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 - Q2 (Medicine, General & Internal)
- Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 20.7 days after submission; acceptance to publication is undertaken in 2.8 days (median values for papers published in this journal in the second half of 2023).
- 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 journal: LabMed.
Impact Factor:
3.6 (2022);
5-Year Impact Factor:
3.7 (2022)
Latest Articles
A Pilot Comparative Study between Creatinine- and Cystatin-C-Based Equations to Estimate GFR and Kidney Ultrasound Percentiles in Children with Congenital Anomalies of the Kidney and Urinary Tract
Diagnostics 2024, 14(10), 994; https://doi.org/10.3390/diagnostics14100994 (registering DOI) - 10 May 2024
Abstract
Congenital anomalies affecting the kidneys present significant challenges in pediatric nephrology, needing precise methods for assessing renal function and guiding therapeutic intervention. Bedside Schwartz formula with the cystatin-C-based Full Age Spectrum formula and Chronic Kidney Disease in Children (CKiD) U 25 formula used
[...] Read more.
Congenital anomalies affecting the kidneys present significant challenges in pediatric nephrology, needing precise methods for assessing renal function and guiding therapeutic intervention. Bedside Schwartz formula with the cystatin-C-based Full Age Spectrum formula and Chronic Kidney Disease in Children (CKiD) U 25 formula used in estimating glomerular filtration rate (eGFR) and also to assess if the eGFR in association with kidney length percentiles can be a monitoring parameter for the progression of chronic kidney disease in children with congenital anomalies of the kidney and urinary tract (CAKUT). A total of 64 pediatric patients (median age at diagnostic was 12 months with an interquartile range of 2 to 60) were diagnosed with congenital anomalies in the kidney and urinary tract between June 2018 and May 2023 at “Louis Turcanu” Emergency Hospital for Children in Timisoara, Romania. Baseline characteristics, CAKUT types, associated pathologies, CKD staging, and eGFR using creatinine and cystatin C were analyzed. The mean age at the moment of examination was 116.50 months; (65, 180). Chronic kidney disease staging revealed a predominance of patients in CKD stages G1 and A1. Analysis of eGFR methods revealed a small mean difference between eGFR estimated by creatinine and cystatin C, with a moderate-strong positive correlation observed between the eGFR and ultrasound parameters. Using cystatin-C-based formulas for eGFR, in conjunction with ultrasound measurements, may offer reliable insights into renal function in pediatric patients with congenital anomalies affecting the kidney and urinary tract. However, the economic aspect must be taken into consideration because cystatin C determination is approximately eight times more expensive than that of creatinine. An interdisciplinary approach is crucial for managing patients with CAKUT.
Full article
(This article belongs to the Special Issue Advances in the Diagnosis, Prognosis, and Management of Urinary Disease)
►
Show Figures
Open AccessArticle
MedKnee: A New Deep Learning-Based Software for Automated Prediction of Radiographic Knee Osteoarthritis
by
Said Touahema, Imane Zaimi, Nabila Zrira, Mohamed Nabil Ngote, Hassan Doulhousne and Mohsine Aouial
Diagnostics 2024, 14(10), 993; https://doi.org/10.3390/diagnostics14100993 (registering DOI) - 10 May 2024
Abstract
In computer-aided medical diagnosis, deep learning techniques have shown that it is possible to offer performance similar to that of experienced medical specialists in the diagnosis of knee osteoarthritis. In this study, a new deep learning (DL) software, called “MedKnee” is developed to
[...] Read more.
In computer-aided medical diagnosis, deep learning techniques have shown that it is possible to offer performance similar to that of experienced medical specialists in the diagnosis of knee osteoarthritis. In this study, a new deep learning (DL) software, called “MedKnee” is developed to assist physicians in the diagnosis process of knee osteoarthritis according to the Kellgren and Lawrence (KL) score. To accomplish this task, 5000 knee X-ray images obtained from the Osteoarthritis Initiative public dataset (OAI) were divided into train, valid, and test datasets in a ratio of 7:1:2 with a balanced distribution across each KL grade. The pre-trained Xception model is used for transfer learning and then deployed in a Graphical User Interface (GUI) developed with Tkinter and Python. The suggested software was validated on an external public database, Medical Expert, and compared with a rheumatologist’s diagnosis on a local database, with the involvement of a radiologist for arbitration. The MedKnee achieved an accuracy of 95.36% when tested on Medical Expert-I and 94.94% on Medical Expert-II. In the local dataset, the developed tool and the rheumatologist agreed on 23 images out of 30 images (74%). The MedKnee’s satisfactory performance makes it an effective assistant for doctors in the assessment of knee osteoarthritis.
Full article
(This article belongs to the Special Issue Classifications of Diseases Using Machine Learning Algorithms)
►▼
Show Figures
Figure 1
Open AccessArticle
The Predictors of Early Treatment Effectiveness of Intravitreal Bevacizumab Application in Patients with Diabetic Macular Edema
by
Karla Katić, Josip Katić, Marko Kumrić, Joško Božić, Leida Tandara, Daniela Šupe Domić and Kajo Bućan
Diagnostics 2024, 14(10), 992; https://doi.org/10.3390/diagnostics14100992 (registering DOI) - 10 May 2024
Abstract
The aim of this study was to establish whether multiple blood parameters might predict an early treatment response to intravitreal bevacizumab injections in patients with diabetic macular edema (DME). Seventy-eight patients with non-proliferative diabetic retinopathy (NPDR) and DME were included. The treatment response
[...] Read more.
The aim of this study was to establish whether multiple blood parameters might predict an early treatment response to intravitreal bevacizumab injections in patients with diabetic macular edema (DME). Seventy-eight patients with non-proliferative diabetic retinopathy (NPDR) and DME were included. The treatment response was evaluated with central macular thickness decrease and best corrected visual acuity increase one month after the last bevacizumab injection. Parameters of interest were the neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), vitamin D, and apolipoprotein B to A-I ratio (ApoB/ApoA-I). The NLR (2.03 ± 0.70 vs. 2.80 ± 1.08; p < 0.001), MLR (0.23 ± 0.06 vs. 0.28 ± 0.10; p = 0.011), PLR (107.4 ± 37.3 vs. 135.8 ± 58.0; p = 0.013), and SII (445.3 ± 166.3 vs. 675.3 ± 334.0; p < 0.001) were significantly different between responder and non-responder groups. Receiver operator characteristics analysis showed the NLR (AUC 0.778; 95% CI 0.669–0.864), PLR (AUC 0.628; 95% CI 0.511–0.735), MLR (AUC 0.653; 95% CI 0.536–0.757), and SII (AUC 0.709; 95% CI 0.595–0.806) could be predictors of response to bevacizumab in patients with DME and NPDR. Patients with severe NPDR had a significantly higher ApoB/ApoA-I ratio (0.70 (0.57–0.87) vs. 0.61 (0.49–0.72), p = 0.049) and lower vitamin D (52.45 (43.10–70.60) ng/mL vs. 40.05 (25.95–55.30) ng/mL, p = 0.025). Alterations in the NLR, PLR, MLR, and SII seem to provide prognostic information regarding the response to bevacizumab in patients with DME, whilst vitamin D deficiency and the ApoB/ApoA-I ratio could contribute to better staging.
Full article
(This article belongs to the Special Issue Advances in Diagnosis and Management of Retinal Diseases)
►▼
Show Figures
Figure 1
Open AccessArticle
Method for Detecting Pathology of Internal Organs Using Bioelectrography
by
Yulia Shichkina, Roza Fatkieva, Alexander Sychev and Anatoliy Kazak
Diagnostics 2024, 14(10), 991; https://doi.org/10.3390/diagnostics14100991 (registering DOI) - 9 May 2024
Abstract
This article considers the possibility of using the bioelectrography method to identify the pathology of internal organs. It is shown that with the currently existing methods, there is no possibility of the automatic detection of diseases or abnormalities in the functioning of a
[...] Read more.
This article considers the possibility of using the bioelectrography method to identify the pathology of internal organs. It is shown that with the currently existing methods, there is no possibility of the automatic detection of diseases or abnormalities in the functioning of a particular organ, or of the definition of combined pathology. It has been revealed that the use of various classifiers makes it possible to expand the field of pathology and choose the most optimal method for determining a particular disease. Based on this, a method for detecting the pathology of internal organs is developed, as well as a software package that allows the detection of diseases of the internal organs based on the bioelectrography results. Machine-learning models such as logistic regression, decision tree, random forest, xgboost, KNN, SVM and HyperTab are used for this purpose. HyperTab, logistic regression and xgboost turn out to be the best among them for this task, achieving a performance according to the f1-score metric in the order of 60–70%. The use of the developed method will, in practice, allow us to switch to combining various machine-learning models for the identification of certain diseases, as well as for the identification of combined pathology, which will help solve the problem of detecting pathology during screening studies and lead to a reduction in the burden on the staff of medical institutions.
Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼
Show Figures
Figure 1
Open AccessArticle
Artificial Intelligence-Based Quality Assessment of Histopathology Whole-Slide Images within a Clinical Workflow: Assessment of ‘PathProfiler’ in a Diagnostic Pathology Setting
by
Lisa Browning, Christine Jesus, Stefano Malacrino, Yue Guan, Kieron White, Alison Puddle, Nasullah Khalid Alham, Maryam Haghighat, Richard Colling, Jacqueline Birks, Jens Rittscher and Clare Verrill
Diagnostics 2024, 14(10), 990; https://doi.org/10.3390/diagnostics14100990 - 9 May 2024
Abstract
Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current
[...] Read more.
Digital pathology continues to gain momentum, with the promise of artificial intelligence to aid diagnosis and for assessment of features which may impact prognosis and clinical management. Successful adoption of these technologies depends upon the quality of digitised whole-slide images (WSI); however, current quality control largely depends upon manual assessment, which is inefficient and subjective. We previously developed PathProfiler, an automated image quality assessment tool, and in this feasibility study we investigate its potential for incorporation into a diagnostic clinical pathology setting in real-time. A total of 1254 genitourinary WSI were analysed by PathProfiler. PathProfiler was developed and trained on prostate tissue and, of the prostate biopsy WSI, representing 46% of the WSI analysed, 4.5% were flagged as potentially being of suboptimal quality for diagnosis. All had concordant subjective issues, mainly focus-related, 54% severe enough to warrant remedial action which resulted in improved image quality. PathProfiler was less reliable in assessment of non-prostate surgical resection-type cases, on which it had not been trained. PathProfiler shows potential for incorporation into a digitised clinical pathology workflow, with opportunity for image quality improvement. Whilst its reliability in the current form appears greatest for assessment of prostate specimens, other specimen types, particularly biopsies, also showed benefit.
Full article
(This article belongs to the Special Issue Artificial Intelligence in Pathological Image Analysis—2nd Edition)
►▼
Show Figures
Figure 1
Open AccessArticle
Histological Changes in the Popliteal Artery Wall in Patients with Critical Limb Ischemia
by
Octavian Andercou, Maria Cristina Andrei, Dan Gheban, Dorin Marian, Horațiu F. Coman, Valentin Aron Oprea, Florin Vasile Mihaileanu, Razvan Ciocan, Beatrix Cucuruz and Bogdan Stancu
Diagnostics 2024, 14(10), 989; https://doi.org/10.3390/diagnostics14100989 - 8 May 2024
Abstract
Introduction: This prospective study aims to illustrate the histopathological arterial changes in the popliteal artery in peripheral arterial disease of the lower limbs. Material and method: A total of 60 popliteal artery segments taken from patients who had undergone lower limb amputation were
[...] Read more.
Introduction: This prospective study aims to illustrate the histopathological arterial changes in the popliteal artery in peripheral arterial disease of the lower limbs. Material and method: A total of 60 popliteal artery segments taken from patients who had undergone lower limb amputation were examined between April and June 2023. The degree of arterial stenosis, medial calcinosis, and the vasa vasorum changes in the arterial adventitia were quantified. The presence of risk factors for atherosclerosis was also observed. Results: Atherosclerotic plaque was found in all of the examined segments. Medial calcinosis was observed in 40 (66.6%) of the arterial segments. A positive association between the degree of arterial stenosis and the vasa vasorum changes in the arterial adventitia was also found (p = 0.025). The level of blood sugar and cholesterol were predictive factors for the severity of atherosclerosis. Conclusions: Atherosclerosis and medial calcinosis are significant in patients who underwent lower limb amputation. Medial calcinosis causes damage to the arterial wall and leads to a reduction in responsiveness to dilator stimuli.
Full article
(This article belongs to the Special Issue Cardiovascular Diseases: Diagnosis and Management)
Open AccessArticle
JAKinhibs in Psoriatic Disease: Analysis of the Efficacy/Safety Profile in Daily Clinical Practice
by
Francesco Bizzarri, Ricardo Ruiz-Villaverde, Pilar Morales-Garrido, Jose Carlos Ruiz-Carrascosa, Marta Cebolla-Verdugo, Alvaro Prados-Carmona, Mar Rodriguez-Troncoso and Enrique Raya-Alvarez
Diagnostics 2024, 14(10), 988; https://doi.org/10.3390/diagnostics14100988 - 8 May 2024
Abstract
Psoriatic disease (PsD) affects multiple clinical domains and causes a significant inflammatory burden in patients, requiring comprehensive evaluation and treatment. In recent years, new molecules such as JAK inhibitors (JAKinhibs) have been developed. These have very clear advantages: they act quickly, have a
[...] Read more.
Psoriatic disease (PsD) affects multiple clinical domains and causes a significant inflammatory burden in patients, requiring comprehensive evaluation and treatment. In recent years, new molecules such as JAK inhibitors (JAKinhibs) have been developed. These have very clear advantages: they act quickly, have a beneficial effect on pain, are well tolerated and the administration route is oral. Despite all this, there is still little scientific evidence in daily clinical practice. This observational, retrospective, single-center study was carried out in patients diagnosed with PsA in the last two years, who started treatment with Tofacitinib or Upadacitinib due to failure of a DMARD. The data of 32 patients were analyzed, and the majority of them (75%) started treatment with Tofacitinib. Most had moderate arthritis activity and mild psoriasis involvement according to activity indices. Both Tofacitinib and Upadacitinib demonstrated significant efficacy, with rapid and statistically significant improvement in joint and skin activity indices, C-reactive protein reduction, and objective measures of disease activity such as the number of painful and inflamed joints. Although there was some difference in the baseline characteristics of the cohort, treatment responses were comparable or even superior to those in the pivotal clinical trials. In addition, there was a low frequency of mild adverse events leading to treatment discontinuation and no serious adverse events. These findings emphasize the strong efficacy and tolerability of JAKinhibs in daily clinical practice, supporting their role as effective therapeutic options for patients with PsD.
Full article
(This article belongs to the Topic Rheumatic Disorder: From Basic Science to Clinical Practice)
►▼
Show Figures
Figure 1
Open AccessArticle
Clinical Validation of a Machine-Learned, Point-of-Care System to IDENTIFY Functionally Significant Coronary Artery Disease
by
Thomas D. Stuckey, Frederick J. Meine, Thomas R. McMinn, Jeremiah P. Depta, Brett A. Bennett, Thomas F. McGarry, William S. Carroll, David D. Suh, John A. Steuter, Michael C. Roberts, Horace R. Gillins, Farhad Fathieh, Timothy Burton, Navid Nemati, Ian P. Shadforth, Shyam Ramchandani, Charles R. Bridges and Mark G. Rabbat
Diagnostics 2024, 14(10), 987; https://doi.org/10.3390/diagnostics14100987 - 8 May 2024
Abstract
Many clinical studies have shown wide performance variation in tests to identify coronary artery disease (CAD). Coronary computed tomography angiography (CCTA) has been identified as an effective rule-out test but is not widely available in the USA, particularly so in rural areas. Patients
[...] Read more.
Many clinical studies have shown wide performance variation in tests to identify coronary artery disease (CAD). Coronary computed tomography angiography (CCTA) has been identified as an effective rule-out test but is not widely available in the USA, particularly so in rural areas. Patients in rural areas are underserved in the healthcare system as compared to urban areas, rendering it a priority population to target with highly accessible diagnostics. We previously developed a machine-learned algorithm to identify the presence of CAD (defined by functional significance) in patients with symptoms without the use of radiation or stress. The algorithm requires 215 s temporally synchronized photoplethysmographic and orthogonal voltage gradient signals acquired at rest. The purpose of the present work is to validate the performance of the algorithm in a frozen state (i.e., no retraining) in a large, blinded dataset from the IDENTIFY trial. IDENTIFY is a multicenter, selectively blinded, non-randomized, prospective, repository study to acquire signals with paired metadata from subjects with symptoms indicative of CAD within seven days prior to either left heart catheterization or CCTA. The algorithm’s sensitivity and specificity were validated using a set of unseen patient signals (n = 1816). Pre-specified endpoints were chosen to demonstrate a rule-out performance comparable to CCTA. The ROC-AUC in the validation set was 0.80 (95% CI: 0.78–0.82). This performance was maintained in both male and female subgroups. At the pre-specified cut point, the sensitivity was 0.85 (95% CI: 0.82–0.88), and the specificity was 0.58 (95% CI: 0.54–0.62), passing the pre-specified endpoints. Assuming a 4% disease prevalence, the NPV was 0.99. Algorithm performance is comparable to tertiary center testing using CCTA. Selection of a suitable cut-point results in the same sensitivity and specificity performance in females as in males. Therefore, a medical device embedding this algorithm may address an unmet need for a non-invasive, front-line point-of-care test for CAD (without any radiation or stress), thus offering significant benefits to the patient, physician, and healthcare system.
Full article
(This article belongs to the Special Issue 21st Century Point-of-Care, Near-Patient and Critical Care Testing)
►▼
Show Figures
Figure 1
Open AccessBrief Report
Comparative Performance of COVID-19 Test Methods in Healthcare Workers during the Omicron Wave
by
Emma C. Tornberg, Alexander Tomlinson, Nicholas T. T. Oshiro, Esraa Derfalie, Rabeka A. Ali and Marcel E. Curlin
Diagnostics 2024, 14(10), 986; https://doi.org/10.3390/diagnostics14100986 - 8 May 2024
Abstract
The COVID-19 pandemic presents unique requirements for accessible, reliable testing, and many testing platforms and sampling techniques have been developed over the course of the pandemic. Not all test methods have been systematically compared to each other or a common gold standard, and
[...] Read more.
The COVID-19 pandemic presents unique requirements for accessible, reliable testing, and many testing platforms and sampling techniques have been developed over the course of the pandemic. Not all test methods have been systematically compared to each other or a common gold standard, and the performance of tests developed in the early epidemic have not been consistently re-evaluated in the context of new variants. We conducted a repeated measures study with adult healthcare workers presenting for SARS-CoV-2 testing. Participants were tested using seven testing modalities. Test sensitivity was compared using any positive PCR test as the gold standard. A total of 325 individuals participated in the study. PCR tests were the most sensitive (saliva PCR 0.957 ± 0.048, nasopharyngeal PCR 0.877 ± 0.075, oropharyngeal PCR 0.849 ± 0.082). Standard nasal rapid antigen tests were less sensitive but roughly equivalent (BinaxNOW 0.613 ± 0.110, iHealth 0.627 ± 0.109). Oropharyngeal rapid antigen tests were the least sensitive (BinaxNOW 0.400 ± 0.111, iHealth brands 0.311 ± 0.105). PCR remains the most sensitive testing modality for the diagnosis of COVID-19 and saliva PCR is significantly more sensitive than oropharyngeal PCR and equivalent to nasopharyngeal PCR. Nasal AgRDTs are less sensitive than PCR but have benefits in convenience and accessibility. Saliva-based PCR testing is a viable alternative to traditional swab-based PCR testing for the diagnosis of COVID-19.
Full article
(This article belongs to the Special Issue Laboratory Diagnosis of Infectious Disease: Advances and Challenges)
►▼
Show Figures
Figure 1
Open AccessArticle
Comparing Visual and Software-Based Quantitative Assessment Scores of Lungs’ Parenchymal Involvement Quantification in COVID-19 Patients
by
Marco Nicolò, Altin Adraman, Camilla Risoli, Anna Menta, Francesco Renda, Michele Tadiello, Sara Palmieri, Marco Lechiara, Davide Colombi, Luigi Grazioli, Matteo Pio Natale, Matteo Scardino, Andrea Demeco, Ruben Foresti, Attilio Montanari, Luca Barbato, Mirko Santarelli and Chiara Martini
Diagnostics 2024, 14(10), 985; https://doi.org/10.3390/diagnostics14100985 - 8 May 2024
Abstract
(1) Background: Computed tomography (CT) plays a paramount role in the characterization and follow-up of COVID-19. Several score systems have been implemented to properly assess the lung parenchyma involved in patients suffering from SARS-CoV-2 infection, such as the visual quantitative assessment score (VQAS)
[...] Read more.
(1) Background: Computed tomography (CT) plays a paramount role in the characterization and follow-up of COVID-19. Several score systems have been implemented to properly assess the lung parenchyma involved in patients suffering from SARS-CoV-2 infection, such as the visual quantitative assessment score (VQAS) and software-based quantitative assessment score (SBQAS) to help in managing patients with SARS-CoV-2 infection. This study aims to investigate and compare the diagnostic accuracy of the VQAS and SBQAS with two different types of software based on artificial intelligence (AI) in patients affected by SARS-CoV-2. (2) Methods: This is a retrospective study; a total of 90 patients were enrolled with the following criteria: patients’ age more than 18 years old, positive test for COVID-19 and unenhanced chest CT scan obtained between March and June 2021. The VQAS was independently assessed, and the SBQAS was performed with two different artificial intelligence-driven software programs (Icolung and CT-COPD). The Intraclass Correlation Coefficient (ICC) statistical index and Bland–Altman Plot were employed. (3) Results: The agreement scores between radiologists (R1 and R2) for the VQAS of the lung parenchyma involved in the CT images were good (ICC = 0.871). The agreement score between the two software types for the SBQAS was moderate (ICC = 0.584). The accordance between Icolung and the median of the visual evaluations (Median R1–R2) was good (ICC = 0.885). The correspondence between CT-COPD and the median of the VQAS (Median R1–R2) was moderate (ICC = 0.622). (4) Conclusions: This study showed moderate and good agreement upon the VQAS and the SBQAS; enhancing this approach as a valuable tool to manage COVID-19 patients and the combination of AI tools with physician expertise can lead to the most accurate diagnosis and treatment plans for patients.
Full article
(This article belongs to the Special Issue Advances in Cardiovascular and Pulmonary Imaging)
►▼
Show Figures
Figure 1
Open AccessArticle
Critical Risk Assessment, Diagnosis, and Survival Analysis of Breast Cancer
by
Shamiha Binta Manir and Priya Deshpande
Diagnostics 2024, 14(10), 984; https://doi.org/10.3390/diagnostics14100984 - 8 May 2024
Abstract
Breast cancer is the most prevalent type of cancer in women. Risk factor assessment can aid in directing counseling regarding risk reduction and breast cancer surveillance. This research aims to (1) investigate the relationship between various risk factors and breast cancer incidence using
[...] Read more.
Breast cancer is the most prevalent type of cancer in women. Risk factor assessment can aid in directing counseling regarding risk reduction and breast cancer surveillance. This research aims to (1) investigate the relationship between various risk factors and breast cancer incidence using the BCSC (Breast Cancer Surveillance Consortium) Risk Factor Dataset and create a prediction model for assessing the risk of developing breast cancer; (2) diagnose breast cancer using the Breast Cancer Wisconsin diagnostic dataset; and (3) analyze breast cancer survivability using the SEER (Surveillance, Epidemiology, and End Results) Breast Cancer Dataset. Applying resampling techniques on the training dataset before using various machine learning techniques can affect the performance of the classifiers. The three breast cancer datasets were examined using a variety of pre-processing approaches and classification models to assess their performance in terms of accuracy, precision, F-1 scores, etc. The PCA (principal component analysis) and resampling strategies produced remarkable results. For the BCSC Dataset, the Random Forest algorithm exhibited the best performance out of the applied classifiers, with an accuracy of 87.53%. Out of the different resampling techniques applied to the training dataset for training the Random Forest classifier, the Tomek Link exhibited the best test accuracy, at 87.47%. We compared all the models used with previously used techniques. After applying the resampling techniques, the accuracy scores of the test data decreased even if the training data accuracy increased. For the Breast Cancer Wisconsin diagnostic dataset, the K-Nearest Neighbor algorithm had the best accuracy with the original dataset test set, at 94.71%, and the PCA dataset test set exhibited 95.29% accuracy for detecting breast cancer. Using the SEER Dataset, this study also explores survival analysis, employing supervised and unsupervised learning approaches to offer insights into the variables affecting breast cancer survivability. This study emphasizes the significance of individualized approaches in the management and treatment of breast cancer by incorporating phenotypic variations and recognizing the heterogeneity of the disease. Through data-driven insights and advanced machine learning, this study contributes significantly to the ongoing efforts in breast cancer research, diagnostics, and personalized medicine.
Full article
(This article belongs to the Special Issue Machine Learning and Deep learning for Healthcare Data Processing and Analyzing)
►▼
Show Figures
Figure 1
Open AccessArticle
CSDNet: A Novel Deep Learning Framework for Improved Cataract State Detection
by
Lahari P.L, Ramesh Vaddi, Mahmoud O. Elish, Venkateswarlu Gonuguntla and Siva Sankar Yellampalli
Diagnostics 2024, 14(10), 983; https://doi.org/10.3390/diagnostics14100983 - 8 May 2024
Abstract
Cataracts, known for lens clouding and being a common cause of visual impairment, persist as a primary contributor to vision loss and blindness, presenting notable diagnostic and prognostic challenges. This work presents a novel framework called the Cataract States Detection Network (CSDNet), which
[...] Read more.
Cataracts, known for lens clouding and being a common cause of visual impairment, persist as a primary contributor to vision loss and blindness, presenting notable diagnostic and prognostic challenges. This work presents a novel framework called the Cataract States Detection Network (CSDNet), which utilizes deep learning methods to improve the detection of cataract states. The aim is to create a framework that is more lightweight and adaptable for use in environments or devices with limited memory or storage capacity. This involves reducing the number of trainable parameters while still allowing for effective learning of representations from data. Additionally, the framework is designed to be suitable for real-time or near-real-time applications where rapid inference is essential. This study utilizes cataract and normal images from the Ocular Disease Intelligent Recognition (ODIR) database. The suggested model employs smaller kernels, fewer training parameters, and layers to efficiently decrease the number of trainable parameters, thereby lowering computational costs and average running time compared to other pre-trained models such as VGG19, ResNet50, DenseNet201, MIRNet, Inception V3, Xception, and Efficient net B0. The experimental results illustrate that the proposed approach achieves a binary classification accuracy of 97.24% (normal or cataract) and an average cataract state detection accuracy of 98.17% (normal, grade 1—minimal cloudiness, grade 2—immature cataract, grade 3—mature cataract, and grade 4—hyper mature cataract), competing with state-of-the-art cataract detection methods. The resulting model is lightweight at 17 MB and has fewer trainable parameters (175, 617), making it suitable for deployment in environments or devices with constrained memory or storage capacity. With a runtime of 212 ms, it is well-suited for real-time or near-real-time applications requiring rapid inference.
Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
►▼
Show Figures
Figure 1
Open AccessInteresting Images
Histopathological Confirmed Polycythemia Vera with Transformation to Myelofibrosis Depicted on [18F]FDG PET/CT
by
Moritz B. Bastian, Arne Blickle, Caroline Burgard, Octavian Fleser, Konstantinos Christofyllakis, Samer Ezziddin and Florian Rosar
Diagnostics 2024, 14(10), 982; https://doi.org/10.3390/diagnostics14100982 - 8 May 2024
Abstract
We present a case of a 59-year-old male diagnosed with polycythemia vera (PV) for many years, who presented with a relatively abrupt onset of heavy constitutional symptoms, including fatigue, night sweats, and a 10% weight loss over 6 weeks. Despite the known initial
[...] Read more.
We present a case of a 59-year-old male diagnosed with polycythemia vera (PV) for many years, who presented with a relatively abrupt onset of heavy constitutional symptoms, including fatigue, night sweats, and a 10% weight loss over 6 weeks. Despite the known initial diagnosis of PV, the presence of profound B-symptoms prompted further investigation. A positron emission tomography/computed tomography (PET/CT) scan with 18F-Fluorodeoxyglucose ([18F]FDG) was performed to exclude malignant diseases. The [18F]FDG PET/CT revealed intense metabolic activity in the bone marrow of the proximal extremities and trunk skeleton, as well as a massively enlarged spleen with increased metabolic activity. Histopathologically, a transformation to myelofibrosis was revealed on a bone marrow biopsy. The case intends to serve as an exemplification for [18F]FDG PET/CT in PV with transformation to myelofibrosis (post-PV myelofibrosis).
Full article
(This article belongs to the Special Issue 18F-FDG PET/CT: Current and Future Clinical Applications)
►▼
Show Figures
Figure 1
Open AccessArticle
Machine Learning for Short-Term Mortality in Acute Decompensation of Liver Cirrhosis: Better than MELD Score
by
Nermin Salkić, Predrag Jovanović, Mislav Barišić Jaman, Nedim Selimović, Frane Paštrović and Ivica Grgurević
Diagnostics 2024, 14(10), 981; https://doi.org/10.3390/diagnostics14100981 - 8 May 2024
Abstract
Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two
[...] Read more.
Prediction of short-term mortality in patients with acute decompensation of liver cirrhosis could be improved. We aimed to develop and validate two machine learning (ML) models for predicting 28-day and 90-day mortality in patients hospitalized with acute decompensated liver cirrhosis. We trained two artificial neural network (ANN)-based ML models using a training sample of 165 out of 290 (56.9%) patients, and then tested their predictive performance against Model of End-stage Liver Disease-Sodium (MELD-Na) and MELD 3.0 scores using a different validation sample of 125 out of 290 (43.1%) patients. The area under the ROC curve (AUC) for predicting 28-day mortality for the ML model was 0.811 (95%CI: 0.714- 0.907; p < 0.001), while the AUC for the MELD-Na score was 0.577 (95%CI: 0.435–0.720; p = 0.226) and for MELD 3.0 was 0.600 (95%CI: 0.462–0.739; p = 0.117). The area under the ROC curve (AUC) for predicting 90-day mortality for the ML model was 0.839 (95%CI: 0.776- 0.884; p < 0.001), while the AUC for the MELD-Na score was 0.682 (95%CI: 0.575–0.790; p = 0.002) and for MELD 3.0 was 0.703 (95%CI: 0.590–0.816; p < 0.001). Our study demonstrates that ML-based models for predicting short-term mortality in patients with acute decompensation of liver cirrhosis perform significantly better than MELD-Na and MELD 3.0 scores in a validation cohort.
Full article
(This article belongs to the Special Issue Diagnosis and Management of Liver Diseases and Inflammatory Bowel Diseases)
►▼
Show Figures
Figure 1
Open AccessArticle
Exercise-Induced Electrocardiographic Changes in Healthy Young Males with Early Repolarization Pattern
by
Loránd Kocsis, Zsuzsanna Pap, Szabolcs Attila László, Hunor Gábor-Kelemen, István Adorján Szabó, Erhard Heidenhoffer and Attila Frigy
Diagnostics 2024, 14(10), 980; https://doi.org/10.3390/diagnostics14100980 - 8 May 2024
Abstract
Background: Exercise-induced modifications in ECG parameters among individuals with an early repolarization pattern (ERP) have not been evaluated in detail. We aimed to assess this phenomenon, with potential associations with arrhythmogenesis. Methods: Twenty-three young, healthy males with ERP (ERP+) participated in
[...] Read more.
Background: Exercise-induced modifications in ECG parameters among individuals with an early repolarization pattern (ERP) have not been evaluated in detail. We aimed to assess this phenomenon, with potential associations with arrhythmogenesis. Methods: Twenty-three young, healthy males with ERP (ERP+) participated in this study, alongside a control group, which consisted of nineteen healthy males without ERP (ERP−). ECGs at baseline, at peak exercise (Bruce protocol), and during the recovery phase were analyzed and compared between the two groups. Results: The treadmill test demonstrated strong cardiovascular fitness, with similar chronotropic and pressor responses in both groups. In the baseline ECGs, the QRS complex and the QT interval were shorter in the ERP+ group. During exercise, the P-wave duration was significantly longer and the QRS was narrower in the ERP+ group. In the recovery phase, there was a longer P wave and a narrower QRS in the ERP+ group. During the treadmill test, the J wave disappeared or did not meet the criteria required for ERP diagnosis. Conclusions: The slowed intra-atrial conduction found during exercise could be predictive of atrial arrhythmogenesis in the setting of ERP. The disappearing of J waves during exercise, due to increased sympathetic activity, has potential clinical significance.
Full article
(This article belongs to the Section Medical Imaging and Theranostics)
►▼
Show Figures
Figure 1
Open AccessArticle
Machine Learning Prediction of Prediabetes in a Young Male Chinese Cohort with 5.8-Year Follow-Up
by
Chi-Hao Liu, Chun-Feng Chang, I-Chien Chen, Fan-Min Lin, Shiow-Jyu Tzou, Chung-Bao Hsieh, Ta-Wei Chu and Dee Pei
Diagnostics 2024, 14(10), 979; https://doi.org/10.3390/diagnostics14100979 - 8 May 2024
Abstract
The identification of risk factors for future prediabetes in young men remains largely unexamined. This study enrolled 6247 young ethnic Chinese men with normal fasting plasma glucose at the baseline (FPGbase), and used machine learning (Mach-L) methods to predict prediabetes after
[...] Read more.
The identification of risk factors for future prediabetes in young men remains largely unexamined. This study enrolled 6247 young ethnic Chinese men with normal fasting plasma glucose at the baseline (FPGbase), and used machine learning (Mach-L) methods to predict prediabetes after 5.8 years. The study seeks to achieve the following: 1. Evaluate whether Mach-L outperformed traditional multiple linear regression (MLR). 2. Identify the most important risk factors. The baseline data included demographic, biochemistry, and lifestyle information. Two models were built, where Model 1 included all variables and Model 2 excluded FPGbase, since it had the most profound effect on prediction. Random forest, stochastic gradient boosting, eXtreme gradient boosting, and elastic net were used, and the model performance was compared using different error metrics. All the Mach-L errors were smaller than those for MLR, thus Mach-L provided the most accurate results. In descending order of importance, the key factors for Model 1 were FPGbase, body fat (BF), creatinine (Cr), thyroid stimulating hormone (TSH), WBC, and age, while those for Model 2 were BF, white blood cell, age, TSH, TG, and LDL-C. We concluded that FPGbase was the most important factor to predict future prediabetes. However, after removing FPGbase, WBC, TSH, BF, HDL-C, and age were the key factors after 5.8 years.
Full article
(This article belongs to the Special Issue Advances in Modern Diabetes Diagnosis and Treatment Technology)
►▼
Show Figures
Figure 1
Open AccessArticle
Two for One—Combined Morphologic and Quantitative Knee Joint MRI Using a Versatile Turbo Spin-Echo Platform
by
Teresa Lemainque, Nicola Pridöhl, Marc Huppertz, Manuel Post, Can Yüksel, Robert Siepmann, Karl Ludger Radke, Shuo Zhang, Masami Yoneyama, Andreas Prescher, Christiane Kuhl, Daniel Truhn and Sven Nebelung
Diagnostics 2024, 14(10), 978; https://doi.org/10.3390/diagnostics14100978 - 8 May 2024
Abstract
Quantitative MRI techniques such as T2 and T1ρ mapping are beneficial in evaluating knee joint pathologies; however, long acquisition times limit their clinical adoption. MIXTURE (Multi-Interleaved X-prepared Turbo Spin-Echo with IntUitive RElaxometry) provides a versatile turbo spin-echo (TSE) platform for simultaneous morphologic and
[...] Read more.
Quantitative MRI techniques such as T2 and T1ρ mapping are beneficial in evaluating knee joint pathologies; however, long acquisition times limit their clinical adoption. MIXTURE (Multi-Interleaved X-prepared Turbo Spin-Echo with IntUitive RElaxometry) provides a versatile turbo spin-echo (TSE) platform for simultaneous morphologic and quantitative joint imaging. Two MIXTURE sequences were designed along clinical requirements: “MIX1”, combining proton density (PD)-weighted fat-saturated (FS) images and T2 mapping (acquisition time: 4:59 min), and “MIX2”, combining T1-weighted images and T1ρ mapping (6:38 min). MIXTURE sequences and their reference 2D and 3D TSE counterparts were acquired from ten human cadaveric knee joints at 3.0 T. Contrast, contrast-to-noise ratios, and coefficients of variation were comparatively evaluated using parametric tests. Clinical radiologists (n = 3) assessed diagnostic quality as a function of sequence and anatomic structure using five-point Likert scales and ordinal regression, with a significance level of α = 0.01. MIX1 and MIX2 had at least equal diagnostic quality compared to reference sequences of the same image weighting. Contrast, contrast-to-noise ratios, and coefficients of variation were largely similar for the PD-weighted FS and T1-weighted images. In clinically feasible scan times, MIXTURE sequences yield morphologic, TSE-based images of diagnostic quality and quantitative parameter maps with additional insights on soft tissue composition and ultrastructure.
Full article
(This article belongs to the Section Medical Imaging and Theranostics)
►▼
Show Figures
Figure 1
Open AccessBrief Report
Captive Bolt Gun-Related Vascular Injury: A Single Center Experience
by
Jure Pešak, Andrej Porčnik and Borut Prestor
Diagnostics 2024, 14(10), 977; https://doi.org/10.3390/diagnostics14100977 - 8 May 2024
Abstract
This article investigates the clinical and radiological characteristics of captive bolt gun head injuries, a rare form of low-velocity penetrating brain injury. Eleven consecutive patients were included in the study. Vascular injuries and the rate of infection were systematically analyzed. Radiological findings reveal
[...] Read more.
This article investigates the clinical and radiological characteristics of captive bolt gun head injuries, a rare form of low-velocity penetrating brain injury. Eleven consecutive patients were included in the study. Vascular injuries and the rate of infection were systematically analyzed. Radiological findings reveal common bolt trajectories in the anterior cranial fossa, with identified risk factors for a poor outcome including trajectory crossing midline, hematocephalus, and paranasal sinus involvement. Only one patient had a good outcome. Despite meticulous microsurgical techniques, this study highlights often unfavorable clinical outcomes in captive bolt gun injuries, with vascular injury identified as a potential contributing risk factor for a poor outcome. Knowledge of variant vascular tree anatomy and corresponding vascular territory is important. To avoid potential vascular injuries, a complete removal of bone fragments was not always performed and it did not increase the rate of infection, challenging the conventional wisdom advocating for the complete removal of bone fragments. These findings contribute novel insights into captive bolt gun-related injuries, paving the way for further research.
Full article
(This article belongs to the Special Issue New Advances in Neurosurgery: Clinical Diagnosis, Treatment and Prognosis)
►▼
Show Figures
Figure 1
Open AccessArticle
Multiplex Assays in Allergy Diagnosis: Allergy Explorer 2 versus ImmunoCAP ISAC E112i
by
Hannes Nösslinger, Ewald Mair, Gertie J. Oostingh, Verena Ahlgrimm-Siess, Anna Ringauf and Roland Lang
Diagnostics 2024, 14(10), 976; https://doi.org/10.3390/diagnostics14100976 - 8 May 2024
Abstract
ImmunoCAP ISAC E112i (ISAC) and Allergy Explorer 2 (ALEX2) detect specific immunoglobulin E (IgE) reactivity. Both multiplex assays contain molecular allergens and ALEX2 additionally includes allergen extracts and inhibitors that block the binding of IgE to cross-reacting carbohydrate determinants (CCDs).
[...] Read more.
ImmunoCAP ISAC E112i (ISAC) and Allergy Explorer 2 (ALEX2) detect specific immunoglobulin E (IgE) reactivity. Both multiplex assays contain molecular allergens and ALEX2 additionally includes allergen extracts and inhibitors that block the binding of IgE to cross-reacting carbohydrate determinants (CCDs). This study aimed to compare the performance of ISAC and ALEX2 by determining the IgE reactivity against allergen extracts and/or allergen components and by using qualitative, semiquantitative, and quantitative analyses of all comparable allergen components in sera from 216 participants recruited in South Tyrol/Italy. For extract sensitization in ALEX2, the analysis revealed negative corresponding allergen components in 18.4% and at least one positive corresponding allergen component in 81.6% of all cases. For ISAC, the corresponding results were 23.5% and 76.5% of cases, respectively. The ALEX2 CCD inhibitor eliminated CCD-positive signals detected by ISAC in 88.5% of cases. Based on sensitization values of 0.3–14.9 ISU or kUA/L, there was good agreement between ALEX2 and ISAC, although ALEX2 showed higher values than ISAC. The addition of allergen-extract tests in ALEX2 resulted in the detection of more sensitizations than with corresponding allergen components alone. In the range of <15 ISU or kUA/L, ALEX2 may be more effective in detecting sensitizations.
Full article
(This article belongs to the Special Issue Diagnostics in Immunological, Allergic and Inflammatory Disorders)
►▼
Show Figures
Figure 1
Open AccessArticle
Human versus Artificial Intelligence: Validation of a Deep Learning Model for Retinal Layer and Fluid Segmentation in Optical Coherence Tomography Images from Patients with Age-Related Macular Degeneration
by
Mariana Miranda, Joana Santos-Oliveira, Ana Maria Mendonça, Vânia Sousa, Tânia Melo and Ângela Carneiro
Diagnostics 2024, 14(10), 975; https://doi.org/10.3390/diagnostics14100975 - 8 May 2024
Abstract
Artificial intelligence (AI) models have received considerable attention in recent years for their ability to identify optical coherence tomography (OCT) biomarkers with clinical diagnostic potential and predict disease progression. This study aims to externally validate a deep learning (DL) algorithm by comparing its
[...] Read more.
Artificial intelligence (AI) models have received considerable attention in recent years for their ability to identify optical coherence tomography (OCT) biomarkers with clinical diagnostic potential and predict disease progression. This study aims to externally validate a deep learning (DL) algorithm by comparing its segmentation of retinal layers and fluid with a gold-standard method for manually adjusting the automatic segmentation of the Heidelberg Spectralis HRA + OCT software Version 6.16.8.0. A total of sixty OCT images of healthy subjects and patients with intermediate and exudative age-related macular degeneration (AMD) were included. A quantitative analysis of the retinal thickness and fluid area was performed, and the discrepancy between these methods was investigated. The results showed a moderate-to-strong correlation between the metrics extracted by both software types, in all the groups, and an overall near-perfect area overlap was observed, except for in the inner segment ellipsoid (ISE) layer. The DL system detected a significant difference in the outer retinal thickness across disease stages and accurately identified fluid in exudative cases. In more diseased eyes, there was significantly more disagreement between these methods. This DL system appears to be a reliable method for accessing important OCT biomarkers in AMD. However, further accuracy testing should be conducted to confirm its validity in real-world settings to ultimately aid ophthalmologists in OCT imaging management and guide timely treatment approaches.
Full article
(This article belongs to the Special Issue Artificial Intelligence in Eye Disease—3rd Edition)
►▼
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
Algorithms, Diagnostics, Entropy, Information, J. Imaging
Application of Machine Learning in Molecular Imaging
Topic Editors: Allegra Conti, Nicola Toschi, Marianna Inglese, Andrea Duggento, Matthew Grech-Sollars, Serena Monti, Giancarlo Sportelli, Pietro CarraDeadline: 31 May 2024
Topic in
Biomedicines, Current Oncology, Diagnostics, Gastrointestinal Disorders, JCM
Advances in Gastrointestinal and Liver Disease: From Physiological Mechanisms to Clinical Practice
Topic Editors: Davide Giuseppe Ribaldone, Gian Paolo CavigliaDeadline: 20 June 2024
Topic in
Biomolecules, Diagnostics, JCM, Metabolites, JPM, Nutrients
Metabolic Syndrome, Biomarkers and Lifestyles
Topic Editors: Sang Yeoup Lee, Young Hye ChoDeadline: 30 June 2024
Topic in
Cancers, Diagnostics, JCM, Current Oncology, Gastrointestinal Disorders, Biomedicines
Hepatobiliary and Pancreatic Diseases: Novel Strategies of Diagnosis and Treatments
Topic Editors: Alessandro Coppola, Damiano Caputo, Roberta Angelico, Domenech Asbun, Chiara MazzarelliDeadline: 20 July 2024
Conferences
Special Issues
Special Issue in
Diagnostics
Fifth Anniversary of "Machine Learning and Artificial Intelligence in Diagnostics" Section
Guest Editors: Dania Cioni, Salvatore Claudio FanniDeadline: 10 May 2024
Special Issue in
Diagnostics
Monitoring and Diagnosis of Patients during Rehabilitation Training
Guest Editor: Redha TaiarDeadline: 31 May 2024
Special Issue in
Diagnostics
Improvement of Diagnostic Sensitivity for Tumor Markers
Guest Editors: Jong-Han Lee, Jooyoung ChoDeadline: 16 June 2024
Special Issue in
Diagnostics
Endoscopy and Diagnostic Tools in Hepatobiliary and Pancreatic Diseases
Guest Editor: Stefano Francesco CrinòDeadline: 30 June 2024
Topical Collections
Topical Collection in
Diagnostics
Editorial Board Members' Collection Series: Diagnostic Approaches to Gastrointestinal and Pancreatic Diseases
Collection Editors: Paolo Aseni, Ervin Toth