-
Fetal Cerebral Blood Flow (Dys)autoregulation -
From Lab to Clinic: Artificial Intelligence with Spectroscopic Liquid Biopsies -
Multi-Task Deep Learning on MRI for Tumor Segmentation and Treatment Response Prediction in an Experimental Model of Hepatocellular Carcinoma -
Current Concepts of the Applications and Treatment Implications of Drug-Induced Sleep Endoscopy for the Management of Obstructive Sleep Apnoea
Journal Description
Diagnostics
Diagnostics
is an international, peer-reviewed, open access journal on medical diagnosis published semimonthly online by MDPI. The British Neuro-Oncology Society (BNOS), the International Society for Infectious Diseases in Obstetrics and Gynaecology (ISIDOG) and the Swiss Union of Laboratory Medicine (SULM) are affiliated with Diagnostics and their members receive a discount on the article processing charges.
- Open Access— free for readers, with article processing charges (APC) paid by authors or their institutions.
- High Visibility: indexed within Scopus, SCIE (Web of Science), PubMed, PMC, Embase, Inspec, CAPlus / SciFinder, and other databases.
- Journal Rank: JCR - Q1 (Medicine, General and Internal) / CiteScore - Q2 (Internal Medicine)
- Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 21.6 days after submission; acceptance to publication is undertaken in 2.7 days (median values for papers published in this journal in the second half of 2025).
- Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.
- Companion journals for Diagnostics include: LabMed and AI in Medicine.
Impact Factor:
3.3 (2024);
5-Year Impact Factor:
3.3 (2024)
Latest Articles
NF1 with Multiple Cardiac Structural Abnormalities Leading to Cerebral Infarction
Diagnostics 2026, 16(1), 163; https://doi.org/10.3390/diagnostics16010163 (registering DOI) - 4 Jan 2026
Abstract
Background/Objectives: Neurofibromatosis type 1 (NF1) is an autosomal dominant disorder driven by mutations in the NF1 gene, whose pathogenesis centers on the loss of neurofibromin function and subsequent hyperactivation of the RAS/MAPK pathway. Notably, to the best of our knowledge and following
[...] Read more.
Background/Objectives: Neurofibromatosis type 1 (NF1) is an autosomal dominant disorder driven by mutations in the NF1 gene, whose pathogenesis centers on the loss of neurofibromin function and subsequent hyperactivation of the RAS/MAPK pathway. Notably, to the best of our knowledge and following a systematic literature search conducted by our research team, no cases of NF1 complicated by severe cardiac structural abnormalities that ultimately lead to cerebral infarction have been reported to date. Thus, it is of paramount importance to avoid missed diagnosis by performing comprehensive cardiac-related examinations in patients with NF1. Case Presentation: A 20-year-old male patient diagnosed with NF1 presented with right-sided limb weakness and was initially identified with cerebral infarction. To clarify the underlying etiology, a comprehensive clinical evaluation was performed, including cardiac imaging assessments (to characterize cardiac structural changes) and whole-exome sequencing (to identify the presence of procoagulant gene mutations). Comprehensive evaluation revealed a spectrum of cardiac structural abnormalities in the patient: aortic valve prolapse with severe regurgitation, non-infective vegetations on the aortic valve leaflets, mild-to-moderate mitral regurgitation, left ventricular hypertrophy and dilation, and left atrial dilation. Whole-exome sequencing detected exclusively a pathogenic variant in the NF1 gene, with no other pathogenic/likely pathogenic variants or thrombophilia-associated polymorphisms being found. Laboratory investigations ruled out infectious etiologies, supporting the notion that NF1-mediated cardiac structural and developmental anomalies are the primary driver of cardiac vegetation formation, given the absence of other identified contributing factors; embolization of one such vegetation ultimately led to both splenic and cerebral infarction. Conclusions: This case emphasizes the necessity of implementing early and proactive cardiac evaluations in patients with NF1. Additionally, for NF1 individuals—particularly those presenting with suggestive vascular or cardiac symptoms—a comprehensive multifactorial assessment of thrombotic risk is critical. Collectively, maintaining clinical vigilance for cardiac abnormalities in NF1 patients and avoiding diagnostic oversight is essential to reduce life-threatening risks.
Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
►
Show Figures
Open AccessArticle
Sinus Tarsi Morphometry Is Correlated with Flatfoot Severity on Weight-Bearing CT
by
Bingshu Chen, Xing Gao, Ying Xu, Tianyuan Zhao, Siyao Yang, Yuan Liu, Bin Jiang, Xihan Zhou, Xiaoqiang Chen, Wencui Li and Jiawei Guo
Diagnostics 2026, 16(1), 162; https://doi.org/10.3390/diagnostics16010162 (registering DOI) - 4 Jan 2026
Abstract
Background: Flexible flatfoot is a common musculoskeletal disorder in adolescents, which is characterized by a collapsed longitudinal arch. A common surgery like subtalar arthroereisis depends on the implant in sinus tarsi. Optimal match between them can potentially avoid postoperative pain and obtain improved
[...] Read more.
Background: Flexible flatfoot is a common musculoskeletal disorder in adolescents, which is characterized by a collapsed longitudinal arch. A common surgery like subtalar arthroereisis depends on the implant in sinus tarsi. Optimal match between them can potentially avoid postoperative pain and obtain improved prognosis. Investigations into anatomical morphology of sinus tarsi by weight-bearing CT (WBCT) may unveil the pathogenesis and facilitate the treatment of flexible flatfoot. Methods: This retrospective study included 28 control cases and 42 flatfoot cases. The sinus tarsi length (STL), the sinus tarsi width (STW), the angle between its long axis and the horizontal line (ST-H angle), the sinus tarsi angle (ST angle), and the tibial width were measured. We also calculated two ratios (STL/tibia width and STW/tibia width) to standardize individual differences. Data analysis was conducted via mean/median comparisons and subsequent linear regression. Results: The STL and the STL/tibia width were significantly greater in the flatfoot group (25.73 ± 3.50 vs. 23.09 ± 3.77 mm, p = 0.004; 0.90 ± 0.15 vs. 0.81 ± 0.14, p = 0.009). The ST angle was significantly smaller in the flatfoot group by an average of 4.63° (13.20° vs. 17.83°, p < 0.001). Linear regression revealed that female gender and smaller ST angle were significantly correlated with higher Meary angle, while smaller ST angle and greater STL/tibia width were significantly correlated with lower Pitch angle (p = 0.002, p = 0.007; p = 0.003, p = 0.004). No statistical predictive effects were observed for the other variables. Conclusions: The ST angle and STL/tibia width may serve as auxiliary parameters for implant selection in subtalar arthroereisis to improve sizing match within the sinus tarsi.
Full article
(This article belongs to the Section Medical Imaging and Theranostics)
►▼
Show Figures

Figure 1
Open AccessSystematic Review
Challenges in the Classification of Cardiac Arrhythmias and Ischemia Using End-to-End Deep Learning and the Electrocardiogram: A Systematic Review
by
Edgard Oporto, David Mauricio, Nelson Maculan and Giuliana Uribe
Diagnostics 2026, 16(1), 161; https://doi.org/10.3390/diagnostics16010161 (registering DOI) - 4 Jan 2026
Abstract
Background: Cardiac arrhythmias and ischemia are increasingly problematic worldwide because of their frequency, as well as the economic burden they confer. Methods: This research presents a systematic literature review (SLR), based on the PRISMA 2020 statement, that looks into the difficulties
[...] Read more.
Background: Cardiac arrhythmias and ischemia are increasingly problematic worldwide because of their frequency, as well as the economic burden they confer. Methods: This research presents a systematic literature review (SLR), based on the PRISMA 2020 statement, that looks into the difficulties in their classification using end-to-end deep learning (DL) techniques and the electrocardiogram (ECG) from 2019 to 2025. A total of 121 relevant studies were identified from Scopus, Web of Science, and IEEE Xplore, and an inventory was created, categorized into six facets that researchers apply in DL studies: preprocessing, DL architectures, databases, evaluation metrics, pathologies, and explainability techniques. Results: Fifty-three challenges were reported, divided between end-to-end DL techniques (15), databases (18), pathologies (9), preprocessing (2), explainability (8), and evaluation metrics (1). Some of the complications identified were the complexity of pathological manifestations in the ECG signal, the large number of classes, the use of multiple leads, comorbidity, and the presence of different factors that change the expected patterns. Crucially, this SLR identified 18 new issues: four related to preprocessing, three related to end-to-end DL, one to databases, one to pathologies, four to metrics, and five to explainability. Particularly notable are the limitations of current metrics for assessing explainability and model decision confidence. Conclusions: This study clarifies all these limitations and provides a structured inventory and discussion of them, which can be useful to researchers, clinicians, and developers in enhancing existing techniques and designing new ECG-based end-to-end DL strategies, leading to more robust, generalizable, and reliable solutions.
Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼
Show Figures

Figure 1
Open AccessArticle
The Role of Aurora Kinase A in HBV-Associated Hepatocellular Carcinomas: A Molecular and Immunohistochemical Study
by
Mustafa Huz, Nese Karadag Soylu, Ahmet Koc, Zeynep Kucukakcali, Nefsun Danis and Onural Ozhan
Diagnostics 2026, 16(1), 160; https://doi.org/10.3390/diagnostics16010160 (registering DOI) - 4 Jan 2026
Abstract
Objectives: Although Aurora kinase A (AURKA) expression has been investigated in many cancer types, studies focusing on its role in hepatitis B virus-associated hepatocellular carcinoma (HBV-HCC) are limited. In this study, we examined the activity of AURKA and its substrates (PLK1, P53, and
[...] Read more.
Objectives: Although Aurora kinase A (AURKA) expression has been investigated in many cancer types, studies focusing on its role in hepatitis B virus-associated hepatocellular carcinoma (HBV-HCC) are limited. In this study, we examined the activity of AURKA and its substrates (PLK1, P53, and BRCA1) in HBV-HCC and cryptogenic hepatocellular carcinoma (Cr-HCC) cases. Methods: The study groups consisted of HBV-HCC, Cr-HCC, and healthy liver tissue cases. AURKA copy number variation (CNV) was analyzed using molecular methods. AURKA expression was evaluated by molecular and immunohistochemical (IHC) methods. AURKA substrates P53Ser315, PLK1Thr210, and BRCA1 were also analyzed by IHC. Results: There was no increase in AURKA gene copy number among the groups (2−∆∆Ct < 2). AURKA level was significantly increased in both test groups (p < 0.001). At the protein level, AURKA was significantly higher in both cancer groups compared to the control group (p < 0.001). Phospho-P53Ser315 levels were significantly higher in both HBV-HCC and Cr-HCC groups compared to the control group (p = 0.002 and p < 0.001, respectively). Cr-HCC cases also showed significantly higher levels compared to HBV-HCC (p = 0.025). For phospho-PLK1Thr210, Cr-HCC cases showed statistically higher expression compared to both the control group and HBV-HCC cases (p = 0.001).
Full article
(This article belongs to the Special Issue Hepatocellular Carcinoma: Diagnosis and Management)
►▼
Show Figures

Figure 1
Open AccessArticle
Anatomy-Guided Hybrid CNN–ViT Model with Neuro-Symbolic Reasoning for Early Diagnosis of Thoracic Diseases Multilabel
by
Naif Almughamisi, Gibrael Abosamra, Adnan Albar and Mostafa Saleh
Diagnostics 2026, 16(1), 159; https://doi.org/10.3390/diagnostics16010159 (registering DOI) - 4 Jan 2026
Abstract
Background/Objectives: The clinical adoption of AI in radiology requires models that balance high accuracy with interpretable, anatomically plausible reasoning. This study presents an integrated diagnostic framework that addresses this need by unifying a hybrid deep-learning architecture with explicit anatomical guidance and neuro-symbolic
[...] Read more.
Background/Objectives: The clinical adoption of AI in radiology requires models that balance high accuracy with interpretable, anatomically plausible reasoning. This study presents an integrated diagnostic framework that addresses this need by unifying a hybrid deep-learning architecture with explicit anatomical guidance and neuro-symbolic inference. Methods: The proposed system employs a dual-path model: an enhanced EfficientNetV2 backbone extracts hierarchical local features, whereas a refined Vision Transformer captures global contextual dependencies across the thoracic cavity. These representations are fused and critically disciplined through auxiliary segmentation supervision using CheXmask. This anchors the learned features to lung and cardiac anatomy, reducing reliance on spurious artifacts. This anatomical basis is fundamental to the interpretability pipeline. It confines Gradient-weighted Class Activation Mapping (Grad-CAM) visual explanations to clinically valid regions. Then, a novel neuro-symbolic reasoning layer is introduced. Using a fuzzy logic engine and radiological ontology, this module translates anatomically aligned neural activations into structured, human-readable diagnostic statements that explicitly articulate the model’s clinical rationale. Results: Evaluated on the NIH ChestX-ray14 dataset, the framework achieved a macro-AUROC of 0.9056 and a macro-accuracy of 93.9% across 14 pathologies, with outstanding performance on emphysema (0.9694), hernia (0.9711), and cardiomegaly (0.9589). The model’s generalizability was confirmed through external validation on the CheXpert dataset, yielding a macro-AUROC of 0.85. Conclusions: This study demonstrates a cohesive path toward clinically transparent and trustworthy AI by seamlessly integrating data-driven learning with anatomical knowledge and symbolic reasoning.
Full article
(This article belongs to the Special Issue Artificial Intelligence for Health and Medicine)
►▼
Show Figures

Figure 1
Open AccessArticle
Systemic Sclerosis-Associated ILD: Insights and Limitations of ScleroID
by
Cristina Niță and Laura Groșeanu
Diagnostics 2026, 16(1), 158; https://doi.org/10.3390/diagnostics16010158 (registering DOI) - 4 Jan 2026
Abstract
Background/Objective: Pulmonary involvement in systemic sclerosis (SSc) is typically assessed using pulmonary function tests (PFTs), high-resolution CT (HRCT), and composite indices. Patient-reported outcomes (PRO), including ScleroID, provide insight into quality of life, but their relationship with clinical measures and role in overall disease
[...] Read more.
Background/Objective: Pulmonary involvement in systemic sclerosis (SSc) is typically assessed using pulmonary function tests (PFTs), high-resolution CT (HRCT), and composite indices. Patient-reported outcomes (PRO), including ScleroID, provide insight into quality of life, but their relationship with clinical measures and role in overall disease assessment remain unclear. To assess the correlation between ScleroID scores and both lung involvement and disease activity/damage in a cohort of SSc-ILD patients from a large tertiary care center. Methods: Disease activity [European Scleroderma Study Group Activity Index (EScSG-AI), Scleroderma Clinical Trials Consortium Activity Index (SCTC-AI)], disease severity [Medsger severity scale (MSS)], and PRO measure ScleroID were assessed for associations with the extent and severity of SSc-ILD. Results: In 82 patients with SSc-ILD (mean age 56.0 ± 10.8 years; median disease duration 4.2 ± 4.7 years), higher fibrosis extent (>20%) was associated with worse lung function, greater exercise limitation, and higher ScleroID scores, particularly in fatigue, social life, and body mobility domains (all p ≤ 0.03). Patients with >20% fibrosis also had worse NYHA class and Borg scores during 6-MWD (p < 0.001). Cross-sectional correlations showed that ScleroID total and individual domains were negatively associated with FVC% and 6-MWD, and positively with ILD extent on HRCT. Fatigue, social impact, and mobility domains correlated most strongly with disease activity and severity scores, especially in patients with > 20% fibrosis (r = 0.384–0.635, all p ≤ 0.016), whereas breathlessness showed minimal associations (r < 0.2). Conclusions: In SSc-ILD, greater lung fibrosis and functional impairment are associated with worse patient-reported quality of life, particularly in fatigue, mobility, and social domains. ScleroID scores reflect both physiological severity and disease burden highlighting its value as a multidimensional outcome measure in patients with more advanced disease.
Full article
(This article belongs to the Special Issue Lung Involvement in Connective Tissue Disease: Advances in Diagnosis and Management)
►▼
Show Figures

Figure 1
Open AccessArticle
Live-Cell-Based Assay Outperforms Fixed Assay in MOGAD Diagnosis: A Retrospective Validation Against the 2023 International Criteria
by
Anna Zhou, Weihua Zhang, Ji Zhou, Changhong Ren, Ke Zhan, Wenhan Li, Hui Xiong and Xiaotun Ren
Diagnostics 2026, 16(1), 157; https://doi.org/10.3390/diagnostics16010157 (registering DOI) - 4 Jan 2026
Abstract
Background and Objective: Myelin oligodendrocyte glycoprotein (MOG) antibody-associated disease (MOGAD) is a significant component of demyelinating diseases in pediatric populations. Recently, diagnostic criteria for MOGAD were established. This study aims to evaluate and compare the diagnostic efficacy of the fixed-cell-based assay (Fixed-CBA)
[...] Read more.
Background and Objective: Myelin oligodendrocyte glycoprotein (MOG) antibody-associated disease (MOGAD) is a significant component of demyelinating diseases in pediatric populations. Recently, diagnostic criteria for MOGAD were established. This study aims to evaluate and compare the diagnostic efficacy of the fixed-cell-based assay (Fixed-CBA) and the live cell-based assay (Live-CBA) in patients who meet the 2023 clinical diagnostic criteria for MOGAD. Methods: This retrospective study included patients suspected of having MOGAD who were enrolled between June 2023 and June 2024. Patients were selected based on the “core clinical demyelinating events” outlined in the 2023 proposed criteria of the International MOGAD Panel. Patients with multiple sclerosis (MS), neuromyelitis optica spectrum disorders (NMOSD) with aquaporin-4 antibody-positive (AQP4-Abs-positive), and non-central nervous system (non-CNS) inflammatory diseases were chosen as controls. Serum samples were simultaneously tested for MOG-Abs using Fixed-CBA and Live-CBA. Results: A total of 86 patients were enrolled in the study: 52 in the suspected MOGAD group and 34 in the control group. Out of these patients studied, 16 presented with optic neuritis (ON), 5 with myelitis, 8 with acute disseminated encephalomyelitis (ADEM), and 7 with cortical encephalitis. Sixteen patients could not be classified by clinical phenotype. The highest MOG-Ab positivity rate was among patients with cortical encephalitis [85.7% (Live-CBA)/71.4% (Fixed-CBA)]. Both assays identified 22 positive samples, with Fixed-CBA and Live-CBA sensitivities at 44.2% and 55.8%, respectively, and a specificity of 97%. Of the patients suspected of having MOGAD, 19 cases were confirmed using the Fixed-CBA, while 28 cases were confirmed using the Live-CBA. This resulted in an upgrade in diagnostic classification for nine cases. This led to a diagnostic reclassification in nine cases. Conclusions: Both the Fixed-CBA and Live-CBA were associated with higher sensitivity for patients selected based on the 2023 MOGAD clinical diagnostic criteria. The Live-CBA exhibited an 11.6% increase in sensitivity, contributing to a 17.3% (9/52) enhancement in clinical diagnostic accuracy.
Full article
(This article belongs to the Section Clinical Diagnosis and Prognosis)
►▼
Show Figures

Figure 1
Open AccessCase Report
Ultrasound-Guided Dextrose Hydrodissection for Mixed Sensory–Motor Wartenberg’s Syndrome Following a Healed Scaphoid Fracture: A Case Report
by
Yonghyun Yoon, King Hei Stanley Lam, Jeimylo C. de Castro, Jihyo Hwang, Jaeyoung Lee, Teinny Suryadi, Anwar Suhaimi, Chun-Wei Kang, Jaeik Choi and Seungbeom Kim
Diagnostics 2026, 16(1), 156; https://doi.org/10.3390/diagnostics16010156 (registering DOI) - 4 Jan 2026
Abstract
Background and Clinical Significance: Wartenberg’s syndrome (cheiralgia paresthetica) is classically described as a pure sensory neuropathy of the superficial branch of the radial nerve (SBRN). However, in rare circumstances, dynamic mechanical irritation around the radial styloid may produce an atypical clinical phenotype
[...] Read more.
Background and Clinical Significance: Wartenberg’s syndrome (cheiralgia paresthetica) is classically described as a pure sensory neuropathy of the superficial branch of the radial nerve (SBRN). However, in rare circumstances, dynamic mechanical irritation around the radial styloid may produce an atypical clinical phenotype with concurrent motor impairment, broadening the clinical significance of recognizing motion-related compression mechanisms. Case Presentation: A 35-year-old woman presented with persistent dorsoradial wrist pain and numbness, accompanied by progressive weakness of thumb extension, five years after a conservatively treated nondisplaced scaphoid fracture. Neurological examination demonstrated sensory loss in the SBRN distribution and Medical Research Council (MRC) grade 3/5 strength of the extensor pollicis longus (EPL). Nerve conduction studies revealed a markedly prolonged EPL motor latency (4.5 ms; normal ≤ 2.5 ms) with preserved sensory conduction. High-resolution ultrasound showed focal enlargement of the SBRN (cross-sectional area 0.13 cm2) and, critically, dynamic snapping of the nerve over the radial styloid that reproduced the patient’s symptoms. The patient underwent ten weekly sessions of ultrasound-guided hydrodissection with 5% dextrose. After treatment, the pain Visual Analog Scale improved from 8/10 to 0/10 and EPL strength recovered to MRC 5/5. Follow-up nerve conduction studies demonstrated normalization of EPL motor latency (2.1 ms), and repeat ultrasound confirmed resolution of SBRN enlargement and snapping. Conclusions: This case expands the phenotype of Wartenberg’s syndrome to include mixed sensory–motor involvement associated with dynamic SBRN snapping at the radial styloid. Dynamic ultrasound was pivotal for identifying the motion-dependent mechanism, and ultrasound-guided 5% dextrose hydrodissection achieved complete sensory and motor recovery as a minimally invasive and effective treatment option.
Full article
(This article belongs to the Special Issue Advanced Ultrasound Techniques in Diagnosis)
►▼
Show Figures

Figure 1
Open AccessReview
Milestone to Ensure Safety and Efficacy of Companion Diagnostic (CDx) That Support Treatment Decisions in Cancer Patients
by
Sulim Kang and Sungmin Kim
Diagnostics 2026, 16(1), 155; https://doi.org/10.3390/diagnostics16010155 (registering DOI) - 4 Jan 2026
Abstract
As demand for biomarker-based companion diagnostics (CDx) tests in clinical oncology of precision medicine increases, a clear understanding of the regulatory framework (especially analytical and clinical performance) is imperative to ensure the safety and efficacy of CDx in enhancing patient quality of life
[...] Read more.
As demand for biomarker-based companion diagnostics (CDx) tests in clinical oncology of precision medicine increases, a clear understanding of the regulatory framework (especially analytical and clinical performance) is imperative to ensure the safety and efficacy of CDx in enhancing patient quality of life and aiding in treatment decisions. This study analyzes the regulatory policies and approval reports in major countries and identifies regulatory checklists for the pre- and post-marketing analytical and clinical performance to ensure safety and efficacy of CDx. It categorizes the pre-marketing analysis into four commonly used techniques, IHC, FISH, PCR, and NGS, reflecting the diversity of CDx types. All analyses are grounded in the latest regulations and guidelines. The developed checklists were subjected to feasibility assessment by industry experts. Our analysis revealed that there are differences in the pre- and post-marketing regulatory frameworks for CDx, reflecting unique characteristics of each country. In particular, differences were observed in the safety and efficacy assessment methods applied to the platform based on technological principle. Evidence-based checklists are established, which support manufacturers in implementing efficient practices and creating systematic regulatory strategies. Furthermore, these checklists facilitate global market access, activate R&D, enhance clinical implementation, and improve licensing practices.
Full article
(This article belongs to the Section Pathology and Molecular Diagnostics)
Open AccessArticle
A Pilot Study of Klebsiella pneumoniae in Community-Acquired Pneumonia: Comparative Insights from Culture and Targeted Next-Generation Sequencing
by
Vyacheslav Beloussov, Vitaliy Strochkov, Nurlan Sandybayev, Alyona Lavrinenko and Maxim Solomadin
Diagnostics 2026, 16(1), 154; https://doi.org/10.3390/diagnostics16010154 (registering DOI) - 4 Jan 2026
Abstract
Background/Objectives: Klebsiella pneumoniae is a major Gram-negative pathogen associated with community-acquired pneumonia (CAP) and a critical contributor to antimicrobial resistance (AMR). Culture-based diagnostics remain the clinical standard but may underestimate microbial diversity and resistance gene profiles. This pilot study compared pathogen detection
[...] Read more.
Background/Objectives: Klebsiella pneumoniae is a major Gram-negative pathogen associated with community-acquired pneumonia (CAP) and a critical contributor to antimicrobial resistance (AMR). Culture-based diagnostics remain the clinical standard but may underestimate microbial diversity and resistance gene profiles. This pilot study compared pathogen detection and antimicrobial resistance gene (ARG) repertoires in matched K. pneumoniae pure cultures and primary sputum samples using targeted next-generation sequencing (tNGS). Methods: We analyzed 153 sputum samples from patients with CAP. Among 48 culture-positive cases, 22 (14% overall; 54% culture-positive) yielded K. pneumoniae. MALDI-TOF MS, phenotypic drug susceptibility testing, and tNGS were conducted on both culture isolates and matched sputum specimens. Microbial composition, ARG diversity, and method concordance were evaluated, with focused analysis of discordant and fatal cases. Results: K. pneumoniae was detected in 14.4% of all CAP cases and accounted for 54.2% of culture-positive samples. Identification rates differed across methods: 35% by MALDI-TOF MS, 45% by culture tNGS, and 29% by sputum tNGS. Sputum tNGS revealed substantially higher microbial diversity than cultures (3.04 vs. 1.42 species per sample) and detected more than sixfold unique ARGs (38 vs. 7), including clinically relevant determinants that were absent from culture isolates. Concordance was high between MALDI-TOF MS and culture tNGS (κ = 0.712), but low between sputum and culture tNGS (κ = 0.279). Among twelve K. pneumoniae isolates included in AMR analysis, all showed resistance to β-lactams, and two-thirds exhibited MDR/XDR phenotypes. Genotypic screening identified seven ARGs, but major ESBL and carbapenemase genes were not detected, suggesting the presence of alternative resistance mechanisms. Overall, sputum tNGS provided additional etiological and resistome information not captured by cultivation and complemented classical diagnostics in CAP involving K. pneumoniae. Conclusions: Culture-based diagnostics and tNGS provide complementary insights into the detection and resistance profiling of K. pneumoniae in CAP, with sputum tNGS revealing broader microbial and resistome information than pure cultures, while classical methods remain essential for species confirmation and phenotypic AST. An integrated diagnostic approach combining both methodologies may improve pathogen detection, guide antimicrobial therapy, and enhance AMR surveillance in K. pneumoniae-associated CAP.
Full article
(This article belongs to the Special Issue Applications of Next-Generation Sequencing Technologies for the Diagnosis and Management of Infectious Diseases)
►▼
Show Figures

Figure 1
Open AccessArticle
Integrated Cross-Platform Analysis Reveals Candidate Variants and Linkage Disequilibrium-Defined Loci Associated with Osteoporosis in Korean Postmenopausal Women
by
Su Kang Kim, Seoung-Jin Hong, Seung Il Song, Jeong Keun Lee, Gyutae Kim, Byung-Joon Choi, Suyun Seon, Seung Jun Kim, Ju Yeon Ban and Sang Wook Kang
Diagnostics 2026, 16(1), 153; https://doi.org/10.3390/diagnostics16010153 (registering DOI) - 3 Jan 2026
Abstract
Background: Osteoporosis is highly prevalent in postmenopausal women, yet genome-wide association studies often miss disease-relevant variants because of incomplete single nucleotide polymorphism (SNP) coverage and platform-specific limitations. We aimed to identify genetic contributors to osteoporosis risk by integrating two exome-based genotyping platforms with
[...] Read more.
Background: Osteoporosis is highly prevalent in postmenopausal women, yet genome-wide association studies often miss disease-relevant variants because of incomplete single nucleotide polymorphism (SNP) coverage and platform-specific limitations. We aimed to identify genetic contributors to osteoporosis risk by integrating two exome-based genotyping platforms with multilayer analytic approaches. Methods: We analyzed extreme osteoporosis phenotypes in Korean postmenopausal women from the Korean Genome and Epidemiology Study (KoGES) Ansan–Anseong cohorts using the Illumina Infinium HumanExome BeadChip and the Affymetrix Axiom Exome Array. After standard quality control, single-SNP logistic regression, cross-platform overlap analysis, and three machine-learning models were applied. Predicted functional impact was evaluated using multiple in silico algorithms and conservation scores. Finally, datasets from both platforms were merged, and cross-platform linkage disequilibrium (LD) blocks were defined to identify loci containing SNPs with p < 1 × 10−4. Results: No overlapped SNP reached genome-wide significance, but rs2076212 in PNPLA3 achieved suggestive significance (p < 1 × 10−5) only on the Illumina array. Cross-platform analysis identified 111 overlapping SNPs in 70 genes. Integrated machine-learning, in silico, and conservation evidence prioritized ARMS2, CCDC92, NQO1, ZNF510, PTPRB, and DYNC2H1 as candidate genes. LD-block analysis revealed 10 blocks with at least one SNP at p < 1 × 10−4, including four chromosome 12 loci (NAV2, BICD1, CCDC92, ZNF664) that became apparent only when LD patterns were evaluated jointly across platforms. Conclusions: Combining dual exome arrays with LD-block analysis, machine learning, and functional prediction improved sensitivity for detecting low bone mineral density-related loci and highlighted CCDC92, DYNC2H1, NQO1, and related genes as biologically plausible candidates for future validation.
Full article
(This article belongs to the Special Issue Current Diagnosis and Management of Metabolic Bone Disease)
►▼
Show Figures

Figure 1
Open AccessArticle
Endothelial Activation and Stress Index (EASIX) Predicts In-Hospital Mortality in Acute Decompensated Heart Failure with Reduced Ejection Fraction
by
Bülent Özlek, Veysel Ozan Tanık, Alperen Taş, Süleyman Barutçu, Buse Çuvalcıoğlu, Çağatay Tunca, Kürşat Akbuğa, Yusuf Bozkurt Şahin and Murat Akdoğan
Diagnostics 2026, 16(1), 152; https://doi.org/10.3390/diagnostics16010152 - 2 Jan 2026
Abstract
Background: Early risk stratification in acute decompensated heart failure with reduced ejection fraction (ADHF-rEF) remains challenging. The Endothelial Activation and Stress Index (EASIX)—a composite of lactate dehydrogenase, creatinine, and platelet count—reflects endothelial dysfunction, a pathophysiological contributor to early deterioration in ADHF-rEF. This study
[...] Read more.
Background: Early risk stratification in acute decompensated heart failure with reduced ejection fraction (ADHF-rEF) remains challenging. The Endothelial Activation and Stress Index (EASIX)—a composite of lactate dehydrogenase, creatinine, and platelet count—reflects endothelial dysfunction, a pathophysiological contributor to early deterioration in ADHF-rEF. This study evaluated the prognostic utility of admission-based EASIX for in-hospital mortality. Methods: In this retrospective single-center cohort, 850 consecutive patients hospitalized with ADHF-rEF between January 2022 and June 2025 were analyzed. EASIX was calculated from first-day laboratory values. Logistic regression, ROC analysis, restricted cubic splines, and Kaplan–Meier survival methods were used to assess the association between EASIX and in-hospital mortality, and to evaluate its incremental value beyond established clinical and laboratory predictors. Results: In-hospital mortality was 12.4%. Higher EASIX values were significantly associated with mortality in both univariable and multivariable models (adjusted OR 1.273; p < 0.001). EASIX demonstrated moderate discriminative performance among evaluated biomarkers (AUC 0.751) and showed a clear dose–response risk gradient, with mortality rising from 1.4% in the lowest tertile to 26.2% in the highest. Incorporating EASIX into clinical and laboratory prediction models yielded substantial continuous net reclassification improvement (0.59 and 0.38, respectively). Survival curves diverged early and remained distinctly separated across EASIX strata. Conclusions: Admission EASIX is an independent predictor of in-hospital mortality in ADHF-rEF and provides complementary prognostic information beyond conventional models. This is the first study to demonstrate the prognostic value of EASIX in the ADHF-rEF setting, supporting its potential utility as an accessible endothelial stress biomarker for early risk stratification.
Full article
(This article belongs to the Special Issue Recent Advances in Heart Failure: Clinical Diagnosis, Treatment, and Prognosis)
►▼
Show Figures

Figure 1
Open AccessArticle
Development of a Prognostic Nomogram in Epithelial Ovarian Cancer Based on KELIM: A Retrospective Study at TuDu Hospital, Vietnam
by
Hoang T. Pham, Tuan M. Vo, Le N. N. Phan and Hien T. Nguyen
Diagnostics 2026, 16(1), 151; https://doi.org/10.3390/diagnostics16010151 - 2 Jan 2026
Abstract
Background/Objectives: Epithelial ovarian cancer (EOC) constitutes the predominant form of ovarian malignancies. The primary goal of this study was to determine predictors of patient survival and construct a nomogram for survival prediction in individuals diagnosed with epithelial ovarian cancer. Methods: A retrospective cohort
[...] Read more.
Background/Objectives: Epithelial ovarian cancer (EOC) constitutes the predominant form of ovarian malignancies. The primary goal of this study was to determine predictors of patient survival and construct a nomogram for survival prediction in individuals diagnosed with epithelial ovarian cancer. Methods: A retrospective cohort analysis was performed, including 418 patients who received treatment for epithelial ovarian cancer at Tu Du Hospital from January 2015 to December 2019. The median follow-up time was 77.1 months (range: 5.7–121.6 months). Survival analyses were conducted using the log-rank test and Cox proportional hazard regression analysis. A nomogram was developed, incorporating KELIM and other statistically significant variables. Results: The median follow-up time was 77.1 months. The observed cumulative mortality rates were 1.4% (95% confidence interval [CI]: 0.7–3.2), 10.4% (95% CI: 7.8–13.8), and 16.5% (95% CI: 13.2–20.6) at 1, 3, and 5 years, respectively. Factors demonstrating a significant correlation with survival included KELIM < 1 (HR = 1.78 [95% CI: 1.16–2.72]), pre-treatment CA-125 levels ≥ 35 U/mL (HR = 2.47 [95% CI: 1.10–5.55]), FIGO stages III-IV (HR = 2.40 [95% CI: 1.36–4.21]), and the presence of residual tumor tissue following surgical intervention (HR = 3.14 [95% CI: 1.75–5.65]). Conclusions: Prognosis is significantly influenced by KELIM, pre-treatment CA-125, tumor stage, and residual tumor post-surgery. The nomogram developed here offers a tool to assist in personalized prognostic assessments of Vietnamese EOC patients.
Full article
(This article belongs to the Special Issue Diagnostic Progress in Gynecologic Oncology)
►▼
Show Figures

Figure 1
Open AccessReview
Single-Use Flexible Bronchoscopy: Advances in Technology and Applications
by
Siti Amanina Azman and Marcus Peter Kennedy
Diagnostics 2026, 16(1), 150; https://doi.org/10.3390/diagnostics16010150 - 2 Jan 2026
Abstract
With advances in scope and imaging technology, the use of single-use flexible bronchoscopy (SUFB) has broadened beyond intensive care units and operating rooms to bronchoscopy units, with an expanding body of literature suggesting adequate and comparable procedure outcomes, including airway inspection, bronchoalveolar lavage,
[...] Read more.
With advances in scope and imaging technology, the use of single-use flexible bronchoscopy (SUFB) has broadened beyond intensive care units and operating rooms to bronchoscopy units, with an expanding body of literature suggesting adequate and comparable procedure outcomes, including airway inspection, bronchoalveolar lavage, endobronchial brushing and endobronchial biopsy, in comparison to standard reusable flexible bronchoscopy (RFB). Advantages such as mobility, ease of use and lack of requirement for cleaning staff during the COVID-19 pandemic led to a global increase in usage, with many companies developing SUFB as part of their bronchoscopy portfolio. In parallel, there has been more attention and initiatives to minimise the risk of infection transmission related to bronchoscopy. RFB requires maximum adherence to manufacturer-recommended cleaning protocols. However, evidence of transmissible organisms after cleaning is reported in healthcare settings of all types. After initial benchtop, retrospective and single-arm studies, comparative bronchoscopy studies are identifying that SUFB are as versatile and non-inferior to RFB. However, cost-effectiveness and sustainability factors have to be included in deciding the use of SUFB in routine practice.
Full article
(This article belongs to the Special Issue Advances in Interventional Pulmonology)
►▼
Show Figures

Figure 1
Open AccessArticle
Predictors of Impaired Reperfusion in ST-Elevation Myocardial Infarction Treated with Primary PCI: Preliminary Results from COMA.NET Project
by
Maciej Południewski, Emil Julian Dąbrowski, Piotr Pogorzelski, Michał Łuczaj, Julia Kobylińska, Joanna Kruszyńska, Marcin Kożuch and Sławomir Dobrzycki
Diagnostics 2026, 16(1), 149; https://doi.org/10.3390/diagnostics16010149 - 2 Jan 2026
Abstract
Background: The no-reflow phenomenon remains a frequent and clinically significant complication in patients with ST-segment elevation myocardial infarction (STEMI) despite advances in primary percutaneous coronary intervention (pPCI). Its determinants are multifactorial and not fully established. This study aimed to identify independent predictors of
[...] Read more.
Background: The no-reflow phenomenon remains a frequent and clinically significant complication in patients with ST-segment elevation myocardial infarction (STEMI) despite advances in primary percutaneous coronary intervention (pPCI). Its determinants are multifactorial and not fully established. This study aimed to identify independent predictors of impaired reperfusion after pPCI. Methods: In this prospective study, 100 consecutive STEMI patients treated with successful pPCI in a high-volume tertiary center were analyzed. Impaired reperfusion was defined as ST-segment resolution < 50% or final TIMI flow < 3. Clinical characteristics, laboratory findings, including platelet reactivity, and detailed angiographic and procedural parameters were collected. Independent predictors were evaluated using multivariable logistic regression. Thirty-day and twelve-month mortality were assessed with Kaplan–Meier analysis. Results: Impaired reperfusion occurred in 39% of patients. Compared with the normal reperfusion group, patients with noreflow were older, had lower left ventricular ejection fraction, eGFR, longer ischemia times, and more often presented with anterior STEMI. Platelet reactivity did not differ between groups. Four variables independently predicted impaired reperfusion: longer pain-to-balloon time (OR 1.05 per 10 min, 95% CI 1.02–1.07; p < 0.001), anterior myocardial infarction (OR 5.05, 95% CI 1.14–22.38; p = 0.03), use of predilatation (OR 7.66, 95% CI 1.78–32.9; p = 0.006), and higher Killip–Kimball class (OR 7.69, 95% CI 1.88–31.38; p = 0.004). Impaired reperfusion was associated with significantly higher mortality at 30 days (1.6% vs. 10%; p < 0.001) and 12 months (3.2% vs. 25.6%; p < 0.001). Conclusions: In this prospective STEMI cohort, impaired reperfusion was frequent and strongly associated with adverse short- and long-term outcomes. Ischemia duration, infarct location, hemodynamic status, and procedural strategy were key determinants of noreflow, while platelet reactivity showed no significant association.
Full article
(This article belongs to the Special Issue Novel Diagnostic Approaches and Treatment of Angina and Myocardial Ischemia)
►▼
Show Figures

Figure 1
Open AccessReview
The Incremental Role of Stress Echocardiography in Valvular Heart Disease: A Narrative Review
by
Adriana Correra, Alfredo Mauriello, Carmen Del Giudice, Celeste Fonderico, Matilde Di Peppo, Vincenzo Russo, Antonello D’Andrea, Giovanni Esposito and Natale Daniele Brunetti
Diagnostics 2026, 16(1), 148; https://doi.org/10.3390/diagnostics16010148 - 2 Jan 2026
Abstract
Background/Objectives: The diagnosis and risk stratification of valvular heart disease have traditionally relied on resting echocardiography. However, in a significant portion of patients, resting findings do not fully reflect the hemodynamic severity of the condition, particularly in asymptomatic individuals with severe valvular disease
[...] Read more.
Background/Objectives: The diagnosis and risk stratification of valvular heart disease have traditionally relied on resting echocardiography. However, in a significant portion of patients, resting findings do not fully reflect the hemodynamic severity of the condition, particularly in asymptomatic individuals with severe valvular disease or those with nonspecific symptoms. In this context, stress echocardiography emerges as a vital imaging modality, providing a dynamic assessment of valvular, ventricular, and pulmonary function under hemodynamic load (from physical exercise or pharmacological agents). Methods: We conducted a comprehensive synthesis and critical evaluation of the current landscape, recent advancements, and future directions regarding the application of stress echocardiography in valvular heart disease. Results: This comprehensive review explores the incremental role of stress echocardiography in valvular heart disease, analyzing the evolution of its clinical applications, from low-flow, low-gradient aortic stenosis to the evaluation of contractile reserve and exercise-induced pulmonary hypertension in mitral stenosis and regurgitation. We discuss standardized protocols, key parameters to monitor, and the diagnostic and prognostic outcomes from major clinical trials and current guidelines. Attention is given to stress echocardiography’s ability to unmask the true severity of the disease and to identify patients at high risk for adverse events, thereby guiding crucial clinical decisions, such as the optimal timing for surgical or transcatheter intervention. Conclusions: The review evaluates the limitations of modality and outlines future research directions, including its integration with new technologies like 3D echocardiography and speckle tracking techniques, to further optimize the role of stress echocardiography as a decision-making tool in the multidisciplinary management of valvular heart disease.
Full article
(This article belongs to the Special Issue Recent Advances in Echocardiography, 2nd Edition)
►▼
Show Figures

Figure 1
Open AccessSystematic Review
Artificial Intelligence-Based Automated Analysis for Pleural Effusion Detection on Thoracic Ultrasound: A Systematic Review
by
Guido Marchi, Luciano Gabbrielli, Marco Gherardi, Massimiliano Serradori, Francesco Baglivo, Salvatore Claudio Fanni, Jacopo Cefalo, Carmine Salerni, Giacomo Guglielmi, Francesco Pistelli, Laura Carrozzi and Michele Mondoni
Diagnostics 2026, 16(1), 147; https://doi.org/10.3390/diagnostics16010147 - 2 Jan 2026
Abstract
Background: Pleural effusion (PE) is a common condition where accurate detection is essential for management. Thoracic ultrasound (TUS) is the first-line modality owing to safety, portability, and high sensitivity, but accuracy is operator-dependent. Artificial intelligence (AI)-based automated analysis has been explored as
[...] Read more.
Background: Pleural effusion (PE) is a common condition where accurate detection is essential for management. Thoracic ultrasound (TUS) is the first-line modality owing to safety, portability, and high sensitivity, but accuracy is operator-dependent. Artificial intelligence (AI)-based automated analysis has been explored as an adjunct, with early evidence suggesting potential to reduce variability and standardise interpretation. This review evaluates the diagnostic accuracy of AI-assisted TUS for PE detection. Methods: This review was registered with PROSPERO (CRD420251128416) and followed PRISMA guidelines. MEDLINE, Scopus, Google Scholar, IEEE Xplore, Cochrane CENTRAL, and ClinicalTrials.gov were searched through 20 August 2025 for studies assessing AI-based TUS analysis for PE. Eligible studies required recognised reference standards (expert interpretation or chest CT). Risk of bias was assessed with QUADAS-2, and certainty with GRADE. Owing to heterogeneity, structured narrative synthesis was performed instead of meta-analysis. Results: Five studies (7565 patients) published between 2021–2025 were included. All used convolutional neural networks with varied architectures (ResNet, EfficientNet, U-net). Sensitivity ranged 70.6–100%, specificity 67–100%, and AUC 0.77–0.99. Performance was reduced for small, trace, or complex effusions and in critically ill patients. External validation showed attenuation compared with internal testing. All studies had high risk of bias in patient selection and index test conduct, reflecting retrospective designs and inadequate dataset separation. Conclusions: AI-assisted TUS shows promising diagnostic performance for PE detection in curated datasets; however, evidence is inconsistent and limited by key methodological weaknesses. Overall certainty is low-to-moderate, constrained by retrospective designs, limited dataset separation, and scarce external validation. Current evidence is insufficient to support routine clinical use. Robust prospective multicentre studies with rigorous independent validation and evaluation of clinically meaningful outcomes are essential before clinical implementation can be considered.
Full article
(This article belongs to the Special Issue Diagnostic Imaging of Pulmonary Diseases)
►▼
Show Figures

Figure 1
Open AccessArticle
Leveraging Large-Scale Public Data for Artificial Intelligence-Driven Chest X-Ray Analysis and Diagnosis
by
Farzeen Khalid Khan, Waleed Bin Tahir, Mu Sook Lee, Jin Young Kim, Shi Sub Byon, Sun-Woo Pi and Byoung-Dai Lee
Diagnostics 2026, 16(1), 146; https://doi.org/10.3390/diagnostics16010146 - 1 Jan 2026
Abstract
Background: Chest X-ray (CXR) imaging is crucial for diagnosing thoracic abnormalities; however, the rising demand burdens radiologists, particularly in resource-limited settings. Method: We used large-scale, diverse public CXR datasets with noisy labels to train general-purpose deep learning models (ResNet, DenseNet, EfficientNet,
[...] Read more.
Background: Chest X-ray (CXR) imaging is crucial for diagnosing thoracic abnormalities; however, the rising demand burdens radiologists, particularly in resource-limited settings. Method: We used large-scale, diverse public CXR datasets with noisy labels to train general-purpose deep learning models (ResNet, DenseNet, EfficientNet, and DLAD-10) for multi-label classification of thoracic conditions. Uncertainty quantification was incorporated to assess model reliability. Performance was evaluated on both internal and external validation sets, with analyses of data scale, diversity, and fine-tuning effects. Result: EfficientNet achieved the highest overall area under the receiver operating characteristic curve (0.8944) with improved sensitivity and F1-score. Moreover, as training data volume increased—particularly using multi-source datasets—both diagnostic performance and generalizability were enhanced. Although larger datasets reduced predictive uncertainty, conditions such as tuberculosis remained challenging due to limited high-quality samples. Conclusions: General-purpose deep learning models can achieve robust CXR diagnostic performance when trained on large-scale, diverse public datasets despite noisy labels. However, further targeted strategies are needed for underrepresented conditions.
Full article
(This article belongs to the Special Issue Machine-Learning-Based Disease Diagnosis and Prediction)
►▼
Show Figures

Figure 1
Open AccessStudy Protocol
Application of Telemedicine and Artificial Intelligence in Outpatient Cardiology Care: TeleAI-CVD Study (Design)
by
Stefan Toth, Marianna Barbierik Vachalcova, Kamil Barbierik, Adriana Jarolimkova, Pavol Fulop, Mariana Dvoroznakova, Dominik Pella and Tibor Poruban
Diagnostics 2026, 16(1), 145; https://doi.org/10.3390/diagnostics16010145 - 1 Jan 2026
Abstract
Background/Objectives: Cardiovascular (CV) diseases remain the leading cause of morbidity and mortality across Europe. Despite substantial progress in prevention, diagnostics, and therapeutics, outpatient cardiology care continues to face systemic challenges, including limited consultation time, workforce constraints, and incomplete clinical information at the point
[...] Read more.
Background/Objectives: Cardiovascular (CV) diseases remain the leading cause of morbidity and mortality across Europe. Despite substantial progress in prevention, diagnostics, and therapeutics, outpatient cardiology care continues to face systemic challenges, including limited consultation time, workforce constraints, and incomplete clinical information at the point of care. The primary objective of this study is threefold. First, to evaluate whether AI-enhanced telemedicine improves clinical control of hypertension, dyslipidemia, and heart failure compared to standard ambulatory care. Second, to assess the impact on physician workflow efficiency and documentation burden through AI-assisted clinical documentation. Third, to determine patient satisfaction and safety profiles of integrated telemedicine–AI systems. Clinical control will be measured by a composite endpoint of disease-specific targets assessed at the 12-month follow-up visit. Methods: The TeleAI-CVD Concept Study aims to evaluate the integration of telemedicine and artificial intelligence (AI) to enhance the efficiency, quality, and individualization of cardiovascular disease management in the ambulatory setting. Within this framework, AI-driven tools will be employed to collect structured clinical histories and current symptomatology from patients prior to outpatient visits using digital questionnaires and conversational interfaces. Results: Obtained data, combined with telemonitoring metrics, laboratory parameters, and existing clinical records, will be synthesized to support clinical decision-making. Conclusions: This approach is expected to streamline consultations, increase diagnostic accuracy, and enable personalized, data-driven care through continuous evaluation of patient trajectories. The anticipated outcomes of the TeleAI-CVD study include the development of optimized, AI-assisted management protocols for cardiology patients, a reduction in unnecessary in-person visits through effective telemedicine-based follow-up, and accelerated attainment of therapeutic targets. Ultimately, this concept seeks to redefine the paradigm of outpatient cardiovascular care by embedding advanced digital technologies within routine clinical workflows.
Full article
(This article belongs to the Special Issue AI and Digital Health for Disease Diagnosis and Monitoring, 2nd Edition)
►▼
Show Figures

Figure 1
Open AccessArticle
Evaluating the Impact of Demographic Factors on Subject-Independent EEG-Based Emotion Recognition Approaches
by
Nathan Douglas, Maximilien Oosterhuis and Camilo E. Valderrama
Diagnostics 2026, 16(1), 144; https://doi.org/10.3390/diagnostics16010144 - 1 Jan 2026
Abstract
Background: Emotion recognition using electroencephalography (EEG) offers a non-invasive means of measuring brain responses to affective stimuli. However, since EEG signals can vary significantly between subjects, developing a deep learning model capable of accurately predicting emotions is challenging. Methods: To address
[...] Read more.
Background: Emotion recognition using electroencephalography (EEG) offers a non-invasive means of measuring brain responses to affective stimuli. However, since EEG signals can vary significantly between subjects, developing a deep learning model capable of accurately predicting emotions is challenging. Methods: To address that challenge, this study proposes a deep learning approach that fuses EEG features with demographic information, specifically age, sex, and nationality, using an attention-based mechanism that learns to weigh each modality during classification. The method was evaluated using three benchmark datasets: SEED, SEED-FRA, and SEED-GER, which include EEG recordings of 31 subjects of different demographic backgrounds. Results: We compared a baseline model trained solely on the EEG-derived features against an extended model that fused the subjects’ EEG and demographic information. Including demographic information improved the performance, achieving 80.2%, 80.5%, and 88.8% for negative, neutral, and positive classes. The attention weights also revealed different contributions of EEG and demographic inputs, suggesting that the model learns to adapt based on subjects’ demographic information. Conclusions: These findings support integrating demographic data to enhance the performance and fairness of subject-independent EEG-based emotion recognition models.
Full article
(This article belongs to the Special Issue 3rd Edition: AI/ML-Based Medical Image Processing and Analysis)
►▼
Show Figures

Figure 1
Journal Menu
► ▼ Journal Menu-
- Diagnostics Home
- Aims & Scope
- Editorial Board
- Reviewer Board
- Topical Advisory Panel
- Instructions for Authors
- Special Issues
- Topics
- Sections & Collections
- Article Processing Charge
- Indexing & Archiving
- Editor’s Choice Articles
- Most Cited & Viewed
- Journal Statistics
- Journal History
- Journal Awards
- Society Collaborations
- Conferences
- Editorial Office
Journal Browser
► ▼ Journal BrowserHighly Accessed Articles
Latest Books
E-Mail Alert
News
Topics
Topic in
Biomedicines, Diagnostics, Endocrines, JCM, JPM, IJMS
Development of Diagnosis and Treatment Modalities in Obstetrics and Gynecology
Topic Editors: Osamu Hiraike, Fuminori TaniguchiDeadline: 20 March 2026
Topic in
Diagnostics, Geriatrics, JCDD, Medicina, JPM, Medicines
New Research on Atrial Fibrillation
Topic Editors: Michele Magnocavallo, Domenico G. Della Rocca, Stefano Bianchi, Pietro Rossi, Antonio BisignaniDeadline: 31 March 2026
Topic in
Biology, JCM, Diagnostics, Dentistry Journal
Assessment of Craniofacial Morphology: Traditional Methods and Innovative Approaches
Topic Editors: Nikolaos Gkantidis, Carlalberta VernaDeadline: 1 June 2026
Topic in
Diagnostics, Electronics, Eng, Micro, Micromachines
Micro-Nanoelectronic Systems for Diagnosis and Therapies
Topic Editors: Wubin Bai, Jiho ShinDeadline: 30 June 2026
Conferences
Special Issues
Special Issue in
Diagnostics
Endoscopy and Diagnostic Tools in Hepatobiliary and Pancreatic Diseases, Second Edition
Guest Editor: Stefano Francesco CrinòDeadline: 31 January 2026
Special Issue in
Diagnostics
Inflammatory Pathologies
Guest Editor: Uday Nagesh ShivajiDeadline: 31 January 2026
Special Issue in
Diagnostics
Musculoskeletal Imaging in Clinical Practice: From Detection to Decision-Making
Guest Editor: Seul Ki LeeDeadline: 31 January 2026
Special Issue in
Diagnostics
Advances in Diagnostic and Interventional Nephrology
Guest Editor: Ammar AlmehmiDeadline: 31 January 2026
Topical Collections
Topical Collection in
Diagnostics
Editorial Board Members' Collection Series: Diagnostic Approaches to Gastrointestinal and Pancreatic Diseases
Collection Editors: Paolo Aseni, Ervin Toth
Topical Collection in
Diagnostics
Reviews on Artificial Intelligence and Natural Language Processing in Medical Diagnostics
Collection Editor: Shang-Ming Zhou



