Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (108)

Search Parameters:
Keywords = prognostic uncertainty

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
17 pages, 1098 KiB  
Article
Attentional Functioning in Healthy Older Adults and aMCI Patients: Results from the Attention Network Test with a Focus on Sex Differences
by Laura Facci, Laura Sandrini and Gabriella Bottini
Brain Sci. 2025, 15(7), 770; https://doi.org/10.3390/brainsci15070770 - 19 Jul 2025
Viewed by 372
Abstract
Background/Objectives: The prognostic uncertainty of Mild Cognitive Impairment (MCI) imposes comprehensive neuropsychological evaluations beyond mere memory assessment. However, previous investigations into other cognitive domains, such as attention, have yielded divergent findings. Furthermore, while evidence suggests the presence of sex differences across the [...] Read more.
Background/Objectives: The prognostic uncertainty of Mild Cognitive Impairment (MCI) imposes comprehensive neuropsychological evaluations beyond mere memory assessment. However, previous investigations into other cognitive domains, such as attention, have yielded divergent findings. Furthermore, while evidence suggests the presence of sex differences across the spectrum of dementia-related conditions, no study has systematically explored attentional disparities between genders within this context. The current study aims to investigate differences in the attentional subcomponents, i.e., alerting, orienting, and executive control, between patients with MCI and healthy older controls (HOCs), emphasizing interactions between biological sex and cognitive impairment. Methods: Thirty-six participants (18 MCI, and 18 HOCs) were evaluated using the Attention Network Test (ANT). Raw RTs as well as RTs corrected for general slowing were analyzed using Generalized Mixed Models. Results: Both health status and sex influenced ANT performance, when considering raw RTs. Nevertheless, after adjusting for the baseline processing speed, the effect of cognitive impairment was no longer evident in men, while it persisted in women, suggesting specific vulnerabilities in females not attributable to general slowing nor to the MCI diagnosis. Moreover, women appeared significantly slower and less accurate when dealing with conflicting information. Orienting and alerting did not differ between groups. Conclusions: To the best of our knowledge, this is the first study investigating sex differences in attentional subcomponents in the aging population. Our results suggest that previously reported inconsistencies about the decline of attentional subcomponents may be attributable to such diversities. Systematically addressing sex differences in cognitive decline appears pivotal for informing the development of precision medicine approaches. Full article
Show Figures

Figure 1

17 pages, 913 KiB  
Review
Cell Membrane Capacitance (Cm) Measured by Bioimpedance Spectroscopy (BIS): A Narrative Review of Its Clinical Relevance and Biomarker Potential
by Steven Brantlov, Leigh C. Ward, Søren Isidor, Christian Lodberg Hvas, Charlotte Lock Rud and Lars Jødal
Sensors 2025, 25(14), 4362; https://doi.org/10.3390/s25144362 - 12 Jul 2025
Viewed by 455
Abstract
Cell membrane capacitance (Cm) is a potential biomarker that reflects the structural and functional integrity of cell membranes. It is essential for physiological processes such as signal transduction, ion transport, and cellular homeostasis. In clinical practice, Cm can be [...] Read more.
Cell membrane capacitance (Cm) is a potential biomarker that reflects the structural and functional integrity of cell membranes. It is essential for physiological processes such as signal transduction, ion transport, and cellular homeostasis. In clinical practice, Cm can be determined using bioimpedance spectroscopy (BIS), a non-invasive technique for analysing the intrinsic electrical properties of biological tissues across a range of frequencies. Cm may be relevant in various clinical fields, where high capacitance is associated with healthy and intact membranes, while low capacitance indicates cellular damage or disease. Despite its promise as a prognostic indicator, several knowledge gaps limit the broader clinical application of Cm. These include variability in measurement techniques (e.g., electrode placement, frequency selection), the lack of standardised measurement protocols, uncertainty on how Cm is related to pathology, and the relatively low amount of Cm research. By addressing these gaps, Cm may become a valuable tool for examining cellular health, early disease detection, and evaluating treatment efficacy in clinical practice. This review explores the fundamental principles of Cm measured with the BIS technique, its mathematical basis and relationship to the biophysical Cole model, and its potential clinical applications. It identifies current gaps in our knowledge and outlines future research directions to enhance the understanding and use of Cm. For example, Cm has shown promise in identifying membrane degradation in sepsis, predicting malnutrition in anorexia nervosa, and as a prognostic factor in cancer. Full article
(This article belongs to the Special Issue Biomedical Imaging, Sensing and Signal Processing)
Show Figures

Figure 1

18 pages, 4979 KiB  
Systematic Review
Discordant High-Gradient Aortic Stenosis: A Systematic Review
by Nadera N. Bismee, Mohammed Tiseer Abbas, Hesham Sheashaa, Fatmaelzahraa E. Abdelfattah, Juan M. Farina, Kamal Awad, Isabel G. Scalia, Milagros Pereyra Pietri, Nima Baba Ali, Sogol Attaripour Esfahani, Omar H. Ibrahim, Steven J. Lester, Said Alsidawi, Chadi Ayoub and Reza Arsanjani
J. Cardiovasc. Dev. Dis. 2025, 12(7), 255; https://doi.org/10.3390/jcdd12070255 - 3 Jul 2025
Viewed by 566
Abstract
Aortic stenosis (AS), the most common valvular heart disease, is traditionally graded based on several echocardiographic quantitative parameters, such as aortic valve area (AVA), mean pressure gradient (MPG), and peak jet velocity (Vmax). This systematic review evaluates the clinical significance and prognostic implications [...] Read more.
Aortic stenosis (AS), the most common valvular heart disease, is traditionally graded based on several echocardiographic quantitative parameters, such as aortic valve area (AVA), mean pressure gradient (MPG), and peak jet velocity (Vmax). This systematic review evaluates the clinical significance and prognostic implications of discordant high-gradient AS (DHG-AS), a distinct hemodynamic phenotype characterized by elevated MPG despite a preserved AVA (>1.0 cm2). Although often overlooked, DHG-AS presents unique diagnostic and therapeutic challenges, as high gradients remain a strong predictor of adverse outcomes despite moderately reduced AVA. Sixty-three studies were included following rigorous selection and quality assessment of the key studies. Prognostic outcomes across five key studies were discrepant: some showed better survival in DHG-AS compared to concordant high-gradient AS (CHG-AS), while others reported similar or worse outcomes. For instance, a retrospective observational study including 3209 patients with AS found higher mortality in CHG-AS (unadjusted HR: 1.4; 95% CI: 1.1 to 1.7), whereas another retrospective multicenter study including 2724 patients with AS observed worse outcomes in DHG-AS (adjusted HR: 1.59; 95% CI: 1.04 to 2.56). These discrepancies may stem from delays in intervention or heterogeneity in study populations. Despite the diagnostic ambiguity, the presence of high gradients warrants careful evaluation, aggressive risk stratification, and timely management. Current guidelines recommend a multimodal approach combining echocardiography, computed tomography (CT) calcium scoring, transesophageal echocardiography (TEE) planimetry, and, when needed, catheterization. Anatomic AVA assessment by TEE, CT, and cardiac magnetic resonance imaging (CMR) can improve diagnostic accuracy by directly visualizing valve morphology and planimetry-based AVA, helping to clarify the true severity in discordant cases. However, these modalities are limited by factors such as image quality (especially with TEE), radiation exposure and contrast use (in CT), and availability or contraindications (in CMR). Management remains largely based on CHG-AS protocols, with intervention primarily guided by transvalvular gradient and symptom burden. The variability among the different guidelines in defining severity and therapeutic thresholds highlights the need for tailored approaches in DHG-AS. DHG-AS is clinically relevant and associated with substantial prognostic uncertainty. Timely recognition and individualized treatment could improve outcomes in this complex subgroup. Full article
(This article belongs to the Special Issue Cardiovascular Imaging in Heart Failure and in Valvular Heart Disease)
Show Figures

Figure 1

14 pages, 1027 KiB  
Review
Seronegative Sicca Syndrome: Diagnostic Considerations and Management Strategies
by Yordanka M. Basheva-Kraeva, Krasimir I. Kraev, Petar A. Uchikov, Maria I. Kraeva, Bozhidar K. Hristov, Nina St. Stoyanova, Vesela T. Mitkova-Hristova, Borislav Ivanov, Stanislav S. Karamitev, Nina Koleva, Aleksandar Marinkov and Veselin A. Vassilev
Life 2025, 15(6), 966; https://doi.org/10.3390/life15060966 - 17 Jun 2025
Viewed by 619
Abstract
Seronegative sicca syndrome encompasses patients who present with xerostomia and/or keratoconjunctivitis sicca but lack anti-SSA/SSB antibodies and do not fulfill current classification criteria for primary Sjögren’s syndrome (pSS). Despite symptom overlap with pSS, these individuals remain diagnostically and therapeutically unclassified. This review studies [...] Read more.
Seronegative sicca syndrome encompasses patients who present with xerostomia and/or keratoconjunctivitis sicca but lack anti-SSA/SSB antibodies and do not fulfill current classification criteria for primary Sjögren’s syndrome (pSS). Despite symptom overlap with pSS, these individuals remain diagnostically and therapeutically unclassified. This review studies the clinical, immunological, and pathological spectrum of seronegative sicca, highlighting its heterogeneity and the limitations of antibody-centric diagnostic frameworks. Histopathologic findings in some seronegative patients—including focal lymphocytic sialadenitis—mirror those seen in pSS, suggesting underlying immune-mediated glandular damage. In others, nonspecific or normal biopsy findings suggest non-immune mechanisms. New evidence of immune activity, such as elevated cytokines (BAFF, IFN-α), and novel autoantibodies (SP-1, CA-VI), further supports the concept of subclinical autoimmunity in a subset of these patients. Clinically, they often face significant burden, including dryness, fatigue, and pain, yet remain excluded from most research cohorts, therapeutic trials, and clinical guidelines. Their management is often individualized, relying on symptomatic therapies rather than immunomodulatory agents. The lack of validated diagnostic criteria and prognostic markers compounds the uncertainty surrounding disease evolution, as some patients may later seroconvert or develop systemic features. To address these gaps, a paradigm shift is needed—one that embraces the spectrum of sicca syndromes, incorporates advanced immunophenotyping, and allows inclusion of seronegative patients in research and care algorithms. Full article
(This article belongs to the Special Issue Feature Paper in Physiology and Pathology: 2nd Edition)
Show Figures

Figure 1

27 pages, 4256 KiB  
Article
A Robust Conformal Framework for IoT-Based Predictive Maintenance
by Alberto Moccardi, Claudia Conte, Rajib Chandra Ghosh and Francesco Moscato
Future Internet 2025, 17(6), 244; https://doi.org/10.3390/fi17060244 - 30 May 2025
Viewed by 677
Abstract
This study, set within the vast and varied research field of industrial Internet of Things (IoT) systems, proposes a methodology to address uncertainty quantification (UQ) issues in predictive maintenance (PdM) practices. At its core, this paper leverages the commercial modular aero-propulsion system simulation [...] Read more.
This study, set within the vast and varied research field of industrial Internet of Things (IoT) systems, proposes a methodology to address uncertainty quantification (UQ) issues in predictive maintenance (PdM) practices. At its core, this paper leverages the commercial modular aero-propulsion system simulation (CMAPSS) dataset to evaluate different artificial intelligence (AI) prognostic algorithms for remaining useful life (RUL) forecasting while supporting the estimation of a robust confidence interval (CI). The methodology primarily involves the comparison of statistical learning (SL), machine learning (ML), and deep learning (DL) techniques for each different scenario of the CMAPSS, evaluating the performances through a tailored metric, the S-score metric, and then benchmarking diverse conformal-based uncertainty estimation techniques, remarkably naive, weighted, and bootstrapping, offering a more suitable and reliable alternative to classical RUL prediction. The results obtained highlight the peculiarities and benefits of the conformal approach, despite probabilistic models favoring the adoption of complex models in cases where the operating conditions of the machine are multiple, and suggest the use of weighted conformal practices in non-exchangeability conditions while recommending bootstrapping alternatives for contexts with a more substantial presence of noise in the data. Full article
(This article belongs to the Special Issue Artificial Intelligence-Enabled Internet of Things (IoT))
Show Figures

Figure 1

17 pages, 1448 KiB  
Article
Novel Hybrid Prognostics of Aircraft Systems
by Shuai Fu, Nicolas P. Avdelidis and Angelos Plastropoulos
Electronics 2025, 14(11), 2193; https://doi.org/10.3390/electronics14112193 - 28 May 2025
Viewed by 398
Abstract
Accurate forecasting of the remaining useful life (RUL) of aviation equipment is crucial for enhancing safety and reducing maintenance costs. This study presents a novel hybrid prognostic methodology that integrates physics-based and data-driven models to improve RUL estimations for critical aircraft components. The [...] Read more.
Accurate forecasting of the remaining useful life (RUL) of aviation equipment is crucial for enhancing safety and reducing maintenance costs. This study presents a novel hybrid prognostic methodology that integrates physics-based and data-driven models to improve RUL estimations for critical aircraft components. The physics-based approach simulates long-term degradation patterns using fundamental principles such as mass conservation and Bernoulli’s equation, while the data-driven model employs a hyper tangent boosted neural network (HTBNN) to detect short-term anomalies and deviations in real-time sensor data. The integration of various models enhances accuracy, adaptability, and reliability in prognostics. The proposed methodology is assessed using NASA’s N-CMAPSS dataset for gas turbines and a fuel system test rig, demonstrating a 15% improvement in prediction accuracy and a 20% reduction in uncertainty compared to traditional methods. These findings highlight the potential for widespread application of this hybrid methodology in predictive maintenance and prognostic and health management (PHM) of aircraft systems. Full article
(This article belongs to the Special Issue Fault Detection Technology Based on Deep Learning)
Show Figures

Figure 1

12 pages, 857 KiB  
Article
Preoperative Axillary Ultrasound in the Era of Z0011: A Model for Predicting High Axillary Disease Burden
by Ashley DiPasquale and Lashan Peiris
Curr. Oncol. 2025, 32(6), 307; https://doi.org/10.3390/curroncol32060307 - 27 May 2025
Viewed by 422
Abstract
The ACOSOG Z0011 and IBCSG 23-01 trials demonstrated that axillary lymph node dissection (ALND) offers no prognostic benefit in breast cancer patients with clinically negative axillae and low disease burden (one to two positive nodes) on sentinel lymph node biopsy (SLNB). However, uncertainty [...] Read more.
The ACOSOG Z0011 and IBCSG 23-01 trials demonstrated that axillary lymph node dissection (ALND) offers no prognostic benefit in breast cancer patients with clinically negative axillae and low disease burden (one to two positive nodes) on sentinel lymph node biopsy (SLNB). However, uncertainty remains regarding the management of patients with clinically negative axillae (cN0) who are found to have suspicious lymph nodes on imaging that are subsequently confirmed positive by biopsy. The current practice often directs these patients to upfront ALND, potentially exposing them to unnecessary surgical morbidity. This study aimed to assess the role of axillary ultrasound in predicting high axillary nodal burden and guiding surgical management. Using the Alberta Cancer Registry, we identified 107 cN0 breast cancer patients from 2010 to 2017 who underwent preoperative axillary ultrasound with positive biopsy followed by ALND. Our findings reveal that 42% of these patients had low axillary nodal burden on final pathology, meeting Z0011 criteria, and might potentially have avoided ALND. Furthermore, axillary ultrasound findings were not predictive of high axillary burden. These results highlight that many patients undergoing upfront ALND based on positive ultrasound-guided biopsy could benefit from SLNB alone. This supports the 2023 NCCN guidelines advocating for more selective use of ALND to minimize overtreatment and associated morbidity. Full article
(This article belongs to the Section Breast Cancer)
Show Figures

Graphical abstract

12 pages, 489 KiB  
Article
Generative Artificial Intelligence and Risk Appetite in Medical Decisions in Rheumatoid Arthritis
by Florian Berghea, Dan Andras and Elena Camelia Berghea
Appl. Sci. 2025, 15(10), 5700; https://doi.org/10.3390/app15105700 - 20 May 2025
Viewed by 689
Abstract
With Generative AI (GenAI) entering medicine, understanding its decision-making under uncertainty is important. It is well known that human subjective risk appetite influences medical decisions. This study investigated whether the risk appetite of GenAI can be evaluated and if established human risk assessment [...] Read more.
With Generative AI (GenAI) entering medicine, understanding its decision-making under uncertainty is important. It is well known that human subjective risk appetite influences medical decisions. This study investigated whether the risk appetite of GenAI can be evaluated and if established human risk assessment tools are applicable for this purpose in a medical context. Five GenAI systems (ChatGPT 4.5, Gemini 2.0, Qwen 2.5 MAX, DeepSeek-V3, and Perplexity) were evaluated using Rheumatoid Arthritis (RA) clinical scenarios. We employed two methods adapted from human risk assessment: the General Risk Propensity Scale (GRiPS) and the Time Trade-Off (TTO) technique. Queries involving RA cases with varying prognoses and hypothetical treatment choices were posed repeatedly to assess risk profiles and response consistency. All GenAIs consistently identified the same RA cases for the best and worst prognoses. However, the two risk assessment methodologies yielded varied results. The adapted GRiPS showed significant differences in general risk propensity among GenAIs (ChatGPT being the least risk-averse and Qwen/DeepSeek the most), though these differences diminished in specific prognostic contexts. Conversely, the TTO method indicated a strong general risk aversion (unwillingness to trade lifespan for pain relief) across systems yet revealed Perplexity as significantly more risk-tolerant than Gemini. The variability in risk profiles obtained using the GRiPS versus the TTO for the same AI systems raises questions about tool applicability. This discrepancy suggests that these human-centric instruments may not adequately or consistently capture the nuances of risk processing in Artificial Intelligence. The findings imply that current tools might be insufficient, highlighting the need for methodologies specifically tailored for evaluating AI decision-making under medical uncertainty. Full article
(This article belongs to the Special Issue Machine Learning in Biomedical Sciences)
Show Figures

Figure 1

20 pages, 3468 KiB  
Article
Bayesian Integration of Bronchoalveolar Lavage miRNAs and KL-6 in Progressive Pulmonary Fibrosis Diagnosis
by Piera Soccio, Valerio Longo, Corrado Mencar, Pasquale Tondo, Fabiola Murgolo, Giulia Scioscia and Donato Lacedonia
Diagnostics 2025, 15(10), 1257; https://doi.org/10.3390/diagnostics15101257 - 15 May 2025
Viewed by 448
Abstract
Background/Objectives: Progressive pulmonary fibrosis (PPF) represents one of the most severe and complex challenges in respiratory medicine, characterized by a rapid decline in lung function and often poor prognosis, making it a priority in research on interstitial lung diseases (ILDs). The aim [...] Read more.
Background/Objectives: Progressive pulmonary fibrosis (PPF) represents one of the most severe and complex challenges in respiratory medicine, characterized by a rapid decline in lung function and often poor prognosis, making it a priority in research on interstitial lung diseases (ILDs). The aim of this study is to correlate classical clinical features and three genetic biomarkers with the diagnosis and prognosis of progressive pulmonary fibrosis in ILDs. Methods: This study involved 19 patients with progressive pulmonary fibrosis (PPF) and 20 patients with non-progressive pulmonary fibrosis (nPPF) from the S.C. of Respiratory System Diseases at the Policlinico of Foggia (Italy) between 2015 and 2022. All participants underwent pulmonary function tests (PFTs), a 6 min walk test (6MWT), and bronchoalveolar lavage (BAL) sampling, following the acquisition of written consent for these procedures. Bayesian analysis with generalized linear models has been applied for both diagnostic and prognostic classification. Results: The proposed Bayesian model enables the estimation of the contribution of each considered feature, and the quantification of the uncertainty that is consequential to the small size of the dataset. The analysis of miRNAs such as miR-21 and miR-92a, alongside the protein biomarker KL-6, was identified as a significant indicator for PPF diagnosis, enhancing both the sensitivity and specificity of predictions. Conclusions: The identification of specific genetic markers such as microRNAs and their integration with traditional clinical characteristics can significantly enhance the management of patients with the disease. This multidimensional approach, which integrates clinical data with omics data, could enable more precise identification and monitoring of the disease and potentially optimize future treatments through larger studies and extended follow-ups. Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
Show Figures

Figure 1

9 pages, 202 KiB  
Review
The Role of Genetic Testing in Palliative Care Decisions for Critically Ill Newborns
by Ashley Mowery and Luca Brunelli
Children 2025, 12(5), 634; https://doi.org/10.3390/children12050634 - 15 May 2025
Viewed by 325
Abstract
Genetic testing is rapidly becoming standard practice in the care of critically ill newborns within NICUs. Numerous studies have demonstrated the utility of genetic testing, including changes in clinical care, improved diagnostic certainty, and cost savings, related to a reduced length of hospital [...] Read more.
Genetic testing is rapidly becoming standard practice in the care of critically ill newborns within NICUs. Numerous studies have demonstrated the utility of genetic testing, including changes in clinical care, improved diagnostic certainty, and cost savings, related to a reduced length of hospital stay. Changes in clinical management reported in previous studies also included redirection to comfort or end-of-life care. However, it has been difficult to study the influence of genetic testing in the redirection of care decisions within the NICU because of the complexity of the medical decision-making process. Redirection of care decisions are deeply personal for each individual family and often must be made in the setting of clinical instability and diagnostic and prognostic uncertainty. A recent study exploring the impact of genetic testing in redirection of care decisions by surveying palliative care providers suggested genetic testing plays a minor role in decisions to redirect to end-of-life care or in the implementation of DNR/DNI orders. However, factors such inadequate treatment options were found to be important in redirection of care decisions, implying the need for further investigation to clarify the role of genetic testing. Future studies will need to focus on how genetic information affects healthcare provider recommendations regarding palliative care and how families use this information to make end-of-life care decisions. Full article
12 pages, 674 KiB  
Article
The ‘Surprise’ Question in Haemato-Oncology: The Estimating Physician and Time to Death Reduce the Prognostic Uncertainty—An Observational Study
by Christina Gerlach, Martin Weber and Irene Schmidtmann
Cancers 2025, 17(8), 1326; https://doi.org/10.3390/cancers17081326 - 15 Apr 2025
Viewed by 392
Abstract
Background/Objectives: Patients with haematological malignancies less frequently receive specialist palliative care, although they may have unmet needs for symptom control and alleviating psychosocial and existential burdens. The ‘Surprise’ Question, ‘Would you be surprised if this patient died in the next 12 months?’, helps [...] Read more.
Background/Objectives: Patients with haematological malignancies less frequently receive specialist palliative care, although they may have unmet needs for symptom control and alleviating psychosocial and existential burdens. The ‘Surprise’ Question, ‘Would you be surprised if this patient died in the next 12 months?’, helps physicians to identify patients who may benefit from palliative care. We tested the influencing factors of the feasibility of the ‘Surprise’ Question in haemato-oncology outpatients. Methods: We performed a prospective cohort study comparing patients with solid tumours and haematological malignancies. All the patients in the haemato-oncology outpatient clinics of a German university hospital were screened by haemato-oncologists using the ‘Surprise’ Question. Results: A survival analysis was performed on 672 patients (76% with haematological malignancies) at 3 and 12 months. Within one year, 110 patients (16%) died. Of these, 30/52 (58%) were patients with solid tumours, but only 12/53 (23%) patients with haematological malignancies were identified in advance by the ‘Surprise’ Question, which reflects ambiguous test sensitivity. A substantial part of the haematology patients in their last year of life were not identified (77%). The match between the survival estimates and actual outcomes was fair (Cohen’s kappa 0.37). The proximity from prediction to event and the estimating physician rather than patient characteristics influenced the accuracy of the instrument. Conclusions: For the first time, the feasibility of the ‘Surprise’ Question in haematology outpatients was proven. Factors that would improve haemato-oncologists’ clinical intuition should be further explored to facilitate timely conversations about issues important to patients nearing the end of life. Full article
(This article belongs to the Special Issue Integrating Palliative Care in Oncology)
Show Figures

Figure 1

26 pages, 1261 KiB  
Review
Strategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging
by Anh T. Tran, Tal Zeevi and Seyedmehdi Payabvash
BioMedInformatics 2025, 5(2), 20; https://doi.org/10.3390/biomedinformatics5020020 - 14 Apr 2025
Cited by 1 | Viewed by 4225
Abstract
Artificial Intelligence (AI) and deep learning models have revolutionized diagnosis, prognostication, and treatment planning by extracting complex patterns from medical images, enabling more accurate, personalized, and timely clinical decisions. Despite its promise, challenges such as image heterogeneity across different centers, variability in acquisition [...] Read more.
Artificial Intelligence (AI) and deep learning models have revolutionized diagnosis, prognostication, and treatment planning by extracting complex patterns from medical images, enabling more accurate, personalized, and timely clinical decisions. Despite its promise, challenges such as image heterogeneity across different centers, variability in acquisition protocols and scanners, and sensitivity to artifacts hinder the reliability and clinical integration of deep learning models. Addressing these issues is critical for ensuring accurate and practical AI-powered neuroimaging applications. We reviewed and summarized the strategies for improving the robustness and generalizability of deep learning models for the segmentation and classification of neuroimages. This review follows a structured protocol, comprehensively searching Google Scholar, PubMed, and Scopus for studies on neuroimaging, task-specific applications, and model attributes. Peer-reviewed, English-language studies on brain imaging were included. The extracted data were analyzed to evaluate the implementation and effectiveness of these techniques. The study identifies key strategies to enhance deep learning in neuroimaging, including regularization, data augmentation, transfer learning, and uncertainty estimation. These approaches address major challenges such as data variability and domain shifts, improving model robustness and ensuring consistent performance across diverse clinical settings. The technical strategies summarized in this review can enhance the robustness and generalizability of deep learning models for segmentation and classification to improve their reliability for real-world clinical practice. Full article
(This article belongs to the Section Imaging Informatics)
Show Figures

Figure 1

12 pages, 2016 KiB  
Article
Machine Health Indicators and Digital Twins
by Tal Bublil, Roee Cohen, Ron S. Kenett and Jacob Bortman
Sensors 2025, 25(7), 2246; https://doi.org/10.3390/s25072246 - 2 Apr 2025
Cited by 2 | Viewed by 1106
Abstract
Health indicators (HIs) are quantitative indices that assess the condition of engineering systems by linking sensor data with monitoring, diagnostic, and prognostic methods to estimate the remaining useful life (RUL). Digital twins (DTs), which serve as digital representations of physical assets, enhance system [...] Read more.
Health indicators (HIs) are quantitative indices that assess the condition of engineering systems by linking sensor data with monitoring, diagnostic, and prognostic methods to estimate the remaining useful life (RUL). Digital twins (DTs), which serve as digital representations of physical assets, enhance system monitoring, diagnostics, and prognostics by operationalizing analytic capabilities derived from sensor data. This paper explores the integration of HIs and DTs, illustrating their roles in condition-based maintenance and structural health monitoring. The methodologies discussed span data-driven and physics-based approaches, emphasizing their applications in rotary machinery, including bearings and gears. These approaches not only detect anomalies but also predict system failures through advanced modeling and machine learning (ML) techniques. The paper provides examples of HIs derived from vibration analysis and soft sensors and maps future research directions for improving health monitoring systems through hybrid modeling and uncertainty quantification. It concludes by addressing the challenges of data labeling and uncertainties and the role of HIs in advancing performance engineering, making DTs a pivotal tool in predictive maintenance strategies. Full article
Show Figures

Figure 1

23 pages, 6020 KiB  
Article
A Weighted-Transfer Domain-Adaptation Network Applied to Unmanned Aerial Vehicle Fault Diagnosis
by Jian Yang, Hairong Chu, Lihong Guo and Xinhong Ge
Sensors 2025, 25(6), 1924; https://doi.org/10.3390/s25061924 - 19 Mar 2025
Cited by 2 | Viewed by 488
Abstract
With the development of UAV technology, the composition of UAVs has become increasingly complex, interconnected, and tightly coupled. Fault features are characterized by weakness, nonlinearity, coupling, and uncertainty. A promising approach is the use of deep learning methods, which can effectively extract useful [...] Read more.
With the development of UAV technology, the composition of UAVs has become increasingly complex, interconnected, and tightly coupled. Fault features are characterized by weakness, nonlinearity, coupling, and uncertainty. A promising approach is the use of deep learning methods, which can effectively extract useful diagnostic information from weak, coupled, nonlinear data from inputs with background noise. However, due to the diversity of flight environments and missions, the distribution of the obtained sample data varies. The types of fault data and corresponding labels under different conditions are unknown, and it is time-consuming and expensive to label sample data. These challenges reduce the performance of traditional deep learning models in anomaly detection. To overcome these challenges, a novel weighted-transfer domain-adaptation network (WTDAN) method is introduced to realize the online anomaly detection and fault diagnosis of UAV electromagnetic-sensitive flight data. The method is based on unsupervised transfer learning, which can transfer the knowledge learnt from existing datasets to solve problems in the target domain. The method contains three novel multiscale modules: a feature extractor, used to extract multidimensional features from the input; a domain discriminator, used to improve the imbalance of the data distribution between the source domain and the target domain; and a label classifier, used to classify data categories for the target domain. Multilayer domain adaptation is used to reduce the distance between the source domain datasets and the target domain datasets distributions. The WTDAN assigns different weights to the source domain samples in order to weight the different contributions of source samples to solve the problem during the training process. The dataset adopts not only open datasets from the website but also test datasets from experiments to evaluate the transferability of the proposed WTDAN model. The experimental results show that, under the condition of fewer anomalous target data samples, the proposed method had a classification accuracy of up to 90%, which is higher than that of the other compared methods, and performed with superior transferability on the cross-domain datasets. The capability of fault diagnosis can provide a novel method for online anomaly detection and the prognostics and health management (PHM) of UAVs, which, in turn, would improve the reliability, repairability, and safety of UAV systems. Full article
(This article belongs to the Section Fault Diagnosis & Sensors)
Show Figures

Figure 1

23 pages, 6169 KiB  
Article
Uncertain Particle Filtering: A New Real-Time State Estimation Method for Failure Prognostics
by Jingyu Liang, Yinghua Shao, Waichon Lio, Jie Liu and Rui Kang
Mathematics 2025, 13(5), 702; https://doi.org/10.3390/math13050702 - 21 Feb 2025
Cited by 1 | Viewed by 573
Abstract
Particle filtering (PF) has become a state-of-the-art method in predicting the future degradation trend of the target equipment based on its current state, with its advantage in sequentially processing the observed data for continual state estimation. The convergence speed is important in PF [...] Read more.
Particle filtering (PF) has become a state-of-the-art method in predicting the future degradation trend of the target equipment based on its current state, with its advantage in sequentially processing the observed data for continual state estimation. The convergence speed is important in PF for real-time state estimation. However, the Bayesian theorem can only converge when sufficient observations are available, which does not always fulfill the requirement in time-varying scenarios with abrupt changes in health state. In this work, based on the newly proposed Uncertainty Theory, Uncertain Particle Filtering (UPF) is derived for the first time. The initialization, prediction, update, and resampling processes are explained in detail in the scope of Uncertainty Theory. The UPF method significantly improves the performance of traditional particle filters by enhancing the speed of convergence in dynamic parameter estimation. Resampling techniques are introduced to mitigate particle phagocytosis, thereby improving computational accuracy and efficiency. Two case studies, addressing the degradation of the capacitor in an enhanced electromagnetic railgun and the degradation of the battery, are conducted to verify the effectiveness of the proposed UPF method. The results show that the UPF method achieves a faster convergence speed compared to traditional approaches. Full article
Show Figures

Figure 1

Back to TopTop