Smart Health

Journal of Organizational and End User Computing, Год журнала: 2022, Номер 34(1), С. 1 - 14

Опубликована: Авг. 11, 2022

In recent decades, healthcare organizations around the world have increasingly appreciated value of information technologies for a variety applications. Three new technological advancements that are impacting smart health metaverse, artificial intelligence (AI), and data science. The metaverse is intersection three major — AI, augmented reality (AR), virtual (VR). Metaverse provides possibilities potential still emerging. increased work efficiency enabled by science in hospitals not only improves patient care but also cuts costs workload providers. Artificial intelligence, coupled with machine learning, transforming industry. availability big enables scientists to use descriptive, predictive, prescriptive analytics. This article reviews multiple case studies literature on AI applications hospital administration. presents unresolved research questions challenges context. For researchers, addition providing good synopsis development area, this identifies possible future directions discusses health. practitioners, both decision-makers workers practical guidelines management model.

Язык: Английский

---

Urban Tree Classification Based on Object-Oriented Approach and Random Forest Algorithm Using Unmanned Aerial Vehicle (UAV) Multispectral Imagery

Remote Sensing, Год журнала: 2022, Номер 14(16), С. 3885 - 3885

Опубликована: Авг. 11, 2022

Timely and accurate information on the spatial distribution of urban trees is critical for sustainable development, management planning. Compared with satellite-based remote sensing, Unmanned Aerial Vehicle (UAV) sensing has a higher temporal resolution, which provides new method identification trees. In this study, we aim to establish an efficient practical tree by combining object-oriented approach random forest algorithm using UAV multispectral images. Firstly, image was segmented multi-scale segmentation based scale determined Estimation Scale Parameter 2 (ESP2) tool visual discrimination. Secondly, spectral features, index texture features geometric were combined form schemes S1–S8, S9, consisting selected recursive feature elimination (RFE) method. Finally, classification performed nine (RF), support vector machine (SVM) k-nearest neighbor (KNN) classifiers, respectively. The results show that RF classifier performs better than SVM KNN, achieves highest accuracy in overall (OA) 91.89% Kappa coefficient (Kappa) 0.91. This study reveals have negative impact classification, other three types positive impact. importance ranking map shows are most important type followed features. Most species high accuracy, but Camphor Cinnamomum Japonicum much lower species, suggesting cannot accurately distinguish these two so it necessary add such as height future improve accuracy. illustrates combination images powerful classification.

Язык: Английский

---

Sarcopenia in hepatocellular carcinoma: Current knowledge and future directions

World Journal of Gastroenterology, Год журнала: 2022, Номер 28(4), С. 432 - 448

Опубликована: Янв. 19, 2022

Liver cancer is the second most occurring worldwide and one of leading causes cancer-related deaths. Hepatocellular carcinoma (HCC) common (80%-90%) type among malignant liver cancers. Sarcopenia occurs very early in HCC can predict provide an opportunity to improve muscle health before engaging treatment options such as loco-regional, systemic, transplant management. Multiple prognostic stating systems have been developed HCC, Barcelona Clinic Cancer, Child-Pugh score Albumin-Bilirubin grade. However, evaluation patients' performance status a major limitation these scoring systems. In this review, we aim summarize current knowledge recent advances about role sarcopenia cirrhosis general, while focusing specifically on HCC. Additionally, predicting clinical outcomes prognostication patients undergoing loco-regional therapies, resection, transplantation systematic therapy has discussed. A literature review was performed using databases PubMed/MEDLINE, EMBASE, Cochrane, Web Science, CINAHL April 1, 2021, identify published reports independently HCC-related mortality especially treatments surgical systemic therapies. Basic research focused evaluating balance anabolic catabolic pathways responsible for health. Early studies shown promising results methods which potentially increase prognosis patients. As it Further, measurement obviate confounding caused by abdominal ascites The use add existing better prognosticate

Язык: Английский

---

Precision medicine and nucleotide-based therapeutics to treat MASH

Clinical and Molecular Hepatology, Год журнала: 2024, Номер unknown

Опубликована: Авг. 5, 2024

Metabolic dysfunction-associated steatotic liver disease (MASLD) is a complex multifactorial and becoming the leading cause of liver-related morbidity mortality. MASLD spans from isolated steatosis to metabolic steatohepatitis (MASH), that may progress cirrhosis hepatocellular carcinoma (HCC). Genetic, metabolic, environmental factors strongly contribute heterogeneity MASLD. Lifestyle intervention weight loss represent viable treatment for Moreover, Resmetirom, thyroid hormone beta receptor agonist, has recently been approved treatment. However, most individuals treated did not respond this therapeutic suggesting need more tailored approach treat Oligonucleotide-based therapies, namely small-interfering RNA (siRNA) antisense oligonucleotide (ASO), have developed tackle by reducing expression genes influencing MASH progression, such as PNPLA3 HSD17B13. Here, we review latest made in synthesis development oligonucleotide-based agents targeting genetic determinants MASH.

Язык: Английский

---

FibrAIm – The machine learning approach to identify the early stage of liver fibrosis and steatosis

International Journal of Medical Informatics, Год журнала: 2025, Номер unknown, С. 105837 - 105837

Опубликована: Фев. 1, 2025

Язык: Английский

---

Explainable AI in thermal modelling enhancing precision in thermal gradient monitoring for additive manufacturing using LSTM networks

Thermal Science and Engineering Progress, Год журнала: 2025, Номер unknown, С. 103465 - 103465

Опубликована: Март 1, 2025

Язык: Английский

---

Artificial intelligence predicts direct-acting antivirals failure among hepatitis C virus patients: A nationwide hepatitis C virus registry program

Clinical and Molecular Hepatology, Год журнала: 2023, Номер 30(1), С. 64 - 79

Опубликована: Янв. 1, 2023

Background/Aims: Despite the high efficacy of direct-acting antivirals (DAAs), approximately 1–3% hepatitis C virus (HCV) patients fail to achieve a sustained virological response. We conducted nationwide study investigate risk factors associated with DAA treatment failure. Machine-learning algorithms have been applied discriminate subjects who may respond therapy.Methods: analyzed Taiwan HCV Registry Program database explore predictors failure in patients. Fifty-five host and features were assessed using multivariate logistic regression, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), artificial neural network. The primary outcome was undetectable RNA at 12 weeks after end treatment. Results: training (n=23,955) validation (n=10,346) datasets had similar baseline demographics, an overall rate 1.6% (n=538). Multivariate regression analysis revealed that liver cirrhosis, hepatocellular carcinoma, poor adherence, higher hemoglobin A1c significantly XGBoost outperformed other models, area under receiver operating characteristic curve 1.000 dataset 0.803 dataset. top five RNA, body mass index, α-fetoprotein, platelets, FIB-4 index. accuracy, sensitivity, specificity, positive predictive value, negative value model (cutoff value=0.5) 99.5%, 69.7%, 99.9%, 97.4%, respectively, for entire dataset.Conclusions: Machine learning effectively provide stratification additional information on

Язык: Английский

---

Artificial Intelligence-Based Opportunities in Liver Pathology—A Systematic Review

Diagnostics, Год журнала: 2023, Номер 13(10), С. 1799 - 1799

Опубликована: Май 19, 2023

Background: Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including the liver pathology field. Objective: The present study aims provide systematic review performances provided by DNN algorithms throughout Pubmed Embase databases up December 2022, for tumoral, metabolic inflammatory fields. Results: 42 articles were selected fully reviewed. Each article was evaluated through Quality Assessment Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks bias. Conclusions: DNN-based models are well represented field pathology, diverse. Most studies, however, presented at least one domain with high risk bias according QUADAS-2 tool. Hence, future opportunities persistent limitations. To our knowledge, this is first solely focused on evaluate lens QUADAS2

Язык: Английский

---

Paradigm shift in the treatment options of hepatocellular carcinoma

Liver International, Год журнала: 2021, Номер 42(9), С. 2067 - 2079

Опубликована: Сен. 13, 2021

Abstract Hepatocellular carcinoma (HCC) is prevalent worldwide with suboptimal therapeutic outcomes. The advancement of options and the development new systemic therapies expand armamentarium to tackle HCC. Treatment should be provided based on hierarchy efficacy in a multidisciplinary perspective, instead traditional stage‐guided scheme. In advanced HCC, lenvatinib has comparable as sorafenib for first‐line therapy HCC; while regorafenib, cabozantinib, ramucirumab have been approved second‐line after failure sorafenib. Immune checkpoint inhibitor prolongs response rate survival enables long‐term cure. Atezolizumab plus bevacizumab superior Several emerging regimens by combination various are currently under clinical trials. Systemic may used neoadjuvant, adjuvant or even initial intermediate‐stage paradigm shift HCC treatment will improve patient

Язык: Английский

---

The Emerging Factors and Treatment Options for NAFLD-Related Hepatocellular Carcinoma

Cancers, Год журнала: 2021, Номер 13(15), С. 3740 - 3740

Опубликована: Июль 26, 2021

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, followed by cholangiocarcinoma (CCA). HCC third cause cancer death worldwide, and its incidence rising, associated with an increased prevalence obesity nonalcoholic fatty disease (NAFLD). However, current treatment options are limited. Genetic factors epigenetic factors, influenced age environment, significantly impact initiation progression NAFLD-related HCC. In addition, both transcriptional post-transcriptional modification critically important for development in under inflammatory fibrotic conditions. The early diagnosis predicts curative longer survival. clinical cases commonly found a very late stage due to asymptomatic nature diagnostic methods novel biomarkers, as well combined evaluation algorithm artificial intelligence, support precise HCC, timely monitoring during progression. Treatment include immunotherapy, CAR T cell therapy, peptide treatment, bariatric surgery, anti-fibrotic so on. Overall, increasing, better understanding underlying mechanism implicated essential improving prognosis.

Язык: Английский

---