Previous Issue
Volume 15, June-1
 
 

Diagnostics, Volume 15, Issue 12 (June-2 2025) – 9 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
11 pages, 1071 KiB  
Article
Functional Outcomes and Activity Levels in Patients After Internal Hemipelvectomy for Primary Sarcoma Involving the Bony Pelvis
by Burkhard Lehner, Jakob Bollmann, Andreas Geisbüsch and Nicholas Andreas Beckmann
Diagnostics 2025, 15(12), 1452; https://doi.org/10.3390/diagnostics15121452 - 6 Jun 2025
Abstract
Background: Internal hemipelvectomies are rare procedures for primary musculoskeletal sarcomas of the bony pelvis. There is a sparse amount of data on functional outcomes and activity levels in postoperative patients. The aim of this study was to investigate functional outcomes, including sport activity [...] Read more.
Background: Internal hemipelvectomies are rare procedures for primary musculoskeletal sarcomas of the bony pelvis. There is a sparse amount of data on functional outcomes and activity levels in postoperative patients. The aim of this study was to investigate functional outcomes, including sport activity levels, and the impact of tumor grade, resection margins, adjuvant therapies, pelvic reconstruction, and patient age at the time of surgery. Methods: Patients who underwent internal hemipelvectomy at our clinic between 1995 and 2019, with a minimum follow-up of 12 months, were assessed using the Musculoskeletal Tumor Society Score (MSTS), the Toronto Extremity Salvage Score (TESS), the Oxford Hip Score (OHS), and the University of Los Angeles Activity Scale (UCLA AS). Results: Our cross-sectional study included 29 patients (14 male, 15 female; 15 with chondrosarcoma, 8 with Ewing’s sarcoma, 2 with osteosarcoma, 2 with chordoma, and 2 with other sarcomas) with a median follow-up of 8.7 years (range: 12 months to 25.4 years; interquartile range (IQR): 13.1 years). The median MSTS was 16 (range: 1–30; IQR: 9), median TESS was 75.8% (range: 12.9–100%; IQR: 31.7%), median OHS was 35 (range: 10–48; IQR: 16), and median UCLA AS was 5 (range: 1–9; IQR: 3). Tumor grade, resection margins, chemotherapy, radiation therapy, and pelvic reconstruction had no significant effect on functional outcomes. Patient age at the time of surgery had a statistically significant effect on all measured outcome parameters, although all parameters exhibited a wide range and large IQR, likely reflecting the small, heterogeneous patient cohort. Conclusions: Surviving patients who underwent internal hemipelvectomy for primary musculoskeletal sarcomas of the pelvic bone demonstrated overall moderate to good functional outcomes and moderate sport activity levels. Full article
(This article belongs to the Special Issue Bone Tumours: From Molecular Pathology to Clinical Practice)
Show Figures

Figure 1

19 pages, 447 KiB  
Article
Risk of Bias Assessment of Diagnostic Accuracy Studies Using QUADAS 2 by Large Language Models
by Daniel-Corneliu Leucuța, Andrada Elena Urda-Cîmpean, Dan Istrate and Tudor Drugan
Diagnostics 2025, 15(12), 1451; https://doi.org/10.3390/diagnostics15121451 - 6 Jun 2025
Abstract
Background/Objectives: Diagnostic accuracy studies are essential for the evaluation of the performance of medical tests. The risk of bias (RoB) for these studies is commonly assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool. This study aimed to assess the [...] Read more.
Background/Objectives: Diagnostic accuracy studies are essential for the evaluation of the performance of medical tests. The risk of bias (RoB) for these studies is commonly assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool. This study aimed to assess the capabilities and reasoning accuracy of large language models (LLMs) in evaluating the RoB in diagnostic accuracy studies, using QUADAS 2, compared to human experts. Methods: Four LLMs were used for the AI assessment: ChatGPT 4o model, X.AI Grok 3 model, Gemini 2.0 flash model, and DeepSeek V3 model. Ten recent open-access diagnostic accuracy studies were selected. Each article was independently assessed by human experts and by LLMs using QUADAS 2. Results: Out of 110 signaling questions assessments (11 questions for each of the 10 articles) by the four AI models, and the mean percentage of correct assessments of all the models was 72.95%. The most accurate model was Grok 3, followed by ChatGPT 4o, DeepSeek V3, and Gemini 2.0 Flash, with accuracies ranging from 74.45% to 67.27%. When analyzed by domain, the most accurate responses were for “flow and timing”, followed by “index test”, and then similarly for “patient selection” and “reference standard”. An extensive list of reasoning errors was documented. Conclusions: This study demonstrates that LLMs can achieve a moderate level of accuracy in evaluating the RoB in diagnostic accuracy studies. However, they are not yet a substitute for expert clinical and methodological judgment. LLMs may serve as complementary tools in systematic reviews, with compulsory human supervision. Full article
(This article belongs to the Special Issue A New Era in Diagnosis: From Biomarkers to Artificial Intelligence)
18 pages, 821 KiB  
Article
Standardisation and Optimisation of Chest and Pelvis X-Ray Imaging Protocols Across Multiple Radiography Systems in a Radiology Department
by Ahmed Jibril Abdi, Kasper Rørdam Jensen, Pia Iben Pietersen, Janni Jensen, Rune Lau Hovgaard, Ask Kristian Aas Holmboe and Sofie Gregersen
Diagnostics 2025, 15(12), 1450; https://doi.org/10.3390/diagnostics15121450 - 6 Jun 2025
Abstract
X-ray imaging protocols in radiology departments often exhibit variability in exposure parameters and geometric setups, leading to inconsistencies in image quality and potential variations in patient dose. Objectives: This study aimed to harmonise and optimise chest and pelvis X-ray imaging protocols by [...] Read more.
X-ray imaging protocols in radiology departments often exhibit variability in exposure parameters and geometric setups, leading to inconsistencies in image quality and potential variations in patient dose. Objectives: This study aimed to harmonise and optimise chest and pelvis X-ray imaging protocols by standardising exposure parameters and geometric setups across departmental systems, minimising radiation dose while ensuring adequate image quality for accurate diagnosis. Methods: The image quality of five pelvic and three chest protocols across different radiographic systems was evaluated both quantitatively and visually. Visual image quality for both chest and pelvis protocols was assessed by radiologists and radiographers using the Visual Grading Analysis (VGA) method. Additionally, the quantitative image quality figure inverse (IQFinv) metric for all protocols was determined using the CDRAD image quality phantom. Moreover, the patient radiation dose for both chest and pelvis protocols was evaluated using dose area product (DAP) values measured by the systems’ built-in DAP metres. Results: Different quantitative image quality and radiation dose to patients were achieved in various protocol settings for both chest and pelvis examinations, but the visual image quality assessment showed satisfactory image quality for all observers in both the pelvis and chest protocols. The selected protocols for harmonising chest radiography across all imaging systems result in reduced radiation exposure for patients while maintaining adequate image quality compared to the previously used system-specific protocol. Conclusions: The clinical protocol for chest and pelvis radiography has been standardised and optimised in accordance with patient radiation exposure and image quality. This approach aligns with the ALARA (As Low As Reasonably Achievable) principle, ensuring optimal diagnostic information while minimising the radiation risks. Full article
(This article belongs to the Section Medical Imaging and Theranostics)
21 pages, 3055 KiB  
Article
Alzheimer’s Disease Prediction Using Fisher Mantis Optimization and Hybrid Deep Learning Models
by Sameer Abbas, Mustafa Yeniad and Javad Rahebi
Diagnostics 2025, 15(12), 1449; https://doi.org/10.3390/diagnostics15121449 - 6 Jun 2025
Abstract
Background/Objectives: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder causing memory, cognitive, and behavioral decline. Early and accurate diagnosis is critical for timely treatment and management. This study proposes a novel hybrid deep learning framework, GLCM + VGG16 + FMO + CNN-LSTM, [...] Read more.
Background/Objectives: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder causing memory, cognitive, and behavioral decline. Early and accurate diagnosis is critical for timely treatment and management. This study proposes a novel hybrid deep learning framework, GLCM + VGG16 + FMO + CNN-LSTM, to improve AD diagnosis using MRI data. Methods: MRI images were preprocessed through normalization and noise reduction. Feature extraction combined texture features from the Gray-Level Co-occurrence Matrix (GLCM) and spatial features extracted from a pretrained VGG-16 network. Fisher Mantis Optimization (FMO) was employed for optimal feature selection. The selected features were classified using a CNN-LSTM model, capturing both spatial and temporal patterns. The MLP-LSTM model was included only for benchmarking purposes. The framework was evaluated on The ADNI and MIRIAD datasets. Results: The proposed method achieved 98.63% accuracy, 98.69% sensitivity, 98.66% precision, and 98.67% F1-score, outperforming CNN + SVM and 3D-CNN + BiLSTM by 2.4–3.5%. Comparative analysis confirmed FMO’s superiority over other metaheuristics, such as PSO, ACO, GWO, and BFO. Sensitivity analysis demonstrated robustness to hyperparameter changes. Conclusions: The results confirm the efficacy and stability of the GLCM + VGG16 + FMO + CNN-LSTM model for accurate and early AD diagnosis, supporting its potential clinical application. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

11 pages, 856 KiB  
Article
Diagnostic Properties of Different Serological Methods for Syphilis Testing in Brazil
by Suelen Basgalupp, Thayane Dornelles, Luana Pedrotti, Aniúsca dos Santos, Cáren de Oliveira, Giovana dos Santos, Emerson de Brito, Ben Hur Pinheiro, Ana Cláudia Philippus, Álisson Bigolin, Pamela Cristina Gaspar, Flávia Moreno, Gerson Pereira, Maiko Luis Tonini and Eliana Wendland
Diagnostics 2025, 15(12), 1448; https://doi.org/10.3390/diagnostics15121448 - 6 Jun 2025
Abstract
Background/Objectives: Syphilis remains a significant public health challenge worldwide. Accurate and efficient diagnostic tools are essential to controlling the spread of the disease. Current diagnostic approaches primarily rely on serologic treponemal tests (TTs) and nontreponemal tests (NTTs). The aim of this study [...] Read more.
Background/Objectives: Syphilis remains a significant public health challenge worldwide. Accurate and efficient diagnostic tools are essential to controlling the spread of the disease. Current diagnostic approaches primarily rely on serologic treponemal tests (TTs) and nontreponemal tests (NTTs). The aim of this study was to evaluate the diagnostic properties of various serological methods for syphilis diagnosis. Methods: Samples were collected from participants of the Health, Information, and Sexually Transmitted Infection Monitoring (SIM study) between March 2020 and May 2023, using convenience sampling at a mobile health unit in Porto Alegre, Brazil. A total of 250 individuals were tested using the point-of-care (POC) lateral flow treponemal test, Venereal Disease Research Laboratory (VDRL) test, Rapid Plasma Reagin (RPR) test, Enzyme-Linked Immunosorbent Assay (ELISA), and Treponema pallidum hemagglutination assay (TPHA). Of these, 125 participants tested positive for syphilis in the POC screening. Diagnostic properties such as sensitivity, specificity, and predictive values were assessed for the POC test, ELISA, and VDRL test. The TPHA was used as the reference standard for the TT, and the RPR test as the reference standard for the NTT. Results: Among individuals with positive POC test results, 97.6% (122/125) were also positive by the ELISA, and 85.6% (107/125) were positive by the TPHA. Additionally, 48.0% (60/125) and 42.4% (53/125) tested positive by the VDRL and RPR tests, respectively. Using the TPHA as a reference, TT tests showed sensitivities of 97–98% and specificities of 93–95% for detecting anti-Treponema pallidum antibodies using the ELISA and POC test, respectively. For the NTT, the VDRL test demonstrated a sensitivity of 98% and a specificity of 95% compared to the RPR test. The kappa coefficients were 0.85 for the POC test vs. the TPHA, 0.81 for the ELISA vs. the TPHA, and 0.89 for the VDRL vs. the RPR tests, indicating substantial agreement. Conclusions: This study highlights a good diagnostic performance and high agreement levels among the evaluated serological tests for syphilis, reinforcing their utility in clinical and public health settings, as well as epidemiological studies. Full article
(This article belongs to the Section Diagnostic Microbiology and Infectious Disease)
Show Figures

Figure 1

13 pages, 2770 KiB  
Article
Comparison of Myocardial Function in Young and Old Mice During Acute Myocardial Infarction: A Cardiac Magnetic Resonance Study
by Antonia Dalmer, Paul Wörner, Mathias Manzke, Ralf Gäbel, Tobias Lindner, Felix G. Meinel, Marc-André Weber, Robert David and Cajetan I. Lang
Diagnostics 2025, 15(12), 1447; https://doi.org/10.3390/diagnostics15121447 - 6 Jun 2025
Abstract
Background/Objectives: This study aimed to compare changes in functional and strain parameters in young and old mice using cardiac MRI before and shortly after myocardial infarction. Methods: In this prospective experimental study, 7 young mice and 10 old mice underwent a [...] Read more.
Background/Objectives: This study aimed to compare changes in functional and strain parameters in young and old mice using cardiac MRI before and shortly after myocardial infarction. Methods: In this prospective experimental study, 7 young mice and 10 old mice underwent a cardiac MRI 5 days before and 2 days after myocardial infarction by LAD ligation. Functional parameters such as EDV, ESV, EF, SV, and Strain were determined. Results: EDV in the young mice before LAD ligation was significantly lower than in the old mice (p-value 0.002). EDV significantly increased after infarction in both groups. ESV was significantly lower in young mice before infarction than in old mice (9.7 ± 2.6 vs. 13.8 ± 3.9 [µL], p = 0.029). After infarction, the mean value was still lower but no longer significant. There was no significant difference between young and old mice either before or after infarction for the EF. But again, the decrease was significant for both groups (old: p < 0.0001 and young: p = 0.0009). Each global strain showed deterioration after infarction. This difference was significant in both subgroups for young mice and old mice for each strain. There were no differences either before or after infarction between the young and old mice. Conclusions: There were differences in functional parameters between young and old mice in EDV, SV, and CO. Changes in strain parameters in the acute phase post-myocardial infarction did not differ significantly between young and old mice, while there was a clear deterioration in strain parameters after infarction in both groups. Full article
(This article belongs to the Special Issue New Trends in Cardiovascular Imaging)
Show Figures

Figure 1

20 pages, 1173 KiB  
Article
Validation of an Eye-Tracking Algorithm Based on Smartphone Videos: A Pilot Study
by Wanzi Su, Damon Hoad, Leandro Pecchia and Davide Piaggio
Diagnostics 2025, 15(12), 1446; https://doi.org/10.3390/diagnostics15121446 - 6 Jun 2025
Abstract
Introduction: This study aimed to develop and validate an efficient eye-tracking algorithm suitable for the analysis of images captured in the visible-light spectrum using a smartphone camera. Methods: The investigation primarily focused on comparing two algorithms, which were named CHT_TM and CHT_ACM, abbreviated [...] Read more.
Introduction: This study aimed to develop and validate an efficient eye-tracking algorithm suitable for the analysis of images captured in the visible-light spectrum using a smartphone camera. Methods: The investigation primarily focused on comparing two algorithms, which were named CHT_TM and CHT_ACM, abbreviated from the core functions: Circular Hough Transform (CHT), Active Contour Models (ACMs), and Template Matching (TM). Results: CHT_TM significantly improved the running speed of the CHT_ACM algorithm, with not much difference in the resource consumption, and improved the accuracy on the x axis. CHT_TM achieved a reduction by 79% of the execution time. CHT_TM performed with an average mean percentage error of 0.34% and 0.95% in the x and y direction across the 19 manually validated videos, compared to 0.81% and 0.85% for CHT_ACM. Different conditions, like manually opening the eyelids with a finger versus without a finger, were also compared across four different tasks. Conclusions: This study shows that applying TM improves the original eye-tracking algorithm with CHT_ACM. The new algorithm has the potential to help the tracking of eye movement, which can facilitate the early screening and diagnosis of neurodegenerative diseases. Full article
(This article belongs to the Special Issue Machine-Learning-Based Disease Diagnosis and Prediction)
Show Figures

Figure 1

11 pages, 2345 KiB  
Article
BioInnovate AI: A Machine Learning Platform for Rapid PCR Assay Design in Emerging Infectious Disease Diagnostics
by Hung-Hsin Lin, Hsing-Yi Chung, Tai-Han Lin, Chih-Kai Chang, Cherng-Lih Perng, Kuo-Sheng Hung, Katsunori Yanagihara, Hung-Sheng Shang and Ming-Jr Jian
Diagnostics 2025, 15(12), 1445; https://doi.org/10.3390/diagnostics15121445 - 6 Jun 2025
Abstract
Background/Objectives: Emerging infectious diseases pose significant global threats due to their rapid transmission, limited therapeutic options, and profound socioeconomic impact. Conventional diagnostic techniques that rely on sequencing and polymerase chain reactions (PCR) frequently lack the speed necessary to efficiently respond to rapidly evolving [...] Read more.
Background/Objectives: Emerging infectious diseases pose significant global threats due to their rapid transmission, limited therapeutic options, and profound socioeconomic impact. Conventional diagnostic techniques that rely on sequencing and polymerase chain reactions (PCR) frequently lack the speed necessary to efficiently respond to rapidly evolving pathogens. This study describes the development of BioInnovate AI to overcome these limitations using machine learning to expedite PCR assay development. Methods: The ability of BioInnovate AI to predict optimal PCR reagents across multiple pathogens was assessed. Additionally, random forest classifier, light gradient boosting machine (LGBM), and gradient boosting classifier models were evaluated for their ability to predict effective PCR primer–probe combinations. Performance metrics, including the area under the curve (AUC), sensitivity, specificity, accuracy, and F1 score, were assessed to identify the optimal model for platform integration. Results: All machine learning models performed well, with the LGBM model achieving the highest metrics (AUC: 0.97, sensitivity: 0.93, specificity: 0.91). BioInnovate AI significantly reduced PCR assay development time by approximately 90%, enabling rapid design and reagent optimization for multiple pathogens. Conclusions: BioInnovate AI provides a rapid, accurate, and efficient method for PCR reagent design, significantly enhancing global diagnostic preparedness by optimizing primers and probes for the timely detection of infectious diseases. Full article
(This article belongs to the Special Issue AI-Powered Clinical Diagnosis and Decision-Support Systems)
Show Figures

Figure 1

23 pages, 3830 KiB  
Article
A Hybrid Artificial Intelligence Approach for Down Syndrome Risk Prediction in First Trimester Screening
by Emre Yalçın, Serpil Aslan, Mesut Toğaçar and Süleyman Cansun Demir
Diagnostics 2025, 15(12), 1444; https://doi.org/10.3390/diagnostics15121444 - 6 Jun 2025
Abstract
Background/Objectives: The aim of this study is to develop a hybrid artificial intelligence (AI) approach to improve the accuracy, efficiency, and reliability of Down Syndrome (DS) risk prediction during first trimester prenatal screening. The proposed method transforms one-dimensional (1D) patient data—including features such [...] Read more.
Background/Objectives: The aim of this study is to develop a hybrid artificial intelligence (AI) approach to improve the accuracy, efficiency, and reliability of Down Syndrome (DS) risk prediction during first trimester prenatal screening. The proposed method transforms one-dimensional (1D) patient data—including features such as nuchal translucency (NT), human chorionic gonadotropin (hCG), and pregnancy-associated plasma protein A (PAPP-A)—into two-dimensional (2D) Aztec barcode images, enabling advanced feature extraction using transformer-based deep learning models. Methods: The dataset consists of 958 anonymous patient records. Each record includes four first trimester screening markers, hCG, PAPP-A, and NT, expressed as multiples of the median. The DS risk outcome was categorized into three classes: high, medium, and low. Three transformer architectures—DeiT3, MaxViT, and Swin—are employed to extract high-level features from the generated barcodes. The extracted features are combined into a unified set, and dimensionality reduction is performed using two feature selection techniques: minimum Redundancy Maximum Relevance (mRMR) and RelieF. Intersecting features from both selectors are retained to form a compact and informative feature subset. The final features are classified using machine learning algorithms, including Bagged Trees and Naive Bayes. Results: The proposed approach achieved up to 100% classification accuracy using the Naive Bayes classifier with 1250 features selected by RelieF and 527 intersecting features from mRMR. By selecting a smaller but more informative subset of features, the system significantly reduced hardware and processing demands while maintaining strong predictive performance. Conclusions: The results suggest that the proposed hybrid AI method offers a promising and resource-efficient solution for DS risk assessment in first trimester screening. However, further comparative studies are recommended to validate its performance in broader clinical contexts. Full article
(This article belongs to the Special Issue Artificial Intelligence for Health and Medicine)
Show Figures

Figure 1

Previous Issue
Back to TopTop