MRI-based artificial intelligence models for post-neoadjuvant surgery personalization in breast cancer: a narrative review of evidence from Western Pacific DOI Creative Commons

Yingyi Lin,

Minyi Cheng,

Cangui Wu

и другие.

The Lancet Regional Health - Western Pacific, Год журнала: 2024, Номер 57, С. 101254 - 101254

Опубликована: Дек. 6, 2024

Breast magnetic resonance imaging (MRI) is the most sensitive method for diagnosing breast cancer and assessing treatment response. Artificial intelligence (AI) radiomics offer new opportunities to identify patterns in data, supporting personalized post-neoadjuvant surgical decisions. This paper reviewed MRI-based AI models predicting outcomes after neoadjuvant therapy, with a focus on evidence from Western Pacific region, evaluate quality of existing models, discuss their inherent limitations, outline potential future directions. A literature search MEDLINE, EMBASE, Web Science identified 51 relevant studies majority conducted China, followed by South Korea Japan. Most focused pathologic complete response (pCR), median sample size 152 largely retrospective single-center designs. Model performance was commonly assessed using validation sets, pooled sensitivity specificity pCR prediction showing promising results. Models incorporating multitemporal MRI features were associated improved accuracy. While show guiding planning, methodological algorithmic explainability are needed facilitate clinical translation.

Язык: Английский

A review of Explainable Artificial Intelligence in healthcare DOI Creative Commons
Zahra Sadeghi, Roohallah Alizadehsani, Mehmet Akif Çifçi

и другие.

Computers & Electrical Engineering, Год журнала: 2024, Номер 118, С. 109370 - 109370

Опубликована: Июнь 7, 2024

Язык: Английский

Процитировано

63
Blockchain and explainable-AI integrated system for Polycystic Ovary Syndrome (PCOS) detection DOI Creative Commons
Gowthami Jaganathan,

Shanthi Natesan

PeerJ Computer Science, Год журнала: 2025, Номер 11, С. e2702 - e2702

Опубликована: Фев. 28, 2025

In the modern era of digitalization, integration with blockchain and machine learning (ML) technologies is most important for improving applications in healthcare management secure prediction analysis health data. This research aims to develop a novel methodology securely storing patient medical data analyzing it PCOS prediction. The main goals are leverage Hyperledger Fabric immutable, private integrate Explainable Artificial Intelligence (XAI) techniques enhance transparency decision-making. innovation this study unique technology ML XAI, solving critical issues security model interpretability healthcare. With Caliper tool, blockchain’s performance evaluated enhanced. suggested AI-based system Polycystic Ovary Syndrome detection (EAIBS-PCOS) demonstrates outstanding records 98% accuracy, 100% precision, 98.04% recall, resultant F1-score 99.01%. Such quantitative measures ensure success proposed delivering dependable intelligible predictions diagnosis, therefore making great addition literature while serving as solid solution near future.

Язык: Английский

Процитировано

0
A Comparative Study of Machine Learning, Deep Learning Algorithms, and Explainable AI Techniques for Diabetes Prediction DOI
Muhammad Imad,

Muhammad Shakeel,

Habib Zaidi

и другие.

Advances in medical technologies and clinical practice book series, Год журнала: 2025, Номер unknown, С. 157 - 180

Опубликована: Фев. 14, 2025

Diabetes prediction remains a crucial area of research due to its profound impact on global health. Diabetes, chronic metabolic disorder, affects millions people worldwide and poses significant challenges healthcare systems. Early diagnosis are essential managing the disease effectively, preventing complications, improving quality life for patients. Recent advancements in artificial intelligence (AI) have paved way powerful tools diabetes prediction, particularly through machine learning deep algorithms. These methods offer promising solutions enhancing early personalized care.

Язык: Английский

Процитировано

0
Large Language Models in Genomics—A Perspective on Personalized Medicine DOI Creative Commons
Shahid Ali, Yazdan Ahmad Qadri, Khurshid Ahmad

и другие.

Bioengineering, Год журнала: 2025, Номер 12(5), С. 440 - 440

Опубликована: Апрель 23, 2025

Integrating artificial intelligence (AI), particularly large language models (LLMs), into the healthcare industry is revolutionizing field of medicine. LLMs possess capability to analyze scientific literature and genomic data by comprehending producing human-like text. This enhances accuracy, precision, efficiency extensive analyses through contextualization. have made significant advancements in their ability understand complex genetic terminology accurately predict medical outcomes. These capabilities allow for a more thorough understanding influences on health issues creation effective therapies. review emphasizes LLMs’ impact healthcare, evaluates triumphs limitations processing, makes recommendations addressing these order enhance system. It explores latest analysis, focusing enhancing disease diagnosis treatment accuracy taking account an individual’s composition. also anticipates future which AI-driven analysis commonplace clinical practice, suggesting potential research areas. To effectively leverage personalized medicine, it vital actively support innovation across multiple sectors, ensuring that AI developments directly contribute solutions tailored individual patients.

Язык: Английский

Процитировано

0
An Explainable AI Approach Towards Automatic Sleep Apnea Detection Based on ECG Signal DOI Open Access
Jyoti Gupta,

K. R. Seeja

Procedia Computer Science, Год журнала: 2025, Номер 258, С. 937 - 946

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
ChatGPT-4o vs Psychiatrists in Responding to Common Antidepressant Concerns DOI
Erman Şentürk, Buket Koparal

American Journal of Health Promotion, Год журнала: 2025, Номер unknown

Опубликована: Май 29, 2025

Purpose Artificial intelligence (AI) is increasingly integrated into healthcare, including psychiatric care. This study evaluates ChatGPT-4o’s reliability in answering frequently asked antidepressant-related questions by comparing its performance with psychiatrists across four key dimensions: accuracy, conciseness, readability, and clarity. Design A comparative analyzing ChatGPT-4o-generated responses those of at least five years clinical experience. Setting Participants were recruited through institutional professional networks provided standardized derived from authoritative treatment guidelines. Subjects Twenty-six participated, ChatGPT-4o generated using a prompt for each question. Measures Two independent evaluated accuracy conciseness blinded rating system. Readability was assessed the Flesch-Kincaid Grade Level test, clarity measured Writing Clarity Index Calculator. Analysis The Shapiro-Wilk test normality. Paired t-tests used normally distributed data, Wilcoxon signed-rank non-normally data. Statistical significance set P < .05. Results showed comparable to ( = .0645) but significantly more concise .0019). differences not statistically significant .0892), while clearer .0059). Conclusion delivers accurate responses, highlighting potential as patient education tool. However, offer greater clarity, underscoring indispensable role expertise

Язык: Английский

Процитировано

0
Predicting anorexia nervosa treatment efficacy: an explainable machine learning approach DOI Creative Commons
Giulia Brizzi, Chiara Pupillo, Elena Sajno

и другие.

Journal of Eating Disorders, Год журнала: 2025, Номер 13(1)

Опубликована: Июнь 2, 2025

Abstract Introduction Anorexia nervosa (AN) is a psychopathology with an alarmingly high mortality rate. The growing number of individuals seeking help, coupled the limited resources clinics, highlights critical need to identify factors that can predict treatment efficacy. Machine learning (ML) techniques hold great promise in this regard. This data-driven approach offers unbiased means uncover predictors specific outcomes, advancing understanding and management challenging condition. Objective Six supervised ML algorithms (e.g., Decision Tree Random Forest) were applied develop binary classification model predicting short-term weight recovery/stabilization AN inpatients most influencing outcome. Methods Change Body Mass Index (BMI) from admission discharge (ΔBMI) was used as outcome, allowing classify patients into “improved” (BMI stability or increase) “aggravation” decrease). Predictors included clinically relevant psychological tests physical parameters. Scikit-learn features importance, SHAP (SHapley Additive exPlanations) analyses investigate predictor importance. Results Forest achieved accuracy 0.77, AUC-ROC 0.72, PR curve score 0.88. Uneasiness, Personal Alienation, Interpersonal Problems subscales emerged best predictors. analysis confirmed these results at individual prediction level. Discussion encouraged interventions focused on body-self experience addition interpersonal relationships, including body-swapping experiences metaverse activities, respectively. could maximize efficacy, effectively allocating achieve outcomes.

Язык: Английский

Процитировано

0
MRI-based artificial intelligence models for post-neoadjuvant surgery personalization in breast cancer: a narrative review of evidence from Western Pacific DOI Creative Commons

Yingyi Lin,

Minyi Cheng,

Cangui Wu

и другие.

The Lancet Regional Health - Western Pacific, Год журнала: 2024, Номер 57, С. 101254 - 101254

Опубликована: Дек. 6, 2024

Breast magnetic resonance imaging (MRI) is the most sensitive method for diagnosing breast cancer and assessing treatment response. Artificial intelligence (AI) radiomics offer new opportunities to identify patterns in data, supporting personalized post-neoadjuvant surgical decisions. This paper reviewed MRI-based AI models predicting outcomes after neoadjuvant therapy, with a focus on evidence from Western Pacific region, evaluate quality of existing models, discuss their inherent limitations, outline potential future directions. A literature search MEDLINE, EMBASE, Web Science identified 51 relevant studies majority conducted China, followed by South Korea Japan. Most focused pathologic complete response (pCR), median sample size 152 largely retrospective single-center designs. Model performance was commonly assessed using validation sets, pooled sensitivity specificity pCR prediction showing promising results. Models incorporating multitemporal MRI features were associated improved accuracy. While show guiding planning, methodological algorithmic explainability are needed facilitate clinical translation.

Язык: Английский

Процитировано

1