Diagnostics

Journal: Diagnostics

Publisher

MDPI

ISSN

2075-4418

Show all metadata

Search Results

Publications 1 - 10 of 15

Development and clinical validation of the lymphmonitor technology to quantitatively assess lymphatic function
Polomska, Anna; Gousopoulos, Epameinondas; Fehr, Daniel; et al. (2021)
Diagnostics
Current diagnostic methods for evaluating the functionality of the lymphatic vascular system usually do not provide quantitative data and suffer from many limitations including high costs, complexity, and the need to perform them in hospital settings. In this work, we present a quantitative, simple outpatient technology named LymphMonitor to quantitatively assess lymphatic function. This method is based on the painless injection of the lymphatic-specific near-infrared fluorescent tracer indocyanine green complexed with human serum albumin, using MicronJet600™ microneedles, and monitoring the disappearance of the fluorescence signal at the injection site over time using a portable detection device named LymphMeter. This technology was investigated in 10 patients with unilateral leg or arm lymphedema. After injection of a tracer solution into each limb, the signal was measured over 3 h and the area under the normalized clearance curve was calculated to quantify the lymphatic function. A statistically significant difference in lymphatic clearance in the healthy versus the lymphedema extremities was found, based on the obtained area under curves of the normalized clearance curves. This study provides the first evidence that the LymphMonitor technology has the potential to diagnose and monitor the lymphatic function in patients.
Novel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset
Ganesan, Prasanth; Feng, Ruibin; Deb, Brototo; et al. (2024)
Diagnostics
Background: Segmenting computed tomography (CT) is crucial in various clinical applications, such as tailoring personalized cardiac ablation for managing cardiac arrhythmias. Automating segmentation through machine learning (ML) is hindered by the necessity for large, labeled training data, which can be challenging to obtain. This article proposes a novel approach for automated, robust labeling using domain knowledge to achieve high-performance segmentation by ML from a small training set. The approach, the domain knowledge-encoding (DOKEN) algorithm, reduces the reliance on large training datasets by encoding cardiac geometry while automatically labeling the training set. The method was validated in a hold-out dataset of CT results from an atrial fibrillation (AF) ablation study. Methods: The DOKEN algorithm parses left atrial (LA) structures, extracts “anatomical knowledge” by leveraging digital LA models (available publicly), and then applies this knowledge to achieve high ML segmentation performance with a small number of training samples. The DOKEN-labeled training set was used to train a nnU-Net deep neural network (DNN) model for segmenting cardiac CT in N = 20 patients. Subsequently, the method was tested in a hold-out set with N = 100 patients (five times larger than training set) who underwent AF ablation. Results: The DOKEN algorithm integrated with the nn-Unet model achieved high segmentation performance with few training samples, with a training to test ratio of 1:5. The Dice score of the DOKEN-enhanced model was 96.7% (IQR: 95.3% to 97.7%), with a median error in surface distance of boundaries of 1.51 mm (IQR: 0.72 to 3.12) and a mean centroid–boundary distance of 1.16 mm (95% CI: −4.57 to 6.89), similar to expert results (r = 0.99; p < 0.001). In digital hearts, the novel DOKEN approach segmented the LA structures with a mean difference for the centroid–boundary distances of −0.27 mm (95% CI: −3.87 to 3.33; r = 0.99; p < 0.0001). Conclusions: The proposed novel domain knowledge-encoding algorithm was able to perform the segmentation of six substructures of the LA, reducing the need for large training data sets. The combination of domain knowledge encoding and a machine learning approach could reduce the dependence of ML on large training datasets and could potentially be applied to AF ablation procedures and extended in the future to other imaging, 3D printing, and data science applications.
Novel blood biomarkers for a diagnostic workup of acute aortic dissection
Forrer, Anja; Schoenrath, Felix; Torzewski, Michael; et al. (2021)
Diagnostics
Acute aortic dissection (AAD) is a rare condition, but together with acute myocardial infarction (AMI) and pulmonary embolism (PE) it belongs to the most relevant and life-threatening causes of acute chest pain. Until now, there has been no specific blood test in the diagnostic workup of AAD. To identify clinically relevant biomarkers for AAD, we applied Proseek® Multiplex assays to plasma samples from patients with AAD, AMI, PE, thoracic aortic aneurysm (TAA), and non-cardiovascular chest pain (nonCVD). Subsequently, we validated top hits using conventional immunoassays and examined their expression in the aortic tissue. Interleukin 10 (IL-10) alone showed the best performance with a sensitivity of 55% and a specificity of 98% for AAD diagnosis. The combination of D-dimers, high-sensitive troponin T (hs-TnT), interleukin 6 (IL-6), and plasminogen activator inhibitor 1 (PAI1) correctly classified 75% of AAD cases, delivering a sensitivity of 83% and specificity of 95% for its diagnosis. Moreover, this model provided the correct classification of 77% of all analyzed cases. Our data suggest that IL-10 shows potential to be a rule-in biomarker for AAD. Moreover, the addition of PAI1 and IL-6 to hs-TnT and D-dimers may improve the discrimination of suspected AAD, AMI, and PE in patients presenting with acute chest pain.
Advanced Diffusion-Weighted Imaging Sequences for Breast MRI: Comprehensive Comparison of Improved Sequences and Ultra-High B-Values to Identify the Optimal Combination
Hausmann, Daniel; Todorski, Inga; Pindur, Alexandra; et al. (2023)
Diagnostics
This study investigated the image quality and choice of ultra-high b-value of two DWI breast-MRI research applications. The study cohort comprised 40 patients (20 malignant lesions). In addition to s-DWI with two m-b-values (b50 and b800) and three e-b-values (e-b1500, e-b2000, and e-b2500), z-DWI and IR m-b1500 DWI were applied. z-DWI was acquired with the same measured b-values and e-b-values as the standard sequence. For IR m-b1500 DWI, b50 and b1500 were measured, and e-b2000 and e-b2500 were mathematically extrapolated. Three readers used Likert scales to independently analyze all ultra-high b-values (b1500–b2500) for each DWI with regards to scan preference and image quality. ADC values were measured in all 20 lesions. z-DWI was the most preferred (54%), followed by IR m-b1500 DWI (46%). b1500 was significantly preferred over b2000 for z-DWI and IR m-b1500 DWI (p = 0.001 and p = 0.002, respectively). Lesion detection was not significantly different among sequences or b-values (p = 0.174). There were no significant differences in measured ADC values within lesions between s-DWI (ADC: 0.97 [±0.09] × 10−3 mm2/s) and z-DWI (ADC: 0.99 [±0.11] × 10−3 mm2/s; p = 1.000). However, there was a trend toward lower values in IR m-b1500 DWI (ADC: 0.80 [±0.06] × 10−3 mm2/s) than in s-DWI (p = 0.090) and z-DWI (p = 0.110). Overall, image quality was superior and there were fewer image artifacts when using the advanced sequences (z-DWI + IR m-b1500 DWI) compared with s-DWI. Considering scan preferences, we found that the optimal combination was z-DWI with a calculated b1500, especially regarding examination time.
Use of a Silicon Microneedle Chip-Based Device for the Extraction and Subsequent Analysis of Dermal Interstitial Fluid in Heart Failure Patients
Renlund, Markus; Kopp Fernandes, Laurenz; Rangsten, Pelle; et al. (2025)
Diagnostics
Background/Objectives: Dermal interstitial fluid (dISF) is probably the most interesting biofluid for biomarker analysis as an alternative to blood, enabling higher patient comfort and closer or even continuous biomarker monitoring. The prerequisite for dISF-based analysis tools is having convenient access to dISF, as well as a better knowledge of the presence, concentration, and dynamics of biomarkers in dISF. Hollow microneedles represent one of the most promising platforms for access to pure dISF, enabling the mining of biomarker information. Methods and Results: Here, a microneedle-based method for dISF sampling is presented, where a combination of hollow microneedles and sub-pressure is used to optimize both penetration depth in skin and dermal interstitial fluid sampling volumes, and the design of an open, prospective, exploratory, and interventional study to examine the detectability of inflammatory and cardiocirculatory biomarkers in the dISF of heart failure patients, the relationship between dISF-derived and blood-derived biomarker levels, and their kinetics during a cardiopulmonary exercise test (CPET) is introduced. Conclusions: The dISF sampling method and study presented here will foster research on biomarkers in dISF in general and in heart failure patients in particular. The study is part of the European project DIGIPREDICT—Digital Edge AI-deployed DIGItal Twins for PREDICTing disease progression and the need for early intervention in infectious and cardiovascular diseases beyond COVID-19.
Differential Diagnosis of Preeclampsia Based on Urine Peptidome Features Revealed by High Resolution Mass Spectrometry
Kononikhin, Alexey S.; Zakharova, Natalia V.; Sergeeva, Viktoria A.; et al. (2020)
Diagnostics
Preeclampsia (PE) is a severe pregnancy complication, which may be considered as a systemic response in the second half of pregnancy to physiological failures in the first trimester, and can lead to very serious consequences for the health of the mother and fetus. Since PE is often associated with proteinuria, urine proteomic assays may represent a powerful tool for timely diagnostics and appropriate management. High resolution mass spectrometry was applied for peptidome analysis of 127 urine samples of pregnant women with various hypertensive complications: normotensive controls (n = 17), chronic hypertension (n = 16), gestational hypertension (n = 15), mild PE (n = 25), severe PE (n = 25), and 29 patients with complicated diagnoses. Analysis revealed 3869 peptides, which mostly belong to 116 groups with overlapping sequences. A panel of 22 marker peptide groups reliably differentiating PE was created by multivariate statistics, and included 15 collagen groups (from COL1A1, COL3A1, COL2A1, COL4A4, COL5A1, and COL8A1), and single loci from alpha-1-antitrypsin, fibrinogen, membrane-associated progesterone receptor component 1, insulin, EMI domain-containing protein 1, lysine-specific demethylase 6B, and alpha-2-HS-glycoprotein each. ROC analysis of the created model resulted in 88% sensitivity, 96.8% specificity, and receiver operating characteristic curve (AUC) = 0.947. Obtained results confirm the high diagnostic potential of urinary peptidome profiling for pregnancy hypertensive disorders diagnostics.
Machine Learning for Anxiety Detection Using Biosignals: A Review
Ancillon, Lou; Elgendi, Mohamed; Menon, Carlo (2022)
Diagnostics
Anxiety disorder (AD) is a major mental health illness. However, due to the many symptoms and confounding factors associated with AD, it is difficult to diagnose, and patients remain untreated for a long time. Therefore, researchers have become increasingly interested in non-invasive biosignals, such as electroencephalography (EEG), electrocardiogram (ECG), electrodermal response (EDA), and respiration (RSP). Applying machine learning to these signals enables clinicians to recognize patterns of anxiety and differentiate a sick patient from a healthy one. Further, models with multiple and diverse biosignals have been developed to improve accuracy and convenience. This paper reviews and summarizes studies published from 2012 to 2022 that applied different machine learning algorithms with various biosignals. In doing so, it offers perspectives on the strengths and weaknesses of current developments to guide future advancements in anxiety detection. Specifically, this literature review reveals promising measurement accuracies ranging from 55% to 98% for studies with sample sizes of 10 to 102 participants. On average, studies using only EEG seemed to obtain the best performance, but the most accurate results were obtained with EDA, RSP, and heart rate. Random forest and support vector machines were found to be widely used machine learning methods, and they lead to good results as long as feature selection has been performed. Neural networks are also extensively used and provide good accuracy, with the benefit that no feature selection is needed. This review also comments on the effective combinations of modalities and the success of different models for detecting anxiety.
Assessment of Retinal Capillary Dropout after Transcatheter Aortic Valve Implantation by Optical Coherence Tomography Angiography
Gunzinger, Jeanne M.; Ibrahimi, Burbuqe; Baur, Joel; et al. (2021)
Diagnostics
Transcatheter aortic valve implantation (TAVI) is an alternative to open heart surgery in the treatment of symptomatic aortic valve stenosis, which is often the treatment of choice in elderly and frail patients. It carries a risk of embolic complications in the whole cerebral vascular bed, which includes the retinal vasculature. The main objective was the evaluation of retinal emboli visible on optical coherence tomography angiography (OCTA) following TAVI. This is a prospective, single center, observational study enrolling consecutive patients over two years. Patients were assessed pre-and post-TAVI. Twenty-eight patients were included in the final analysis, 82.1% were male, median age was 79.5 (range 52–88), median BCVA was 82.5 letters (range 75–93). Eight patients (28.6%) presented new capillary dropout lesions in their post-TAVI OCTA scans. There was no statistically significant change in BCVA. Quantitative analysis of macular or peripapillary OCTA parameters did not show any statistically significant difference in pre-and post-intervention. In conclusion, capillary dropout lesions could frequently be found in patients after TAVI. Quantitative measurements of macular and peripapillary flow remained stable, possibly indicating effective ocular blood flow regulation within the range of left ventricular ejection fraction in our cohort.
Automatic ECG Quality Assessment Techniques: A Systematic Review
van der Bijl, Kirina; Elgendi, Mohamed; Menon, Carlo (2022)
Diagnostics
Cardiovascular diseases are the leading cause of death, globally. Stroke and heart attacks account for more than 80% of cardiovascular disease-related deaths. To prevent patient mismanagement and potentially save lives, effective screening at an early stage is needed. Diagnosis is typically made using an electrocardiogram (ECG) analysis. However, ECG recordings are often corrupted by different types of noise, degrading the quality of the recording and making diagnosis more difficult. This paper reviews research on automatic ECG quality assessment techniques used in studies published from 2012-2022. The CinC11 Dataset is most often used for training and testing algorithms. Only one study tested its algorithm on people in real-time, but it did not specify the demographic data of the subjects. Most of the reviewed papers evaluated the quality of the ECG recordings per single lead. The accuracy of the algorithms reviewed in this paper range from 85.75% to 97.15%. More clarity on the research methods used is needed to improve the quality of automatic ECG quality assessment techniques and implement them in a clinical setting. This paper discusses the possible shortcomings in current research and provides recommendations on how to advance the field of automatic ECG quality assessment.
Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review
Ghrabli, Syrine; Elgendi, Mohamed; Menon, Carlo (2022)
Diagnostics
In the past two years, medical researchers and data scientists worldwide have focused their efforts on containing the pandemic of coronavirus disease 2019 (COVID-19). Deep learning models have been proven to be capable of efficient medical diagnosis and prognosis in cancer, common lung diseases, and COVID-19. On the other hand, artificial neural networks have demonstrated their potential in pattern recognition and classification in various domains, including healthcare. This literature review aims to report the state of research on developing neural network models to diagnose COVID-19 from cough sounds to create a cost-efficient and accessible testing tool in the fight against the pandemic. A total of 35 papers were included in this review following a screening of the 161 outputs of the literature search. We extracted information from articles on data resources, model structures, and evaluation metrics and then explored the scope of experimental studies and methodologies and analyzed their outcomes and limitations. We found that cough is a biomarker, and its associated information can determine an individual's health status. Convolutional neural networks were predominantly used, suggesting they are particularly suitable for feature extraction and classification. The reported accuracy values ranged from 73.1% to 98.5%. Moreover, the dataset sizes ranged from 16 to over 30,000 cough audio samples. Although deep learning is a promising prospect in identifying COVID-19, we identified a gap in the literature on research conducted over large and diversified data sets.

Publications 1 - 10 of 15

Journal: Diagnostics

Abbreviation

Publisher

Journal Volumes

ISSN

Description

Filters

Search Results