-2-positive, respectively. also estimated minimum that need be maximum order equal SOC’s contact. Results In SOC, 849 identified, 463, 123 5 ITV, 854 801, 182 4 reached US$70, US$262 US$6437. US$48, US$210 US$9573. needs find 6 US$25 748, Conclusion Using increased clients’ reduced tested. Trial registration NCT05684887 .

Language: Английский

---

Interpretable artificial intelligence (AI) for cervical cancer risk analysis leveraging stacking ensemble and expert knowledge

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: March 1, 2025

Objectives This study develops a machine learning (ML)-based cervical cancer prediction system emphasizing explainability. A hybrid feature selection method is proposed to enhance predictive accuracy and stability, alongside evaluation of multiple classification algorithms. The integration explainable artificial intelligence (XAI) techniques ensures transparency interpretability in model decisions. Methods approach combining correlation-based recursive elimination introduced. An ensemble integrating random forest, extreme gradient boosting, logistic regression compared against eight classical ML Generative methods, such as variational autoencoders generative teaching networks, were evaluated but showed suboptimal performance. research integrates global local XAI techniques, including individual contributions tree-based explanations, interpret effects data balancing on performance are examined stabilize precision, recall, F1 scores. Classical models without preprocessing achieve 95-96% exhibit instability. Results strategies significantly creating robust model. achieves 98% with an area under the curve 99.50%, outperforming other models. Domain experts validate critical contributing features, confirming practical relevance. Incorporating domain knowledge increases transparency, making predictions interpretable trustworthy for clinical use. Conclusion Hybrid combined substantially improves reliability. supporting trustworthiness, demonstrating significant potential decision-making.

Language: Английский

---

Comprehensive lifecycle quality control of medical data - automated monitoring and feedback mechanisms based on artificial intelligence

Technology and Health Care, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Background Digital healthcare's advance has underscored an urgent requirement for solid medical record quality control, critical data integrity, surpassing manual methods’ inadequacies. Objective The goal was to develop AI system manage control comprehensively, using advanced like reinforcement learning and NLP boost management's precision efficiency. Methods This uses a closed-loop framework real-time review natural language processing techniques learning, synchronized with the hospital information system. It features layer monitoring, service analysis, presentation user engagement. Its impact evaluated by comparing metrics pre- post-deployment. Results With system, became fully operational, times per plummeting from 4200 s 2 s. share of Grade A records rose 89.43% 99.21%, markedly minimized formal substantive errors, enhancing completeness accuracy. implementation artificial intelligence-based optimizes process, dynamically regulates diagnostic behavior staff, promotes standardization normalization clinical writing. Conclusions AI-driven significantly upgraded management in terms efficiency provides scalable approach hospitals refine propelling healthcare towards heightened intelligence automation, foreshadowing AI's pivotal role future management.

Language: Английский

---