Advanced Fuzzy Logic for Predicting Hospital Readmissions in Diabetic Patients

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 137 - 160

Опубликована: Янв. 10, 2025

The development of the predictive model for forecasting hospital readmissions among diabetic patients represents a remarkable footstep in applying fuzzy logic techniques. proposed Utilizing Long Short-Term Memory (LSTM) neural networks, has indicated magnificent accuracy rate 83% during pilot testing, this results 39% reduction 30-day readmission rate. Although model's current state is promising, several areas need focused attention establishment its successful deployment realistic situations and long-term sustainability. Ongoing research efforts should enhance interpretability, explore new data sources, maintain relevance through evolving architectures methodologies. By addressing these multifaceted challenges comprehensive iterative approach, can potentially revolutionize chronic illness management, leading to improved patient outcomes reduced operational costs within healthcare systems.

Язык: Английский

---

Improving Symptom‐Based Medical Diagnosis Using Ensemble Learning Approaches

Systems Research and Behavioral Science, Год журнала: 2025, Номер unknown

Опубликована: Фев. 20, 2025

ABSTRACT Symptoms‐based health checkers are emerging as digital tools in modern healthcare offering patients the ability to self‐assess their status by inputting symptoms and receiving diagnostic suggestions. These systems rely on machine learning models accurately predict medical conditions based symptom data. In this study, we explore effectiveness of various algorithms with a particular focus ensemble methods improve accuracy reliability checkers. We evaluate multiple models—Decision Trees, Support Vector Machines (SVM), Logistic Regression, variations (Bagging, Stacking)—across three distinct datasets: ‘Reference Dataset,’ ‘Cough‐DDX Dataset’ ‘Cough‐DDX2 Dataset.’ Our results demonstrate that models, especially Bagging Decision Trees SVM, significantly outperform individual terms accuracy, precision, recall, F1 score. also tested clinical use cases achieved excellent highlighting real‐world applicability potential our approaches.

Язык: Английский

---

Bone tumors: a systematic review of prevalence, risk determinants, and survival patterns

BMC Cancer, Год журнала: 2025, Номер 25(1)

Опубликована: Фев. 21, 2025

Язык: Английский

---

WE-XAI: explainable AI for CVD prediction using weighted feature selection and ensemble classifiers

Network Modeling Analysis in Health Informatics and Bioinformatics, Год журнала: 2025, Номер 14(1)

Опубликована: Фев. 24, 2025

Язык: Английский

---

Pathology in the artificial intelligence era: Guiding innovation and implementation to preserve human insight

Academic Pathology, Год журнала: 2025, Номер 12(1), С. 100166 - 100166

Опубликована: Янв. 1, 2025

The integration of artificial intelligence in pathology has ignited discussions about the role technology diagnostics-whether serves as a tool for augmentation or risks replacing human expertise. This manuscript explores intelligence's evolving contributions to pathology, emphasizing its potential capacity enhance, rather than eclipse, pathologist's role. Through historical comparisons, such transition from analog digital radiology, this paper highlights how technological advancements have historically expanded professional capabilities without diminishing essential element. Current applications pathology-from diagnostic standardization workflow efficiency-demonstrate augment accuracy, expedite processes, and improve consistency across institutions. However, challenges remain algorithmic bias, regulatory oversight, maintaining interpretive skills among pathologists. discussion underscores importance comprehensive governance frameworks, educational curricula, public engagement initiatives ensure remains collaborative endeavor that empowers professionals, upholds ethical standards, enhances patient outcomes. ultimately advocates balanced approach where expertise work concert advance future medicine.

Язык: Английский

---

Advanced Liver Tumour Detection Using Optimized YOLOv8 Modules

International Journal of Computational and Experimental Science and Engineering, Год журнала: 2025, Номер 11(2)

Опубликована: Апрель 4, 2025

Health fraternity is invariably challenged with early diagnosis, detection, identification, classification, treatment and convalescence of globally prevalent life-threatening fatal diseases as liver cancer. The detection cancer through medical image processing technique so challenging that an iota deviation conspicuous among healthy tissues, benign tumour malignant tissues a matter wake up call. This work entailed introduction novel, optimized YOLOv8-based model for harnessing the strengths transformer-based feature extraction, global attention mechanisms, advanced aggregation techniques. was subjected to rigorous performance relevant methods messages parameters time again repeated refinements. Eventually, it concluded proposed surpasses all models in extant now terms precision, recall, means average precision (mAP). ascertained by inference drawn from model’s achievement attaining 95.34% 96.49% 97.31% [email protected]. In regard excels differentiating normal cases, tumours, tumours. These innovations represent significant step toward improving accuracy automated diagnosis systems, potential revolutionize clinical workflows enhance patient outcomes.

Язык: Английский

---

Detection of COVID-19, lung opacity, and viral pneumonia via X-ray using machine learning and deep learning

Computers in Biology and Medicine, Год журнала: 2025, Номер 191, С. 110131 - 110131

Опубликована: Апрель 8, 2025

The COVID-19 pandemic has significantly strained healthcare systems, highlighting the need for early diagnosis to isolate positive cases and prevent spread. This study combines machine learning, deep transfer learning techniques automatically diagnose other pulmonary conditions from radiographic images. First, we used Convolutional Neural Networks (CNNs) a Support Vector Machine (SVM) classifier on dataset of 21,165 chest X-ray Our model achieved an accuracy 86.18 %. approach aids medical experts in rapidly accurateky detecting lung diseases. Next, applied using ResNet18 combined with SVM comprising normal, COVID-19, opacity, viral pneumonia outperformed traditional methods, classification rates 98 % Stochastic Gradient Descent (SGD), 97 Adam, 96 RMSProp, 94 Adagrad optimizers. Additionally, incorporated two additional models, EfficientNet-CNN Xception-CNN, which accuracies 99.20 98.80 %, respectively. However, observed limitations diversity representativeness, may affect generalization. Future work will focus implementing advanced data augmentation collaborations enhance performance.This research demonstrates potential cutting-edge improve diagnostic efficiency imaging applications.

Язык: Английский

---

The Role of Artificial Intelligence in the Diagnosis and Management of Rheumatoid Arthritis

Medicina, Год журнала: 2025, Номер 61(4), С. 689 - 689

Опубликована: Апрель 9, 2025

Background and Objectives: Artificial intelligence has emerged as a transformative tool in healthcare, offering capabilities such early diagnosis, personalised treatment, real-time patient monitoring. In the context of rheumatoid arthritis, chronic autoimmune disease that demands timely intervention, artificial shows promise overcoming diagnostic delays optimising management. This study examines role diagnosis management focusing on perceived benefits, challenges, acceptance levels among healthcare professionals patients. Materials Methods: A cross-sectional was conducted using detailed questionnaire distributed to 205 participants, including rheumatologists, general practitioners, arthritis patients from Romania. The used descriptive statistics, chi-square tests, logistic regression analyse AI rheumatology. Data visualisation multiple imputations addressed missing values, ensuring accuracy. Statistical significance set at p < 0.05 for hypothesis testing. Results: Respondents with prior experience it more useful RA (p 0.001). Familiarity concepts positively correlated routine rheumatology practice (ρ = 1.066, main barriers identified were high costs (36%), lack medical staff training (37%), concerns regarding accuracy (21%). Although less frequently mentioned, data privacy remained relevant subset respondents. revealed could improve monitoring, being valuable by familiar digital technologies. However, 42% participants cited standardisation across systems major barrier, underscoring need effective interoperability solutions. Conclusions: potential revolutionise through faster accurate diagnoses, treatments, optimised Nevertheless, challenges costs, training, be ensure efficient integration into clinical practice. Educational programmes interdisciplinary collaboration are essential increase adoption

Язык: Английский

---

Advancing Breast Cancer Diagnosis: Integrating Deep Transfer Learning and U-Net Segmentation for Precise Classification and Delineation of Ultrasound Images

Results in Engineering, Год журнала: 2025, Номер unknown, С. 105047 - 105047

Опубликована: Апрель 1, 2025

Язык: Английский

---

Optimized deep learning model for comprehensive medical image analysis across multiple modalities

Neurocomputing, Год журнала: 2024, Номер 619, С. 129182 - 129182

Опубликована: Дек. 12, 2024

Язык: Английский

---